diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..721f2d0c53abfbaf4d56cbb67c73669aa495bc3c 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-152/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-228/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-304/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d045d0a3733119f500edd4a685eb2f8e1da115e9
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-152/README.md b/checkpoint-152/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1b184114a0c28ed3e4c082c18486736dc818166d
--- /dev/null
+++ b/checkpoint-152/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0
\ No newline at end of file
diff --git a/checkpoint-152/adapter_config.json b/checkpoint-152/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..763d98264e556bcbc60c63c5b9f70b53c7bbe722
--- /dev/null
+++ b/checkpoint-152/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-152/adapter_model.safetensors b/checkpoint-152/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6015b4b8cbf8efa5e33e64932b8f5b0cc51373c5
--- /dev/null
+++ b/checkpoint-152/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee6c04ff0628403245a0aff20f9ace524305eb5ae003589232461e48959ae2f
+size 10829849744
diff --git a/checkpoint-152/global_step152/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-152/global_step152/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b69e7195c5a9e9fe00ba507350f0c168077e66fe
--- /dev/null
+++ b/checkpoint-152/global_step152/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee7d746d5ff200ceb3b92c507700288562d5a3f3d394377919cd4870e1f2538
+size 21659418140
diff --git a/checkpoint-152/global_step152/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-152/global_step152/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04e82c155f8cc86d0048a8d45dad2eae70d9ff0e
--- /dev/null
+++ b/checkpoint-152/global_step152/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc0b82d6e9ef771b223c4afd3c115bd266a4bb305de31db8bb63df19de903ad
+size 21659457372
diff --git a/checkpoint-152/global_step152/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-152/global_step152/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b6f92e1de796ef9159ac6c0bcab75b1bea302138
--- /dev/null
+++ b/checkpoint-152/global_step152/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaf15afc8da44353267f2f92672fe0b66c6915733444653d246f89eae4f4860
+size 21659417820
diff --git a/checkpoint-152/global_step152/mp_rank_00_model_states.pt b/checkpoint-152/global_step152/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5585f0619e464bf25de42da08d43657b2be4fe69
--- /dev/null
+++ b/checkpoint-152/global_step152/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb420a06dd2df3159fea7cb337a050c9c23a376b527699b0432632462d24823
+size 11918643933
diff --git a/checkpoint-152/latest b/checkpoint-152/latest
new file mode 100644
index 0000000000000000000000000000000000000000..60406aecd15beeaa730a071c614fe2ab5b4c734b
--- /dev/null
+++ b/checkpoint-152/latest
@@ -0,0 +1 @@
+global_step152
\ No newline at end of file
diff --git a/checkpoint-152/rng_state_0.pth b/checkpoint-152/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1273774ecb9e0ba6283be0c2e8531a122e231d68
--- /dev/null
+++ b/checkpoint-152/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd406425ef68395a3dcb05f97990b4ddc0a85ccc26e2550b978b0f0905f63fca
+size 14768
diff --git a/checkpoint-152/rng_state_1.pth b/checkpoint-152/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7e626e64f550afe32c3368c8e040cd7056a74bb6
--- /dev/null
+++ b/checkpoint-152/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483a6993ec4e0cbec89e300d2a3bbeaf7fff23e01afc2457568a12aad958f9ac
+size 14768
diff --git a/checkpoint-152/rng_state_2.pth b/checkpoint-152/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1019e5921f219a14d8e09734eb68025ace867a77
--- /dev/null
+++ b/checkpoint-152/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f8203e92e896c8414d617110a8f97cc8e8be34d1aec495713321cbbe176d78
+size 14768
diff --git a/checkpoint-152/scheduler.pt b/checkpoint-152/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..92432b11da80f35807484df38118e1ccd8d23aaa
--- /dev/null
+++ b/checkpoint-152/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa27436a75b1cdfdf2a48cad061d7983f71c2e5ca468127002dad296770375e
+size 1064
diff --git a/checkpoint-152/special_tokens_map.json b/checkpoint-152/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/checkpoint-152/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-152/tokenizer.json b/checkpoint-152/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-152/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-152/tokenizer_config.json b/checkpoint-152/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/checkpoint-152/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-152/trainer_state.json b/checkpoint-152/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3919906ab6e95336c5d159bd15945535de39a994
--- /dev/null
+++ b/checkpoint-152/trainer_state.json
@@ -0,0 +1,1097 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 37.79440689086914,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.1402,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 38.45823287963867,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 3.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 38.25625228881836,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.1316,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 37.2024040222168,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.1011,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 38.17294692993164,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 3.133,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 37.374794006347656,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.0731,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 37.226966857910156,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.069,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 38.40094757080078,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 3.1223,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 37.86320877075195,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.062,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 38.02171325683594,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.0008,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 38.5522346496582,
+      "learning_rate": 5.5e-07,
+      "loss": 3.0047,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 37.72829818725586,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.9274,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 38.488494873046875,
+      "learning_rate": 6.5e-07,
+      "loss": 2.8727,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 38.87471389770508,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.8422,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 37.584896087646484,
+      "learning_rate": 7.5e-07,
+      "loss": 2.6728,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 37.04607391357422,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 37.30121994018555,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.4689,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 35.99961853027344,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.3,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 35.817543029785156,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 2.1423,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 35.056915283203125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 34.83850860595703,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.7845,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 34.32366943359375,
+      "learning_rate": 1.1e-06,
+      "loss": 1.5864,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 33.79611587524414,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.4011,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 32.596031188964844,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 30.045007705688477,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9883,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.89093589782715,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7669,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 23.454408645629883,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.6304,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 19.837312698364258,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.4717,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 15.185093879699707,
+      "learning_rate": 1.45e-06,
+      "loss": 0.363,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 9.057796478271484,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2439,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 5.976982593536377,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1864,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.067375421524048,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1134,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.3589119911193848,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0985,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.0044353008270264,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.4279972314834595,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0728,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.9807674288749695,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.906160295009613,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8837690353393555,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0622,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.9579435586929321,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0557,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.8149510622024536,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.8899760246276855,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0517,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.6007645130157471,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0518,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.48819127678871155,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0429,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.42939358949661255,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5706579685211182,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0453,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.3034597337245941,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.5601783394813538,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0411,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.35388317704200745,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.04,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.48609891533851624,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.04,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.4638507068157196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.5685771703720093,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0428,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.46358174085617065,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0483,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.35054436326026917,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0391,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3350559175014496,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.039,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.2875112295150757,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0383,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.4492928683757782,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0358,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29484888911247253,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0355,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.36551928520202637,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0403,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.4458053708076477,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0342,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.34047460556030273,
+      "learning_rate": 3e-06,
+      "loss": 0.0302,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3420606255531311,
+      "learning_rate": 3.05e-06,
+      "loss": 0.034,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3902851939201355,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0327,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29165828227996826,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0341,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.40872958302497864,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.035,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.36295783519744873,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0323,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.3857724368572235,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.3207017481327057,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0332,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2903987169265747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0327,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.3386954963207245,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0308,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.4339621365070343,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0361,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.28095564246177673,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0306,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4141469895839691,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.028,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.35212820768356323,
+      "learning_rate": 3.65e-06,
+      "loss": 0.032,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.26956063508987427,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0294,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.32735681533813477,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0272,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4906782805919647,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0324,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3451901078224182,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.30598726868629456,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0305,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.31189921498298645,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.31895947456359863,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0236,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.3290308117866516,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0284,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.3651576638221741,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0274,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.2393084615468979,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0301,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.333898663520813,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0235,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3287582993507385,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0248,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3432455360889435,
+      "learning_rate": 4.3e-06,
+      "loss": 0.026,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3176783621311188,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0249,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.33373433351516724,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.36087968945503235,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0251,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3681696057319641,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0276,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.46539774537086487,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0229,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23368288576602936,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.021,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.26623716950416565,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0265,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.28750717639923096,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0221,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.46578383445739746,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0236,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.33406543731689453,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0239,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.21247217059135437,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0188,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.26229164004325867,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.022,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.2967258393764496,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0218,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.419189453125,
+      "learning_rate": 5e-06,
+      "loss": 0.0247,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.25418952107429504,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0223,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.20174147188663483,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0266,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.21732494235038757,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0188,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.2683119773864746,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0203,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.18175765872001648,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0185,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3932501971721649,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0238,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.31145599484443665,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0199,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.41356661915779114,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0187,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22484919428825378,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0182,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.28703081607818604,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0239,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.2394670695066452,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0171,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.3552885949611664,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0226,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24968908727169037,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0193,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.24420695006847382,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0226,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.34696799516677856,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.02,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.23682132363319397,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0194,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.2485751509666443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0149,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2815033495426178,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0153,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.24127744138240814,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.019,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.2987695038318634,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0165,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.33492133021354675,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0185,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.20466521382331848,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0151,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.36396247148513794,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0138,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.2000381350517273,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0125,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.24977952241897583,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0152,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.26705336570739746,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0148,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.26699599623680115,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0151,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.20149633288383484,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0151,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.1961003988981247,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2148503214120865,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0137,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20505128800868988,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0136,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.19462467730045319,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0139,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21602794528007507,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.015,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.22933153808116913,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0142,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.1785646229982376,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0097,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.21535581350326538,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0106,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.2360723614692688,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0123,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.18098825216293335,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0126,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.1836131066083908,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0125,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.34765973687171936,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0158,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22595159709453583,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0101,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2811257243156433,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.0111,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.1875840127468109,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0086,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.19390800595283508,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0106,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.3725268244743347,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0095,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.2201736867427826,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0074,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.17423805594444275,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0072,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.22169643640518188,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0121,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.3247295618057251,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0121,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.1830369532108307,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0077,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.2967239022254944,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0104,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.17589347064495087,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0075,
+      "step": 152
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.77843856062441e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-152/training_args.bin b/checkpoint-152/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd15c797edde13f0f3e0490d0aec249c013df912
--- /dev/null
+++ b/checkpoint-152/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebcaf257fe89a74904f6ea50b526a559eb74a53ebc4dfb373932a4d0fa515f5
+size 7928
diff --git a/checkpoint-152/zero_to_fp32.py b/checkpoint-152/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8
--- /dev/null
+++ b/checkpoint-152/zero_to_fp32.py
@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-228/README.md b/checkpoint-228/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1b184114a0c28ed3e4c082c18486736dc818166d
--- /dev/null
+++ b/checkpoint-228/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0
\ No newline at end of file
diff --git a/checkpoint-228/adapter_config.json b/checkpoint-228/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..763d98264e556bcbc60c63c5b9f70b53c7bbe722
--- /dev/null
+++ b/checkpoint-228/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-228/adapter_model.safetensors b/checkpoint-228/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bdab41222c049449d79a1003853f62a85dec55c4
--- /dev/null
+++ b/checkpoint-228/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fab299726d605d2f5ceb2a11af287f81e2135549b729f0075df0de5f20ad6a
+size 10829849744
diff --git a/checkpoint-228/global_step228/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-228/global_step228/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e391abed0c614f6524d84e63ac92a01f9c4305a2
--- /dev/null
+++ b/checkpoint-228/global_step228/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae6a6acd59fa9c511c32a1dd91691882210cb133c903a180bcd7b3bd3f8f9dd
+size 21659418140
diff --git a/checkpoint-228/global_step228/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-228/global_step228/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..79435d1c62a06b89768c0b30b77dc807647bb34d
--- /dev/null
+++ b/checkpoint-228/global_step228/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4136b0bdb400646b469fedc212cb6af0720e7e212a5f4817b86eb87fc44b1e8
+size 21659457372
diff --git a/checkpoint-228/global_step228/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-228/global_step228/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..791676147b126d57964031881da2d1f26eb0d39d
--- /dev/null
+++ b/checkpoint-228/global_step228/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee1c09b33b0ff556569f218ec8aca8be0a1df4d9f4618c6063e6141b26bb20c
+size 21659417820
diff --git a/checkpoint-228/global_step228/mp_rank_00_model_states.pt b/checkpoint-228/global_step228/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4bd54e1359a3df13ce38f367e6672a14cce4c5aa
--- /dev/null
+++ b/checkpoint-228/global_step228/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687f3ef46063e7ad784945fe4bec3c074ae2191658556817f6489e66ca84f401
+size 11918643933
diff --git a/checkpoint-228/latest b/checkpoint-228/latest
new file mode 100644
index 0000000000000000000000000000000000000000..74f667dd5aec7b1dcf458da255b4d04f2e864037
--- /dev/null
+++ b/checkpoint-228/latest
@@ -0,0 +1 @@
+global_step228
\ No newline at end of file
diff --git a/checkpoint-228/rng_state_0.pth b/checkpoint-228/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7e4e448cfbd2b0add7bf99082d4db1840a91b8ff
--- /dev/null
+++ b/checkpoint-228/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f597b8a8ff3fa0c1ca0852531a2c83f947d8ea6229f12dcf84cd40e9d2bdd735
+size 14768
diff --git a/checkpoint-228/rng_state_1.pth b/checkpoint-228/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23d948eb6390eec22634357b14847f9feadb29dc
--- /dev/null
+++ b/checkpoint-228/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2630593d343fda4e989879bfd0f94abc55cf145925788b6d823f88bb73bfdfe
+size 14768
diff --git a/checkpoint-228/rng_state_2.pth b/checkpoint-228/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8ee328e2bdcbd65a0af107cef8782b2d2759fb7b
--- /dev/null
+++ b/checkpoint-228/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7138f65fc4992f28f481beb719c5f1191669f411d0001b0b14e2535745da64d
+size 14768
diff --git a/checkpoint-228/scheduler.pt b/checkpoint-228/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..281433de4d85a441705e6ae0cdc6d3d9fb9482f3
--- /dev/null
+++ b/checkpoint-228/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7d1e7bc6044d2a4e5e390e5599228af42cccdc946da11715716db6eef73066
+size 1064
diff --git a/checkpoint-228/special_tokens_map.json b/checkpoint-228/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/checkpoint-228/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-228/tokenizer.json b/checkpoint-228/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-228/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-228/tokenizer_config.json b/checkpoint-228/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/checkpoint-228/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-228/trainer_state.json b/checkpoint-228/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b2428cc9afa27aca4e40c00cc221a0822b471c2
--- /dev/null
+++ b/checkpoint-228/trainer_state.json
@@ -0,0 +1,1629 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 37.79440689086914,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.1402,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 38.45823287963867,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 3.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 38.25625228881836,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.1316,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 37.2024040222168,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.1011,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 38.17294692993164,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 3.133,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 37.374794006347656,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.0731,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 37.226966857910156,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.069,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 38.40094757080078,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 3.1223,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 37.86320877075195,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.062,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 38.02171325683594,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.0008,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 38.5522346496582,
+      "learning_rate": 5.5e-07,
+      "loss": 3.0047,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 37.72829818725586,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.9274,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 38.488494873046875,
+      "learning_rate": 6.5e-07,
+      "loss": 2.8727,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 38.87471389770508,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.8422,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 37.584896087646484,
+      "learning_rate": 7.5e-07,
+      "loss": 2.6728,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 37.04607391357422,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 37.30121994018555,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.4689,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 35.99961853027344,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.3,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 35.817543029785156,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 2.1423,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 35.056915283203125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 34.83850860595703,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.7845,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 34.32366943359375,
+      "learning_rate": 1.1e-06,
+      "loss": 1.5864,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 33.79611587524414,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.4011,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 32.596031188964844,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 30.045007705688477,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9883,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.89093589782715,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7669,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 23.454408645629883,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.6304,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 19.837312698364258,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.4717,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 15.185093879699707,
+      "learning_rate": 1.45e-06,
+      "loss": 0.363,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 9.057796478271484,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2439,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 5.976982593536377,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1864,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.067375421524048,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1134,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.3589119911193848,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0985,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.0044353008270264,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.4279972314834595,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0728,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.9807674288749695,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.906160295009613,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8837690353393555,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0622,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.9579435586929321,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0557,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.8149510622024536,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.8899760246276855,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0517,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.6007645130157471,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0518,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.48819127678871155,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0429,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.42939358949661255,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5706579685211182,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0453,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.3034597337245941,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.5601783394813538,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0411,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.35388317704200745,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.04,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.48609891533851624,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.04,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.4638507068157196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.5685771703720093,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0428,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.46358174085617065,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0483,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.35054436326026917,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0391,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3350559175014496,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.039,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.2875112295150757,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0383,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.4492928683757782,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0358,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29484888911247253,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0355,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.36551928520202637,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0403,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.4458053708076477,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0342,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.34047460556030273,
+      "learning_rate": 3e-06,
+      "loss": 0.0302,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3420606255531311,
+      "learning_rate": 3.05e-06,
+      "loss": 0.034,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3902851939201355,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0327,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29165828227996826,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0341,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.40872958302497864,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.035,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.36295783519744873,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0323,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.3857724368572235,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.3207017481327057,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0332,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2903987169265747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0327,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.3386954963207245,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0308,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.4339621365070343,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0361,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.28095564246177673,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0306,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4141469895839691,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.028,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.35212820768356323,
+      "learning_rate": 3.65e-06,
+      "loss": 0.032,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.26956063508987427,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0294,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.32735681533813477,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0272,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4906782805919647,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0324,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3451901078224182,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.30598726868629456,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0305,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.31189921498298645,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.31895947456359863,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0236,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.3290308117866516,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0284,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.3651576638221741,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0274,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.2393084615468979,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0301,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.333898663520813,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0235,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3287582993507385,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0248,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3432455360889435,
+      "learning_rate": 4.3e-06,
+      "loss": 0.026,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3176783621311188,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0249,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.33373433351516724,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.36087968945503235,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0251,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3681696057319641,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0276,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.46539774537086487,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0229,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23368288576602936,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.021,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.26623716950416565,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0265,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.28750717639923096,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0221,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.46578383445739746,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0236,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.33406543731689453,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0239,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.21247217059135437,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0188,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.26229164004325867,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.022,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.2967258393764496,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0218,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.419189453125,
+      "learning_rate": 5e-06,
+      "loss": 0.0247,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.25418952107429504,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0223,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.20174147188663483,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0266,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.21732494235038757,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0188,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.2683119773864746,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0203,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.18175765872001648,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0185,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3932501971721649,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0238,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.31145599484443665,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0199,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.41356661915779114,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0187,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22484919428825378,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0182,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.28703081607818604,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0239,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.2394670695066452,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0171,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.3552885949611664,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0226,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24968908727169037,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0193,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.24420695006847382,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0226,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.34696799516677856,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.02,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.23682132363319397,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0194,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.2485751509666443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0149,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2815033495426178,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0153,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.24127744138240814,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.019,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.2987695038318634,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0165,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.33492133021354675,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0185,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.20466521382331848,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0151,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.36396247148513794,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0138,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.2000381350517273,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0125,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.24977952241897583,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0152,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.26705336570739746,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0148,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.26699599623680115,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0151,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.20149633288383484,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0151,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.1961003988981247,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2148503214120865,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0137,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20505128800868988,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0136,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.19462467730045319,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0139,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21602794528007507,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.015,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.22933153808116913,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0142,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.1785646229982376,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0097,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.21535581350326538,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0106,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.2360723614692688,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0123,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.18098825216293335,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0126,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.1836131066083908,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0125,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.34765973687171936,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0158,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22595159709453583,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0101,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2811257243156433,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.0111,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.1875840127468109,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0086,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.19390800595283508,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0106,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.3725268244743347,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0095,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.2201736867427826,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0074,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.17423805594444275,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0072,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.22169643640518188,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0121,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.3247295618057251,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0121,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.1830369532108307,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0077,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.2967239022254944,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0104,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.17589347064495087,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0075,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.15554101765155792,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0063,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.13191422820091248,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0039,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.1909502148628235,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0055,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.16942323744297028,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0055,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.1740521341562271,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.006,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.19565710425376892,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0057,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.13488221168518066,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0033,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.16322746872901917,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0042,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.2087877243757248,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0052,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.12736408412456512,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0051,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.13264045119285583,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0035,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.2015363723039627,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0055,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.21640510857105255,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.008,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.17276327311992645,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0058,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.15923018753528595,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0039,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.14791631698608398,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0032,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.16776816546916962,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0043,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.12374848127365112,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0035,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.13051433861255646,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0036,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.12607790529727936,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0052,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.09630817174911499,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0031,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.11332327872514725,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.0043,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.16632875800132751,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.005,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.12856662273406982,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.0031,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.197174072265625,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0045,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.17151176929473877,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0044,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.14734052121639252,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0053,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.13286560773849487,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.1636727899312973,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0039,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.1082785576581955,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.0025,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.1716354638338089,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.004,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.14045757055282593,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0026,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.1682705134153366,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0042,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.11872018873691559,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0028,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.12182936072349548,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0018,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.2031281590461731,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0032,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.0959291160106659,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0015,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.15291978418827057,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0036,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.15930163860321045,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0047,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.2150997817516327,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0038,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.1317511945962906,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0032,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.07808093726634979,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0011,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.13284094631671906,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.0037,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.16264718770980835,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0039,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.10431212931871414,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0023,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.08813079446554184,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0018,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.22164294123649597,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0037,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.09111231565475464,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0019,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.0871724933385849,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0014,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.2138734757900238,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0022,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.11238733679056168,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.0023,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.0815015360713005,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0011,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.304352343082428,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.003,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.10469458252191544,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0009,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.1440751701593399,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0025,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.2173687070608139,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0028,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2922506332397461,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.003,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.18853916227817535,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0014,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.12060266733169556,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0015,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14512351155281067,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.002,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.15343990921974182,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0012,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.09639029949903488,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0017,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.09907295554876328,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0012,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.05898207053542137,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0006,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.10509718954563141,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0013,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.17495931684970856,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.001,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.12321923673152924,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.001,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.11147578060626984,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0015,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.06215621903538704,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0006,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.03004705347120762,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0002,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.09312062710523605,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0014,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.05324690416455269,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0005,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.06438126415014267,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0005,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.08646634221076965,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0006,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.05682829022407532,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.11831886321306229,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0006,
+      "step": 228
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4667657840936616e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-228/training_args.bin b/checkpoint-228/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd15c797edde13f0f3e0490d0aec249c013df912
--- /dev/null
+++ b/checkpoint-228/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebcaf257fe89a74904f6ea50b526a559eb74a53ebc4dfb373932a4d0fa515f5
+size 7928
diff --git a/checkpoint-228/zero_to_fp32.py b/checkpoint-228/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8
--- /dev/null
+++ b/checkpoint-228/zero_to_fp32.py
@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-304/README.md b/checkpoint-304/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1b184114a0c28ed3e4c082c18486736dc818166d
--- /dev/null
+++ b/checkpoint-304/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0
\ No newline at end of file
diff --git a/checkpoint-304/adapter_config.json b/checkpoint-304/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..763d98264e556bcbc60c63c5b9f70b53c7bbe722
--- /dev/null
+++ b/checkpoint-304/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-304/adapter_model.safetensors b/checkpoint-304/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d3683983b7b09039b8095da811c679df8d463ec
--- /dev/null
+++ b/checkpoint-304/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0782e530ad6759cc55d8e42fe4991859dad2ca4ff1f4601a0faa88f06d5152d8
+size 10829849744
diff --git a/checkpoint-304/global_step304/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-304/global_step304/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fb8aef282684d1a97b787721903b4808052e7e69
--- /dev/null
+++ b/checkpoint-304/global_step304/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f3daa4f2546f4a5efcf1c806a775680a332f7f2fb33101eb96327c03d97763
+size 21659418140
diff --git a/checkpoint-304/global_step304/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-304/global_step304/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e691b2ef6e6ad840c2522079e3070e157fdd3dc1
--- /dev/null
+++ b/checkpoint-304/global_step304/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d751ed5a8d3b01c20f42ab3e61bc2b1c4b20ab1c966aa10a08075cee41c7c16
+size 21659457372
diff --git a/checkpoint-304/global_step304/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-304/global_step304/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..248a083dafa39f1e577164331390baf4b1b74f81
--- /dev/null
+++ b/checkpoint-304/global_step304/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197cddc77f298f1974484ed707bb201f68960b230d2c69769978ba7faad90d46
+size 21659417820
diff --git a/checkpoint-304/global_step304/mp_rank_00_model_states.pt b/checkpoint-304/global_step304/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..18d97ce6e9fc696eeda12a5670b11bc37f26bbd7
--- /dev/null
+++ b/checkpoint-304/global_step304/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dc5cefb7fa37a2b35e90209ec149de61aa019306a4b43c92b2b582756a4b5a
+size 11918643933
diff --git a/checkpoint-304/latest b/checkpoint-304/latest
new file mode 100644
index 0000000000000000000000000000000000000000..3761843487f150944adef329837340fd2ed0b7ff
--- /dev/null
+++ b/checkpoint-304/latest
@@ -0,0 +1 @@
+global_step304
\ No newline at end of file
diff --git a/checkpoint-304/rng_state_0.pth b/checkpoint-304/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ff604c8c4474afbed94401dfd5d6c1473f9d3583
--- /dev/null
+++ b/checkpoint-304/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a3d324f952ce2014535fcab16510a458a3013d4a495eadb02ed7fff34e2363
+size 14768
diff --git a/checkpoint-304/rng_state_1.pth b/checkpoint-304/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ef8d9c6fa11f39be0d41b6080c2fdbc5dcfb7349
--- /dev/null
+++ b/checkpoint-304/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8aa11659794f1549b168457979fc560787dd21e97b4f2ad4e52b23c8576c2de
+size 14768
diff --git a/checkpoint-304/rng_state_2.pth b/checkpoint-304/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5626492adca4ab2303b5cbd44ed33ad4523b3c8e
--- /dev/null
+++ b/checkpoint-304/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b24784f5720fe4389d0dffe37c832973528a7aafd8842126a0d5a23d49aff4
+size 14768
diff --git a/checkpoint-304/scheduler.pt b/checkpoint-304/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6b5db44d423bc56da0906bba71e4a2c62d1f77f9
--- /dev/null
+++ b/checkpoint-304/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1ee26d42c6bb20a44e8946dadecd2cff0ca8ab5815e472d6bc7cfc6f35c116
+size 1064
diff --git a/checkpoint-304/special_tokens_map.json b/checkpoint-304/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/checkpoint-304/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-304/tokenizer.json b/checkpoint-304/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-304/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-304/tokenizer_config.json b/checkpoint-304/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/checkpoint-304/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-304/trainer_state.json b/checkpoint-304/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d7a09553afc501fce32205da9ad69954491b7fe
--- /dev/null
+++ b/checkpoint-304/trainer_state.json
@@ -0,0 +1,2161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 304,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 37.79440689086914,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.1402,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 38.45823287963867,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 3.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 38.25625228881836,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.1316,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 37.2024040222168,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.1011,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 38.17294692993164,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 3.133,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 37.374794006347656,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.0731,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 37.226966857910156,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.069,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 38.40094757080078,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 3.1223,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 37.86320877075195,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.062,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 38.02171325683594,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.0008,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 38.5522346496582,
+      "learning_rate": 5.5e-07,
+      "loss": 3.0047,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 37.72829818725586,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.9274,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 38.488494873046875,
+      "learning_rate": 6.5e-07,
+      "loss": 2.8727,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 38.87471389770508,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.8422,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 37.584896087646484,
+      "learning_rate": 7.5e-07,
+      "loss": 2.6728,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 37.04607391357422,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 37.30121994018555,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.4689,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 35.99961853027344,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.3,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 35.817543029785156,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 2.1423,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 35.056915283203125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 34.83850860595703,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.7845,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 34.32366943359375,
+      "learning_rate": 1.1e-06,
+      "loss": 1.5864,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 33.79611587524414,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.4011,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 32.596031188964844,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 30.045007705688477,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9883,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.89093589782715,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7669,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 23.454408645629883,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.6304,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 19.837312698364258,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.4717,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 15.185093879699707,
+      "learning_rate": 1.45e-06,
+      "loss": 0.363,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 9.057796478271484,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2439,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 5.976982593536377,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1864,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.067375421524048,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1134,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.3589119911193848,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0985,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.0044353008270264,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.4279972314834595,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0728,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.9807674288749695,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.906160295009613,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8837690353393555,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0622,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.9579435586929321,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0557,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.8149510622024536,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.8899760246276855,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0517,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.6007645130157471,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0518,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.48819127678871155,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0429,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.42939358949661255,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5706579685211182,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0453,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.3034597337245941,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.5601783394813538,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0411,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.35388317704200745,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.04,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.48609891533851624,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.04,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.4638507068157196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.5685771703720093,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0428,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.46358174085617065,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0483,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.35054436326026917,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0391,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3350559175014496,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.039,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.2875112295150757,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0383,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.4492928683757782,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0358,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29484888911247253,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0355,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.36551928520202637,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0403,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.4458053708076477,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0342,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.34047460556030273,
+      "learning_rate": 3e-06,
+      "loss": 0.0302,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3420606255531311,
+      "learning_rate": 3.05e-06,
+      "loss": 0.034,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3902851939201355,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0327,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29165828227996826,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0341,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.40872958302497864,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.035,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.36295783519744873,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0323,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.3857724368572235,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.3207017481327057,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0332,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2903987169265747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0327,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.3386954963207245,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0308,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.4339621365070343,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0361,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.28095564246177673,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0306,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4141469895839691,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.028,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.35212820768356323,
+      "learning_rate": 3.65e-06,
+      "loss": 0.032,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.26956063508987427,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0294,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.32735681533813477,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0272,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4906782805919647,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0324,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3451901078224182,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.30598726868629456,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0305,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.31189921498298645,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.31895947456359863,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0236,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.3290308117866516,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0284,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.3651576638221741,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0274,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.2393084615468979,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0301,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.333898663520813,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0235,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3287582993507385,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0248,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3432455360889435,
+      "learning_rate": 4.3e-06,
+      "loss": 0.026,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3176783621311188,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0249,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.33373433351516724,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.36087968945503235,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0251,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3681696057319641,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0276,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.46539774537086487,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0229,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23368288576602936,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.021,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.26623716950416565,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0265,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.28750717639923096,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0221,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.46578383445739746,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0236,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.33406543731689453,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0239,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.21247217059135437,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0188,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.26229164004325867,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.022,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.2967258393764496,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0218,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.419189453125,
+      "learning_rate": 5e-06,
+      "loss": 0.0247,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.25418952107429504,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0223,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.20174147188663483,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0266,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.21732494235038757,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0188,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.2683119773864746,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0203,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.18175765872001648,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0185,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3932501971721649,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0238,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.31145599484443665,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0199,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.41356661915779114,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0187,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22484919428825378,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0182,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.28703081607818604,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0239,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.2394670695066452,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0171,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.3552885949611664,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0226,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24968908727169037,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0193,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.24420695006847382,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0226,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.34696799516677856,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.02,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.23682132363319397,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0194,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.2485751509666443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0149,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2815033495426178,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0153,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.24127744138240814,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.019,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.2987695038318634,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0165,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.33492133021354675,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0185,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.20466521382331848,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0151,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.36396247148513794,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0138,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.2000381350517273,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0125,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.24977952241897583,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0152,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.26705336570739746,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0148,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.26699599623680115,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0151,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.20149633288383484,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0151,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.1961003988981247,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2148503214120865,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0137,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20505128800868988,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0136,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.19462467730045319,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0139,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21602794528007507,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.015,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.22933153808116913,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0142,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.1785646229982376,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0097,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.21535581350326538,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0106,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.2360723614692688,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0123,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.18098825216293335,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0126,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.1836131066083908,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0125,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.34765973687171936,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0158,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22595159709453583,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0101,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2811257243156433,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.0111,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.1875840127468109,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0086,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.19390800595283508,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0106,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.3725268244743347,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0095,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.2201736867427826,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0074,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.17423805594444275,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0072,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.22169643640518188,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0121,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.3247295618057251,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0121,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.1830369532108307,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0077,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.2967239022254944,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0104,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.17589347064495087,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0075,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.15554101765155792,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0063,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.13191422820091248,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0039,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.1909502148628235,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0055,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.16942323744297028,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0055,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.1740521341562271,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.006,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.19565710425376892,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0057,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.13488221168518066,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0033,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.16322746872901917,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0042,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.2087877243757248,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0052,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.12736408412456512,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0051,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.13264045119285583,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0035,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.2015363723039627,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0055,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.21640510857105255,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.008,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.17276327311992645,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0058,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.15923018753528595,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0039,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.14791631698608398,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0032,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.16776816546916962,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0043,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.12374848127365112,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0035,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.13051433861255646,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0036,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.12607790529727936,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0052,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.09630817174911499,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0031,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.11332327872514725,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.0043,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.16632875800132751,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.005,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.12856662273406982,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.0031,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.197174072265625,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0045,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.17151176929473877,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0044,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.14734052121639252,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0053,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.13286560773849487,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.1636727899312973,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0039,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.1082785576581955,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.0025,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.1716354638338089,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.004,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.14045757055282593,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0026,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.1682705134153366,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0042,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.11872018873691559,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0028,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.12182936072349548,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0018,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.2031281590461731,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0032,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.0959291160106659,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0015,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.15291978418827057,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0036,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.15930163860321045,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0047,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.2150997817516327,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0038,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.1317511945962906,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0032,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.07808093726634979,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0011,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.13284094631671906,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.0037,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.16264718770980835,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0039,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.10431212931871414,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0023,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.08813079446554184,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0018,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.22164294123649597,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0037,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.09111231565475464,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0019,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.0871724933385849,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0014,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.2138734757900238,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0022,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.11238733679056168,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.0023,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.0815015360713005,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0011,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.304352343082428,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.003,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.10469458252191544,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0009,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.1440751701593399,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0025,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.2173687070608139,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0028,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2922506332397461,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.003,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.18853916227817535,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0014,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.12060266733169556,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0015,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14512351155281067,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.002,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.15343990921974182,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0012,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.09639029949903488,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0017,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.09907295554876328,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0012,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.05898207053542137,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0006,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.10509718954563141,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0013,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.17495931684970856,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.001,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.12321923673152924,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.001,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.11147578060626984,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0015,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.06215621903538704,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0006,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.03004705347120762,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0002,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.09312062710523605,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0014,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.05324690416455269,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0005,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.06438126415014267,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0005,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.08646634221076965,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0006,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.05682829022407532,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.11831886321306229,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0006,
+      "step": 228
+    },
+    {
+      "epoch": 3.013157894736842,
+      "grad_norm": 0.0533737950026989,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0003,
+      "step": 229
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.06704334169626236,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0005,
+      "step": 230
+    },
+    {
+      "epoch": 3.039473684210526,
+      "grad_norm": 0.024390004575252533,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0002,
+      "step": 231
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.10754281282424927,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0009,
+      "step": 232
+    },
+    {
+      "epoch": 3.0657894736842106,
+      "grad_norm": 0.032474737614393234,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0002,
+      "step": 233
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.11489477753639221,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0008,
+      "step": 234
+    },
+    {
+      "epoch": 3.0921052631578947,
+      "grad_norm": 0.11805123090744019,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0013,
+      "step": 235
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.04284543916583061,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.1184210526315788,
+      "grad_norm": 0.0592227578163147,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0005,
+      "step": 237
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.08888686448335648,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0007,
+      "step": 238
+    },
+    {
+      "epoch": 3.1447368421052633,
+      "grad_norm": 0.04613477736711502,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0004,
+      "step": 239
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.024109596386551857,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 3.1710526315789473,
+      "grad_norm": 0.04759601503610611,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0002,
+      "step": 241
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.06583128869533539,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0003,
+      "step": 242
+    },
+    {
+      "epoch": 3.1973684210526314,
+      "grad_norm": 0.03406457230448723,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0001,
+      "step": 243
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.020209595561027527,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.0002,
+      "step": 244
+    },
+    {
+      "epoch": 3.223684210526316,
+      "grad_norm": 0.04148108884692192,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0002,
+      "step": 245
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.05275535210967064,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0003,
+      "step": 246
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.03692334517836571,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0004,
+      "step": 247
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.06586624681949615,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0004,
+      "step": 248
+    },
+    {
+      "epoch": 3.276315789473684,
+      "grad_norm": 0.06966730207204819,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0003,
+      "step": 249
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.10422863811254501,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0004,
+      "step": 250
+    },
+    {
+      "epoch": 3.3026315789473686,
+      "grad_norm": 0.10132399946451187,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0008,
+      "step": 251
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.06418923288583755,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0004,
+      "step": 252
+    },
+    {
+      "epoch": 3.3289473684210527,
+      "grad_norm": 0.1488313227891922,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0021,
+      "step": 253
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.05905044823884964,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0006,
+      "step": 254
+    },
+    {
+      "epoch": 3.3552631578947367,
+      "grad_norm": 0.05011991411447525,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0004,
+      "step": 255
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.026315532624721527,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0002,
+      "step": 256
+    },
+    {
+      "epoch": 3.3815789473684212,
+      "grad_norm": 0.031153831630945206,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.019811732694506645,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0001,
+      "step": 258
+    },
+    {
+      "epoch": 3.4078947368421053,
+      "grad_norm": 0.029009979218244553,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0002,
+      "step": 259
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.08594539761543274,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 3.4342105263157894,
+      "grad_norm": 0.07609947770833969,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0006,
+      "step": 261
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.052105486392974854,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0003,
+      "step": 262
+    },
+    {
+      "epoch": 3.4605263157894735,
+      "grad_norm": 0.023044012486934662,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0001,
+      "step": 263
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.01714818924665451,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0001,
+      "step": 264
+    },
+    {
+      "epoch": 3.486842105263158,
+      "grad_norm": 0.024353889748454094,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0002,
+      "step": 265
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.044456806033849716,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0004,
+      "step": 266
+    },
+    {
+      "epoch": 3.513157894736842,
+      "grad_norm": 0.06826099753379822,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0005,
+      "step": 267
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.2765248417854309,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0005,
+      "step": 268
+    },
+    {
+      "epoch": 3.5394736842105265,
+      "grad_norm": 0.04589018225669861,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0004,
+      "step": 269
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.023166710510849953,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0001,
+      "step": 270
+    },
+    {
+      "epoch": 3.5657894736842106,
+      "grad_norm": 0.03657109662890434,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0002,
+      "step": 271
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.08881364017724991,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0004,
+      "step": 272
+    },
+    {
+      "epoch": 3.5921052631578947,
+      "grad_norm": 0.022605225443840027,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0001,
+      "step": 273
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.05161530151963234,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0002,
+      "step": 274
+    },
+    {
+      "epoch": 3.6184210526315788,
+      "grad_norm": 0.039631813764572144,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0003,
+      "step": 275
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.03075975738465786,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0001,
+      "step": 276
+    },
+    {
+      "epoch": 3.6447368421052633,
+      "grad_norm": 0.04068103805184364,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0001,
+      "step": 277
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.08374299108982086,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0006,
+      "step": 278
+    },
+    {
+      "epoch": 3.6710526315789473,
+      "grad_norm": 0.014881132170557976,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0001,
+      "step": 279
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.08170844614505768,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0004,
+      "step": 280
+    },
+    {
+      "epoch": 3.6973684210526314,
+      "grad_norm": 0.02605108916759491,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0001,
+      "step": 281
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.056749701499938965,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0008,
+      "step": 282
+    },
+    {
+      "epoch": 3.723684210526316,
+      "grad_norm": 0.043280281126499176,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0002,
+      "step": 283
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.01662975363433361,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0001,
+      "step": 284
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.045024238526821136,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0001,
+      "step": 285
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.02116972580552101,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0001,
+      "step": 286
+    },
+    {
+      "epoch": 3.776315789473684,
+      "grad_norm": 0.028999928385019302,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0001,
+      "step": 287
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.05580444633960724,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0006,
+      "step": 288
+    },
+    {
+      "epoch": 3.8026315789473686,
+      "grad_norm": 0.03946217522025108,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0002,
+      "step": 289
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.01824789121747017,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0001,
+      "step": 290
+    },
+    {
+      "epoch": 3.8289473684210527,
+      "grad_norm": 0.09996017813682556,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0002,
+      "step": 291
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.04970015585422516,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0002,
+      "step": 292
+    },
+    {
+      "epoch": 3.8552631578947367,
+      "grad_norm": 0.05343327671289444,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0003,
+      "step": 293
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.007754841353744268,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8815789473684212,
+      "grad_norm": 0.06841913610696793,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0002,
+      "step": 295
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.0050100889056921005,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 3.9078947368421053,
+      "grad_norm": 0.2890152931213379,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0001,
+      "step": 297
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.010258257389068604,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 3.9342105263157894,
+      "grad_norm": 0.031965699046850204,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0001,
+      "step": 299
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.00890852976590395,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9605263157894735,
+      "grad_norm": 0.030713632702827454,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0001,
+      "step": 301
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.010088774375617504,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.986842105263158,
+      "grad_norm": 0.006950493901968002,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.03781810402870178,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0003,
+      "step": 304
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.955687712124882e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-304/training_args.bin b/checkpoint-304/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd15c797edde13f0f3e0490d0aec249c013df912
--- /dev/null
+++ b/checkpoint-304/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebcaf257fe89a74904f6ea50b526a559eb74a53ebc4dfb373932a4d0fa515f5
+size 7928
diff --git a/checkpoint-304/zero_to_fp32.py b/checkpoint-304/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8
--- /dev/null
+++ b/checkpoint-304/zero_to_fp32.py
@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-380/README.md b/checkpoint-380/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1b184114a0c28ed3e4c082c18486736dc818166d
--- /dev/null
+++ b/checkpoint-380/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0
\ No newline at end of file
diff --git a/checkpoint-380/adapter_config.json b/checkpoint-380/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..763d98264e556bcbc60c63c5b9f70b53c7bbe722
--- /dev/null
+++ b/checkpoint-380/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-380/adapter_model.safetensors b/checkpoint-380/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..94395f80bca67a993544557687bbcd0edff5799f
--- /dev/null
+++ b/checkpoint-380/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3141131baac97c57ea89187b190eae4ccf3988702aabad982d04b4ab83ff82ac
+size 10829849744
diff --git a/checkpoint-380/global_step380/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-380/global_step380/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..03d32413666115d6048ff15cae9fcfed2ed6ce3e
--- /dev/null
+++ b/checkpoint-380/global_step380/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db72035810cec0d8924e0038c0c8ecaec5f05d8b42a75090257158d04e38ef6b
+size 21659418140
diff --git a/checkpoint-380/global_step380/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-380/global_step380/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dac570ca7cdd6987a12027d0617fd33865563d60
--- /dev/null
+++ b/checkpoint-380/global_step380/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1920638c8d06725c94a7f04be2e6d33b7070c3b03abfe25250d686b123ed46be
+size 21659457372
diff --git a/checkpoint-380/global_step380/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-380/global_step380/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0881dd3f23d22f30fcf3089a12bfe5c7ad0cd38a
--- /dev/null
+++ b/checkpoint-380/global_step380/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c887c8d1aff85bc382a35114f73ad79fe03817244e33ef121cc1a6e0f47fbdf9
+size 21659417820
diff --git a/checkpoint-380/global_step380/mp_rank_00_model_states.pt b/checkpoint-380/global_step380/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39c9ffdd3cca3daf35fd0fbd5e3e2cec2676ac8a
--- /dev/null
+++ b/checkpoint-380/global_step380/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017462fd854827452c31f671810c8242a5e44134c42ddd44ce9451df06ad0909
+size 11918643933
diff --git a/checkpoint-380/latest b/checkpoint-380/latest
new file mode 100644
index 0000000000000000000000000000000000000000..97a28d1c33298568d84d9916417869e8f7800fb7
--- /dev/null
+++ b/checkpoint-380/latest
@@ -0,0 +1 @@
+global_step380
\ No newline at end of file
diff --git a/checkpoint-380/rng_state_0.pth b/checkpoint-380/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..360b0f6a03a87f6aed26f672cfc6136b7bbf1611
--- /dev/null
+++ b/checkpoint-380/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe26d5c64cbc7d621141b185caf2009e21d51970e79374540d8781688adeaf8
+size 14768
diff --git a/checkpoint-380/rng_state_1.pth b/checkpoint-380/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..acb1b5e3308c9e88d4c63b5928d441d53b890547
--- /dev/null
+++ b/checkpoint-380/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c608d9a2f68dfe0957985d05001d8334947b7cfbf16e6d2348f077e306d8cc
+size 14768
diff --git a/checkpoint-380/rng_state_2.pth b/checkpoint-380/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0f9ceea00dd006196381c120c6c3d96bf762fe79
--- /dev/null
+++ b/checkpoint-380/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d769eb76f77879c1fcd6116be4251a854ae051175d403fb920f7282b89fff9
+size 14768
diff --git a/checkpoint-380/scheduler.pt b/checkpoint-380/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d79447f5e29bdc91f65c41e7c702584c9ad3f146
--- /dev/null
+++ b/checkpoint-380/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93097201a634931518316956d488c8df82e81f7fc29c1bde6ce7bd6033e7827
+size 1064
diff --git a/checkpoint-380/special_tokens_map.json b/checkpoint-380/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/checkpoint-380/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-380/tokenizer.json b/checkpoint-380/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-380/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-380/tokenizer_config.json b/checkpoint-380/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/checkpoint-380/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-380/trainer_state.json b/checkpoint-380/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..eedeb27303058c876dd93da086967789a5d8ae97
--- /dev/null
+++ b/checkpoint-380/trainer_state.json
@@ -0,0 +1,2693 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 37.79440689086914,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.1402,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 38.45823287963867,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 3.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 38.25625228881836,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.1316,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 37.2024040222168,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.1011,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 38.17294692993164,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 3.133,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 37.374794006347656,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.0731,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 37.226966857910156,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.069,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 38.40094757080078,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 3.1223,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 37.86320877075195,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.062,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 38.02171325683594,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.0008,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 38.5522346496582,
+      "learning_rate": 5.5e-07,
+      "loss": 3.0047,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 37.72829818725586,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.9274,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 38.488494873046875,
+      "learning_rate": 6.5e-07,
+      "loss": 2.8727,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 38.87471389770508,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.8422,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 37.584896087646484,
+      "learning_rate": 7.5e-07,
+      "loss": 2.6728,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 37.04607391357422,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 37.30121994018555,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.4689,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 35.99961853027344,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.3,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 35.817543029785156,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 2.1423,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 35.056915283203125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 34.83850860595703,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.7845,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 34.32366943359375,
+      "learning_rate": 1.1e-06,
+      "loss": 1.5864,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 33.79611587524414,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.4011,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 32.596031188964844,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 30.045007705688477,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9883,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.89093589782715,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7669,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 23.454408645629883,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.6304,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 19.837312698364258,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.4717,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 15.185093879699707,
+      "learning_rate": 1.45e-06,
+      "loss": 0.363,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 9.057796478271484,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2439,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 5.976982593536377,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1864,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.067375421524048,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1134,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.3589119911193848,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0985,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.0044353008270264,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.4279972314834595,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0728,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.9807674288749695,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.906160295009613,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8837690353393555,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0622,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.9579435586929321,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0557,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.8149510622024536,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.8899760246276855,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0517,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.6007645130157471,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0518,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.48819127678871155,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0429,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.42939358949661255,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5706579685211182,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0453,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.3034597337245941,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.5601783394813538,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0411,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.35388317704200745,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.04,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.48609891533851624,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.04,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.4638507068157196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.5685771703720093,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0428,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.46358174085617065,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0483,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.35054436326026917,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0391,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3350559175014496,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.039,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.2875112295150757,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0383,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.4492928683757782,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0358,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29484888911247253,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0355,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.36551928520202637,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0403,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.4458053708076477,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0342,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.34047460556030273,
+      "learning_rate": 3e-06,
+      "loss": 0.0302,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3420606255531311,
+      "learning_rate": 3.05e-06,
+      "loss": 0.034,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3902851939201355,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0327,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29165828227996826,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0341,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.40872958302497864,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.035,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.36295783519744873,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0323,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.3857724368572235,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.3207017481327057,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0332,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2903987169265747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0327,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.3386954963207245,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0308,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.4339621365070343,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0361,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.28095564246177673,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0306,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4141469895839691,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.028,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.35212820768356323,
+      "learning_rate": 3.65e-06,
+      "loss": 0.032,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.26956063508987427,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0294,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.32735681533813477,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0272,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4906782805919647,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0324,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3451901078224182,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.30598726868629456,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0305,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.31189921498298645,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.31895947456359863,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0236,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.3290308117866516,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0284,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.3651576638221741,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0274,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.2393084615468979,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0301,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.333898663520813,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0235,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3287582993507385,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0248,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3432455360889435,
+      "learning_rate": 4.3e-06,
+      "loss": 0.026,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3176783621311188,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0249,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.33373433351516724,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.36087968945503235,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0251,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3681696057319641,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0276,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.46539774537086487,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0229,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23368288576602936,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.021,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.26623716950416565,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0265,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.28750717639923096,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0221,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.46578383445739746,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0236,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.33406543731689453,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0239,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.21247217059135437,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0188,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.26229164004325867,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.022,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.2967258393764496,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0218,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.419189453125,
+      "learning_rate": 5e-06,
+      "loss": 0.0247,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.25418952107429504,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0223,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.20174147188663483,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0266,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.21732494235038757,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0188,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.2683119773864746,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0203,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.18175765872001648,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0185,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3932501971721649,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0238,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.31145599484443665,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0199,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.41356661915779114,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0187,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22484919428825378,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0182,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.28703081607818604,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.0239,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.2394670695066452,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0171,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.3552885949611664,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0226,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24968908727169037,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0193,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.24420695006847382,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0226,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.34696799516677856,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.02,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.23682132363319397,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0194,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.2485751509666443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0149,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2815033495426178,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0153,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.24127744138240814,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.019,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.2987695038318634,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0165,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.33492133021354675,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0185,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.20466521382331848,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0151,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.36396247148513794,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0138,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.2000381350517273,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0125,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.24977952241897583,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0152,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.26705336570739746,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0148,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.26699599623680115,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0151,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.20149633288383484,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0151,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.1961003988981247,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0163,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2148503214120865,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0137,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20505128800868988,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0136,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.19462467730045319,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0139,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21602794528007507,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.015,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.22933153808116913,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0142,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.1785646229982376,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0097,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.21535581350326538,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0106,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.2360723614692688,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0123,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.18098825216293335,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0126,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.1836131066083908,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.0125,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.34765973687171936,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.0158,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22595159709453583,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0101,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2811257243156433,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.0111,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.1875840127468109,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0086,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.19390800595283508,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0106,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.3725268244743347,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.0095,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.2201736867427826,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0074,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.17423805594444275,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0072,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.22169643640518188,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0121,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.3247295618057251,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0121,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.1830369532108307,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0077,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.2967239022254944,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0104,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.17589347064495087,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0075,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.15554101765155792,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0063,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.13191422820091248,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0039,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.1909502148628235,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0055,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.16942323744297028,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0055,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.1740521341562271,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.006,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.19565710425376892,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0057,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.13488221168518066,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0033,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.16322746872901917,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0042,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.2087877243757248,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0052,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.12736408412456512,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0051,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.13264045119285583,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0035,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.2015363723039627,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0055,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.21640510857105255,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.008,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.17276327311992645,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0058,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.15923018753528595,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0039,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.14791631698608398,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0032,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.16776816546916962,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0043,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.12374848127365112,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0035,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.13051433861255646,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0036,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.12607790529727936,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0052,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.09630817174911499,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0031,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.11332327872514725,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.0043,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.16632875800132751,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.005,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.12856662273406982,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.0031,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.197174072265625,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0045,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.17151176929473877,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0044,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.14734052121639252,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0053,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.13286560773849487,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0039,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.1636727899312973,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0039,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.1082785576581955,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.0025,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.1716354638338089,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.004,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.14045757055282593,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0026,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.1682705134153366,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0042,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.11872018873691559,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0028,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.12182936072349548,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0018,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.2031281590461731,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0032,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.0959291160106659,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0015,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.15291978418827057,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0036,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.15930163860321045,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0047,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.2150997817516327,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0038,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.1317511945962906,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0032,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.07808093726634979,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0011,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.13284094631671906,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.0037,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.16264718770980835,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0039,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.10431212931871414,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0023,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.08813079446554184,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0018,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.22164294123649597,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0037,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.09111231565475464,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0019,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.0871724933385849,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0014,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.2138734757900238,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0022,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.11238733679056168,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.0023,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.0815015360713005,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0011,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.304352343082428,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.003,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.10469458252191544,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0009,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.1440751701593399,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0025,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.2173687070608139,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0028,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2922506332397461,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.003,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.18853916227817535,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0014,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.12060266733169556,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0015,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14512351155281067,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.002,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.15343990921974182,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0012,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.09639029949903488,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0017,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.09907295554876328,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0012,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.05898207053542137,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0006,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.10509718954563141,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0013,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.17495931684970856,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.001,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.12321923673152924,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.001,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.11147578060626984,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0015,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.06215621903538704,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0006,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.03004705347120762,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0002,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.09312062710523605,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0014,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.05324690416455269,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0005,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.06438126415014267,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0005,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.08646634221076965,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0006,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.05682829022407532,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.11831886321306229,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0006,
+      "step": 228
+    },
+    {
+      "epoch": 3.013157894736842,
+      "grad_norm": 0.0533737950026989,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0003,
+      "step": 229
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.06704334169626236,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0005,
+      "step": 230
+    },
+    {
+      "epoch": 3.039473684210526,
+      "grad_norm": 0.024390004575252533,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0002,
+      "step": 231
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.10754281282424927,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0009,
+      "step": 232
+    },
+    {
+      "epoch": 3.0657894736842106,
+      "grad_norm": 0.032474737614393234,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0002,
+      "step": 233
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.11489477753639221,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0008,
+      "step": 234
+    },
+    {
+      "epoch": 3.0921052631578947,
+      "grad_norm": 0.11805123090744019,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0013,
+      "step": 235
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.04284543916583061,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.1184210526315788,
+      "grad_norm": 0.0592227578163147,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0005,
+      "step": 237
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.08888686448335648,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0007,
+      "step": 238
+    },
+    {
+      "epoch": 3.1447368421052633,
+      "grad_norm": 0.04613477736711502,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0004,
+      "step": 239
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.024109596386551857,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 3.1710526315789473,
+      "grad_norm": 0.04759601503610611,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0002,
+      "step": 241
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.06583128869533539,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0003,
+      "step": 242
+    },
+    {
+      "epoch": 3.1973684210526314,
+      "grad_norm": 0.03406457230448723,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0001,
+      "step": 243
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.020209595561027527,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.0002,
+      "step": 244
+    },
+    {
+      "epoch": 3.223684210526316,
+      "grad_norm": 0.04148108884692192,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0002,
+      "step": 245
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.05275535210967064,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0003,
+      "step": 246
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.03692334517836571,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0004,
+      "step": 247
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.06586624681949615,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0004,
+      "step": 248
+    },
+    {
+      "epoch": 3.276315789473684,
+      "grad_norm": 0.06966730207204819,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0003,
+      "step": 249
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.10422863811254501,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0004,
+      "step": 250
+    },
+    {
+      "epoch": 3.3026315789473686,
+      "grad_norm": 0.10132399946451187,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0008,
+      "step": 251
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.06418923288583755,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0004,
+      "step": 252
+    },
+    {
+      "epoch": 3.3289473684210527,
+      "grad_norm": 0.1488313227891922,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0021,
+      "step": 253
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.05905044823884964,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0006,
+      "step": 254
+    },
+    {
+      "epoch": 3.3552631578947367,
+      "grad_norm": 0.05011991411447525,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0004,
+      "step": 255
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.026315532624721527,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0002,
+      "step": 256
+    },
+    {
+      "epoch": 3.3815789473684212,
+      "grad_norm": 0.031153831630945206,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.019811732694506645,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0001,
+      "step": 258
+    },
+    {
+      "epoch": 3.4078947368421053,
+      "grad_norm": 0.029009979218244553,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0002,
+      "step": 259
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.08594539761543274,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 3.4342105263157894,
+      "grad_norm": 0.07609947770833969,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0006,
+      "step": 261
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.052105486392974854,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0003,
+      "step": 262
+    },
+    {
+      "epoch": 3.4605263157894735,
+      "grad_norm": 0.023044012486934662,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0001,
+      "step": 263
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.01714818924665451,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0001,
+      "step": 264
+    },
+    {
+      "epoch": 3.486842105263158,
+      "grad_norm": 0.024353889748454094,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0002,
+      "step": 265
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.044456806033849716,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0004,
+      "step": 266
+    },
+    {
+      "epoch": 3.513157894736842,
+      "grad_norm": 0.06826099753379822,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0005,
+      "step": 267
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.2765248417854309,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0005,
+      "step": 268
+    },
+    {
+      "epoch": 3.5394736842105265,
+      "grad_norm": 0.04589018225669861,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0004,
+      "step": 269
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.023166710510849953,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0001,
+      "step": 270
+    },
+    {
+      "epoch": 3.5657894736842106,
+      "grad_norm": 0.03657109662890434,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0002,
+      "step": 271
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.08881364017724991,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0004,
+      "step": 272
+    },
+    {
+      "epoch": 3.5921052631578947,
+      "grad_norm": 0.022605225443840027,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0001,
+      "step": 273
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.05161530151963234,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0002,
+      "step": 274
+    },
+    {
+      "epoch": 3.6184210526315788,
+      "grad_norm": 0.039631813764572144,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0003,
+      "step": 275
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.03075975738465786,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0001,
+      "step": 276
+    },
+    {
+      "epoch": 3.6447368421052633,
+      "grad_norm": 0.04068103805184364,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0001,
+      "step": 277
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.08374299108982086,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0006,
+      "step": 278
+    },
+    {
+      "epoch": 3.6710526315789473,
+      "grad_norm": 0.014881132170557976,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0001,
+      "step": 279
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.08170844614505768,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0004,
+      "step": 280
+    },
+    {
+      "epoch": 3.6973684210526314,
+      "grad_norm": 0.02605108916759491,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0001,
+      "step": 281
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.056749701499938965,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0008,
+      "step": 282
+    },
+    {
+      "epoch": 3.723684210526316,
+      "grad_norm": 0.043280281126499176,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0002,
+      "step": 283
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.01662975363433361,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0001,
+      "step": 284
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.045024238526821136,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0001,
+      "step": 285
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.02116972580552101,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0001,
+      "step": 286
+    },
+    {
+      "epoch": 3.776315789473684,
+      "grad_norm": 0.028999928385019302,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0001,
+      "step": 287
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.05580444633960724,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0006,
+      "step": 288
+    },
+    {
+      "epoch": 3.8026315789473686,
+      "grad_norm": 0.03946217522025108,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0002,
+      "step": 289
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.01824789121747017,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0001,
+      "step": 290
+    },
+    {
+      "epoch": 3.8289473684210527,
+      "grad_norm": 0.09996017813682556,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0002,
+      "step": 291
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.04970015585422516,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0002,
+      "step": 292
+    },
+    {
+      "epoch": 3.8552631578947367,
+      "grad_norm": 0.05343327671289444,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0003,
+      "step": 293
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.007754841353744268,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8815789473684212,
+      "grad_norm": 0.06841913610696793,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0002,
+      "step": 295
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.0050100889056921005,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 3.9078947368421053,
+      "grad_norm": 0.2890152931213379,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0001,
+      "step": 297
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.010258257389068604,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 3.9342105263157894,
+      "grad_norm": 0.031965699046850204,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0001,
+      "step": 299
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.00890852976590395,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9605263157894735,
+      "grad_norm": 0.030713632702827454,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0001,
+      "step": 301
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.010088774375617504,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.986842105263158,
+      "grad_norm": 0.006950493901968002,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.03781810402870178,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0003,
+      "step": 304
+    },
+    {
+      "epoch": 4.0131578947368425,
+      "grad_norm": 0.028575751930475235,
+      "learning_rate": 1.9099529895768552e-06,
+      "loss": 0.0002,
+      "step": 305
+    },
+    {
+      "epoch": 4.026315789473684,
+      "grad_norm": 0.007214389741420746,
+      "learning_rate": 1.8885377742480005e-06,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 4.0394736842105265,
+      "grad_norm": 0.021563267335295677,
+      "learning_rate": 1.8671701764162287e-06,
+      "loss": 0.0001,
+      "step": 307
+    },
+    {
+      "epoch": 4.052631578947368,
+      "grad_norm": 0.014376094564795494,
+      "learning_rate": 1.8458518600788988e-06,
+      "loss": 0.0001,
+      "step": 308
+    },
+    {
+      "epoch": 4.065789473684211,
+      "grad_norm": 0.010882866568863392,
+      "learning_rate": 1.8245844853955786e-06,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 4.078947368421052,
+      "grad_norm": 0.007655533961951733,
+      "learning_rate": 1.8033697085587698e-06,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 4.092105263157895,
+      "grad_norm": 0.004504406359046698,
+      "learning_rate": 1.782209181664924e-06,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 4.105263157894737,
+      "grad_norm": 0.00908347126096487,
+      "learning_rate": 1.7611045525857902e-06,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 4.118421052631579,
+      "grad_norm": 0.012282164767384529,
+      "learning_rate": 1.740057464840088e-06,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 4.131578947368421,
+      "grad_norm": 0.006549667567014694,
+      "learning_rate": 1.7190695574655147e-06,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 4.144736842105263,
+      "grad_norm": 0.025752369314432144,
+      "learning_rate": 1.6981424648911112e-06,
+      "loss": 0.0001,
+      "step": 315
+    },
+    {
+      "epoch": 4.157894736842105,
+      "grad_norm": 0.0477922260761261,
+      "learning_rate": 1.677277816809975e-06,
+      "loss": 0.0002,
+      "step": 316
+    },
+    {
+      "epoch": 4.171052631578948,
+      "grad_norm": 0.026114268228411674,
+      "learning_rate": 1.6564772380523546e-06,
+      "loss": 0.0001,
+      "step": 317
+    },
+    {
+      "epoch": 4.184210526315789,
+      "grad_norm": 0.02332746423780918,
+      "learning_rate": 1.635742348459109e-06,
+      "loss": 0.0001,
+      "step": 318
+    },
+    {
+      "epoch": 4.197368421052632,
+      "grad_norm": 0.008722717873752117,
+      "learning_rate": 1.6150747627555713e-06,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.004474959336221218,
+      "learning_rate": 1.5944760904257944e-06,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 4.223684210526316,
+      "grad_norm": 0.0274661872535944,
+      "learning_rate": 1.5739479355872162e-06,
+      "loss": 0.0001,
+      "step": 321
+    },
+    {
+      "epoch": 4.2368421052631575,
+      "grad_norm": 0.008118880912661552,
+      "learning_rate": 1.5534918968657423e-06,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.011024386622011662,
+      "learning_rate": 1.5331095672712463e-06,
+      "loss": 0.0001,
+      "step": 323
+    },
+    {
+      "epoch": 4.2631578947368425,
+      "grad_norm": 0.00726787094026804,
+      "learning_rate": 1.5128025340735223e-06,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 4.276315789473684,
+      "grad_norm": 0.003688193392008543,
+      "learning_rate": 1.4925723786786691e-06,
+      "loss": 0.0,
+      "step": 325
+    },
+    {
+      "epoch": 4.2894736842105265,
+      "grad_norm": 0.045026637613773346,
+      "learning_rate": 1.4724206765059456e-06,
+      "loss": 0.0002,
+      "step": 326
+    },
+    {
+      "epoch": 4.302631578947368,
+      "grad_norm": 0.004103303886950016,
+      "learning_rate": 1.4523489968650795e-06,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 4.315789473684211,
+      "grad_norm": 0.0039488510228693485,
+      "learning_rate": 1.4323589028340598e-06,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 4.328947368421053,
+      "grad_norm": 0.004720236640423536,
+      "learning_rate": 1.4124519511374158e-06,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 4.342105263157895,
+      "grad_norm": 0.004932956770062447,
+      "learning_rate": 1.3926296920249796e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 4.355263157894737,
+      "grad_norm": 0.017614832147955894,
+      "learning_rate": 1.3728936691511704e-06,
+      "loss": 0.0001,
+      "step": 331
+    },
+    {
+      "epoch": 4.368421052631579,
+      "grad_norm": 0.004803107585757971,
+      "learning_rate": 1.3532454194547734e-06,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 4.381578947368421,
+      "grad_norm": 0.028480617329478264,
+      "learning_rate": 1.3336864730392587e-06,
+      "loss": 0.0001,
+      "step": 333
+    },
+    {
+      "epoch": 4.394736842105263,
+      "grad_norm": 0.0031023717019706964,
+      "learning_rate": 1.314218353053619e-06,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 4.407894736842105,
+      "grad_norm": 0.008832458406686783,
+      "learning_rate": 1.2948425755737592e-06,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.005478347185999155,
+      "learning_rate": 1.2755606494844294e-06,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 4.434210526315789,
+      "grad_norm": 0.012723652645945549,
+      "learning_rate": 1.2563740763617198e-06,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 4.447368421052632,
+      "grad_norm": 0.007557735778391361,
+      "learning_rate": 1.2372843503561318e-06,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 4.4605263157894735,
+      "grad_norm": 0.02057843655347824,
+      "learning_rate": 1.218292958076213e-06,
+      "loss": 0.0001,
+      "step": 339
+    },
+    {
+      "epoch": 4.473684210526316,
+      "grad_norm": 0.006118930876255035,
+      "learning_rate": 1.1994013784727948e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 4.4868421052631575,
+      "grad_norm": 0.0338875874876976,
+      "learning_rate": 1.180611082723814e-06,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.01357252337038517,
+      "learning_rate": 1.161923534119752e-06,
+      "loss": 0.0001,
+      "step": 342
+    },
+    {
+      "epoch": 4.5131578947368425,
+      "grad_norm": 0.014216500334441662,
+      "learning_rate": 1.1433401879496723e-06,
+      "loss": 0.0001,
+      "step": 343
+    },
+    {
+      "epoch": 4.526315789473684,
+      "grad_norm": 0.004121949430555105,
+      "learning_rate": 1.1248624913878966e-06,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 4.5394736842105265,
+      "grad_norm": 0.005702656228095293,
+      "learning_rate": 1.1064918833813073e-06,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 4.552631578947368,
+      "grad_norm": 0.0023520493414252996,
+      "learning_rate": 1.088229794537283e-06,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 4.565789473684211,
+      "grad_norm": 0.0023677553981542587,
+      "learning_rate": 1.0700776470122981e-06,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 4.578947368421053,
+      "grad_norm": 0.01764129102230072,
+      "learning_rate": 1.0520368544011661e-06,
+      "loss": 0.0001,
+      "step": 348
+    },
+    {
+      "epoch": 4.592105263157895,
+      "grad_norm": 0.008476192131638527,
+      "learning_rate": 1.0341088216269625e-06,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 4.605263157894737,
+      "grad_norm": 0.0017920136451721191,
+      "learning_rate": 1.0162949448316089e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 4.618421052631579,
+      "grad_norm": 0.0061067817732691765,
+      "learning_rate": 9.98596611267158e-07,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.004206137731671333,
+      "learning_rate": 9.81015199187753e-07,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 4.644736842105263,
+      "grad_norm": 0.02187529392540455,
+      "learning_rate": 9.63552077742301e-07,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 4.657894736842105,
+      "grad_norm": 0.0074692717753350735,
+      "learning_rate": 9.462086068678519e-07,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 4.671052631578947,
+      "grad_norm": 0.004613088443875313,
+      "learning_rate": 9.289861371836886e-07,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 4.684210526315789,
+      "grad_norm": 0.0051763323135674,
+      "learning_rate": 9.118860098861538e-07,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 4.697368421052632,
+      "grad_norm": 0.004479160998016596,
+      "learning_rate": 8.949095566441985e-07,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 4.7105263157894735,
+      "grad_norm": 0.0031334473751485348,
+      "learning_rate": 8.78058099495685e-07,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 4.723684210526316,
+      "grad_norm": 0.005216387566179037,
+      "learning_rate": 8.613329507444274e-07,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.0030827040318399668,
+      "learning_rate": 8.44735412857999e-07,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.008658899925649166,
+      "learning_rate": 8.282667783663056e-07,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 4.7631578947368425,
+      "grad_norm": 0.00587991438806057,
+      "learning_rate": 8.119283297609238e-07,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 4.776315789473684,
+      "grad_norm": 0.01003989763557911,
+      "learning_rate": 7.957213393952335e-07,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 4.7894736842105265,
+      "grad_norm": 0.005186410155147314,
+      "learning_rate": 7.796470693853281e-07,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 4.802631578947368,
+      "grad_norm": 0.0056229582987725735,
+      "learning_rate": 7.637067715117327e-07,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 4.815789473684211,
+      "grad_norm": 0.002910787472501397,
+      "learning_rate": 7.479016871219174e-07,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 4.828947368421053,
+      "grad_norm": 0.025458911433815956,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0001,
+      "step": 367
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.008555232547223568,
+      "learning_rate": 7.167020714390502e-07,
+      "loss": 0.0,
+      "step": 368
+    },
+    {
+      "epoch": 4.855263157894737,
+      "grad_norm": 0.012796996161341667,
+      "learning_rate": 7.013099698097539e-07,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 4.868421052631579,
+      "grad_norm": 0.008186944760382175,
+      "learning_rate": 6.860579408025436e-07,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 4.881578947368421,
+      "grad_norm": 0.008431337773799896,
+      "learning_rate": 6.709471721660904e-07,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 4.894736842105263,
+      "grad_norm": 0.021517649292945862,
+      "learning_rate": 6.559788406484446e-07,
+      "loss": 0.0001,
+      "step": 372
+    },
+    {
+      "epoch": 4.907894736842105,
+      "grad_norm": 0.008807409554719925,
+      "learning_rate": 6.41154111905393e-07,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 4.921052631578947,
+      "grad_norm": 0.028927143663167953,
+      "learning_rate": 6.264741404096875e-07,
+      "loss": 0.0001,
+      "step": 374
+    },
+    {
+      "epoch": 4.934210526315789,
+      "grad_norm": 0.008634347468614578,
+      "learning_rate": 6.119400693611358e-07,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 4.947368421052632,
+      "grad_norm": 0.0028107326943427324,
+      "learning_rate": 5.975530305975808e-07,
+      "loss": 0.0,
+      "step": 376
+    },
+    {
+      "epoch": 4.9605263157894735,
+      "grad_norm": 0.0016718370607122779,
+      "learning_rate": 5.833141445067541e-07,
+      "loss": 0.0,
+      "step": 377
+    },
+    {
+      "epoch": 4.973684210526316,
+      "grad_norm": 0.007590409368276596,
+      "learning_rate": 5.692245199390281e-07,
+      "loss": 0.0,
+      "step": 378
+    },
+    {
+      "epoch": 4.9868421052631575,
+      "grad_norm": 0.003609555773437023,
+      "learning_rate": 5.552852541210651e-07,
+      "loss": 0.0,
+      "step": 379
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.03264299035072327,
+      "learning_rate": 5.414974325703687e-07,
+      "loss": 0.0001,
+      "step": 380
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4446096401561027e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-380/training_args.bin b/checkpoint-380/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd15c797edde13f0f3e0490d0aec249c013df912
--- /dev/null
+++ b/checkpoint-380/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebcaf257fe89a74904f6ea50b526a559eb74a53ebc4dfb373932a4d0fa515f5
+size 7928
diff --git a/checkpoint-380/zero_to_fp32.py b/checkpoint-380/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8
--- /dev/null
+++ b/checkpoint-380/zero_to_fp32.py
@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-76/README.md b/checkpoint-76/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1b184114a0c28ed3e4c082c18486736dc818166d
--- /dev/null
+++ b/checkpoint-76/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0
\ No newline at end of file
diff --git a/checkpoint-76/adapter_config.json b/checkpoint-76/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..763d98264e556bcbc60c63c5b9f70b53c7bbe722
--- /dev/null
+++ b/checkpoint-76/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-76/adapter_model.safetensors b/checkpoint-76/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..db58bd213b3090ac6c620e1a62b8c7a7d6ffe43e
--- /dev/null
+++ b/checkpoint-76/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0adf11ea8989f8925fd2a1c5ea841eec2675aef8b0edf99afc159d34fbdf512d
+size 10829849744
diff --git a/checkpoint-76/global_step76/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-76/global_step76/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9284b074cc9938abb3904f0f98bca8fd9c20172d
--- /dev/null
+++ b/checkpoint-76/global_step76/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a24f96602c436bd3643e2ebd7bb35792c78d154ea76be6b1ec0cf0434aac0a4
+size 21659418140
diff --git a/checkpoint-76/global_step76/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-76/global_step76/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..454bcb1e198a56ccfa782c501379e94e0c1048a0
--- /dev/null
+++ b/checkpoint-76/global_step76/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540de66bfffd0df8dba29a777ffca49e244a43e33fac83bdeb116c74ca6c603d
+size 21659457372
diff --git a/checkpoint-76/global_step76/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-76/global_step76/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4831774b32b17b6fdb0e5300518c95390a15ce53
--- /dev/null
+++ b/checkpoint-76/global_step76/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9f8de718771f2b937e78986446656e9bc408f1b5aa039ab191dccee57efd50
+size 21659417820
diff --git a/checkpoint-76/global_step76/mp_rank_00_model_states.pt b/checkpoint-76/global_step76/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..79b7e8051b705f1e754c936c51339d343fdd39ae
--- /dev/null
+++ b/checkpoint-76/global_step76/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7353e33af25bbe1dc5f514aa7f92a6f391ca5f640fc22416b0551e0a03950405
+size 11918643933
diff --git a/checkpoint-76/latest b/checkpoint-76/latest
new file mode 100644
index 0000000000000000000000000000000000000000..3137f19948d5aa563b9948e1161e2ee9665c4f33
--- /dev/null
+++ b/checkpoint-76/latest
@@ -0,0 +1 @@
+global_step76
\ No newline at end of file
diff --git a/checkpoint-76/rng_state_0.pth b/checkpoint-76/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f0243a35107f9351684b4b491b92475dc82efd3d
--- /dev/null
+++ b/checkpoint-76/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4caef4c46f6d195a03b7ac9efc175ac61a61d226f3ba835e0fb9bac39e6bc64
+size 14768
diff --git a/checkpoint-76/rng_state_1.pth b/checkpoint-76/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..81018554b8d83534e404729a34be576aba370f9e
--- /dev/null
+++ b/checkpoint-76/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33674d0cb90389e7c73070665b3a44c29b2a2e3d5ae9dd280aeddf03fcad3db6
+size 14768
diff --git a/checkpoint-76/rng_state_2.pth b/checkpoint-76/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb9fddced9c2ef113e1fe83cb8d35aae87b9c46a
--- /dev/null
+++ b/checkpoint-76/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86d3f237c14ca71c248f48fd103d5f3f60e3d6f92df22f71396c5e09ff918ae
+size 14768
diff --git a/checkpoint-76/scheduler.pt b/checkpoint-76/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f7c7c864b80bf300100f0f6e4794b1332e6b06fe
--- /dev/null
+++ b/checkpoint-76/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c315fe8040ff17806bbc85e0852bb90368308daf9b2756cfe9934a4972441ebd
+size 1064
diff --git a/checkpoint-76/special_tokens_map.json b/checkpoint-76/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/checkpoint-76/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-76/tokenizer.json b/checkpoint-76/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-76/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-76/tokenizer_config.json b/checkpoint-76/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/checkpoint-76/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-76/trainer_state.json b/checkpoint-76/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fb58c593aa737ea599c5058db5a382067a9ba983
--- /dev/null
+++ b/checkpoint-76/trainer_state.json
@@ -0,0 +1,565 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 76,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 37.79440689086914,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.1402,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 38.45823287963867,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 3.1787,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 38.25625228881836,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.1316,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 37.2024040222168,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.1011,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 38.17294692993164,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 3.133,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 37.374794006347656,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.0731,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 37.226966857910156,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.069,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 38.40094757080078,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 3.1223,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 37.86320877075195,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.062,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 38.02171325683594,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.0008,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 38.5522346496582,
+      "learning_rate": 5.5e-07,
+      "loss": 3.0047,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 37.72829818725586,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.9274,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 38.488494873046875,
+      "learning_rate": 6.5e-07,
+      "loss": 2.8727,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 38.87471389770508,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.8422,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 37.584896087646484,
+      "learning_rate": 7.5e-07,
+      "loss": 2.6728,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 37.04607391357422,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.5215,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 37.30121994018555,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.4689,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 35.99961853027344,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.3,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 35.817543029785156,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 2.1423,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 35.056915283203125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 34.83850860595703,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.7845,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 34.32366943359375,
+      "learning_rate": 1.1e-06,
+      "loss": 1.5864,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 33.79611587524414,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.4011,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 32.596031188964844,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 30.045007705688477,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9883,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.89093589782715,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7669,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 23.454408645629883,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.6304,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 19.837312698364258,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.4717,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 15.185093879699707,
+      "learning_rate": 1.45e-06,
+      "loss": 0.363,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 9.057796478271484,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2439,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 5.976982593536377,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1864,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.067375421524048,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1134,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.3589119911193848,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0985,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.0044353008270264,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.0859,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.4279972314834595,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0728,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.9807674288749695,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.061,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.906160295009613,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8837690353393555,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0622,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.9579435586929321,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0557,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.8149510622024536,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.8899760246276855,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0517,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.6007645130157471,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0518,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.48819127678871155,
+      "learning_rate": 2.15e-06,
+      "loss": 0.0429,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.42939358949661255,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5706579685211182,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0453,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.3034597337245941,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.5601783394813538,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0411,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.35388317704200745,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.04,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.48609891533851624,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.04,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.4638507068157196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.5685771703720093,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0428,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.46358174085617065,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0483,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.35054436326026917,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0391,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3350559175014496,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.039,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.2875112295150757,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0383,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.4492928683757782,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0358,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29484888911247253,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0355,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.36551928520202637,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0403,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.4458053708076477,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0342,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.34047460556030273,
+      "learning_rate": 3e-06,
+      "loss": 0.0302,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3420606255531311,
+      "learning_rate": 3.05e-06,
+      "loss": 0.034,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3902851939201355,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0327,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29165828227996826,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0341,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.40872958302497864,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.035,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.36295783519744873,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0323,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.3857724368572235,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.3207017481327057,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0332,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2903987169265747,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0327,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.3386954963207245,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0308,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.4339621365070343,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0361,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.28095564246177673,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0306,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4141469895839691,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.028,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.35212820768356323,
+      "learning_rate": 3.65e-06,
+      "loss": 0.032,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.26956063508987427,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0294,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.32735681533813477,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0272,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4906782805919647,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0324,
+      "step": 76
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 76,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.889219280312205e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-76/training_args.bin b/checkpoint-76/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd15c797edde13f0f3e0490d0aec249c013df912
--- /dev/null
+++ b/checkpoint-76/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebcaf257fe89a74904f6ea50b526a559eb74a53ebc4dfb373932a4d0fa515f5
+size 7928
diff --git a/checkpoint-76/zero_to_fp32.py b/checkpoint-76/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8
--- /dev/null
+++ b/checkpoint-76/zero_to_fp32.py
@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9d764aead97a826f7aae3b9cfcfe2606e1d2eeec
--- /dev/null
+++ b/config.json
@@ -0,0 +1,52 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca91a2ef55f4239a7af81d7c9abb05f53621a07b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}