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..997faa1b89c230966ec24841fa4d3fbf3dcaedd6
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_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..fdf619c317c2fe82074662582dbd68166b6f9d50
--- /dev/null
+++ b/checkpoint-152/README.md
@@ -0,0 +1,202 @@
+---
+base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+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..a192388a7b55129be9ad9168abc396b47bbda6f7
--- /dev/null
+++ b/checkpoint-152/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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..37bf07bb5ac06c1eff8cfca5b99d2e928094699f
--- /dev/null
+++ b/checkpoint-152/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0c61458020c30affe57a79c4c7d5f769fe8b936ffb7021ed5dab0c45b17a70
+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..f9c833582c7cff5c7c9faa52143f7512a66f8b22
--- /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 sha256:2fe8afff7aaba765b6240a521193dbf428c406b06475e9129624dc50d67a5a52
+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..cb62cd8861cc2766c3902b9071bca96f19b818bc
--- /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 sha256:193cd1f2b2e47fd145128f3307fbe4114ddd4cfa36e3dd861e8291f98806a3df
+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..5d23c6471b732d4fe19254dda9e47c9990ee0693
--- /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 sha256:3b068efe3c1a280067ef6499a0a9f9e4d687740eaa33639912116d7b8738b9ea
+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..a7f86072d7cd8f79e7ab04fc7592779bbf75eb27
--- /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 sha256:6b08c67c92634fcdf05035a39e0631e5a64899934bd4781c74b05282f0571716
+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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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..5021b354c42aae3511fd76c6ddacbdb31b31179a
--- /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": 34.99433898925781,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.595,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 35.6848258972168,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.6447,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 35.07997512817383,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.5819,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 34.3863525390625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 35.443077087402344,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 34.70173263549805,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.5487,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 34.421295166015625,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.5494,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 35.152748107910156,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.5936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 34.947021484375,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.5574,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 34.67315673828125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.4894,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 34.679954528808594,
+      "learning_rate": 5.5e-07,
+      "loss": 2.4985,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 33.57002258300781,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 33.517276763916016,
+      "learning_rate": 6.5e-07,
+      "loss": 2.4055,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 33.5312385559082,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.3806,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 32.01276779174805,
+      "learning_rate": 7.5e-07,
+      "loss": 2.2505,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 31.827980041503906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 31.437101364135742,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.1117,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 30.315187454223633,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.9795,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 29.622655868530273,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.8472,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 28.628408432006836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7283,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 27.83180046081543,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.5942,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 26.911596298217773,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4467,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 25.88102149963379,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.3007,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 25.146381378173828,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1319,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 24.800382614135742,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9359,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.648332595825195,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7054,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 22.947620391845703,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 17.80010414123535,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 11.841789245605469,
+      "learning_rate": 1.45e-06,
+      "loss": 0.26,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 7.275839805603027,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1808,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 4.6324543952941895,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.1281485557556152,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.062562942504883,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0966,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.1343328952789307,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.6768524646759033,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0783,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.0879229307174683,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0623,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.83177649974823,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0655,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5678385496139526,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0565,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.6994458436965942,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0491,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.711387038230896,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0507,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.7169735431671143,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0478,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.603631317615509,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0507,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.617487907409668,
+      "learning_rate": 2.15e-06,
+      "loss": 0.043,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.4638065993785858,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5996385216712952,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0429,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.39118286967277527,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.3118075728416443,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31731992959976196,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.041,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.5413194298744202,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.32958006858825684,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.596309244632721,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0413,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.4557362496852875,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0461,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.3345410227775574,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0385,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3047848343849182,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0383,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.43763449788093567,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.038,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.26870036125183105,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0374,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.38762542605400085,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0349,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.27517396211624146,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0398,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.30815261602401733,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0364,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.30011361837387085,
+      "learning_rate": 3e-06,
+      "loss": 0.0307,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3269154727458954,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0344,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3750869333744049,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0339,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29285815358161926,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.034,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.4157550632953644,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0348,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.2852867543697357,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0319,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.4384031593799591,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0319,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.4003254771232605,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0347,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.49913832545280457,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0347,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.22642269730567932,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0306,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.34004101157188416,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0337,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.21503636240959167,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0311,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.33802086114883423,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2488064169883728,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0318,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.21124528348445892,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0293,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.3108712136745453,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33483418822288513,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.031,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3099130690097809,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0286,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.22946476936340332,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0307,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.36924120783805847,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.30895617604255676,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0274,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.42033568024635315,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0298,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.35573887825012207,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0286,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.24631913006305695,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0294,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.2908592224121094,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0243,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3293064832687378,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0253,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3789626359939575,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0253,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3900983929634094,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0248,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.28972727060317993,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0256,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.4615432620048523,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0259,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3959222137928009,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0277,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.4927828907966614,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0251,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23854510486125946,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0214,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.2470882534980774,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0255,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.22575952112674713,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0208,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.437495619058609,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0234,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.2712303102016449,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0236,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.2843461334705353,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0195,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.21141311526298523,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0223,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.25484079122543335,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0211,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.358674556016922,
+      "learning_rate": 5e-06,
+      "loss": 0.027,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.20442990958690643,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0234,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.2281407117843628,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0243,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.23803724348545074,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0189,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.21493025124073029,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0207,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.2565159797668457,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0178,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3488551378250122,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0226,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.27695611119270325,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0189,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.23477056622505188,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0182,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22611404955387115,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0168,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.25616368651390076,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.022,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.23842717707157135,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0163,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.24285905063152313,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0202,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24602730572223663,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0173,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.26218464970588684,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0206,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.2999787926673889,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0178,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.20500704646110535,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0181,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.25106561183929443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0128,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2686936855316162,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0146,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.2770400047302246,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0167,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.27510589361190796,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0162,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.3720133602619171,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0163,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.2288741022348404,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0133,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.31084850430488586,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0124,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.19490985572338104,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0114,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.3074445426464081,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0153,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.29279908537864685,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0117,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.3299407362937927,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0128,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.24818794429302216,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0146,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.35983219742774963,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0138,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2583932876586914,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0136,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20754319429397583,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0116,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.30609601736068726,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0111,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.3754304349422455,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0126,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.2517055571079254,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0118,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.198478102684021,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0087,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.2307695895433426,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0094,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.17823486030101776,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0098,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.2157433032989502,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0114,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.21051311492919922,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.011,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.32886555790901184,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.011,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22413378953933716,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0087,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2896019518375397,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.011,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.26163023710250854,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0084,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.23998413980007172,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0094,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.2334728091955185,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.007,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.17431940138339996,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0047,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.19151932001113892,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0056,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.2352588027715683,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0107,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.2848915159702301,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0074,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.218011736869812,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0075,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.3043143153190613,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0073,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16677772998809814,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0065,
+      "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..5a1edbdcc63a93daa09112168cf20c0f8fcb7512
--- /dev/null
+++ b/checkpoint-152/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041cfaa5bf8383821dea4fa5a9d2eab2caad4644c4cd651398c8b0ab1541b270
+size 7992
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..fdf619c317c2fe82074662582dbd68166b6f9d50
--- /dev/null
+++ b/checkpoint-228/README.md
@@ -0,0 +1,202 @@
+---
+base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+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..a192388a7b55129be9ad9168abc396b47bbda6f7
--- /dev/null
+++ b/checkpoint-228/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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..552238fb19f5bee846efa646160c8a6de77c7fa5
--- /dev/null
+++ b/checkpoint-228/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ce11f4b2ce49bf748bc7fdaad8acb0700e9819541af009bb2f641b962cd27d
+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..ade9d2a22111f8db8781f64e595d28131c276828
--- /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:d37d6738b6c219466caf1821d05aa5edf4b0fd99e128743bb42259934efbcb77
+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..4050e7420030871334cc998bf4caf4cb9d8e21d9
--- /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:a88511d54c9d9a9c220a6746b09ac106594ca8a7dd0b6a68c600206a4317f0bc
+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..9e732369059ca208581df3274ca7c58a47c6465c
--- /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:abc6d214d1e3892f0f1a4ba79c1f88979e993f1311f740deaa3fea6045a076a1
+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..622707c19a9df03a293d46b1fde2a8c941a5ecff
--- /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 sha256:7569f86e5b8ad4531c06e5247ce8f5365b9ff384a45c41572a37f7795e769612
+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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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..8d6baf0d1c0b59d58524e279fb3843787c04fca6
--- /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": 34.99433898925781,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.595,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 35.6848258972168,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.6447,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 35.07997512817383,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.5819,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 34.3863525390625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 35.443077087402344,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 34.70173263549805,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.5487,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 34.421295166015625,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.5494,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 35.152748107910156,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.5936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 34.947021484375,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.5574,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 34.67315673828125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.4894,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 34.679954528808594,
+      "learning_rate": 5.5e-07,
+      "loss": 2.4985,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 33.57002258300781,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 33.517276763916016,
+      "learning_rate": 6.5e-07,
+      "loss": 2.4055,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 33.5312385559082,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.3806,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 32.01276779174805,
+      "learning_rate": 7.5e-07,
+      "loss": 2.2505,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 31.827980041503906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 31.437101364135742,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.1117,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 30.315187454223633,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.9795,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 29.622655868530273,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.8472,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 28.628408432006836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7283,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 27.83180046081543,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.5942,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 26.911596298217773,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4467,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 25.88102149963379,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.3007,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 25.146381378173828,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1319,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 24.800382614135742,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9359,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.648332595825195,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7054,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 22.947620391845703,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 17.80010414123535,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 11.841789245605469,
+      "learning_rate": 1.45e-06,
+      "loss": 0.26,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 7.275839805603027,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1808,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 4.6324543952941895,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.1281485557556152,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.062562942504883,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0966,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.1343328952789307,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.6768524646759033,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0783,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.0879229307174683,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0623,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.83177649974823,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0655,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5678385496139526,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0565,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.6994458436965942,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0491,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.711387038230896,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0507,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.7169735431671143,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0478,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.603631317615509,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0507,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.617487907409668,
+      "learning_rate": 2.15e-06,
+      "loss": 0.043,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.4638065993785858,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5996385216712952,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0429,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.39118286967277527,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.3118075728416443,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31731992959976196,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.041,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.5413194298744202,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.32958006858825684,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.596309244632721,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0413,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.4557362496852875,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0461,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.3345410227775574,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0385,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3047848343849182,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0383,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.43763449788093567,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.038,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.26870036125183105,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0374,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.38762542605400085,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0349,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.27517396211624146,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0398,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.30815261602401733,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0364,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.30011361837387085,
+      "learning_rate": 3e-06,
+      "loss": 0.0307,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3269154727458954,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0344,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3750869333744049,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0339,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29285815358161926,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.034,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.4157550632953644,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0348,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.2852867543697357,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0319,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.4384031593799591,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0319,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.4003254771232605,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0347,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.49913832545280457,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0347,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.22642269730567932,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0306,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.34004101157188416,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0337,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.21503636240959167,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0311,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.33802086114883423,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2488064169883728,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0318,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.21124528348445892,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0293,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.3108712136745453,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33483418822288513,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.031,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3099130690097809,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0286,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.22946476936340332,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0307,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.36924120783805847,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.30895617604255676,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0274,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.42033568024635315,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0298,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.35573887825012207,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0286,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.24631913006305695,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0294,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.2908592224121094,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0243,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3293064832687378,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0253,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3789626359939575,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0253,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3900983929634094,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0248,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.28972727060317993,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0256,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.4615432620048523,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0259,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3959222137928009,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0277,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.4927828907966614,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0251,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23854510486125946,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0214,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.2470882534980774,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0255,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.22575952112674713,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0208,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.437495619058609,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0234,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.2712303102016449,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0236,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.2843461334705353,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0195,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.21141311526298523,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0223,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.25484079122543335,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0211,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.358674556016922,
+      "learning_rate": 5e-06,
+      "loss": 0.027,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.20442990958690643,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0234,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.2281407117843628,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0243,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.23803724348545074,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0189,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.21493025124073029,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0207,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.2565159797668457,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0178,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3488551378250122,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0226,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.27695611119270325,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0189,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.23477056622505188,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0182,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22611404955387115,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0168,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.25616368651390076,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.022,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.23842717707157135,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0163,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.24285905063152313,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0202,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24602730572223663,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0173,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.26218464970588684,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0206,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.2999787926673889,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0178,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.20500704646110535,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0181,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.25106561183929443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0128,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2686936855316162,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0146,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.2770400047302246,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0167,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.27510589361190796,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0162,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.3720133602619171,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0163,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.2288741022348404,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0133,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.31084850430488586,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0124,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.19490985572338104,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0114,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.3074445426464081,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0153,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.29279908537864685,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0117,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.3299407362937927,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0128,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.24818794429302216,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0146,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.35983219742774963,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0138,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2583932876586914,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0136,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20754319429397583,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0116,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.30609601736068726,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0111,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.3754304349422455,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0126,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.2517055571079254,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0118,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.198478102684021,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0087,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.2307695895433426,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0094,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.17823486030101776,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0098,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.2157433032989502,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0114,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.21051311492919922,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.011,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.32886555790901184,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.011,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22413378953933716,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0087,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2896019518375397,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.011,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.26163023710250854,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0084,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.23998413980007172,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0094,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.2334728091955185,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.007,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.17431940138339996,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0047,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.19151932001113892,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0056,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.2352588027715683,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0107,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.2848915159702301,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0074,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.218011736869812,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0075,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.3043143153190613,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0073,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16677772998809814,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0065,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.14940837025642395,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0034,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.14960654079914093,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0034,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.2261868566274643,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0034,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.20907555520534515,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0045,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.15571005642414093,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.0032,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.16968725621700287,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0044,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.1937742531299591,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0027,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.14914007484912872,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0031,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.19651293754577637,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0043,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.2023143172264099,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0036,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.17952999472618103,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0024,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.18410134315490723,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0054,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.18808087706565857,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.0039,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.12346187978982925,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0036,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.140532448887825,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0028,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.8201041221618652,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0028,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.26919177174568176,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0032,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.1321878731250763,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0023,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.12545251846313477,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0024,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.1377445012331009,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0033,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.10942364484071732,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0023,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.17425717413425446,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.003,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.15876342356204987,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.0034,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.1537884920835495,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.002,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.13558532297611237,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0021,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.14405666291713715,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0028,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.19296719133853912,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0034,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.2153935730457306,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0032,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.11674188822507858,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0013,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.21349935233592987,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.002,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.16676126420497894,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.0015,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.20975975692272186,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0025,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.3014683425426483,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0031,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.1687438040971756,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0014,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.13351179659366608,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0012,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.4079025387763977,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0026,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.12639036774635315,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0017,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.1551010012626648,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0022,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.1431741863489151,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0022,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.39600786566734314,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0031,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.13951376080513,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0016,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.10893042385578156,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0007,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.16801239550113678,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.002,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.11393369734287262,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0017,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.23128700256347656,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0018,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.06730300188064575,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0006,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.11693810671567917,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0012,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.1186346486210823,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0012,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.2584531605243683,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0025,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.09868124127388,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0017,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.09907737374305725,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.002,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.06743597984313965,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0006,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.08913715183734894,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.0007,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.12334564328193665,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0006,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.10878646373748779,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0016,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.10623253136873245,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0015,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.15580499172210693,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.0011,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.06405838578939438,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0007,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.17784689366817474,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0017,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14516866207122803,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.0014,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.09510776400566101,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0009,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.1000828891992569,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0008,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.10773428529500961,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0008,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.12319213151931763,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0007,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.07209170609712601,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0006,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.12889248132705688,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.0005,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.05019540339708328,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.0003,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.10657542198896408,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0008,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.15984083712100983,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0003,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.1567343920469284,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0005,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.07294822484254837,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0006,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.04486699402332306,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0003,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.08188032358884811,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0004,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.029995013028383255,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0002,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.029155094176530838,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0002,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.058334361761808395,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0003,
+      "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..5a1edbdcc63a93daa09112168cf20c0f8fcb7512
--- /dev/null
+++ b/checkpoint-228/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041cfaa5bf8383821dea4fa5a9d2eab2caad4644c4cd651398c8b0ab1541b270
+size 7992
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..fdf619c317c2fe82074662582dbd68166b6f9d50
--- /dev/null
+++ b/checkpoint-304/README.md
@@ -0,0 +1,202 @@
+---
+base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+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..a192388a7b55129be9ad9168abc396b47bbda6f7
--- /dev/null
+++ b/checkpoint-304/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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..f08224c74d70e03af0a497046bdf0f4516ade3e6
--- /dev/null
+++ b/checkpoint-304/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8031acd919098475b574e499e8b25ee9c9ff713cae572ada2607a2143510a4dc
+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..f6061ef3170f17b5a4d43ee12447233d44c6dfbc
--- /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 sha256:4b93ac81ce89293290dd1259cd1427457fe7e5aa0594fc5e0a1cbbf474bf3430
+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..d5791f3527f0413d866ec01a666be3943dafe851
--- /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:caaec06ddb51fc223fcd558dea83fe474b40007fc598fab2a6e80db629ca3c88
+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..799c40374aa2cfb0d2e150d55ff87bff0d0b513a
--- /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 sha256:65c702199988cf67ae32a4deeec7d4b4e3237119f35f8060bc27598d799fd019
+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..43e4fd7ad7a3b582cf45b67cabc8f215306cfafb
--- /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:e25b7f1973710e0b194b6bc9ed555a9f53755bd98e0d309381a1f6d430b1b2b4
+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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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..f78b4cde269ad3aa5e673cf5b83eae1ffd978c6e
--- /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": 34.99433898925781,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.595,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 35.6848258972168,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.6447,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 35.07997512817383,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.5819,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 34.3863525390625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 35.443077087402344,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 34.70173263549805,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.5487,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 34.421295166015625,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.5494,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 35.152748107910156,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.5936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 34.947021484375,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.5574,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 34.67315673828125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.4894,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 34.679954528808594,
+      "learning_rate": 5.5e-07,
+      "loss": 2.4985,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 33.57002258300781,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 33.517276763916016,
+      "learning_rate": 6.5e-07,
+      "loss": 2.4055,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 33.5312385559082,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.3806,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 32.01276779174805,
+      "learning_rate": 7.5e-07,
+      "loss": 2.2505,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 31.827980041503906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 31.437101364135742,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.1117,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 30.315187454223633,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.9795,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 29.622655868530273,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.8472,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 28.628408432006836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7283,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 27.83180046081543,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.5942,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 26.911596298217773,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4467,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 25.88102149963379,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.3007,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 25.146381378173828,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1319,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 24.800382614135742,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9359,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.648332595825195,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7054,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 22.947620391845703,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 17.80010414123535,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 11.841789245605469,
+      "learning_rate": 1.45e-06,
+      "loss": 0.26,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 7.275839805603027,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1808,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 4.6324543952941895,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.1281485557556152,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.062562942504883,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0966,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.1343328952789307,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.6768524646759033,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0783,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.0879229307174683,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0623,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.83177649974823,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0655,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5678385496139526,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0565,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.6994458436965942,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0491,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.711387038230896,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0507,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.7169735431671143,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0478,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.603631317615509,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0507,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.617487907409668,
+      "learning_rate": 2.15e-06,
+      "loss": 0.043,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.4638065993785858,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5996385216712952,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0429,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.39118286967277527,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.3118075728416443,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31731992959976196,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.041,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.5413194298744202,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.32958006858825684,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.596309244632721,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0413,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.4557362496852875,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0461,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.3345410227775574,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0385,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3047848343849182,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0383,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.43763449788093567,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.038,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.26870036125183105,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0374,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.38762542605400085,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0349,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.27517396211624146,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0398,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.30815261602401733,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0364,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.30011361837387085,
+      "learning_rate": 3e-06,
+      "loss": 0.0307,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3269154727458954,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0344,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3750869333744049,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0339,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29285815358161926,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.034,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.4157550632953644,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0348,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.2852867543697357,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0319,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.4384031593799591,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0319,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.4003254771232605,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0347,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.49913832545280457,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0347,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.22642269730567932,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0306,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.34004101157188416,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0337,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.21503636240959167,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0311,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.33802086114883423,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2488064169883728,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0318,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.21124528348445892,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0293,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.3108712136745453,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33483418822288513,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.031,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3099130690097809,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0286,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.22946476936340332,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0307,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.36924120783805847,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.30895617604255676,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0274,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.42033568024635315,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0298,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.35573887825012207,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0286,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.24631913006305695,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0294,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.2908592224121094,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0243,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3293064832687378,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0253,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3789626359939575,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0253,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3900983929634094,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0248,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.28972727060317993,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0256,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.4615432620048523,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0259,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3959222137928009,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0277,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.4927828907966614,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0251,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23854510486125946,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0214,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.2470882534980774,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0255,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.22575952112674713,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0208,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.437495619058609,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0234,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.2712303102016449,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0236,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.2843461334705353,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0195,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.21141311526298523,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0223,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.25484079122543335,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0211,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.358674556016922,
+      "learning_rate": 5e-06,
+      "loss": 0.027,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.20442990958690643,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0234,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.2281407117843628,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0243,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.23803724348545074,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0189,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.21493025124073029,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0207,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.2565159797668457,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0178,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3488551378250122,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0226,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.27695611119270325,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0189,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.23477056622505188,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0182,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22611404955387115,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0168,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.25616368651390076,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.022,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.23842717707157135,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0163,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.24285905063152313,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0202,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24602730572223663,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0173,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.26218464970588684,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0206,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.2999787926673889,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0178,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.20500704646110535,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0181,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.25106561183929443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0128,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2686936855316162,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0146,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.2770400047302246,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0167,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.27510589361190796,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0162,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.3720133602619171,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0163,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.2288741022348404,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0133,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.31084850430488586,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0124,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.19490985572338104,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0114,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.3074445426464081,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0153,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.29279908537864685,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0117,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.3299407362937927,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0128,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.24818794429302216,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0146,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.35983219742774963,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0138,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2583932876586914,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0136,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20754319429397583,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0116,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.30609601736068726,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0111,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.3754304349422455,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0126,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.2517055571079254,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0118,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.198478102684021,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0087,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.2307695895433426,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0094,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.17823486030101776,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0098,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.2157433032989502,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0114,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.21051311492919922,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.011,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.32886555790901184,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.011,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22413378953933716,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0087,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2896019518375397,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.011,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.26163023710250854,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0084,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.23998413980007172,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0094,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.2334728091955185,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.007,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.17431940138339996,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0047,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.19151932001113892,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0056,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.2352588027715683,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0107,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.2848915159702301,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0074,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.218011736869812,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0075,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.3043143153190613,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0073,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16677772998809814,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0065,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.14940837025642395,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0034,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.14960654079914093,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0034,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.2261868566274643,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0034,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.20907555520534515,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0045,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.15571005642414093,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.0032,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.16968725621700287,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0044,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.1937742531299591,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0027,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.14914007484912872,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0031,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.19651293754577637,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0043,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.2023143172264099,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0036,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.17952999472618103,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0024,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.18410134315490723,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0054,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.18808087706565857,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.0039,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.12346187978982925,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0036,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.140532448887825,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0028,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.8201041221618652,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0028,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.26919177174568176,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0032,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.1321878731250763,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0023,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.12545251846313477,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0024,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.1377445012331009,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0033,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.10942364484071732,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0023,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.17425717413425446,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.003,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.15876342356204987,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.0034,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.1537884920835495,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.002,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.13558532297611237,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0021,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.14405666291713715,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0028,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.19296719133853912,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0034,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.2153935730457306,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0032,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.11674188822507858,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0013,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.21349935233592987,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.002,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.16676126420497894,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.0015,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.20975975692272186,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0025,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.3014683425426483,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0031,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.1687438040971756,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0014,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.13351179659366608,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0012,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.4079025387763977,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0026,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.12639036774635315,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0017,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.1551010012626648,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0022,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.1431741863489151,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0022,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.39600786566734314,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0031,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.13951376080513,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0016,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.10893042385578156,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0007,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.16801239550113678,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.002,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.11393369734287262,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0017,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.23128700256347656,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0018,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.06730300188064575,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0006,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.11693810671567917,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0012,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.1186346486210823,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0012,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.2584531605243683,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0025,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.09868124127388,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0017,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.09907737374305725,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.002,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.06743597984313965,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0006,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.08913715183734894,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.0007,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.12334564328193665,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0006,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.10878646373748779,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0016,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.10623253136873245,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0015,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.15580499172210693,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.0011,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.06405838578939438,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0007,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.17784689366817474,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0017,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14516866207122803,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.0014,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.09510776400566101,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0009,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.1000828891992569,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0008,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.10773428529500961,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0008,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.12319213151931763,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0007,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.07209170609712601,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0006,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.12889248132705688,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.0005,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.05019540339708328,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.0003,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.10657542198896408,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0008,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.15984083712100983,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0003,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.1567343920469284,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0005,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.07294822484254837,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0006,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.04486699402332306,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0003,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.08188032358884811,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0004,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.029995013028383255,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0002,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.029155094176530838,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0002,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.058334361761808395,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0003,
+      "step": 228
+    },
+    {
+      "epoch": 3.013157894736842,
+      "grad_norm": 0.07227180153131485,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0002,
+      "step": 229
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.03385070338845253,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 3.039473684210526,
+      "grad_norm": 0.025327105075120926,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0002,
+      "step": 231
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.17931883037090302,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0004,
+      "step": 232
+    },
+    {
+      "epoch": 3.0657894736842106,
+      "grad_norm": 0.05045541375875473,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0001,
+      "step": 233
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.1170194149017334,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0003,
+      "step": 234
+    },
+    {
+      "epoch": 3.0921052631578947,
+      "grad_norm": 0.01339724287390709,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.5850052833557129,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.1184210526315788,
+      "grad_norm": 0.06263412535190582,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0008,
+      "step": 237
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0001,
+      "step": 238
+    },
+    {
+      "epoch": 3.1447368421052633,
+      "grad_norm": 0.1614137440919876,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0004,
+      "step": 239
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.04927680641412735,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 3.1710526315789473,
+      "grad_norm": 0.04460301250219345,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0001,
+      "step": 241
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.0417938195168972,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0001,
+      "step": 242
+    },
+    {
+      "epoch": 3.1973684210526314,
+      "grad_norm": 0.04140309989452362,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0001,
+      "step": 243
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.36172497272491455,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.001,
+      "step": 244
+    },
+    {
+      "epoch": 3.223684210526316,
+      "grad_norm": 0.19054804742336273,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0005,
+      "step": 245
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.031062051653862,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0001,
+      "step": 246
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.06263001263141632,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0002,
+      "step": 247
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.016942007467150688,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0001,
+      "step": 248
+    },
+    {
+      "epoch": 3.276315789473684,
+      "grad_norm": 0.03281901404261589,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0002,
+      "step": 249
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.06915819644927979,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0002,
+      "step": 250
+    },
+    {
+      "epoch": 3.3026315789473686,
+      "grad_norm": 0.029176127165555954,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0001,
+      "step": 251
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.03844618797302246,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0002,
+      "step": 252
+    },
+    {
+      "epoch": 3.3289473684210527,
+      "grad_norm": 0.1381211280822754,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0023,
+      "step": 253
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.05453269183635712,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0007,
+      "step": 254
+    },
+    {
+      "epoch": 3.3552631578947367,
+      "grad_norm": 0.17172302305698395,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0002,
+      "step": 255
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.09509152173995972,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0003,
+      "step": 256
+    },
+    {
+      "epoch": 3.3815789473684212,
+      "grad_norm": 0.049044203013181686,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.01755386032164097,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0001,
+      "step": 258
+    },
+    {
+      "epoch": 3.4078947368421053,
+      "grad_norm": 0.06148788705468178,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0002,
+      "step": 259
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.047921039164066315,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0001,
+      "step": 260
+    },
+    {
+      "epoch": 3.4342105263157894,
+      "grad_norm": 0.04058835282921791,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0002,
+      "step": 261
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.04581223055720329,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0003,
+      "step": 262
+    },
+    {
+      "epoch": 3.4605263157894735,
+      "grad_norm": 0.060498207807540894,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0002,
+      "step": 263
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.025159459561109543,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0001,
+      "step": 264
+    },
+    {
+      "epoch": 3.486842105263158,
+      "grad_norm": 0.009322446770966053,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.048437751829624176,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0002,
+      "step": 266
+    },
+    {
+      "epoch": 3.513157894736842,
+      "grad_norm": 0.025815390050411224,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0001,
+      "step": 267
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.038374874740839005,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0002,
+      "step": 268
+    },
+    {
+      "epoch": 3.5394736842105265,
+      "grad_norm": 0.010204033926129341,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0001,
+      "step": 269
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.004963386803865433,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 3.5657894736842106,
+      "grad_norm": 0.0680844709277153,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0002,
+      "step": 271
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.01941310614347458,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0001,
+      "step": 272
+    },
+    {
+      "epoch": 3.5921052631578947,
+      "grad_norm": 0.07440650463104248,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0001,
+      "step": 273
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.044731903821229935,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0002,
+      "step": 274
+    },
+    {
+      "epoch": 3.6184210526315788,
+      "grad_norm": 0.021858500316739082,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0001,
+      "step": 275
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.03670589625835419,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0002,
+      "step": 276
+    },
+    {
+      "epoch": 3.6447368421052633,
+      "grad_norm": 0.015562576241791248,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0001,
+      "step": 277
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.011691650375723839,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 3.6710526315789473,
+      "grad_norm": 0.04999399557709694,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0001,
+      "step": 279
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.07675550132989883,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0001,
+      "step": 280
+    },
+    {
+      "epoch": 3.6973684210526314,
+      "grad_norm": 0.03533118963241577,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0001,
+      "step": 281
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.03588724508881569,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0003,
+      "step": 282
+    },
+    {
+      "epoch": 3.723684210526316,
+      "grad_norm": 0.020976359024643898,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0001,
+      "step": 283
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.008930912241339684,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.02440304309129715,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0001,
+      "step": 285
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.006568162236362696,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 3.776315789473684,
+      "grad_norm": 0.004894652403891087,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.05479031801223755,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0003,
+      "step": 288
+    },
+    {
+      "epoch": 3.8026315789473686,
+      "grad_norm": 0.009381825104355812,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.011159488931298256,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 3.8289473684210527,
+      "grad_norm": 0.0077633000910282135,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.040188852697610855,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0002,
+      "step": 292
+    },
+    {
+      "epoch": 3.8552631578947367,
+      "grad_norm": 0.03593844920396805,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0001,
+      "step": 293
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.011377676390111446,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8815789473684212,
+      "grad_norm": 0.018670417368412018,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.026110412552952766,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0001,
+      "step": 296
+    },
+    {
+      "epoch": 3.9078947368421053,
+      "grad_norm": 0.04683105647563934,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0001,
+      "step": 297
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.04568646103143692,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0001,
+      "step": 298
+    },
+    {
+      "epoch": 3.9342105263157894,
+      "grad_norm": 0.0064105079509317875,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.004660090897232294,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9605263157894735,
+      "grad_norm": 0.023000195622444153,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0001,
+      "step": 301
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.010502593591809273,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.986842105263158,
+      "grad_norm": 0.017971891909837723,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0001,
+      "step": 303
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.019201353192329407,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0001,
+      "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..5a1edbdcc63a93daa09112168cf20c0f8fcb7512
--- /dev/null
+++ b/checkpoint-304/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041cfaa5bf8383821dea4fa5a9d2eab2caad4644c4cd651398c8b0ab1541b270
+size 7992
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..fdf619c317c2fe82074662582dbd68166b6f9d50
--- /dev/null
+++ b/checkpoint-380/README.md
@@ -0,0 +1,202 @@
+---
+base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+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..a192388a7b55129be9ad9168abc396b47bbda6f7
--- /dev/null
+++ b/checkpoint-380/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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..b75fc93660393b3cc13e189d24ff6c13d45c04de
--- /dev/null
+++ b/checkpoint-380/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5f10248781de8c8986a75ccc3d4b70674eabfea266a9228100f1ac8a84131b
+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..16a67dbb2377b01f71538068072735013654e14f
--- /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 sha256:089f52c5c502cd55ac11d7af271077fa5c67ccc0c000db14ec85619957b2a216
+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..c1e5e6a529d6235e21fefb6c8da27b58bf2f1e6d
--- /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 sha256:011eb674537c3bcd7b79af708c05b21e1f43b9d5de2c1418e7a0d8a0ff54ad7f
+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..a3cbdcb99f00c3d2b0f6da1fdbd78e6ac17254be
--- /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 sha256:63b89b837434645d644d03acafbead76b20c45577f744d8d30e2d4c762a5e113
+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..d706f3dd03525b63ce80ecccd819cccd9a43091f
--- /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 sha256:45c1d795b74b5f3050ab1cf311ee5678b3cb4d7155dc814465d5c219e5c19eb0
+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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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..f97ea430dbd30f8526b5a0b3be3ffb8edb7ea56c
--- /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": 34.99433898925781,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.595,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 35.6848258972168,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.6447,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 35.07997512817383,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.5819,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 34.3863525390625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 35.443077087402344,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 34.70173263549805,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.5487,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 34.421295166015625,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.5494,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 35.152748107910156,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.5936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 34.947021484375,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.5574,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 34.67315673828125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.4894,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 34.679954528808594,
+      "learning_rate": 5.5e-07,
+      "loss": 2.4985,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 33.57002258300781,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 33.517276763916016,
+      "learning_rate": 6.5e-07,
+      "loss": 2.4055,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 33.5312385559082,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.3806,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 32.01276779174805,
+      "learning_rate": 7.5e-07,
+      "loss": 2.2505,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 31.827980041503906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 31.437101364135742,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.1117,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 30.315187454223633,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.9795,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 29.622655868530273,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.8472,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 28.628408432006836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7283,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 27.83180046081543,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.5942,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 26.911596298217773,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4467,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 25.88102149963379,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.3007,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 25.146381378173828,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1319,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 24.800382614135742,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9359,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.648332595825195,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7054,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 22.947620391845703,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 17.80010414123535,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 11.841789245605469,
+      "learning_rate": 1.45e-06,
+      "loss": 0.26,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 7.275839805603027,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1808,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 4.6324543952941895,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.1281485557556152,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.062562942504883,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0966,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.1343328952789307,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.6768524646759033,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0783,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.0879229307174683,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0623,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.83177649974823,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0655,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5678385496139526,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0565,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.6994458436965942,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0491,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.711387038230896,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0507,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.7169735431671143,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0478,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.603631317615509,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0507,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.617487907409668,
+      "learning_rate": 2.15e-06,
+      "loss": 0.043,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.4638065993785858,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5996385216712952,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0429,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.39118286967277527,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.3118075728416443,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31731992959976196,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.041,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.5413194298744202,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.32958006858825684,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.596309244632721,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0413,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.4557362496852875,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0461,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.3345410227775574,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0385,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3047848343849182,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0383,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.43763449788093567,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.038,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.26870036125183105,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0374,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.38762542605400085,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0349,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.27517396211624146,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0398,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.30815261602401733,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0364,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.30011361837387085,
+      "learning_rate": 3e-06,
+      "loss": 0.0307,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3269154727458954,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0344,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3750869333744049,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0339,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29285815358161926,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.034,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.4157550632953644,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0348,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.2852867543697357,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0319,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.4384031593799591,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0319,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.4003254771232605,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0347,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.49913832545280457,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0347,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.22642269730567932,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0306,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.34004101157188416,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0337,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.21503636240959167,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0311,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.33802086114883423,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2488064169883728,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0318,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.21124528348445892,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0293,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.3108712136745453,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33483418822288513,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.031,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.3099130690097809,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0286,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.22946476936340332,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0307,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.36924120783805847,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0274,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.30895617604255676,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0274,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.42033568024635315,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0298,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.35573887825012207,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0286,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.24631913006305695,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0294,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.2908592224121094,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0243,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.3293064832687378,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0253,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.3789626359939575,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0253,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.3900983929634094,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.0248,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.28972727060317993,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0256,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.4615432620048523,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0259,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.3959222137928009,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0277,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.4927828907966614,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0251,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.23854510486125946,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0214,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.2470882534980774,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0255,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.22575952112674713,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0208,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.437495619058609,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0234,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.2712303102016449,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0236,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.2843461334705353,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0195,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.21141311526298523,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0223,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.25484079122543335,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0211,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.358674556016922,
+      "learning_rate": 5e-06,
+      "loss": 0.027,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.20442990958690643,
+      "learning_rate": 4.999902656502973e-06,
+      "loss": 0.0234,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.2281407117843628,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.0243,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.23803724348545074,
+      "learning_rate": 4.999123954009797e-06,
+      "loss": 0.0189,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.21493025124073029,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.0207,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.2565159797668457,
+      "learning_rate": 4.997566791583916e-06,
+      "loss": 0.0178,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.3488551378250122,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.0226,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.27695611119270325,
+      "learning_rate": 4.995231654270726e-06,
+      "loss": 0.0189,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.23477056622505188,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.0182,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.22611404955387115,
+      "learning_rate": 4.992119269449445e-06,
+      "loss": 0.0168,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.25616368651390076,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.022,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.23842717707157135,
+      "learning_rate": 4.988230606606552e-06,
+      "loss": 0.0163,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.24285905063152313,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.0202,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.24602730572223663,
+      "learning_rate": 4.983566877033791e-06,
+      "loss": 0.0173,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.26218464970588684,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.0206,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.2999787926673889,
+      "learning_rate": 4.9781295334508664e-06,
+      "loss": 0.0178,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.20500704646110535,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.0181,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.25106561183929443,
+      "learning_rate": 4.9719202695529265e-06,
+      "loss": 0.0128,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.2686936855316162,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.0146,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.2770400047302246,
+      "learning_rate": 4.964941019482995e-06,
+      "loss": 0.0167,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.27510589361190796,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.0162,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.3720133602619171,
+      "learning_rate": 4.9571939572294914e-06,
+      "loss": 0.0163,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.2288741022348404,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.0133,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.31084850430488586,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.0124,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.19490985572338104,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.0114,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.3074445426464081,
+      "learning_rate": 4.939406287214861e-06,
+      "loss": 0.0153,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.29279908537864685,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.0117,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.3299407362937927,
+      "learning_rate": 4.929371220190671e-06,
+      "loss": 0.0128,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.24818794429302216,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.0146,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.35983219742774963,
+      "learning_rate": 4.918579420730884e-06,
+      "loss": 0.0138,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.2583932876586914,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.0136,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.20754319429397583,
+      "learning_rate": 4.907034250406846e-06,
+      "loss": 0.0116,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.30609601736068726,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.0111,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.3754304349422455,
+      "learning_rate": 4.894739305459754e-06,
+      "loss": 0.0126,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.2517055571079254,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.0118,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.198478102684021,
+      "learning_rate": 4.881698415680442e-06,
+      "loss": 0.0087,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.2307695895433426,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.0094,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.17823486030101776,
+      "learning_rate": 4.867915643216434e-06,
+      "loss": 0.0098,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.2157433032989502,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.0114,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.21051311492919922,
+      "learning_rate": 4.85339528130661e-06,
+      "loss": 0.011,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.32886555790901184,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.011,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.22413378953933716,
+      "learning_rate": 4.838141852943891e-06,
+      "loss": 0.0087,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.2896019518375397,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.011,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.26163023710250854,
+      "learning_rate": 4.822160109466361e-06,
+      "loss": 0.0084,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.23998413980007172,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.0094,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.2334728091955185,
+      "learning_rate": 4.805455029077255e-06,
+      "loss": 0.007,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.17431940138339996,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.0047,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.19151932001113892,
+      "learning_rate": 4.788031815294282e-06,
+      "loss": 0.0056,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.2352588027715683,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.0107,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.2848915159702301,
+      "learning_rate": 4.76989589532877e-06,
+      "loss": 0.0074,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.218011736869812,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.0075,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.3043143153190613,
+      "learning_rate": 4.75105291839512e-06,
+      "loss": 0.0073,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16677772998809814,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.0065,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 0.14940837025642395,
+      "learning_rate": 4.7315087539511225e-06,
+      "loss": 0.0034,
+      "step": 153
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.14960654079914093,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.0034,
+      "step": 154
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 0.2261868566274643,
+      "learning_rate": 4.711269489869654e-06,
+      "loss": 0.0034,
+      "step": 155
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.20907555520534515,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.0045,
+      "step": 156
+    },
+    {
+      "epoch": 2.0657894736842106,
+      "grad_norm": 0.15571005642414093,
+      "learning_rate": 4.690341430542351e-06,
+      "loss": 0.0032,
+      "step": 157
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.16968725621700287,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.0044,
+      "step": 158
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 0.1937742531299591,
+      "learning_rate": 4.668731094915835e-06,
+      "loss": 0.0027,
+      "step": 159
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.14914007484912872,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.0031,
+      "step": 160
+    },
+    {
+      "epoch": 2.1184210526315788,
+      "grad_norm": 0.19651293754577637,
+      "learning_rate": 4.646445214461105e-06,
+      "loss": 0.0043,
+      "step": 161
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.2023143172264099,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.0036,
+      "step": 162
+    },
+    {
+      "epoch": 2.1447368421052633,
+      "grad_norm": 0.17952999472618103,
+      "learning_rate": 4.623490731076728e-06,
+      "loss": 0.0024,
+      "step": 163
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.18410134315490723,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.0054,
+      "step": 164
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.18808087706565857,
+      "learning_rate": 4.59987479492649e-06,
+      "loss": 0.0039,
+      "step": 165
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.12346187978982925,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.0036,
+      "step": 166
+    },
+    {
+      "epoch": 2.1973684210526314,
+      "grad_norm": 0.140532448887825,
+      "learning_rate": 4.5756047622121665e-06,
+      "loss": 0.0028,
+      "step": 167
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.8201041221618652,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.0028,
+      "step": 168
+    },
+    {
+      "epoch": 2.223684210526316,
+      "grad_norm": 0.26919177174568176,
+      "learning_rate": 4.550688192882115e-06,
+      "loss": 0.0032,
+      "step": 169
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.1321878731250763,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.0023,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.12545251846313477,
+      "learning_rate": 4.525132848276405e-06,
+      "loss": 0.0024,
+      "step": 171
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.1377445012331009,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.0033,
+      "step": 172
+    },
+    {
+      "epoch": 2.276315789473684,
+      "grad_norm": 0.10942364484071732,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.0023,
+      "step": 173
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.17425717413425446,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.003,
+      "step": 174
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 0.15876342356204987,
+      "learning_rate": 4.4721378709892475e-06,
+      "loss": 0.0034,
+      "step": 175
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.1537884920835495,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.002,
+      "step": 176
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 0.13558532297611237,
+      "learning_rate": 4.444714745878936e-06,
+      "loss": 0.0021,
+      "step": 177
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.14405666291713715,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.0028,
+      "step": 178
+    },
+    {
+      "epoch": 2.3552631578947367,
+      "grad_norm": 0.19296719133853912,
+      "learning_rate": 4.416685855493246e-06,
+      "loss": 0.0034,
+      "step": 179
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.2153935730457306,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.0032,
+      "step": 180
+    },
+    {
+      "epoch": 2.3815789473684212,
+      "grad_norm": 0.11674188822507858,
+      "learning_rate": 4.388059930638865e-06,
+      "loss": 0.0013,
+      "step": 181
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.21349935233592987,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.002,
+      "step": 182
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 0.16676126420497894,
+      "learning_rate": 4.358845888094607e-06,
+      "loss": 0.0015,
+      "step": 183
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.20975975692272186,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.0025,
+      "step": 184
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.3014683425426483,
+      "learning_rate": 4.32905282783391e-06,
+      "loss": 0.0031,
+      "step": 185
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.1687438040971756,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.0014,
+      "step": 186
+    },
+    {
+      "epoch": 2.4605263157894735,
+      "grad_norm": 0.13351179659366608,
+      "learning_rate": 4.298690030190247e-06,
+      "loss": 0.0012,
+      "step": 187
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.4079025387763977,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.0026,
+      "step": 188
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.12639036774635315,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0017,
+      "step": 189
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.1551010012626648,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.0022,
+      "step": 190
+    },
+    {
+      "epoch": 2.513157894736842,
+      "grad_norm": 0.1431741863489151,
+      "learning_rate": 4.236293228488267e-06,
+      "loss": 0.0022,
+      "step": 191
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.39600786566734314,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.0031,
+      "step": 192
+    },
+    {
+      "epoch": 2.5394736842105265,
+      "grad_norm": 0.13951376080513,
+      "learning_rate": 4.204278660604767e-06,
+      "loss": 0.0016,
+      "step": 193
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.10893042385578156,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.0007,
+      "step": 194
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 0.16801239550113678,
+      "learning_rate": 4.171733221633695e-06,
+      "loss": 0.002,
+      "step": 195
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.11393369734287262,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.0017,
+      "step": 196
+    },
+    {
+      "epoch": 2.5921052631578947,
+      "grad_norm": 0.23128700256347656,
+      "learning_rate": 4.138667049255574e-06,
+      "loss": 0.0018,
+      "step": 197
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.06730300188064575,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.0006,
+      "step": 198
+    },
+    {
+      "epoch": 2.6184210526315788,
+      "grad_norm": 0.11693810671567917,
+      "learning_rate": 4.105090443355801e-06,
+      "loss": 0.0012,
+      "step": 199
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.1186346486210823,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.0012,
+      "step": 200
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.2584531605243683,
+      "learning_rate": 4.071013862816311e-06,
+      "loss": 0.0025,
+      "step": 201
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.09868124127388,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.0017,
+      "step": 202
+    },
+    {
+      "epoch": 2.6710526315789473,
+      "grad_norm": 0.09907737374305725,
+      "learning_rate": 4.036447922257699e-06,
+      "loss": 0.002,
+      "step": 203
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.06743597984313965,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.0006,
+      "step": 204
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 0.08913715183734894,
+      "learning_rate": 4.001403388732842e-06,
+      "loss": 0.0007,
+      "step": 205
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.12334564328193665,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.0006,
+      "step": 206
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 0.10878646373748779,
+      "learning_rate": 3.965891178373038e-06,
+      "loss": 0.0016,
+      "step": 207
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.10623253136873245,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.0015,
+      "step": 208
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.15580499172210693,
+      "learning_rate": 3.929922352987702e-06,
+      "loss": 0.0011,
+      "step": 209
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.06405838578939438,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.0007,
+      "step": 210
+    },
+    {
+      "epoch": 2.776315789473684,
+      "grad_norm": 0.17784689366817474,
+      "learning_rate": 3.8935081166186935e-06,
+      "loss": 0.0017,
+      "step": 211
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.14516866207122803,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.0014,
+      "step": 212
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 0.09510776400566101,
+      "learning_rate": 3.856659812050328e-06,
+      "loss": 0.0009,
+      "step": 213
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.1000828891992569,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.0008,
+      "step": 214
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.10773428529500961,
+      "learning_rate": 3.819388917276186e-06,
+      "loss": 0.0008,
+      "step": 215
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.12319213151931763,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.0007,
+      "step": 216
+    },
+    {
+      "epoch": 2.8552631578947367,
+      "grad_norm": 0.07209170609712601,
+      "learning_rate": 3.7817070419237866e-06,
+      "loss": 0.0006,
+      "step": 217
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.12889248132705688,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.0005,
+      "step": 218
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.05019540339708328,
+      "learning_rate": 3.7436259236382797e-06,
+      "loss": 0.0003,
+      "step": 219
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.10657542198896408,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.0008,
+      "step": 220
+    },
+    {
+      "epoch": 2.9078947368421053,
+      "grad_norm": 0.15984083712100983,
+      "learning_rate": 3.7051574244262412e-06,
+      "loss": 0.0003,
+      "step": 221
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.1567343920469284,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.0005,
+      "step": 222
+    },
+    {
+      "epoch": 2.9342105263157894,
+      "grad_norm": 0.07294822484254837,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.0006,
+      "step": 223
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.04486699402332306,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.0003,
+      "step": 224
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.08188032358884811,
+      "learning_rate": 3.6271063308488298e-06,
+      "loss": 0.0004,
+      "step": 225
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.029995013028383255,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.0002,
+      "step": 226
+    },
+    {
+      "epoch": 2.986842105263158,
+      "grad_norm": 0.029155094176530838,
+      "learning_rate": 3.5875480488625847e-06,
+      "loss": 0.0002,
+      "step": 227
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.058334361761808395,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.0003,
+      "step": 228
+    },
+    {
+      "epoch": 3.013157894736842,
+      "grad_norm": 0.07227180153131485,
+      "learning_rate": 3.547651003134921e-06,
+      "loss": 0.0002,
+      "step": 229
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.03385070338845253,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 3.039473684210526,
+      "grad_norm": 0.025327105075120926,
+      "learning_rate": 3.507427621321331e-06,
+      "loss": 0.0002,
+      "step": 231
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.17931883037090302,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.0004,
+      "step": 232
+    },
+    {
+      "epoch": 3.0657894736842106,
+      "grad_norm": 0.05045541375875473,
+      "learning_rate": 3.466890432728754e-06,
+      "loss": 0.0001,
+      "step": 233
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.1170194149017334,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.0003,
+      "step": 234
+    },
+    {
+      "epoch": 3.0921052631578947,
+      "grad_norm": 0.01339724287390709,
+      "learning_rate": 3.426052064412785e-06,
+      "loss": 0.0001,
+      "step": 235
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.5850052833557129,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.0004,
+      "step": 236
+    },
+    {
+      "epoch": 3.1184210526315788,
+      "grad_norm": 0.06263412535190582,
+      "learning_rate": 3.3849252372444295e-06,
+      "loss": 0.0008,
+      "step": 237
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.0001,
+      "step": 238
+    },
+    {
+      "epoch": 3.1447368421052633,
+      "grad_norm": 0.1614137440919876,
+      "learning_rate": 3.343522761947646e-06,
+      "loss": 0.0004,
+      "step": 239
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.04927680641412735,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.0002,
+      "step": 240
+    },
+    {
+      "epoch": 3.1710526315789473,
+      "grad_norm": 0.04460301250219345,
+      "learning_rate": 3.3018575351088894e-06,
+      "loss": 0.0001,
+      "step": 241
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.0417938195168972,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.0001,
+      "step": 242
+    },
+    {
+      "epoch": 3.1973684210526314,
+      "grad_norm": 0.04140309989452362,
+      "learning_rate": 3.2599425351599136e-06,
+      "loss": 0.0001,
+      "step": 243
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.36172497272491455,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.001,
+      "step": 244
+    },
+    {
+      "epoch": 3.223684210526316,
+      "grad_norm": 0.19054804742336273,
+      "learning_rate": 3.217790818335077e-06,
+      "loss": 0.0005,
+      "step": 245
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.031062051653862,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.0001,
+      "step": 246
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.06263001263141632,
+      "learning_rate": 3.175415514604422e-06,
+      "loss": 0.0002,
+      "step": 247
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.016942007467150688,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.0001,
+      "step": 248
+    },
+    {
+      "epoch": 3.276315789473684,
+      "grad_norm": 0.03281901404261589,
+      "learning_rate": 3.132829823583771e-06,
+      "loss": 0.0002,
+      "step": 249
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.06915819644927979,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.0002,
+      "step": 250
+    },
+    {
+      "epoch": 3.3026315789473686,
+      "grad_norm": 0.029176127165555954,
+      "learning_rate": 3.0900470104231456e-06,
+      "loss": 0.0001,
+      "step": 251
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.03844618797302246,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.0002,
+      "step": 252
+    },
+    {
+      "epoch": 3.3289473684210527,
+      "grad_norm": 0.1381211280822754,
+      "learning_rate": 3.047080401674754e-06,
+      "loss": 0.0023,
+      "step": 253
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.05453269183635712,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.0007,
+      "step": 254
+    },
+    {
+      "epoch": 3.3552631578947367,
+      "grad_norm": 0.17172302305698395,
+      "learning_rate": 3.00394338114187e-06,
+      "loss": 0.0002,
+      "step": 255
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.09509152173995972,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.0003,
+      "step": 256
+    },
+    {
+      "epoch": 3.3815789473684212,
+      "grad_norm": 0.049044203013181686,
+      "learning_rate": 2.9606493857098657e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.01755386032164097,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.0001,
+      "step": 258
+    },
+    {
+      "epoch": 3.4078947368421053,
+      "grad_norm": 0.06148788705468178,
+      "learning_rate": 2.9172119011607153e-06,
+      "loss": 0.0002,
+      "step": 259
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.047921039164066315,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.0001,
+      "step": 260
+    },
+    {
+      "epoch": 3.4342105263157894,
+      "grad_norm": 0.04058835282921791,
+      "learning_rate": 2.8736444579722665e-06,
+      "loss": 0.0002,
+      "step": 261
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.04581223055720329,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.0003,
+      "step": 262
+    },
+    {
+      "epoch": 3.4605263157894735,
+      "grad_norm": 0.060498207807540894,
+      "learning_rate": 2.8299606271035913e-06,
+      "loss": 0.0002,
+      "step": 263
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.025159459561109543,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.0001,
+      "step": 264
+    },
+    {
+      "epoch": 3.486842105263158,
+      "grad_norm": 0.009322446770966053,
+      "learning_rate": 2.786174015767721e-06,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.048437751829624176,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.0002,
+      "step": 266
+    },
+    {
+      "epoch": 3.513157894736842,
+      "grad_norm": 0.025815390050411224,
+      "learning_rate": 2.742298263193099e-06,
+      "loss": 0.0001,
+      "step": 267
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.038374874740839005,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.0002,
+      "step": 268
+    },
+    {
+      "epoch": 3.5394736842105265,
+      "grad_norm": 0.010204033926129341,
+      "learning_rate": 2.6983470363750497e-06,
+      "loss": 0.0001,
+      "step": 269
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.004963386803865433,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 3.5657894736842106,
+      "grad_norm": 0.0680844709277153,
+      "learning_rate": 2.6543340258186063e-06,
+      "loss": 0.0002,
+      "step": 271
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.01941310614347458,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.0001,
+      "step": 272
+    },
+    {
+      "epoch": 3.5921052631578947,
+      "grad_norm": 0.07440650463104248,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.0001,
+      "step": 273
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.044731903821229935,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.0002,
+      "step": 274
+    },
+    {
+      "epoch": 3.6184210526315788,
+      "grad_norm": 0.021858500316739082,
+      "learning_rate": 2.5661775074662276e-06,
+      "loss": 0.0001,
+      "step": 275
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.03670589625835419,
+      "learning_rate": 2.544121201607822e-06,
+      "loss": 0.0002,
+      "step": 276
+    },
+    {
+      "epoch": 3.6447368421052633,
+      "grad_norm": 0.015562576241791248,
+      "learning_rate": 2.5220614598197708e-06,
+      "loss": 0.0001,
+      "step": 277
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.011691650375723839,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 3.6710526315789473,
+      "grad_norm": 0.04999399557709694,
+      "learning_rate": 2.477938540180231e-06,
+      "loss": 0.0001,
+      "step": 279
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.07675550132989883,
+      "learning_rate": 2.455878798392179e-06,
+      "loss": 0.0001,
+      "step": 280
+    },
+    {
+      "epoch": 3.6973684210526314,
+      "grad_norm": 0.03533118963241577,
+      "learning_rate": 2.433822492533774e-06,
+      "loss": 0.0001,
+      "step": 281
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.03588724508881569,
+      "learning_rate": 2.411771340235369e-06,
+      "loss": 0.0003,
+      "step": 282
+    },
+    {
+      "epoch": 3.723684210526316,
+      "grad_norm": 0.020976359024643898,
+      "learning_rate": 2.389727058725989e-06,
+      "loss": 0.0001,
+      "step": 283
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.008930912241339684,
+      "learning_rate": 2.3676913646995923e-06,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.02440304309129715,
+      "learning_rate": 2.3456659741813945e-06,
+      "loss": 0.0001,
+      "step": 285
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.006568162236362696,
+      "learning_rate": 2.3236526023942224e-06,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 3.776315789473684,
+      "grad_norm": 0.004894652403891087,
+      "learning_rate": 2.301652963624951e-06,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.05479031801223755,
+      "learning_rate": 2.2796687710909966e-06,
+      "loss": 0.0003,
+      "step": 288
+    },
+    {
+      "epoch": 3.8026315789473686,
+      "grad_norm": 0.009381825104355812,
+      "learning_rate": 2.2577017368069017e-06,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.011159488931298256,
+      "learning_rate": 2.235753571451018e-06,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 3.8289473684210527,
+      "grad_norm": 0.0077633000910282135,
+      "learning_rate": 2.2138259842322794e-06,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.040188852697610855,
+      "learning_rate": 2.191920682757104e-06,
+      "loss": 0.0002,
+      "step": 292
+    },
+    {
+      "epoch": 3.8552631578947367,
+      "grad_norm": 0.03593844920396805,
+      "learning_rate": 2.170039372896409e-06,
+      "loss": 0.0001,
+      "step": 293
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.011377676390111446,
+      "learning_rate": 2.148183758652774e-06,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 3.8815789473684212,
+      "grad_norm": 0.018670417368412018,
+      "learning_rate": 2.126355542027734e-06,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.026110412552952766,
+      "learning_rate": 2.1045564228892404e-06,
+      "loss": 0.0001,
+      "step": 296
+    },
+    {
+      "epoch": 3.9078947368421053,
+      "grad_norm": 0.04683105647563934,
+      "learning_rate": 2.0827880988392856e-06,
+      "loss": 0.0001,
+      "step": 297
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.04568646103143692,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.0001,
+      "step": 298
+    },
+    {
+      "epoch": 3.9342105263157894,
+      "grad_norm": 0.0064105079509317875,
+      "learning_rate": 2.0393506142901347e-06,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.004660090897232294,
+      "learning_rate": 2.017684836476258e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9605263157894735,
+      "grad_norm": 0.023000195622444153,
+      "learning_rate": 1.9960566188581306e-06,
+      "loss": 0.0001,
+      "step": 301
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.010502593591809273,
+      "learning_rate": 1.9744676457288225e-06,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 3.986842105263158,
+      "grad_norm": 0.017971891909837723,
+      "learning_rate": 1.952919598325247e-06,
+      "loss": 0.0001,
+      "step": 303
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.019201353192329407,
+      "learning_rate": 1.9314141546972345e-06,
+      "loss": 0.0001,
+      "step": 304
+    },
+    {
+      "epoch": 4.0131578947368425,
+      "grad_norm": 0.014774768613278866,
+      "learning_rate": 1.9099529895768552e-06,
+      "loss": 0.0001,
+      "step": 305
+    },
+    {
+      "epoch": 4.026315789473684,
+      "grad_norm": 0.004470722749829292,
+      "learning_rate": 1.8885377742480005e-06,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 4.0394736842105265,
+      "grad_norm": 0.0017719039460644126,
+      "learning_rate": 1.8671701764162287e-06,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 4.052631578947368,
+      "grad_norm": 0.0023945686407387257,
+      "learning_rate": 1.8458518600788988e-06,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 4.065789473684211,
+      "grad_norm": 0.008764254860579967,
+      "learning_rate": 1.8245844853955786e-06,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 4.078947368421052,
+      "grad_norm": 0.007987024262547493,
+      "learning_rate": 1.8033697085587698e-06,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 4.092105263157895,
+      "grad_norm": 0.0034283557906746864,
+      "learning_rate": 1.782209181664924e-06,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 4.105263157894737,
+      "grad_norm": 0.006517547182738781,
+      "learning_rate": 1.7611045525857902e-06,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 4.118421052631579,
+      "grad_norm": 0.001932072453200817,
+      "learning_rate": 1.740057464840088e-06,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 4.131578947368421,
+      "grad_norm": 0.0014661611057817936,
+      "learning_rate": 1.7190695574655147e-06,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 4.144736842105263,
+      "grad_norm": 0.00624146917834878,
+      "learning_rate": 1.6981424648911112e-06,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 4.157894736842105,
+      "grad_norm": 0.008011729456484318,
+      "learning_rate": 1.677277816809975e-06,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 4.171052631578948,
+      "grad_norm": 0.009674855507910252,
+      "learning_rate": 1.6564772380523546e-06,
+      "loss": 0.0,
+      "step": 317
+    },
+    {
+      "epoch": 4.184210526315789,
+      "grad_norm": 0.0071542332880198956,
+      "learning_rate": 1.635742348459109e-06,
+      "loss": 0.0,
+      "step": 318
+    },
+    {
+      "epoch": 4.197368421052632,
+      "grad_norm": 0.009431720711290836,
+      "learning_rate": 1.6150747627555713e-06,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.009224318899214268,
+      "learning_rate": 1.5944760904257944e-06,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 4.223684210526316,
+      "grad_norm": 0.010647057555615902,
+      "learning_rate": 1.5739479355872162e-06,
+      "loss": 0.0,
+      "step": 321
+    },
+    {
+      "epoch": 4.2368421052631575,
+      "grad_norm": 0.015793612226843834,
+      "learning_rate": 1.5534918968657423e-06,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.004004765767604113,
+      "learning_rate": 1.5331095672712463e-06,
+      "loss": 0.0,
+      "step": 323
+    },
+    {
+      "epoch": 4.2631578947368425,
+      "grad_norm": 0.003939881455153227,
+      "learning_rate": 1.5128025340735223e-06,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 4.276315789473684,
+      "grad_norm": 0.002702821511775255,
+      "learning_rate": 1.4925723786786691e-06,
+      "loss": 0.0,
+      "step": 325
+    },
+    {
+      "epoch": 4.2894736842105265,
+      "grad_norm": 0.0027509802021086216,
+      "learning_rate": 1.4724206765059456e-06,
+      "loss": 0.0,
+      "step": 326
+    },
+    {
+      "epoch": 4.302631578947368,
+      "grad_norm": 0.007367170415818691,
+      "learning_rate": 1.4523489968650795e-06,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 4.315789473684211,
+      "grad_norm": 0.004167403094470501,
+      "learning_rate": 1.4323589028340598e-06,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 4.328947368421053,
+      "grad_norm": 0.014962514862418175,
+      "learning_rate": 1.4124519511374158e-06,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 4.342105263157895,
+      "grad_norm": 0.0012889838544651866,
+      "learning_rate": 1.3926296920249796e-06,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 4.355263157894737,
+      "grad_norm": 0.006448778789490461,
+      "learning_rate": 1.3728936691511704e-06,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 4.368421052631579,
+      "grad_norm": 0.004137519281357527,
+      "learning_rate": 1.3532454194547734e-06,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 4.381578947368421,
+      "grad_norm": 0.006182932294905186,
+      "learning_rate": 1.3336864730392587e-06,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 4.394736842105263,
+      "grad_norm": 0.0014147404581308365,
+      "learning_rate": 1.314218353053619e-06,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 4.407894736842105,
+      "grad_norm": 0.007514857687056065,
+      "learning_rate": 1.2948425755737592e-06,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.02276490069925785,
+      "learning_rate": 1.2755606494844294e-06,
+      "loss": 0.0001,
+      "step": 336
+    },
+    {
+      "epoch": 4.434210526315789,
+      "grad_norm": 0.0013512762961909175,
+      "learning_rate": 1.2563740763617198e-06,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 4.447368421052632,
+      "grad_norm": 0.002018272178247571,
+      "learning_rate": 1.2372843503561318e-06,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 4.4605263157894735,
+      "grad_norm": 0.0042894985526800156,
+      "learning_rate": 1.218292958076213e-06,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 4.473684210526316,
+      "grad_norm": 0.0010812514228746295,
+      "learning_rate": 1.1994013784727948e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 4.4868421052631575,
+      "grad_norm": 0.0041869827546179295,
+      "learning_rate": 1.180611082723814e-06,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.010349901393055916,
+      "learning_rate": 1.161923534119752e-06,
+      "loss": 0.0,
+      "step": 342
+    },
+    {
+      "epoch": 4.5131578947368425,
+      "grad_norm": 0.007921607233583927,
+      "learning_rate": 1.1433401879496723e-06,
+      "loss": 0.0,
+      "step": 343
+    },
+    {
+      "epoch": 4.526315789473684,
+      "grad_norm": 0.0013929491396993399,
+      "learning_rate": 1.1248624913878966e-06,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 4.5394736842105265,
+      "grad_norm": 0.003571738488972187,
+      "learning_rate": 1.1064918833813073e-06,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 4.552631578947368,
+      "grad_norm": 0.0017180831637233496,
+      "learning_rate": 1.088229794537283e-06,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 4.565789473684211,
+      "grad_norm": 0.0025168503634631634,
+      "learning_rate": 1.0700776470122981e-06,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 4.578947368421053,
+      "grad_norm": 0.010161465033888817,
+      "learning_rate": 1.0520368544011661e-06,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 4.592105263157895,
+      "grad_norm": 0.0024475576356053352,
+      "learning_rate": 1.0341088216269625e-06,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 4.605263157894737,
+      "grad_norm": 0.0035759019665420055,
+      "learning_rate": 1.0162949448316089e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 4.618421052631579,
+      "grad_norm": 0.002835271880030632,
+      "learning_rate": 9.98596611267158e-07,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.014862479642033577,
+      "learning_rate": 9.81015199187753e-07,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 4.644736842105263,
+      "grad_norm": 0.0009296426433138549,
+      "learning_rate": 9.63552077742301e-07,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 4.657894736842105,
+      "grad_norm": 0.002957531251013279,
+      "learning_rate": 9.462086068678519e-07,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 4.671052631578947,
+      "grad_norm": 0.0018816434312611818,
+      "learning_rate": 9.289861371836886e-07,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 4.684210526315789,
+      "grad_norm": 0.0049733612686395645,
+      "learning_rate": 9.118860098861538e-07,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 4.697368421052632,
+      "grad_norm": 0.0017015141202136874,
+      "learning_rate": 8.949095566441985e-07,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 4.7105263157894735,
+      "grad_norm": 0.002689789514988661,
+      "learning_rate": 8.78058099495685e-07,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 4.723684210526316,
+      "grad_norm": 0.00439384626224637,
+      "learning_rate": 8.613329507444274e-07,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.0011757826432585716,
+      "learning_rate": 8.44735412857999e-07,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.004845093935728073,
+      "learning_rate": 8.282667783663056e-07,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 4.7631578947368425,
+      "grad_norm": 0.0011784805683419108,
+      "learning_rate": 8.119283297609238e-07,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 4.776315789473684,
+      "grad_norm": 0.024683140218257904,
+      "learning_rate": 7.957213393952335e-07,
+      "loss": 0.0001,
+      "step": 363
+    },
+    {
+      "epoch": 4.7894736842105265,
+      "grad_norm": 0.0012061076704412699,
+      "learning_rate": 7.796470693853281e-07,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 4.802631578947368,
+      "grad_norm": 0.003571854904294014,
+      "learning_rate": 7.637067715117327e-07,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 4.815789473684211,
+      "grad_norm": 0.0021892369259148836,
+      "learning_rate": 7.479016871219174e-07,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 4.828947368421053,
+      "grad_norm": 0.005559162236750126,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0,
+      "step": 367
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.021778438240289688,
+      "learning_rate": 7.167020714390502e-07,
+      "loss": 0.0001,
+      "step": 368
+    },
+    {
+      "epoch": 4.855263157894737,
+      "grad_norm": 0.0014009246369823813,
+      "learning_rate": 7.013099698097539e-07,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 4.868421052631579,
+      "grad_norm": 0.002133658155798912,
+      "learning_rate": 6.860579408025436e-07,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 4.881578947368421,
+      "grad_norm": 0.01783628761768341,
+      "learning_rate": 6.709471721660904e-07,
+      "loss": 0.0001,
+      "step": 371
+    },
+    {
+      "epoch": 4.894736842105263,
+      "grad_norm": 0.02103368379175663,
+      "learning_rate": 6.559788406484446e-07,
+      "loss": 0.0001,
+      "step": 372
+    },
+    {
+      "epoch": 4.907894736842105,
+      "grad_norm": 0.0016494387527927756,
+      "learning_rate": 6.41154111905393e-07,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 4.921052631578947,
+      "grad_norm": 0.00294311111792922,
+      "learning_rate": 6.264741404096875e-07,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 4.934210526315789,
+      "grad_norm": 0.0028199541848152876,
+      "learning_rate": 6.119400693611358e-07,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 4.947368421052632,
+      "grad_norm": 0.0007045238162390888,
+      "learning_rate": 5.975530305975808e-07,
+      "loss": 0.0,
+      "step": 376
+    },
+    {
+      "epoch": 4.9605263157894735,
+      "grad_norm": 0.0008912527118809521,
+      "learning_rate": 5.833141445067541e-07,
+      "loss": 0.0,
+      "step": 377
+    },
+    {
+      "epoch": 4.973684210526316,
+      "grad_norm": 0.003858179785311222,
+      "learning_rate": 5.692245199390281e-07,
+      "loss": 0.0,
+      "step": 378
+    },
+    {
+      "epoch": 4.9868421052631575,
+      "grad_norm": 0.0017520582769066095,
+      "learning_rate": 5.552852541210651e-07,
+      "loss": 0.0,
+      "step": 379
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.004236061125993729,
+      "learning_rate": 5.414974325703687e-07,
+      "loss": 0.0,
+      "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..5a1edbdcc63a93daa09112168cf20c0f8fcb7512
--- /dev/null
+++ b/checkpoint-380/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041cfaa5bf8383821dea4fa5a9d2eab2caad4644c4cd651398c8b0ab1541b270
+size 7992
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..fdf619c317c2fe82074662582dbd68166b6f9d50
--- /dev/null
+++ b/checkpoint-76/README.md
@@ -0,0 +1,202 @@
+---
+base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+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..a192388a7b55129be9ad9168abc396b47bbda6f7
--- /dev/null
+++ b/checkpoint-76/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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..454894cfae5ac0aee99fe142f3b8a8f903db8169
--- /dev/null
+++ b/checkpoint-76/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddf38d8e5bdcee61a3cef0eefd8abdabaf8fd8ac8c9222a20af79b3cbbbfc9d
+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..6c550f918b7d988cbce152bc906a2860e04c1007
--- /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 sha256:99a5ac92e2b51a99f803ada3c4bc01195ea5ea8a8cf5d0050be0324ae4d1da10
+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..a58d309f73654f0ab73383eb701aff7934e93961
--- /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:cf34473dddb473da1d933f9b4971c1db56bbb7a39faa15deff62c8ae95b9447d
+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..6893b5ea87f9150676abc6114f09ab08ea9cb8a3
--- /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 sha256:07dc1593969387baab70f62b8078b55eb3faa4076d593bb072d3783c775510ec
+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..58539fde3d7c004ff7b49a1e1c7f5bd386941eb6
--- /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 sha256:92b083ac5695003888f71cce2fd08ef6c3da070152619e5d9f493cb6a26e7dfe
+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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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..ba4feb375077acfcdb249ee73f08bc12d489eee4
--- /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": 34.99433898925781,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 2.595,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 35.6848258972168,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.6447,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 35.07997512817383,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 2.5819,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 34.3863525390625,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.5739,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 35.443077087402344,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 34.70173263549805,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 2.5487,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 34.421295166015625,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 2.5494,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 35.152748107910156,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.5936,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 34.947021484375,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 2.5574,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 34.67315673828125,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.4894,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 34.679954528808594,
+      "learning_rate": 5.5e-07,
+      "loss": 2.4985,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 33.57002258300781,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.4339,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 33.517276763916016,
+      "learning_rate": 6.5e-07,
+      "loss": 2.4055,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 33.5312385559082,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 2.3806,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 32.01276779174805,
+      "learning_rate": 7.5e-07,
+      "loss": 2.2505,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 31.827980041503906,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 31.437101364135742,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 2.1117,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 30.315187454223633,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.9795,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 29.622655868530273,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.8472,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 28.628408432006836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7283,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 27.83180046081543,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.5942,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 26.911596298217773,
+      "learning_rate": 1.1e-06,
+      "loss": 1.4467,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 25.88102149963379,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 1.3007,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 25.146381378173828,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1319,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 24.800382614135742,
+      "learning_rate": 1.25e-06,
+      "loss": 0.9359,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 24.648332595825195,
+      "learning_rate": 1.3e-06,
+      "loss": 0.7054,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 22.947620391845703,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 0.5209,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 17.80010414123535,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.3546,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 11.841789245605469,
+      "learning_rate": 1.45e-06,
+      "loss": 0.26,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 7.275839805603027,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1808,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 4.6324543952941895,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 0.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 3.1281485557556152,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 2.062562942504883,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 0.0966,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.1343328952789307,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.088,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.6768524646759033,
+      "learning_rate": 1.75e-06,
+      "loss": 0.0783,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.0879229307174683,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0623,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.83177649974823,
+      "learning_rate": 1.85e-06,
+      "loss": 0.0655,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5678385496139526,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.0565,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.6994458436965942,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.0491,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.711387038230896,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0507,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.7169735431671143,
+      "learning_rate": 2.05e-06,
+      "loss": 0.0478,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.603631317615509,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.0507,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.617487907409668,
+      "learning_rate": 2.15e-06,
+      "loss": 0.043,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.4638065993785858,
+      "learning_rate": 2.2e-06,
+      "loss": 0.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.5996385216712952,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0429,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.39118286967277527,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.0421,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.3118075728416443,
+      "learning_rate": 2.35e-06,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.31731992959976196,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.041,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.5413194298744202,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.32958006858825684,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0355,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.596309244632721,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0413,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.4557362496852875,
+      "learning_rate": 2.6e-06,
+      "loss": 0.0461,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.3345410227775574,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.0385,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.3047848343849182,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0383,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.43763449788093567,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.038,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.26870036125183105,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0374,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.38762542605400085,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0349,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.27517396211624146,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0398,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.30815261602401733,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0364,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.30011361837387085,
+      "learning_rate": 3e-06,
+      "loss": 0.0307,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.3269154727458954,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0344,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.3750869333744049,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0339,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.29285815358161926,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.034,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.4157550632953644,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0348,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.2852867543697357,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0319,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.4384031593799591,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0319,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.4003254771232605,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0347,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.49913832545280457,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0347,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.22642269730567932,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0306,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.34004101157188416,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0337,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.21503636240959167,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0311,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.33802086114883423,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2488064169883728,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0318,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.21124528348445892,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0293,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.3108712136745453,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33483418822288513,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.031,
+      "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..5a1edbdcc63a93daa09112168cf20c0f8fcb7512
--- /dev/null
+++ b/checkpoint-76/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041cfaa5bf8383821dea4fa5a9d2eab2caad4644c4cd651398c8b0ab1541b270
+size 7992
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..dd4e5ad4ad4c9bafb071dccdbf016fd2b2c567d4
--- /dev/null
+++ b/config.json
@@ -0,0 +1,52 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+  "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..fdde94c29816839ec3c29d6c6461206a49911f3c
--- /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\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"
+}