diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..5d63e9fbb43dd6c5dbcea26e3515c17c79719ea2 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,8 @@ 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-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-480/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..3d1dc2dbb47a92750a96471a799fbaf0e686ba9d
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0468018290f56f05a61b7c61f149b4b35460ff46
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f43dab069cfdcacbd2443671997ce7738bb6dc3830c63fa9d0e4d28a5903ffc
+size 486600536
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1ccd9107504d26ae2d65987b64fc7c79aed7c163
--- /dev/null
+++ b/checkpoint-300/README.md
@@ -0,0 +1,202 @@
+---
+base_model: NewEden/Hamanasu-KTO-V2
+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-300/adapter_config.json b/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3d1dc2dbb47a92750a96471a799fbaf0e686ba9d
--- /dev/null
+++ b/checkpoint-300/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5ef90b2b67b0062e5f6fb696c9c282af558063ae
--- /dev/null
+++ b/checkpoint-300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc93317df87d24dbc751827fb8b7261f1eb6df3cf31124032e490d3d6a2fff61
+size 486600536
diff --git a/checkpoint-300/latest b/checkpoint-300/latest
new file mode 100644
index 0000000000000000000000000000000000000000..6761b575fffac7f1984044dcb6446b3a51da04c8
--- /dev/null
+++ b/checkpoint-300/latest
@@ -0,0 +1 @@
+global_step300
\ No newline at end of file
diff --git a/checkpoint-300/rng_state_0.pth b/checkpoint-300/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..07c3f98983631f9cb91de516b4a06664a2cf805b
--- /dev/null
+++ b/checkpoint-300/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080b6d5dd016eedd242f1c87f1c49f6194cbf61dc02b1e8482849da2ffc7bc1d
+size 15024
diff --git a/checkpoint-300/rng_state_1.pth b/checkpoint-300/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..06112654785724565fc6d554ab41d454e5bdbd2f
--- /dev/null
+++ b/checkpoint-300/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b038dedf6c8088f62157bca21d8a81ddc3cf88995a4a31cdc0ce765b8a8c533
+size 15024
diff --git a/checkpoint-300/rng_state_2.pth b/checkpoint-300/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4c4d312c56aab1494c0eaa21e7fb7e22ad00851
--- /dev/null
+++ b/checkpoint-300/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc5c7fa0ff819fadae8b2511d96c19201285725b85fa37843d322b529d01cc8
+size 15024
diff --git a/checkpoint-300/rng_state_3.pth b/checkpoint-300/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c719999a85d9abf3d8fbd0c9125f979457945844
--- /dev/null
+++ b/checkpoint-300/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c75def22398a44a621a99bc32c2853940c7f21955a8423605b2ef4b73bb5b85
+size 15024
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3071b5673f334ae7093e3145e84ed37d8cb4dedf
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840c5d110a77253c19ab9743baad88cf5330aef39fa9b184a3da25d97a87b15d
+size 1064
diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9414f9e36eb995388775c9e63e5588313e7c41d3
--- /dev/null
+++ b/checkpoint-300/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ae94f3cc49ae02ddb8b100e69ba51719000fa01
--- /dev/null
+++ b/checkpoint-300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884
diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c131c4a0f2e6b6f0b564da934a01b86750c6d347
--- /dev/null
+++ b/checkpoint-300/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": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..67d56e2d5c7edb0850e84fb961c320310d3c4a77
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,2222 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5,
+  "eval_steps": 30,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.9462232657835241,
+      "learning_rate": 8.142857142857143e-07,
+      "loss": 2.5443,
+      "step": 1
+    },
+    {
+      "epoch": 0.008333333333333333,
+      "eval_loss": 2.5896365642547607,
+      "eval_runtime": 96.0059,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 0.271,
+      "step": 1
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.9597143397960513,
+      "learning_rate": 1.6285714285714286e-06,
+      "loss": 2.5524,
+      "step": 2
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.9246258453027174,
+      "learning_rate": 2.442857142857143e-06,
+      "loss": 2.5411,
+      "step": 3
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.9822285829186661,
+      "learning_rate": 3.2571428571428572e-06,
+      "loss": 2.5518,
+      "step": 4
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.9044329068814566,
+      "learning_rate": 4.071428571428572e-06,
+      "loss": 2.4922,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9131300887744053,
+      "learning_rate": 4.885714285714286e-06,
+      "loss": 2.5713,
+      "step": 6
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.8336298309675122,
+      "learning_rate": 5.7000000000000005e-06,
+      "loss": 2.4959,
+      "step": 7
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.810775409605909,
+      "learning_rate": 6.5142857142857145e-06,
+      "loss": 2.4943,
+      "step": 8
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.6993505055921954,
+      "learning_rate": 7.3285714285714285e-06,
+      "loss": 2.5022,
+      "step": 9
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.5909140859664664,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 2.468,
+      "step": 10
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.5464791893738283,
+      "learning_rate": 8.957142857142857e-06,
+      "loss": 2.5203,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.41153668995149084,
+      "learning_rate": 9.771428571428571e-06,
+      "loss": 2.4912,
+      "step": 12
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.35433353277028035,
+      "learning_rate": 1.0585714285714287e-05,
+      "loss": 2.4467,
+      "step": 13
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.27579908222756766,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 2.4599,
+      "step": 14
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.22636758420678307,
+      "learning_rate": 1.2214285714285715e-05,
+      "loss": 2.4357,
+      "step": 15
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.22309908436920517,
+      "learning_rate": 1.3028571428571429e-05,
+      "loss": 2.368,
+      "step": 16
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.2384290311446137,
+      "learning_rate": 1.3842857142857143e-05,
+      "loss": 2.4054,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2279055472006466,
+      "learning_rate": 1.4657142857142857e-05,
+      "loss": 2.4162,
+      "step": 18
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.24659885813398136,
+      "learning_rate": 1.547142857142857e-05,
+      "loss": 2.4109,
+      "step": 19
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.21920560481126147,
+      "learning_rate": 1.6285714285714287e-05,
+      "loss": 2.4344,
+      "step": 20
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.21340860355678012,
+      "learning_rate": 1.71e-05,
+      "loss": 2.4532,
+      "step": 21
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.1775246176788835,
+      "learning_rate": 1.7914285714285715e-05,
+      "loss": 2.4398,
+      "step": 22
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.15469100364725502,
+      "learning_rate": 1.872857142857143e-05,
+      "loss": 2.4275,
+      "step": 23
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1261136620302219,
+      "learning_rate": 1.9542857142857143e-05,
+      "loss": 2.3855,
+      "step": 24
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.1251566381945981,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 2.4008,
+      "step": 25
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.12280228065778742,
+      "learning_rate": 2.1171428571428574e-05,
+      "loss": 2.4086,
+      "step": 26
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.1362748806421765,
+      "learning_rate": 2.1985714285714286e-05,
+      "loss": 2.3642,
+      "step": 27
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.12370426656542512,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 2.4168,
+      "step": 28
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.12077140199925576,
+      "learning_rate": 2.3614285714285718e-05,
+      "loss": 2.3502,
+      "step": 29
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.10854652278245232,
+      "learning_rate": 2.442857142857143e-05,
+      "loss": 2.323,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 2.4455511569976807,
+      "eval_runtime": 82.5732,
+      "eval_samples_per_second": 4.965,
+      "eval_steps_per_second": 0.315,
+      "step": 30
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.10286886191993252,
+      "learning_rate": 2.5242857142857142e-05,
+      "loss": 2.4007,
+      "step": 31
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.09687340891245565,
+      "learning_rate": 2.6057142857142858e-05,
+      "loss": 2.4088,
+      "step": 32
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.09653492248714694,
+      "learning_rate": 2.6871428571428574e-05,
+      "loss": 2.3906,
+      "step": 33
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.09022900019263645,
+      "learning_rate": 2.7685714285714286e-05,
+      "loss": 2.4065,
+      "step": 34
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.0912409242342349,
+      "learning_rate": 2.85e-05,
+      "loss": 2.3699,
+      "step": 35
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09592020125185927,
+      "learning_rate": 2.8499644890093217e-05,
+      "loss": 2.3587,
+      "step": 36
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.0907084429462166,
+      "learning_rate": 2.8498579578071537e-05,
+      "loss": 2.4259,
+      "step": 37
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.09390099422567517,
+      "learning_rate": 2.8496804117030106e-05,
+      "loss": 2.3232,
+      "step": 38
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.08704027284958313,
+      "learning_rate": 2.849431859545787e-05,
+      "loss": 2.4027,
+      "step": 39
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.08787482564111378,
+      "learning_rate": 2.849112313723319e-05,
+      "loss": 2.3827,
+      "step": 40
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.08422520058818864,
+      "learning_rate": 2.8487217901617672e-05,
+      "loss": 2.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.07979320980153469,
+      "learning_rate": 2.84826030832482e-05,
+      "loss": 2.3519,
+      "step": 42
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.07814774416810645,
+      "learning_rate": 2.8477278912127266e-05,
+      "loss": 2.3708,
+      "step": 43
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.07237049854036091,
+      "learning_rate": 2.847124565361149e-05,
+      "loss": 2.388,
+      "step": 44
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.07354258492789081,
+      "learning_rate": 2.8464503608398385e-05,
+      "loss": 2.3586,
+      "step": 45
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.0771281784161838,
+      "learning_rate": 2.845705311251141e-05,
+      "loss": 2.3993,
+      "step": 46
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.0763264062020341,
+      "learning_rate": 2.844889453728318e-05,
+      "loss": 2.3838,
+      "step": 47
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07082143620733677,
+      "learning_rate": 2.8440028289336977e-05,
+      "loss": 2.3628,
+      "step": 48
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 0.0715578975320661,
+      "learning_rate": 2.8430454810566477e-05,
+      "loss": 2.361,
+      "step": 49
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.06881630985450242,
+      "learning_rate": 2.8420174578113747e-05,
+      "loss": 2.4392,
+      "step": 50
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.0689279893077156,
+      "learning_rate": 2.8409188104345426e-05,
+      "loss": 2.3519,
+      "step": 51
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.07069081407018309,
+      "learning_rate": 2.8397495936827232e-05,
+      "loss": 2.3981,
+      "step": 52
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 0.07092917277421104,
+      "learning_rate": 2.8385098658296637e-05,
+      "loss": 2.355,
+      "step": 53
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0703607034709259,
+      "learning_rate": 2.8371996886633843e-05,
+      "loss": 2.3793,
+      "step": 54
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.07124199690967324,
+      "learning_rate": 2.8358191274830974e-05,
+      "loss": 2.4275,
+      "step": 55
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.07099804346309355,
+      "learning_rate": 2.8343682510959552e-05,
+      "loss": 2.3323,
+      "step": 56
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.06967632308939245,
+      "learning_rate": 2.8328471318136165e-05,
+      "loss": 2.3883,
+      "step": 57
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.07156300179553134,
+      "learning_rate": 2.831255845448647e-05,
+      "loss": 2.3298,
+      "step": 58
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 0.0704201532980033,
+      "learning_rate": 2.8295944713107387e-05,
+      "loss": 2.331,
+      "step": 59
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.06794782460291071,
+      "learning_rate": 2.8278630922027563e-05,
+      "loss": 2.3776,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.4216628074645996,
+      "eval_runtime": 82.3879,
+      "eval_samples_per_second": 4.976,
+      "eval_steps_per_second": 0.316,
+      "step": 60
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 0.07045949082426937,
+      "learning_rate": 2.8260617944166123e-05,
+      "loss": 2.3319,
+      "step": 61
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 0.0702234192794877,
+      "learning_rate": 2.824190667728965e-05,
+      "loss": 2.3647,
+      "step": 62
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.06946814214632402,
+      "learning_rate": 2.8222498053967434e-05,
+      "loss": 2.3967,
+      "step": 63
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.06563265580127577,
+      "learning_rate": 2.8202393041525005e-05,
+      "loss": 2.3863,
+      "step": 64
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0723770670150652,
+      "learning_rate": 2.8181592641995933e-05,
+      "loss": 2.3823,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06870429029917037,
+      "learning_rate": 2.8160097892071847e-05,
+      "loss": 2.3241,
+      "step": 66
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 0.08615444480664787,
+      "learning_rate": 2.8137909863050806e-05,
+      "loss": 2.3504,
+      "step": 67
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.06980417460436542,
+      "learning_rate": 2.8115029660783887e-05,
+      "loss": 2.3762,
+      "step": 68
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.0691283200064781,
+      "learning_rate": 2.809145842562007e-05,
+      "loss": 2.3202,
+      "step": 69
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.06434433998677834,
+      "learning_rate": 2.8067197332349406e-05,
+      "loss": 2.4117,
+      "step": 70
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 0.06712521054811822,
+      "learning_rate": 2.8042247590144472e-05,
+      "loss": 2.4234,
+      "step": 71
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.07781170630767965,
+      "learning_rate": 2.8016610442500087e-05,
+      "loss": 2.3614,
+      "step": 72
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 0.07179449259884696,
+      "learning_rate": 2.7990287167171357e-05,
+      "loss": 2.327,
+      "step": 73
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.0666012429917219,
+      "learning_rate": 2.7963279076109976e-05,
+      "loss": 2.3606,
+      "step": 74
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07042352420672252,
+      "learning_rate": 2.7935587515398855e-05,
+      "loss": 2.387,
+      "step": 75
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.07141219809062525,
+      "learning_rate": 2.7907213865185014e-05,
+      "loss": 2.3975,
+      "step": 76
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 0.07530038535140655,
+      "learning_rate": 2.787815953961081e-05,
+      "loss": 2.3975,
+      "step": 77
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.06873021297298251,
+      "learning_rate": 2.784842598674345e-05,
+      "loss": 2.3724,
+      "step": 78
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 0.06853494667979494,
+      "learning_rate": 2.781801468850282e-05,
+      "loss": 2.3994,
+      "step": 79
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.07164446612343163,
+      "learning_rate": 2.778692716058762e-05,
+      "loss": 2.3448,
+      "step": 80
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.07112624750325054,
+      "learning_rate": 2.7755164952399844e-05,
+      "loss": 2.2984,
+      "step": 81
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.07679055297227524,
+      "learning_rate": 2.7722729646967527e-05,
+      "loss": 2.3699,
+      "step": 82
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 0.07270378630883641,
+      "learning_rate": 2.768962286086587e-05,
+      "loss": 2.3436,
+      "step": 83
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06869524209312625,
+      "learning_rate": 2.7655846244136654e-05,
+      "loss": 2.3856,
+      "step": 84
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.07006104211903366,
+      "learning_rate": 2.762140148020602e-05,
+      "loss": 2.3852,
+      "step": 85
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.07264285304887648,
+      "learning_rate": 2.758629028580055e-05,
+      "loss": 2.3834,
+      "step": 86
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.07253530482477301,
+      "learning_rate": 2.7550514410861718e-05,
+      "loss": 2.3573,
+      "step": 87
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.07265955522289944,
+      "learning_rate": 2.751407563845866e-05,
+      "loss": 2.3163,
+      "step": 88
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 0.07374626234739601,
+      "learning_rate": 2.747697578469931e-05,
+      "loss": 2.3851,
+      "step": 89
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07255481420091238,
+      "learning_rate": 2.7439216698639904e-05,
+      "loss": 2.3345,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 2.4115521907806396,
+      "eval_runtime": 82.0248,
+      "eval_samples_per_second": 4.998,
+      "eval_steps_per_second": 0.317,
+      "step": 90
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 0.06817548300510701,
+      "learning_rate": 2.7400800262192788e-05,
+      "loss": 2.3449,
+      "step": 91
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.07336990573663302,
+      "learning_rate": 2.7361728390032657e-05,
+      "loss": 2.3448,
+      "step": 92
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.07822885886131264,
+      "learning_rate": 2.732200302950111e-05,
+      "loss": 2.3217,
+      "step": 93
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.07296512071361201,
+      "learning_rate": 2.728162616050959e-05,
+      "loss": 2.3329,
+      "step": 94
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.07367928865175823,
+      "learning_rate": 2.724059979544072e-05,
+      "loss": 2.3208,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.07504139519989858,
+      "learning_rate": 2.719892597904801e-05,
+      "loss": 2.3483,
+      "step": 96
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 0.06790757702451031,
+      "learning_rate": 2.7156606788353906e-05,
+      "loss": 2.4128,
+      "step": 97
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.07011160737870108,
+      "learning_rate": 2.7113644332546336e-05,
+      "loss": 2.3832,
+      "step": 98
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.08077329808935288,
+      "learning_rate": 2.707004075287352e-05,
+      "loss": 2.3308,
+      "step": 99
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.0719496280235162,
+      "learning_rate": 2.7025798222537306e-05,
+      "loss": 2.3254,
+      "step": 100
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 0.07275409855582728,
+      "learning_rate": 2.698091894658483e-05,
+      "loss": 2.3967,
+      "step": 101
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.07201531734077336,
+      "learning_rate": 2.693540516179861e-05,
+      "loss": 2.3346,
+      "step": 102
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 0.0765467775604243,
+      "learning_rate": 2.6889259136585094e-05,
+      "loss": 2.3336,
+      "step": 103
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.077223728318478,
+      "learning_rate": 2.6842483170861568e-05,
+      "loss": 2.3313,
+      "step": 104
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.07639332869289207,
+      "learning_rate": 2.6795079595941553e-05,
+      "loss": 2.4008,
+      "step": 105
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 0.07440505813328589,
+      "learning_rate": 2.6747050774418605e-05,
+      "loss": 2.3425,
+      "step": 106
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 0.06937810484842656,
+      "learning_rate": 2.6698399100048556e-05,
+      "loss": 2.3349,
+      "step": 107
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07336400555418392,
+      "learning_rate": 2.6649126997630225e-05,
+      "loss": 2.3792,
+      "step": 108
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 0.07442564570941794,
+      "learning_rate": 2.6599236922884547e-05,
+      "loss": 2.3683,
+      "step": 109
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.07470689463768693,
+      "learning_rate": 2.65487313623322e-05,
+      "loss": 2.3036,
+      "step": 110
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.07096997017300663,
+      "learning_rate": 2.649761283316966e-05,
+      "loss": 2.3682,
+      "step": 111
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07511821034386772,
+      "learning_rate": 2.6445883883143744e-05,
+      "loss": 2.3346,
+      "step": 112
+    },
+    {
+      "epoch": 0.9416666666666667,
+      "grad_norm": 0.07057540374817312,
+      "learning_rate": 2.639354709042466e-05,
+      "loss": 2.3502,
+      "step": 113
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07300364605060353,
+      "learning_rate": 2.6340605063477456e-05,
+      "loss": 2.3711,
+      "step": 114
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.06925480258849577,
+      "learning_rate": 2.628706044093207e-05,
+      "loss": 2.3816,
+      "step": 115
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.0705107307569524,
+      "learning_rate": 2.623291589145179e-05,
+      "loss": 2.2958,
+      "step": 116
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.07331112076487026,
+      "learning_rate": 2.6178174113600252e-05,
+      "loss": 2.3279,
+      "step": 117
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.06780655482074792,
+      "learning_rate": 2.612283783570695e-05,
+      "loss": 2.4117,
+      "step": 118
+    },
+    {
+      "epoch": 0.9916666666666667,
+      "grad_norm": 0.07485055181125701,
+      "learning_rate": 2.606690981573125e-05,
+      "loss": 2.303,
+      "step": 119
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07276467760742707,
+      "learning_rate": 2.6010392841124932e-05,
+      "loss": 2.3608,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4049572944641113,
+      "eval_runtime": 82.3343,
+      "eval_samples_per_second": 4.98,
+      "eval_steps_per_second": 0.316,
+      "step": 120
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 0.07548790321925977,
+      "learning_rate": 2.5953289728693274e-05,
+      "loss": 2.3185,
+      "step": 121
+    },
+    {
+      "epoch": 1.0166666666666666,
+      "grad_norm": 0.0730570698984131,
+      "learning_rate": 2.5895603324454647e-05,
+      "loss": 2.2877,
+      "step": 122
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.07345139782586493,
+      "learning_rate": 2.5837336503498694e-05,
+      "loss": 2.2836,
+      "step": 123
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.07299378924326991,
+      "learning_rate": 2.5778492169843003e-05,
+      "loss": 2.3436,
+      "step": 124
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.07154250149880004,
+      "learning_rate": 2.5719073256288394e-05,
+      "loss": 2.3822,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0720748804004234,
+      "learning_rate": 2.565908272427274e-05,
+      "loss": 2.2708,
+      "step": 126
+    },
+    {
+      "epoch": 1.0583333333333333,
+      "grad_norm": 0.07269892036621302,
+      "learning_rate": 2.5598523563723373e-05,
+      "loss": 2.3377,
+      "step": 127
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0756770863265576,
+      "learning_rate": 2.5537398792908062e-05,
+      "loss": 2.352,
+      "step": 128
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.07397323539112335,
+      "learning_rate": 2.547571145828459e-05,
+      "loss": 2.3643,
+      "step": 129
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.07438211371538549,
+      "learning_rate": 2.54134646343489e-05,
+      "loss": 2.3387,
+      "step": 130
+    },
+    {
+      "epoch": 1.0916666666666666,
+      "grad_norm": 0.07094248712059498,
+      "learning_rate": 2.5350661423481885e-05,
+      "loss": 2.3221,
+      "step": 131
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.0771622686218861,
+      "learning_rate": 2.5287304955794754e-05,
+      "loss": 2.3183,
+      "step": 132
+    },
+    {
+      "epoch": 1.1083333333333334,
+      "grad_norm": 0.07495056480159959,
+      "learning_rate": 2.5223398388973028e-05,
+      "loss": 2.3697,
+      "step": 133
+    },
+    {
+      "epoch": 1.1166666666666667,
+      "grad_norm": 0.07629199954207538,
+      "learning_rate": 2.515894490811916e-05,
+      "loss": 2.3529,
+      "step": 134
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.0762534542729489,
+      "learning_rate": 2.5093947725593792e-05,
+      "loss": 2.3208,
+      "step": 135
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.07587427933984144,
+      "learning_rate": 2.502841008085565e-05,
+      "loss": 2.3448,
+      "step": 136
+    },
+    {
+      "epoch": 1.1416666666666666,
+      "grad_norm": 0.07490456619530689,
+      "learning_rate": 2.49623352403001e-05,
+      "loss": 2.3435,
+      "step": 137
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.0744781797534131,
+      "learning_rate": 2.4895726497096315e-05,
+      "loss": 2.4,
+      "step": 138
+    },
+    {
+      "epoch": 1.1583333333333332,
+      "grad_norm": 0.07464944817741491,
+      "learning_rate": 2.482858717102319e-05,
+      "loss": 2.318,
+      "step": 139
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.07309033869975678,
+      "learning_rate": 2.4760920608303867e-05,
+      "loss": 2.2891,
+      "step": 140
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.07284517336177344,
+      "learning_rate": 2.469273018143894e-05,
+      "loss": 2.3051,
+      "step": 141
+    },
+    {
+      "epoch": 1.1833333333333333,
+      "grad_norm": 0.07652064520411771,
+      "learning_rate": 2.462401928903839e-05,
+      "loss": 2.3555,
+      "step": 142
+    },
+    {
+      "epoch": 1.1916666666666667,
+      "grad_norm": 0.07701974074136966,
+      "learning_rate": 2.45547913556522e-05,
+      "loss": 2.3015,
+      "step": 143
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.08108352272511765,
+      "learning_rate": 2.448504983159966e-05,
+      "loss": 2.3221,
+      "step": 144
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.07752288456105606,
+      "learning_rate": 2.441479819279742e-05,
+      "loss": 2.3684,
+      "step": 145
+    },
+    {
+      "epoch": 1.2166666666666668,
+      "grad_norm": 0.07881711814524053,
+      "learning_rate": 2.4344039940586235e-05,
+      "loss": 2.3011,
+      "step": 146
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.07757542042787384,
+      "learning_rate": 2.4272778601556472e-05,
+      "loss": 2.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.07228965364348439,
+      "learning_rate": 2.4201017727372336e-05,
+      "loss": 2.3801,
+      "step": 148
+    },
+    {
+      "epoch": 1.2416666666666667,
+      "grad_norm": 0.07389812003829682,
+      "learning_rate": 2.4128760894594853e-05,
+      "loss": 2.3359,
+      "step": 149
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.08146218033856112,
+      "learning_rate": 2.4056011704503633e-05,
+      "loss": 2.3096,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 2.400259494781494,
+      "eval_runtime": 81.604,
+      "eval_samples_per_second": 5.024,
+      "eval_steps_per_second": 0.319,
+      "step": 150
+    },
+    {
+      "epoch": 1.2583333333333333,
+      "grad_norm": 0.07407260421175128,
+      "learning_rate": 2.3982773782917347e-05,
+      "loss": 2.3418,
+      "step": 151
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.07827237096687646,
+      "learning_rate": 2.390905078001306e-05,
+      "loss": 2.2778,
+      "step": 152
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.07699758244967876,
+      "learning_rate": 2.383484637014426e-05,
+      "loss": 2.3245,
+      "step": 153
+    },
+    {
+      "epoch": 1.2833333333333332,
+      "grad_norm": 0.07805943021524937,
+      "learning_rate": 2.3760164251657773e-05,
+      "loss": 2.3782,
+      "step": 154
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.0741687347632035,
+      "learning_rate": 2.368500814670941e-05,
+      "loss": 2.3765,
+      "step": 155
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.07696079818166807,
+      "learning_rate": 2.3609381801078448e-05,
+      "loss": 2.3958,
+      "step": 156
+    },
+    {
+      "epoch": 1.3083333333333333,
+      "grad_norm": 0.08864860865623735,
+      "learning_rate": 2.3533288983980964e-05,
+      "loss": 2.3482,
+      "step": 157
+    },
+    {
+      "epoch": 1.3166666666666667,
+      "grad_norm": 0.07676755572584443,
+      "learning_rate": 2.3456733487881978e-05,
+      "loss": 2.3511,
+      "step": 158
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.07754541163995884,
+      "learning_rate": 2.337971912830641e-05,
+      "loss": 2.3754,
+      "step": 159
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08430746433268149,
+      "learning_rate": 2.3302249743648926e-05,
+      "loss": 2.4063,
+      "step": 160
+    },
+    {
+      "epoch": 1.3416666666666668,
+      "grad_norm": 0.08113759941899056,
+      "learning_rate": 2.322432919498265e-05,
+      "loss": 2.3352,
+      "step": 161
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.08147516272984133,
+      "learning_rate": 2.3145961365866708e-05,
+      "loss": 2.3119,
+      "step": 162
+    },
+    {
+      "epoch": 1.3583333333333334,
+      "grad_norm": 0.07749688842544009,
+      "learning_rate": 2.3067150162152675e-05,
+      "loss": 2.3547,
+      "step": 163
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.08640326754187048,
+      "learning_rate": 2.298789951178992e-05,
+      "loss": 2.3389,
+      "step": 164
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.0795137333109577,
+      "learning_rate": 2.2908213364629812e-05,
+      "loss": 2.3778,
+      "step": 165
+    },
+    {
+      "epoch": 1.3833333333333333,
+      "grad_norm": 0.07739334763959965,
+      "learning_rate": 2.2828095692228886e-05,
+      "loss": 2.3658,
+      "step": 166
+    },
+    {
+      "epoch": 1.3916666666666666,
+      "grad_norm": 0.07783031237693959,
+      "learning_rate": 2.2747550487650887e-05,
+      "loss": 2.3575,
+      "step": 167
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.07682655233706284,
+      "learning_rate": 2.2666581765267758e-05,
+      "loss": 2.2825,
+      "step": 168
+    },
+    {
+      "epoch": 1.4083333333333332,
+      "grad_norm": 0.08359081032268273,
+      "learning_rate": 2.2585193560559563e-05,
+      "loss": 2.261,
+      "step": 169
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.0826940676306091,
+      "learning_rate": 2.250338992991335e-05,
+      "loss": 2.3069,
+      "step": 170
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.08462619097403327,
+      "learning_rate": 2.2421174950421017e-05,
+      "loss": 2.2864,
+      "step": 171
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.07990029642375193,
+      "learning_rate": 2.233855271967606e-05,
+      "loss": 2.3033,
+      "step": 172
+    },
+    {
+      "epoch": 1.4416666666666667,
+      "grad_norm": 0.08051779058857793,
+      "learning_rate": 2.2255527355569372e-05,
+      "loss": 2.3166,
+      "step": 173
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.08604667339713809,
+      "learning_rate": 2.217210299608402e-05,
+      "loss": 2.387,
+      "step": 174
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.07829742536277012,
+      "learning_rate": 2.208828379908899e-05,
+      "loss": 2.311,
+      "step": 175
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.07850219342360719,
+      "learning_rate": 2.200407394213196e-05,
+      "loss": 2.3384,
+      "step": 176
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.08531707041033702,
+      "learning_rate": 2.19194776222311e-05,
+      "loss": 2.3107,
+      "step": 177
+    },
+    {
+      "epoch": 1.4833333333333334,
+      "grad_norm": 0.07652853009760147,
+      "learning_rate": 2.183449905566589e-05,
+      "loss": 2.3494,
+      "step": 178
+    },
+    {
+      "epoch": 1.4916666666666667,
+      "grad_norm": 0.0797336095546633,
+      "learning_rate": 2.1749142477766972e-05,
+      "loss": 2.3291,
+      "step": 179
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.08700079540422817,
+      "learning_rate": 2.166341214270507e-05,
+      "loss": 2.3132,
+      "step": 180
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.3966128826141357,
+      "eval_runtime": 83.184,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 0.313,
+      "step": 180
+    },
+    {
+      "epoch": 1.5083333333333333,
+      "grad_norm": 0.07925581040107615,
+      "learning_rate": 2.157731232327897e-05,
+      "loss": 2.3578,
+      "step": 181
+    },
+    {
+      "epoch": 1.5166666666666666,
+      "grad_norm": 0.07873086864048841,
+      "learning_rate": 2.1490847310702544e-05,
+      "loss": 2.3229,
+      "step": 182
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.07775316849537767,
+      "learning_rate": 2.1404021414390874e-05,
+      "loss": 2.3756,
+      "step": 183
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.07949428482523528,
+      "learning_rate": 2.1316838961745518e-05,
+      "loss": 2.3535,
+      "step": 184
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.08423278187074197,
+      "learning_rate": 2.1229304297938755e-05,
+      "loss": 2.3517,
+      "step": 185
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.07930583119038707,
+      "learning_rate": 2.1141421785697097e-05,
+      "loss": 2.3929,
+      "step": 186
+    },
+    {
+      "epoch": 1.5583333333333333,
+      "grad_norm": 0.07736840323261199,
+      "learning_rate": 2.1053195805083803e-05,
+      "loss": 2.3194,
+      "step": 187
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.08306421066524537,
+      "learning_rate": 2.0964630753280584e-05,
+      "loss": 2.3131,
+      "step": 188
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.0805185815818936,
+      "learning_rate": 2.0875731044368472e-05,
+      "loss": 2.3238,
+      "step": 189
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.07729948838070921,
+      "learning_rate": 2.078650110910779e-05,
+      "loss": 2.3279,
+      "step": 190
+    },
+    {
+      "epoch": 1.5916666666666668,
+      "grad_norm": 0.08053951644296133,
+      "learning_rate": 2.0696945394717355e-05,
+      "loss": 2.3343,
+      "step": 191
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.08184664333069269,
+      "learning_rate": 2.0607068364652783e-05,
+      "loss": 2.3441,
+      "step": 192
+    },
+    {
+      "epoch": 1.6083333333333334,
+      "grad_norm": 0.07894699650259683,
+      "learning_rate": 2.051687449838409e-05,
+      "loss": 2.3384,
+      "step": 193
+    },
+    {
+      "epoch": 1.6166666666666667,
+      "grad_norm": 0.08288692832517489,
+      "learning_rate": 2.042636829117239e-05,
+      "loss": 2.3219,
+      "step": 194
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.09061769591669266,
+      "learning_rate": 2.033555425384586e-05,
+      "loss": 2.3168,
+      "step": 195
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.07607427061534017,
+      "learning_rate": 2.0244436912574938e-05,
+      "loss": 2.3592,
+      "step": 196
+    },
+    {
+      "epoch": 1.6416666666666666,
+      "grad_norm": 0.08827457673533141,
+      "learning_rate": 2.0153020808646715e-05,
+      "loss": 2.3177,
+      "step": 197
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.0757688204165182,
+      "learning_rate": 2.0061310498238618e-05,
+      "loss": 2.2366,
+      "step": 198
+    },
+    {
+      "epoch": 1.6583333333333332,
+      "grad_norm": 0.07815852114026649,
+      "learning_rate": 1.996931055219132e-05,
+      "loss": 2.3161,
+      "step": 199
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.08058901889279678,
+      "learning_rate": 1.9877025555780927e-05,
+      "loss": 2.3749,
+      "step": 200
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.07708027281441528,
+      "learning_rate": 1.978446010849045e-05,
+      "loss": 2.2854,
+      "step": 201
+    },
+    {
+      "epoch": 1.6833333333333333,
+      "grad_norm": 0.08312283019758401,
+      "learning_rate": 1.969161882378058e-05,
+      "loss": 2.3524,
+      "step": 202
+    },
+    {
+      "epoch": 1.6916666666666667,
+      "grad_norm": 0.07784046601849169,
+      "learning_rate": 1.9598506328859717e-05,
+      "loss": 2.3418,
+      "step": 203
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.07906237498578873,
+      "learning_rate": 1.95051272644534e-05,
+      "loss": 2.3514,
+      "step": 204
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.08323464269988524,
+      "learning_rate": 1.9411486284572977e-05,
+      "loss": 2.3133,
+      "step": 205
+    },
+    {
+      "epoch": 1.7166666666666668,
+      "grad_norm": 0.08153670371604982,
+      "learning_rate": 1.931758805628366e-05,
+      "loss": 2.3388,
+      "step": 206
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.08152589045596419,
+      "learning_rate": 1.9223437259471912e-05,
+      "loss": 2.3309,
+      "step": 207
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.08382345786042532,
+      "learning_rate": 1.9129038586612224e-05,
+      "loss": 2.3282,
+      "step": 208
+    },
+    {
+      "epoch": 1.7416666666666667,
+      "grad_norm": 0.0835609429134592,
+      "learning_rate": 1.903439674253321e-05,
+      "loss": 2.3567,
+      "step": 209
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.08252984125014622,
+      "learning_rate": 1.8939516444183143e-05,
+      "loss": 2.3352,
+      "step": 210
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.3933684825897217,
+      "eval_runtime": 83.3063,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 0.312,
+      "step": 210
+    },
+    {
+      "epoch": 1.7583333333333333,
+      "grad_norm": 0.0815481053340795,
+      "learning_rate": 1.884440242039485e-05,
+      "loss": 2.3262,
+      "step": 211
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.08258761118218041,
+      "learning_rate": 1.8749059411650034e-05,
+      "loss": 2.3396,
+      "step": 212
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.0884999967331726,
+      "learning_rate": 1.8653492169843003e-05,
+      "loss": 2.3176,
+      "step": 213
+    },
+    {
+      "epoch": 1.7833333333333332,
+      "grad_norm": 0.0824785010834098,
+      "learning_rate": 1.8557705458043838e-05,
+      "loss": 2.3272,
+      "step": 214
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.08727167025374602,
+      "learning_rate": 1.8461704050261e-05,
+      "loss": 2.2298,
+      "step": 215
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0768016904891171,
+      "learning_rate": 1.8365492731203398e-05,
+      "loss": 2.3554,
+      "step": 216
+    },
+    {
+      "epoch": 1.8083333333333333,
+      "grad_norm": 0.07709533586121158,
+      "learning_rate": 1.8269076296041917e-05,
+      "loss": 2.3702,
+      "step": 217
+    },
+    {
+      "epoch": 1.8166666666666667,
+      "grad_norm": 0.0806446736093232,
+      "learning_rate": 1.8172459550170424e-05,
+      "loss": 2.3585,
+      "step": 218
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.07523532523458193,
+      "learning_rate": 1.8075647308966268e-05,
+      "loss": 2.3609,
+      "step": 219
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.07497201271988578,
+      "learning_rate": 1.797864439755028e-05,
+      "loss": 2.3755,
+      "step": 220
+    },
+    {
+      "epoch": 1.8416666666666668,
+      "grad_norm": 0.08249074177996166,
+      "learning_rate": 1.7881455650546303e-05,
+      "loss": 2.372,
+      "step": 221
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0780160636961897,
+      "learning_rate": 1.7784085911840214e-05,
+      "loss": 2.3823,
+      "step": 222
+    },
+    {
+      "epoch": 1.8583333333333334,
+      "grad_norm": 0.08148680526536918,
+      "learning_rate": 1.7686540034338513e-05,
+      "loss": 2.3314,
+      "step": 223
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0795864595636552,
+      "learning_rate": 1.758882287972646e-05,
+      "loss": 2.2853,
+      "step": 224
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.08198344669246531,
+      "learning_rate": 1.749093931822577e-05,
+      "loss": 2.3605,
+      "step": 225
+    },
+    {
+      "epoch": 1.8833333333333333,
+      "grad_norm": 0.08138145213474299,
+      "learning_rate": 1.739289422835185e-05,
+      "loss": 2.2721,
+      "step": 226
+    },
+    {
+      "epoch": 1.8916666666666666,
+      "grad_norm": 0.08306015511124677,
+      "learning_rate": 1.7294692496670715e-05,
+      "loss": 2.2889,
+      "step": 227
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.07478727556401082,
+      "learning_rate": 1.7196339017555378e-05,
+      "loss": 2.3416,
+      "step": 228
+    },
+    {
+      "epoch": 1.9083333333333332,
+      "grad_norm": 0.08858459574829487,
+      "learning_rate": 1.709783869294196e-05,
+      "loss": 2.3081,
+      "step": 229
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.08175368181940743,
+      "learning_rate": 1.699919643208533e-05,
+      "loss": 2.3304,
+      "step": 230
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.07630479738636474,
+      "learning_rate": 1.6900417151314503e-05,
+      "loss": 2.3454,
+      "step": 231
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.07687273996639293,
+      "learning_rate": 1.6801505773787527e-05,
+      "loss": 2.3901,
+      "step": 232
+    },
+    {
+      "epoch": 1.9416666666666667,
+      "grad_norm": 0.08600269874202937,
+      "learning_rate": 1.670246722924616e-05,
+      "loss": 2.3081,
+      "step": 233
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.07737694968965858,
+      "learning_rate": 1.660330645377018e-05,
+      "loss": 2.3643,
+      "step": 234
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.08165758061569027,
+      "learning_rate": 1.6504028389531333e-05,
+      "loss": 2.355,
+      "step": 235
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.08264378429137093,
+      "learning_rate": 1.640463798454704e-05,
+      "loss": 2.3219,
+      "step": 236
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.0858368818345628,
+      "learning_rate": 1.6305140192433787e-05,
+      "loss": 2.3329,
+      "step": 237
+    },
+    {
+      "epoch": 1.9833333333333334,
+      "grad_norm": 0.07616999163161729,
+      "learning_rate": 1.620553997216023e-05,
+      "loss": 2.3523,
+      "step": 238
+    },
+    {
+      "epoch": 1.9916666666666667,
+      "grad_norm": 0.08241527325980988,
+      "learning_rate": 1.6105842287800046e-05,
+      "loss": 2.2982,
+      "step": 239
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08007891750583127,
+      "learning_rate": 1.600605210828451e-05,
+      "loss": 2.2785,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3910558223724365,
+      "eval_runtime": 83.4904,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 0.311,
+      "step": 240
+    },
+    {
+      "epoch": 2.0083333333333333,
+      "grad_norm": 0.08108687194604622,
+      "learning_rate": 1.5906174407154883e-05,
+      "loss": 2.3367,
+      "step": 241
+    },
+    {
+      "epoch": 2.0166666666666666,
+      "grad_norm": 0.0806511417182259,
+      "learning_rate": 1.5806214162314463e-05,
+      "loss": 2.3011,
+      "step": 242
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.08264392219751603,
+      "learning_rate": 1.5706176355780556e-05,
+      "loss": 2.3036,
+      "step": 243
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.07958409681135217,
+      "learning_rate": 1.5606065973436132e-05,
+      "loss": 2.3056,
+      "step": 244
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.07856642651007223,
+      "learning_rate": 1.550588800478133e-05,
+      "loss": 2.3692,
+      "step": 245
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.08350216798892127,
+      "learning_rate": 1.5405647442684794e-05,
+      "loss": 2.2697,
+      "step": 246
+    },
+    {
+      "epoch": 2.058333333333333,
+      "grad_norm": 0.08390645284684875,
+      "learning_rate": 1.530534928313484e-05,
+      "loss": 2.2425,
+      "step": 247
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.07883358190907572,
+      "learning_rate": 1.5204998524990423e-05,
+      "loss": 2.3281,
+      "step": 248
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.07994560560782488,
+      "learning_rate": 1.5104600169732015e-05,
+      "loss": 2.3285,
+      "step": 249
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.08345016891314849,
+      "learning_rate": 1.5004159221212325e-05,
+      "loss": 2.3252,
+      "step": 250
+    },
+    {
+      "epoch": 2.091666666666667,
+      "grad_norm": 0.0767244585605165,
+      "learning_rate": 1.490368068540692e-05,
+      "loss": 2.3176,
+      "step": 251
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.07853322933102938,
+      "learning_rate": 1.4803169570164703e-05,
+      "loss": 2.286,
+      "step": 252
+    },
+    {
+      "epoch": 2.1083333333333334,
+      "grad_norm": 0.07885223855237164,
+      "learning_rate": 1.4702630884958345e-05,
+      "loss": 2.3293,
+      "step": 253
+    },
+    {
+      "epoch": 2.1166666666666667,
+      "grad_norm": 0.07786083611140765,
+      "learning_rate": 1.4602069640634605e-05,
+      "loss": 2.3241,
+      "step": 254
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.07961379829842732,
+      "learning_rate": 1.4501490849164585e-05,
+      "loss": 2.3218,
+      "step": 255
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.0812119479291348,
+      "learning_rate": 1.4400899523393928e-05,
+      "loss": 2.3101,
+      "step": 256
+    },
+    {
+      "epoch": 2.1416666666666666,
+      "grad_norm": 0.07820228956836967,
+      "learning_rate": 1.4300300676793e-05,
+      "loss": 2.3105,
+      "step": 257
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.0787354321940814,
+      "learning_rate": 1.4199699323207e-05,
+      "loss": 2.2921,
+      "step": 258
+    },
+    {
+      "epoch": 2.158333333333333,
+      "grad_norm": 0.0821168083039209,
+      "learning_rate": 1.4099100476606071e-05,
+      "loss": 2.3449,
+      "step": 259
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.08227570212622978,
+      "learning_rate": 1.3998509150835417e-05,
+      "loss": 2.2804,
+      "step": 260
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.07956552166316343,
+      "learning_rate": 1.3897930359365397e-05,
+      "loss": 2.2798,
+      "step": 261
+    },
+    {
+      "epoch": 2.183333333333333,
+      "grad_norm": 0.08355971196343313,
+      "learning_rate": 1.3797369115041656e-05,
+      "loss": 2.3121,
+      "step": 262
+    },
+    {
+      "epoch": 2.191666666666667,
+      "grad_norm": 0.07664615523847712,
+      "learning_rate": 1.3696830429835303e-05,
+      "loss": 2.3511,
+      "step": 263
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.07875754809310784,
+      "learning_rate": 1.3596319314593088e-05,
+      "loss": 2.276,
+      "step": 264
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.07805417721469433,
+      "learning_rate": 1.3495840778787675e-05,
+      "loss": 2.3156,
+      "step": 265
+    },
+    {
+      "epoch": 2.216666666666667,
+      "grad_norm": 0.08500867883177173,
+      "learning_rate": 1.339539983026799e-05,
+      "loss": 2.3304,
+      "step": 266
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.08575986404103182,
+      "learning_rate": 1.3295001475009578e-05,
+      "loss": 2.3171,
+      "step": 267
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.0796424885760881,
+      "learning_rate": 1.3194650716865163e-05,
+      "loss": 2.3488,
+      "step": 268
+    },
+    {
+      "epoch": 2.2416666666666667,
+      "grad_norm": 0.07791982790558008,
+      "learning_rate": 1.3094352557315207e-05,
+      "loss": 2.3806,
+      "step": 269
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0840055290628465,
+      "learning_rate": 1.299411199521868e-05,
+      "loss": 2.3277,
+      "step": 270
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 2.3895957469940186,
+      "eval_runtime": 83.1157,
+      "eval_samples_per_second": 4.933,
+      "eval_steps_per_second": 0.313,
+      "step": 270
+    },
+    {
+      "epoch": 2.2583333333333333,
+      "grad_norm": 0.07770712903979533,
+      "learning_rate": 1.2893934026563873e-05,
+      "loss": 2.2666,
+      "step": 271
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07846164594226922,
+      "learning_rate": 1.2793823644219445e-05,
+      "loss": 2.2855,
+      "step": 272
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.08498339693180243,
+      "learning_rate": 1.269378583768554e-05,
+      "loss": 2.2733,
+      "step": 273
+    },
+    {
+      "epoch": 2.283333333333333,
+      "grad_norm": 0.07834222258922019,
+      "learning_rate": 1.2593825592845122e-05,
+      "loss": 2.3193,
+      "step": 274
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.08132580954052983,
+      "learning_rate": 1.2493947891715491e-05,
+      "loss": 2.3085,
+      "step": 275
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.07883697009265064,
+      "learning_rate": 1.239415771219996e-05,
+      "loss": 2.3545,
+      "step": 276
+    },
+    {
+      "epoch": 2.3083333333333336,
+      "grad_norm": 0.08023901828387182,
+      "learning_rate": 1.2294460027839779e-05,
+      "loss": 2.3489,
+      "step": 277
+    },
+    {
+      "epoch": 2.3166666666666664,
+      "grad_norm": 0.08930364086676225,
+      "learning_rate": 1.2194859807566216e-05,
+      "loss": 2.2591,
+      "step": 278
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.08343332964333285,
+      "learning_rate": 1.2095362015452961e-05,
+      "loss": 2.3404,
+      "step": 279
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.08292455976075656,
+      "learning_rate": 1.199597161046867e-05,
+      "loss": 2.3028,
+      "step": 280
+    },
+    {
+      "epoch": 2.341666666666667,
+      "grad_norm": 0.08627078651851632,
+      "learning_rate": 1.189669354622982e-05,
+      "loss": 2.343,
+      "step": 281
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.08202097516344958,
+      "learning_rate": 1.1797532770753842e-05,
+      "loss": 2.326,
+      "step": 282
+    },
+    {
+      "epoch": 2.3583333333333334,
+      "grad_norm": 0.08362611496815728,
+      "learning_rate": 1.169849422621248e-05,
+      "loss": 2.3035,
+      "step": 283
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.08888611458113292,
+      "learning_rate": 1.1599582848685506e-05,
+      "loss": 2.2812,
+      "step": 284
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.08217261091117088,
+      "learning_rate": 1.1500803567914671e-05,
+      "loss": 2.3378,
+      "step": 285
+    },
+    {
+      "epoch": 2.3833333333333333,
+      "grad_norm": 0.07985728135451624,
+      "learning_rate": 1.1402161307058047e-05,
+      "loss": 2.3522,
+      "step": 286
+    },
+    {
+      "epoch": 2.3916666666666666,
+      "grad_norm": 0.08014525439116486,
+      "learning_rate": 1.1303660982444624e-05,
+      "loss": 2.2256,
+      "step": 287
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08787593050595495,
+      "learning_rate": 1.1205307503329286e-05,
+      "loss": 2.2974,
+      "step": 288
+    },
+    {
+      "epoch": 2.408333333333333,
+      "grad_norm": 0.08195162040998395,
+      "learning_rate": 1.1107105771648151e-05,
+      "loss": 2.353,
+      "step": 289
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.08267743479386988,
+      "learning_rate": 1.1009060681774236e-05,
+      "loss": 2.3274,
+      "step": 290
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.08798947281948663,
+      "learning_rate": 1.0911177120273537e-05,
+      "loss": 2.3404,
+      "step": 291
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.08828111892887862,
+      "learning_rate": 1.0813459965661489e-05,
+      "loss": 2.3348,
+      "step": 292
+    },
+    {
+      "epoch": 2.4416666666666664,
+      "grad_norm": 0.08102528742267785,
+      "learning_rate": 1.0715914088159789e-05,
+      "loss": 2.2863,
+      "step": 293
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0866645702075036,
+      "learning_rate": 1.06185443494537e-05,
+      "loss": 2.3357,
+      "step": 294
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.08290121294865929,
+      "learning_rate": 1.0521355602449723e-05,
+      "loss": 2.3537,
+      "step": 295
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.08332374744178081,
+      "learning_rate": 1.042435269103374e-05,
+      "loss": 2.3554,
+      "step": 296
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.08367195510948358,
+      "learning_rate": 1.0327540449829583e-05,
+      "loss": 2.3384,
+      "step": 297
+    },
+    {
+      "epoch": 2.4833333333333334,
+      "grad_norm": 0.08673119537467149,
+      "learning_rate": 1.0230923703958083e-05,
+      "loss": 2.2725,
+      "step": 298
+    },
+    {
+      "epoch": 2.4916666666666667,
+      "grad_norm": 0.08235186060858125,
+      "learning_rate": 1.0134507268796605e-05,
+      "loss": 2.328,
+      "step": 299
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08408079009588813,
+      "learning_rate": 1.0038295949739004e-05,
+      "loss": 2.3403,
+      "step": 300
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.3881967067718506,
+      "eval_runtime": 82.1489,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.316,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.7220359996440576e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e71e9ef0b364c8b803828c31c7b34cd4f7001af
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
+size 8504
diff --git a/checkpoint-300/zero_to_fp32.py b/checkpoint-300/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..0e759146cadd92ddfefab3680146c2bd6a2b5c04
--- /dev/null
+++ b/checkpoint-300/zero_to_fp32.py
@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-360/README.md b/checkpoint-360/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1ccd9107504d26ae2d65987b64fc7c79aed7c163
--- /dev/null
+++ b/checkpoint-360/README.md
@@ -0,0 +1,202 @@
+---
+base_model: NewEden/Hamanasu-KTO-V2
+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-360/adapter_config.json b/checkpoint-360/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3d1dc2dbb47a92750a96471a799fbaf0e686ba9d
--- /dev/null
+++ b/checkpoint-360/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-360/adapter_model.safetensors b/checkpoint-360/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8a71ee0b347634644d63f70f642db289b6ff5285
--- /dev/null
+++ b/checkpoint-360/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49824f024f3dcb88857e84ac57519e0e800ee74f51f671d8a845e8316d023b98
+size 486600536
diff --git a/checkpoint-360/latest b/checkpoint-360/latest
new file mode 100644
index 0000000000000000000000000000000000000000..d5218e2cb542fcc2b4f0db115238711239960c7a
--- /dev/null
+++ b/checkpoint-360/latest
@@ -0,0 +1 @@
+global_step360
\ No newline at end of file
diff --git a/checkpoint-360/rng_state_0.pth b/checkpoint-360/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..85aaef1f99eb21d2a409d385d892005758cec6f0
--- /dev/null
+++ b/checkpoint-360/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc27c0ec5192565247549b2b990df01444d0ae2c5e4ef88a04caa8ea3511f368
+size 15024
diff --git a/checkpoint-360/rng_state_1.pth b/checkpoint-360/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f2278468595fee999ab8971ad8e2880114770bd1
--- /dev/null
+++ b/checkpoint-360/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebba24edc22a78099e68ae948789a5f3988d99d2837dc3bf4cb3d90aa25b72c
+size 15024
diff --git a/checkpoint-360/rng_state_2.pth b/checkpoint-360/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2a5e5de697a0f44920564e8d206f374eb5d8a386
--- /dev/null
+++ b/checkpoint-360/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2529034b653929c4c29ceb0c5a2f3f64cad1f7ba74055b08e6c45150153eefb2
+size 15024
diff --git a/checkpoint-360/rng_state_3.pth b/checkpoint-360/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1849b5cbd3322c840a1e1342afdcb4f1cb175c6d
--- /dev/null
+++ b/checkpoint-360/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba98362b76d76c3c8eea947d797b259757fc17dfc963b81f3420b8ff1d7eb7e
+size 15024
diff --git a/checkpoint-360/scheduler.pt b/checkpoint-360/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b63ddaeced955f02e86ccfdfc2ee6e28069bf919
--- /dev/null
+++ b/checkpoint-360/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a16947658fa0da4dd9926fd82031ac7020c56660a3149c81269647590342e23
+size 1064
diff --git a/checkpoint-360/special_tokens_map.json b/checkpoint-360/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9414f9e36eb995388775c9e63e5588313e7c41d3
--- /dev/null
+++ b/checkpoint-360/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-360/tokenizer.json b/checkpoint-360/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ae94f3cc49ae02ddb8b100e69ba51719000fa01
--- /dev/null
+++ b/checkpoint-360/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884
diff --git a/checkpoint-360/tokenizer_config.json b/checkpoint-360/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c131c4a0f2e6b6f0b564da934a01b86750c6d347
--- /dev/null
+++ b/checkpoint-360/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": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-360/trainer_state.json b/checkpoint-360/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9d2a7036462fa21ed7bd1dda809dfb7d38605458
--- /dev/null
+++ b/checkpoint-360/trainer_state.json
@@ -0,0 +1,2658 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.9462232657835241,
+      "learning_rate": 8.142857142857143e-07,
+      "loss": 2.5443,
+      "step": 1
+    },
+    {
+      "epoch": 0.008333333333333333,
+      "eval_loss": 2.5896365642547607,
+      "eval_runtime": 96.0059,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 0.271,
+      "step": 1
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.9597143397960513,
+      "learning_rate": 1.6285714285714286e-06,
+      "loss": 2.5524,
+      "step": 2
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.9246258453027174,
+      "learning_rate": 2.442857142857143e-06,
+      "loss": 2.5411,
+      "step": 3
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.9822285829186661,
+      "learning_rate": 3.2571428571428572e-06,
+      "loss": 2.5518,
+      "step": 4
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.9044329068814566,
+      "learning_rate": 4.071428571428572e-06,
+      "loss": 2.4922,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9131300887744053,
+      "learning_rate": 4.885714285714286e-06,
+      "loss": 2.5713,
+      "step": 6
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.8336298309675122,
+      "learning_rate": 5.7000000000000005e-06,
+      "loss": 2.4959,
+      "step": 7
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.810775409605909,
+      "learning_rate": 6.5142857142857145e-06,
+      "loss": 2.4943,
+      "step": 8
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.6993505055921954,
+      "learning_rate": 7.3285714285714285e-06,
+      "loss": 2.5022,
+      "step": 9
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.5909140859664664,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 2.468,
+      "step": 10
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.5464791893738283,
+      "learning_rate": 8.957142857142857e-06,
+      "loss": 2.5203,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.41153668995149084,
+      "learning_rate": 9.771428571428571e-06,
+      "loss": 2.4912,
+      "step": 12
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.35433353277028035,
+      "learning_rate": 1.0585714285714287e-05,
+      "loss": 2.4467,
+      "step": 13
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.27579908222756766,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 2.4599,
+      "step": 14
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.22636758420678307,
+      "learning_rate": 1.2214285714285715e-05,
+      "loss": 2.4357,
+      "step": 15
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.22309908436920517,
+      "learning_rate": 1.3028571428571429e-05,
+      "loss": 2.368,
+      "step": 16
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.2384290311446137,
+      "learning_rate": 1.3842857142857143e-05,
+      "loss": 2.4054,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2279055472006466,
+      "learning_rate": 1.4657142857142857e-05,
+      "loss": 2.4162,
+      "step": 18
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.24659885813398136,
+      "learning_rate": 1.547142857142857e-05,
+      "loss": 2.4109,
+      "step": 19
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.21920560481126147,
+      "learning_rate": 1.6285714285714287e-05,
+      "loss": 2.4344,
+      "step": 20
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.21340860355678012,
+      "learning_rate": 1.71e-05,
+      "loss": 2.4532,
+      "step": 21
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.1775246176788835,
+      "learning_rate": 1.7914285714285715e-05,
+      "loss": 2.4398,
+      "step": 22
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.15469100364725502,
+      "learning_rate": 1.872857142857143e-05,
+      "loss": 2.4275,
+      "step": 23
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1261136620302219,
+      "learning_rate": 1.9542857142857143e-05,
+      "loss": 2.3855,
+      "step": 24
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.1251566381945981,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 2.4008,
+      "step": 25
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.12280228065778742,
+      "learning_rate": 2.1171428571428574e-05,
+      "loss": 2.4086,
+      "step": 26
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.1362748806421765,
+      "learning_rate": 2.1985714285714286e-05,
+      "loss": 2.3642,
+      "step": 27
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.12370426656542512,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 2.4168,
+      "step": 28
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.12077140199925576,
+      "learning_rate": 2.3614285714285718e-05,
+      "loss": 2.3502,
+      "step": 29
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.10854652278245232,
+      "learning_rate": 2.442857142857143e-05,
+      "loss": 2.323,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 2.4455511569976807,
+      "eval_runtime": 82.5732,
+      "eval_samples_per_second": 4.965,
+      "eval_steps_per_second": 0.315,
+      "step": 30
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.10286886191993252,
+      "learning_rate": 2.5242857142857142e-05,
+      "loss": 2.4007,
+      "step": 31
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.09687340891245565,
+      "learning_rate": 2.6057142857142858e-05,
+      "loss": 2.4088,
+      "step": 32
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.09653492248714694,
+      "learning_rate": 2.6871428571428574e-05,
+      "loss": 2.3906,
+      "step": 33
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.09022900019263645,
+      "learning_rate": 2.7685714285714286e-05,
+      "loss": 2.4065,
+      "step": 34
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.0912409242342349,
+      "learning_rate": 2.85e-05,
+      "loss": 2.3699,
+      "step": 35
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09592020125185927,
+      "learning_rate": 2.8499644890093217e-05,
+      "loss": 2.3587,
+      "step": 36
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.0907084429462166,
+      "learning_rate": 2.8498579578071537e-05,
+      "loss": 2.4259,
+      "step": 37
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.09390099422567517,
+      "learning_rate": 2.8496804117030106e-05,
+      "loss": 2.3232,
+      "step": 38
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.08704027284958313,
+      "learning_rate": 2.849431859545787e-05,
+      "loss": 2.4027,
+      "step": 39
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.08787482564111378,
+      "learning_rate": 2.849112313723319e-05,
+      "loss": 2.3827,
+      "step": 40
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.08422520058818864,
+      "learning_rate": 2.8487217901617672e-05,
+      "loss": 2.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.07979320980153469,
+      "learning_rate": 2.84826030832482e-05,
+      "loss": 2.3519,
+      "step": 42
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.07814774416810645,
+      "learning_rate": 2.8477278912127266e-05,
+      "loss": 2.3708,
+      "step": 43
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.07237049854036091,
+      "learning_rate": 2.847124565361149e-05,
+      "loss": 2.388,
+      "step": 44
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.07354258492789081,
+      "learning_rate": 2.8464503608398385e-05,
+      "loss": 2.3586,
+      "step": 45
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.0771281784161838,
+      "learning_rate": 2.845705311251141e-05,
+      "loss": 2.3993,
+      "step": 46
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.0763264062020341,
+      "learning_rate": 2.844889453728318e-05,
+      "loss": 2.3838,
+      "step": 47
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07082143620733677,
+      "learning_rate": 2.8440028289336977e-05,
+      "loss": 2.3628,
+      "step": 48
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 0.0715578975320661,
+      "learning_rate": 2.8430454810566477e-05,
+      "loss": 2.361,
+      "step": 49
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.06881630985450242,
+      "learning_rate": 2.8420174578113747e-05,
+      "loss": 2.4392,
+      "step": 50
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.0689279893077156,
+      "learning_rate": 2.8409188104345426e-05,
+      "loss": 2.3519,
+      "step": 51
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.07069081407018309,
+      "learning_rate": 2.8397495936827232e-05,
+      "loss": 2.3981,
+      "step": 52
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 0.07092917277421104,
+      "learning_rate": 2.8385098658296637e-05,
+      "loss": 2.355,
+      "step": 53
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0703607034709259,
+      "learning_rate": 2.8371996886633843e-05,
+      "loss": 2.3793,
+      "step": 54
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.07124199690967324,
+      "learning_rate": 2.8358191274830974e-05,
+      "loss": 2.4275,
+      "step": 55
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.07099804346309355,
+      "learning_rate": 2.8343682510959552e-05,
+      "loss": 2.3323,
+      "step": 56
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.06967632308939245,
+      "learning_rate": 2.8328471318136165e-05,
+      "loss": 2.3883,
+      "step": 57
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.07156300179553134,
+      "learning_rate": 2.831255845448647e-05,
+      "loss": 2.3298,
+      "step": 58
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 0.0704201532980033,
+      "learning_rate": 2.8295944713107387e-05,
+      "loss": 2.331,
+      "step": 59
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.06794782460291071,
+      "learning_rate": 2.8278630922027563e-05,
+      "loss": 2.3776,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.4216628074645996,
+      "eval_runtime": 82.3879,
+      "eval_samples_per_second": 4.976,
+      "eval_steps_per_second": 0.316,
+      "step": 60
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 0.07045949082426937,
+      "learning_rate": 2.8260617944166123e-05,
+      "loss": 2.3319,
+      "step": 61
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 0.0702234192794877,
+      "learning_rate": 2.824190667728965e-05,
+      "loss": 2.3647,
+      "step": 62
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.06946814214632402,
+      "learning_rate": 2.8222498053967434e-05,
+      "loss": 2.3967,
+      "step": 63
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.06563265580127577,
+      "learning_rate": 2.8202393041525005e-05,
+      "loss": 2.3863,
+      "step": 64
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0723770670150652,
+      "learning_rate": 2.8181592641995933e-05,
+      "loss": 2.3823,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06870429029917037,
+      "learning_rate": 2.8160097892071847e-05,
+      "loss": 2.3241,
+      "step": 66
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 0.08615444480664787,
+      "learning_rate": 2.8137909863050806e-05,
+      "loss": 2.3504,
+      "step": 67
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.06980417460436542,
+      "learning_rate": 2.8115029660783887e-05,
+      "loss": 2.3762,
+      "step": 68
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.0691283200064781,
+      "learning_rate": 2.809145842562007e-05,
+      "loss": 2.3202,
+      "step": 69
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.06434433998677834,
+      "learning_rate": 2.8067197332349406e-05,
+      "loss": 2.4117,
+      "step": 70
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 0.06712521054811822,
+      "learning_rate": 2.8042247590144472e-05,
+      "loss": 2.4234,
+      "step": 71
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.07781170630767965,
+      "learning_rate": 2.8016610442500087e-05,
+      "loss": 2.3614,
+      "step": 72
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 0.07179449259884696,
+      "learning_rate": 2.7990287167171357e-05,
+      "loss": 2.327,
+      "step": 73
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.0666012429917219,
+      "learning_rate": 2.7963279076109976e-05,
+      "loss": 2.3606,
+      "step": 74
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07042352420672252,
+      "learning_rate": 2.7935587515398855e-05,
+      "loss": 2.387,
+      "step": 75
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.07141219809062525,
+      "learning_rate": 2.7907213865185014e-05,
+      "loss": 2.3975,
+      "step": 76
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 0.07530038535140655,
+      "learning_rate": 2.787815953961081e-05,
+      "loss": 2.3975,
+      "step": 77
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.06873021297298251,
+      "learning_rate": 2.784842598674345e-05,
+      "loss": 2.3724,
+      "step": 78
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 0.06853494667979494,
+      "learning_rate": 2.781801468850282e-05,
+      "loss": 2.3994,
+      "step": 79
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.07164446612343163,
+      "learning_rate": 2.778692716058762e-05,
+      "loss": 2.3448,
+      "step": 80
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.07112624750325054,
+      "learning_rate": 2.7755164952399844e-05,
+      "loss": 2.2984,
+      "step": 81
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.07679055297227524,
+      "learning_rate": 2.7722729646967527e-05,
+      "loss": 2.3699,
+      "step": 82
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 0.07270378630883641,
+      "learning_rate": 2.768962286086587e-05,
+      "loss": 2.3436,
+      "step": 83
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06869524209312625,
+      "learning_rate": 2.7655846244136654e-05,
+      "loss": 2.3856,
+      "step": 84
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.07006104211903366,
+      "learning_rate": 2.762140148020602e-05,
+      "loss": 2.3852,
+      "step": 85
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.07264285304887648,
+      "learning_rate": 2.758629028580055e-05,
+      "loss": 2.3834,
+      "step": 86
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.07253530482477301,
+      "learning_rate": 2.7550514410861718e-05,
+      "loss": 2.3573,
+      "step": 87
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.07265955522289944,
+      "learning_rate": 2.751407563845866e-05,
+      "loss": 2.3163,
+      "step": 88
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 0.07374626234739601,
+      "learning_rate": 2.747697578469931e-05,
+      "loss": 2.3851,
+      "step": 89
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07255481420091238,
+      "learning_rate": 2.7439216698639904e-05,
+      "loss": 2.3345,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 2.4115521907806396,
+      "eval_runtime": 82.0248,
+      "eval_samples_per_second": 4.998,
+      "eval_steps_per_second": 0.317,
+      "step": 90
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 0.06817548300510701,
+      "learning_rate": 2.7400800262192788e-05,
+      "loss": 2.3449,
+      "step": 91
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.07336990573663302,
+      "learning_rate": 2.7361728390032657e-05,
+      "loss": 2.3448,
+      "step": 92
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.07822885886131264,
+      "learning_rate": 2.732200302950111e-05,
+      "loss": 2.3217,
+      "step": 93
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.07296512071361201,
+      "learning_rate": 2.728162616050959e-05,
+      "loss": 2.3329,
+      "step": 94
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.07367928865175823,
+      "learning_rate": 2.724059979544072e-05,
+      "loss": 2.3208,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.07504139519989858,
+      "learning_rate": 2.719892597904801e-05,
+      "loss": 2.3483,
+      "step": 96
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 0.06790757702451031,
+      "learning_rate": 2.7156606788353906e-05,
+      "loss": 2.4128,
+      "step": 97
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.07011160737870108,
+      "learning_rate": 2.7113644332546336e-05,
+      "loss": 2.3832,
+      "step": 98
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.08077329808935288,
+      "learning_rate": 2.707004075287352e-05,
+      "loss": 2.3308,
+      "step": 99
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.0719496280235162,
+      "learning_rate": 2.7025798222537306e-05,
+      "loss": 2.3254,
+      "step": 100
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 0.07275409855582728,
+      "learning_rate": 2.698091894658483e-05,
+      "loss": 2.3967,
+      "step": 101
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.07201531734077336,
+      "learning_rate": 2.693540516179861e-05,
+      "loss": 2.3346,
+      "step": 102
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 0.0765467775604243,
+      "learning_rate": 2.6889259136585094e-05,
+      "loss": 2.3336,
+      "step": 103
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.077223728318478,
+      "learning_rate": 2.6842483170861568e-05,
+      "loss": 2.3313,
+      "step": 104
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.07639332869289207,
+      "learning_rate": 2.6795079595941553e-05,
+      "loss": 2.4008,
+      "step": 105
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 0.07440505813328589,
+      "learning_rate": 2.6747050774418605e-05,
+      "loss": 2.3425,
+      "step": 106
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 0.06937810484842656,
+      "learning_rate": 2.6698399100048556e-05,
+      "loss": 2.3349,
+      "step": 107
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07336400555418392,
+      "learning_rate": 2.6649126997630225e-05,
+      "loss": 2.3792,
+      "step": 108
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 0.07442564570941794,
+      "learning_rate": 2.6599236922884547e-05,
+      "loss": 2.3683,
+      "step": 109
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.07470689463768693,
+      "learning_rate": 2.65487313623322e-05,
+      "loss": 2.3036,
+      "step": 110
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.07096997017300663,
+      "learning_rate": 2.649761283316966e-05,
+      "loss": 2.3682,
+      "step": 111
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07511821034386772,
+      "learning_rate": 2.6445883883143744e-05,
+      "loss": 2.3346,
+      "step": 112
+    },
+    {
+      "epoch": 0.9416666666666667,
+      "grad_norm": 0.07057540374817312,
+      "learning_rate": 2.639354709042466e-05,
+      "loss": 2.3502,
+      "step": 113
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07300364605060353,
+      "learning_rate": 2.6340605063477456e-05,
+      "loss": 2.3711,
+      "step": 114
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.06925480258849577,
+      "learning_rate": 2.628706044093207e-05,
+      "loss": 2.3816,
+      "step": 115
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.0705107307569524,
+      "learning_rate": 2.623291589145179e-05,
+      "loss": 2.2958,
+      "step": 116
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.07331112076487026,
+      "learning_rate": 2.6178174113600252e-05,
+      "loss": 2.3279,
+      "step": 117
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.06780655482074792,
+      "learning_rate": 2.612283783570695e-05,
+      "loss": 2.4117,
+      "step": 118
+    },
+    {
+      "epoch": 0.9916666666666667,
+      "grad_norm": 0.07485055181125701,
+      "learning_rate": 2.606690981573125e-05,
+      "loss": 2.303,
+      "step": 119
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07276467760742707,
+      "learning_rate": 2.6010392841124932e-05,
+      "loss": 2.3608,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4049572944641113,
+      "eval_runtime": 82.3343,
+      "eval_samples_per_second": 4.98,
+      "eval_steps_per_second": 0.316,
+      "step": 120
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 0.07548790321925977,
+      "learning_rate": 2.5953289728693274e-05,
+      "loss": 2.3185,
+      "step": 121
+    },
+    {
+      "epoch": 1.0166666666666666,
+      "grad_norm": 0.0730570698984131,
+      "learning_rate": 2.5895603324454647e-05,
+      "loss": 2.2877,
+      "step": 122
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.07345139782586493,
+      "learning_rate": 2.5837336503498694e-05,
+      "loss": 2.2836,
+      "step": 123
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.07299378924326991,
+      "learning_rate": 2.5778492169843003e-05,
+      "loss": 2.3436,
+      "step": 124
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.07154250149880004,
+      "learning_rate": 2.5719073256288394e-05,
+      "loss": 2.3822,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0720748804004234,
+      "learning_rate": 2.565908272427274e-05,
+      "loss": 2.2708,
+      "step": 126
+    },
+    {
+      "epoch": 1.0583333333333333,
+      "grad_norm": 0.07269892036621302,
+      "learning_rate": 2.5598523563723373e-05,
+      "loss": 2.3377,
+      "step": 127
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0756770863265576,
+      "learning_rate": 2.5537398792908062e-05,
+      "loss": 2.352,
+      "step": 128
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.07397323539112335,
+      "learning_rate": 2.547571145828459e-05,
+      "loss": 2.3643,
+      "step": 129
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.07438211371538549,
+      "learning_rate": 2.54134646343489e-05,
+      "loss": 2.3387,
+      "step": 130
+    },
+    {
+      "epoch": 1.0916666666666666,
+      "grad_norm": 0.07094248712059498,
+      "learning_rate": 2.5350661423481885e-05,
+      "loss": 2.3221,
+      "step": 131
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.0771622686218861,
+      "learning_rate": 2.5287304955794754e-05,
+      "loss": 2.3183,
+      "step": 132
+    },
+    {
+      "epoch": 1.1083333333333334,
+      "grad_norm": 0.07495056480159959,
+      "learning_rate": 2.5223398388973028e-05,
+      "loss": 2.3697,
+      "step": 133
+    },
+    {
+      "epoch": 1.1166666666666667,
+      "grad_norm": 0.07629199954207538,
+      "learning_rate": 2.515894490811916e-05,
+      "loss": 2.3529,
+      "step": 134
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.0762534542729489,
+      "learning_rate": 2.5093947725593792e-05,
+      "loss": 2.3208,
+      "step": 135
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.07587427933984144,
+      "learning_rate": 2.502841008085565e-05,
+      "loss": 2.3448,
+      "step": 136
+    },
+    {
+      "epoch": 1.1416666666666666,
+      "grad_norm": 0.07490456619530689,
+      "learning_rate": 2.49623352403001e-05,
+      "loss": 2.3435,
+      "step": 137
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.0744781797534131,
+      "learning_rate": 2.4895726497096315e-05,
+      "loss": 2.4,
+      "step": 138
+    },
+    {
+      "epoch": 1.1583333333333332,
+      "grad_norm": 0.07464944817741491,
+      "learning_rate": 2.482858717102319e-05,
+      "loss": 2.318,
+      "step": 139
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.07309033869975678,
+      "learning_rate": 2.4760920608303867e-05,
+      "loss": 2.2891,
+      "step": 140
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.07284517336177344,
+      "learning_rate": 2.469273018143894e-05,
+      "loss": 2.3051,
+      "step": 141
+    },
+    {
+      "epoch": 1.1833333333333333,
+      "grad_norm": 0.07652064520411771,
+      "learning_rate": 2.462401928903839e-05,
+      "loss": 2.3555,
+      "step": 142
+    },
+    {
+      "epoch": 1.1916666666666667,
+      "grad_norm": 0.07701974074136966,
+      "learning_rate": 2.45547913556522e-05,
+      "loss": 2.3015,
+      "step": 143
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.08108352272511765,
+      "learning_rate": 2.448504983159966e-05,
+      "loss": 2.3221,
+      "step": 144
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.07752288456105606,
+      "learning_rate": 2.441479819279742e-05,
+      "loss": 2.3684,
+      "step": 145
+    },
+    {
+      "epoch": 1.2166666666666668,
+      "grad_norm": 0.07881711814524053,
+      "learning_rate": 2.4344039940586235e-05,
+      "loss": 2.3011,
+      "step": 146
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.07757542042787384,
+      "learning_rate": 2.4272778601556472e-05,
+      "loss": 2.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.07228965364348439,
+      "learning_rate": 2.4201017727372336e-05,
+      "loss": 2.3801,
+      "step": 148
+    },
+    {
+      "epoch": 1.2416666666666667,
+      "grad_norm": 0.07389812003829682,
+      "learning_rate": 2.4128760894594853e-05,
+      "loss": 2.3359,
+      "step": 149
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.08146218033856112,
+      "learning_rate": 2.4056011704503633e-05,
+      "loss": 2.3096,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 2.400259494781494,
+      "eval_runtime": 81.604,
+      "eval_samples_per_second": 5.024,
+      "eval_steps_per_second": 0.319,
+      "step": 150
+    },
+    {
+      "epoch": 1.2583333333333333,
+      "grad_norm": 0.07407260421175128,
+      "learning_rate": 2.3982773782917347e-05,
+      "loss": 2.3418,
+      "step": 151
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.07827237096687646,
+      "learning_rate": 2.390905078001306e-05,
+      "loss": 2.2778,
+      "step": 152
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.07699758244967876,
+      "learning_rate": 2.383484637014426e-05,
+      "loss": 2.3245,
+      "step": 153
+    },
+    {
+      "epoch": 1.2833333333333332,
+      "grad_norm": 0.07805943021524937,
+      "learning_rate": 2.3760164251657773e-05,
+      "loss": 2.3782,
+      "step": 154
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.0741687347632035,
+      "learning_rate": 2.368500814670941e-05,
+      "loss": 2.3765,
+      "step": 155
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.07696079818166807,
+      "learning_rate": 2.3609381801078448e-05,
+      "loss": 2.3958,
+      "step": 156
+    },
+    {
+      "epoch": 1.3083333333333333,
+      "grad_norm": 0.08864860865623735,
+      "learning_rate": 2.3533288983980964e-05,
+      "loss": 2.3482,
+      "step": 157
+    },
+    {
+      "epoch": 1.3166666666666667,
+      "grad_norm": 0.07676755572584443,
+      "learning_rate": 2.3456733487881978e-05,
+      "loss": 2.3511,
+      "step": 158
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.07754541163995884,
+      "learning_rate": 2.337971912830641e-05,
+      "loss": 2.3754,
+      "step": 159
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08430746433268149,
+      "learning_rate": 2.3302249743648926e-05,
+      "loss": 2.4063,
+      "step": 160
+    },
+    {
+      "epoch": 1.3416666666666668,
+      "grad_norm": 0.08113759941899056,
+      "learning_rate": 2.322432919498265e-05,
+      "loss": 2.3352,
+      "step": 161
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.08147516272984133,
+      "learning_rate": 2.3145961365866708e-05,
+      "loss": 2.3119,
+      "step": 162
+    },
+    {
+      "epoch": 1.3583333333333334,
+      "grad_norm": 0.07749688842544009,
+      "learning_rate": 2.3067150162152675e-05,
+      "loss": 2.3547,
+      "step": 163
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.08640326754187048,
+      "learning_rate": 2.298789951178992e-05,
+      "loss": 2.3389,
+      "step": 164
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.0795137333109577,
+      "learning_rate": 2.2908213364629812e-05,
+      "loss": 2.3778,
+      "step": 165
+    },
+    {
+      "epoch": 1.3833333333333333,
+      "grad_norm": 0.07739334763959965,
+      "learning_rate": 2.2828095692228886e-05,
+      "loss": 2.3658,
+      "step": 166
+    },
+    {
+      "epoch": 1.3916666666666666,
+      "grad_norm": 0.07783031237693959,
+      "learning_rate": 2.2747550487650887e-05,
+      "loss": 2.3575,
+      "step": 167
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.07682655233706284,
+      "learning_rate": 2.2666581765267758e-05,
+      "loss": 2.2825,
+      "step": 168
+    },
+    {
+      "epoch": 1.4083333333333332,
+      "grad_norm": 0.08359081032268273,
+      "learning_rate": 2.2585193560559563e-05,
+      "loss": 2.261,
+      "step": 169
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.0826940676306091,
+      "learning_rate": 2.250338992991335e-05,
+      "loss": 2.3069,
+      "step": 170
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.08462619097403327,
+      "learning_rate": 2.2421174950421017e-05,
+      "loss": 2.2864,
+      "step": 171
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.07990029642375193,
+      "learning_rate": 2.233855271967606e-05,
+      "loss": 2.3033,
+      "step": 172
+    },
+    {
+      "epoch": 1.4416666666666667,
+      "grad_norm": 0.08051779058857793,
+      "learning_rate": 2.2255527355569372e-05,
+      "loss": 2.3166,
+      "step": 173
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.08604667339713809,
+      "learning_rate": 2.217210299608402e-05,
+      "loss": 2.387,
+      "step": 174
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.07829742536277012,
+      "learning_rate": 2.208828379908899e-05,
+      "loss": 2.311,
+      "step": 175
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.07850219342360719,
+      "learning_rate": 2.200407394213196e-05,
+      "loss": 2.3384,
+      "step": 176
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.08531707041033702,
+      "learning_rate": 2.19194776222311e-05,
+      "loss": 2.3107,
+      "step": 177
+    },
+    {
+      "epoch": 1.4833333333333334,
+      "grad_norm": 0.07652853009760147,
+      "learning_rate": 2.183449905566589e-05,
+      "loss": 2.3494,
+      "step": 178
+    },
+    {
+      "epoch": 1.4916666666666667,
+      "grad_norm": 0.0797336095546633,
+      "learning_rate": 2.1749142477766972e-05,
+      "loss": 2.3291,
+      "step": 179
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.08700079540422817,
+      "learning_rate": 2.166341214270507e-05,
+      "loss": 2.3132,
+      "step": 180
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.3966128826141357,
+      "eval_runtime": 83.184,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 0.313,
+      "step": 180
+    },
+    {
+      "epoch": 1.5083333333333333,
+      "grad_norm": 0.07925581040107615,
+      "learning_rate": 2.157731232327897e-05,
+      "loss": 2.3578,
+      "step": 181
+    },
+    {
+      "epoch": 1.5166666666666666,
+      "grad_norm": 0.07873086864048841,
+      "learning_rate": 2.1490847310702544e-05,
+      "loss": 2.3229,
+      "step": 182
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.07775316849537767,
+      "learning_rate": 2.1404021414390874e-05,
+      "loss": 2.3756,
+      "step": 183
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.07949428482523528,
+      "learning_rate": 2.1316838961745518e-05,
+      "loss": 2.3535,
+      "step": 184
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.08423278187074197,
+      "learning_rate": 2.1229304297938755e-05,
+      "loss": 2.3517,
+      "step": 185
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.07930583119038707,
+      "learning_rate": 2.1141421785697097e-05,
+      "loss": 2.3929,
+      "step": 186
+    },
+    {
+      "epoch": 1.5583333333333333,
+      "grad_norm": 0.07736840323261199,
+      "learning_rate": 2.1053195805083803e-05,
+      "loss": 2.3194,
+      "step": 187
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.08306421066524537,
+      "learning_rate": 2.0964630753280584e-05,
+      "loss": 2.3131,
+      "step": 188
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.0805185815818936,
+      "learning_rate": 2.0875731044368472e-05,
+      "loss": 2.3238,
+      "step": 189
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.07729948838070921,
+      "learning_rate": 2.078650110910779e-05,
+      "loss": 2.3279,
+      "step": 190
+    },
+    {
+      "epoch": 1.5916666666666668,
+      "grad_norm": 0.08053951644296133,
+      "learning_rate": 2.0696945394717355e-05,
+      "loss": 2.3343,
+      "step": 191
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.08184664333069269,
+      "learning_rate": 2.0607068364652783e-05,
+      "loss": 2.3441,
+      "step": 192
+    },
+    {
+      "epoch": 1.6083333333333334,
+      "grad_norm": 0.07894699650259683,
+      "learning_rate": 2.051687449838409e-05,
+      "loss": 2.3384,
+      "step": 193
+    },
+    {
+      "epoch": 1.6166666666666667,
+      "grad_norm": 0.08288692832517489,
+      "learning_rate": 2.042636829117239e-05,
+      "loss": 2.3219,
+      "step": 194
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.09061769591669266,
+      "learning_rate": 2.033555425384586e-05,
+      "loss": 2.3168,
+      "step": 195
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.07607427061534017,
+      "learning_rate": 2.0244436912574938e-05,
+      "loss": 2.3592,
+      "step": 196
+    },
+    {
+      "epoch": 1.6416666666666666,
+      "grad_norm": 0.08827457673533141,
+      "learning_rate": 2.0153020808646715e-05,
+      "loss": 2.3177,
+      "step": 197
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.0757688204165182,
+      "learning_rate": 2.0061310498238618e-05,
+      "loss": 2.2366,
+      "step": 198
+    },
+    {
+      "epoch": 1.6583333333333332,
+      "grad_norm": 0.07815852114026649,
+      "learning_rate": 1.996931055219132e-05,
+      "loss": 2.3161,
+      "step": 199
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.08058901889279678,
+      "learning_rate": 1.9877025555780927e-05,
+      "loss": 2.3749,
+      "step": 200
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.07708027281441528,
+      "learning_rate": 1.978446010849045e-05,
+      "loss": 2.2854,
+      "step": 201
+    },
+    {
+      "epoch": 1.6833333333333333,
+      "grad_norm": 0.08312283019758401,
+      "learning_rate": 1.969161882378058e-05,
+      "loss": 2.3524,
+      "step": 202
+    },
+    {
+      "epoch": 1.6916666666666667,
+      "grad_norm": 0.07784046601849169,
+      "learning_rate": 1.9598506328859717e-05,
+      "loss": 2.3418,
+      "step": 203
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.07906237498578873,
+      "learning_rate": 1.95051272644534e-05,
+      "loss": 2.3514,
+      "step": 204
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.08323464269988524,
+      "learning_rate": 1.9411486284572977e-05,
+      "loss": 2.3133,
+      "step": 205
+    },
+    {
+      "epoch": 1.7166666666666668,
+      "grad_norm": 0.08153670371604982,
+      "learning_rate": 1.931758805628366e-05,
+      "loss": 2.3388,
+      "step": 206
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.08152589045596419,
+      "learning_rate": 1.9223437259471912e-05,
+      "loss": 2.3309,
+      "step": 207
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.08382345786042532,
+      "learning_rate": 1.9129038586612224e-05,
+      "loss": 2.3282,
+      "step": 208
+    },
+    {
+      "epoch": 1.7416666666666667,
+      "grad_norm": 0.0835609429134592,
+      "learning_rate": 1.903439674253321e-05,
+      "loss": 2.3567,
+      "step": 209
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.08252984125014622,
+      "learning_rate": 1.8939516444183143e-05,
+      "loss": 2.3352,
+      "step": 210
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.3933684825897217,
+      "eval_runtime": 83.3063,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 0.312,
+      "step": 210
+    },
+    {
+      "epoch": 1.7583333333333333,
+      "grad_norm": 0.0815481053340795,
+      "learning_rate": 1.884440242039485e-05,
+      "loss": 2.3262,
+      "step": 211
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.08258761118218041,
+      "learning_rate": 1.8749059411650034e-05,
+      "loss": 2.3396,
+      "step": 212
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.0884999967331726,
+      "learning_rate": 1.8653492169843003e-05,
+      "loss": 2.3176,
+      "step": 213
+    },
+    {
+      "epoch": 1.7833333333333332,
+      "grad_norm": 0.0824785010834098,
+      "learning_rate": 1.8557705458043838e-05,
+      "loss": 2.3272,
+      "step": 214
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.08727167025374602,
+      "learning_rate": 1.8461704050261e-05,
+      "loss": 2.2298,
+      "step": 215
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0768016904891171,
+      "learning_rate": 1.8365492731203398e-05,
+      "loss": 2.3554,
+      "step": 216
+    },
+    {
+      "epoch": 1.8083333333333333,
+      "grad_norm": 0.07709533586121158,
+      "learning_rate": 1.8269076296041917e-05,
+      "loss": 2.3702,
+      "step": 217
+    },
+    {
+      "epoch": 1.8166666666666667,
+      "grad_norm": 0.0806446736093232,
+      "learning_rate": 1.8172459550170424e-05,
+      "loss": 2.3585,
+      "step": 218
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.07523532523458193,
+      "learning_rate": 1.8075647308966268e-05,
+      "loss": 2.3609,
+      "step": 219
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.07497201271988578,
+      "learning_rate": 1.797864439755028e-05,
+      "loss": 2.3755,
+      "step": 220
+    },
+    {
+      "epoch": 1.8416666666666668,
+      "grad_norm": 0.08249074177996166,
+      "learning_rate": 1.7881455650546303e-05,
+      "loss": 2.372,
+      "step": 221
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0780160636961897,
+      "learning_rate": 1.7784085911840214e-05,
+      "loss": 2.3823,
+      "step": 222
+    },
+    {
+      "epoch": 1.8583333333333334,
+      "grad_norm": 0.08148680526536918,
+      "learning_rate": 1.7686540034338513e-05,
+      "loss": 2.3314,
+      "step": 223
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0795864595636552,
+      "learning_rate": 1.758882287972646e-05,
+      "loss": 2.2853,
+      "step": 224
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.08198344669246531,
+      "learning_rate": 1.749093931822577e-05,
+      "loss": 2.3605,
+      "step": 225
+    },
+    {
+      "epoch": 1.8833333333333333,
+      "grad_norm": 0.08138145213474299,
+      "learning_rate": 1.739289422835185e-05,
+      "loss": 2.2721,
+      "step": 226
+    },
+    {
+      "epoch": 1.8916666666666666,
+      "grad_norm": 0.08306015511124677,
+      "learning_rate": 1.7294692496670715e-05,
+      "loss": 2.2889,
+      "step": 227
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.07478727556401082,
+      "learning_rate": 1.7196339017555378e-05,
+      "loss": 2.3416,
+      "step": 228
+    },
+    {
+      "epoch": 1.9083333333333332,
+      "grad_norm": 0.08858459574829487,
+      "learning_rate": 1.709783869294196e-05,
+      "loss": 2.3081,
+      "step": 229
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.08175368181940743,
+      "learning_rate": 1.699919643208533e-05,
+      "loss": 2.3304,
+      "step": 230
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.07630479738636474,
+      "learning_rate": 1.6900417151314503e-05,
+      "loss": 2.3454,
+      "step": 231
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.07687273996639293,
+      "learning_rate": 1.6801505773787527e-05,
+      "loss": 2.3901,
+      "step": 232
+    },
+    {
+      "epoch": 1.9416666666666667,
+      "grad_norm": 0.08600269874202937,
+      "learning_rate": 1.670246722924616e-05,
+      "loss": 2.3081,
+      "step": 233
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.07737694968965858,
+      "learning_rate": 1.660330645377018e-05,
+      "loss": 2.3643,
+      "step": 234
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.08165758061569027,
+      "learning_rate": 1.6504028389531333e-05,
+      "loss": 2.355,
+      "step": 235
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.08264378429137093,
+      "learning_rate": 1.640463798454704e-05,
+      "loss": 2.3219,
+      "step": 236
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.0858368818345628,
+      "learning_rate": 1.6305140192433787e-05,
+      "loss": 2.3329,
+      "step": 237
+    },
+    {
+      "epoch": 1.9833333333333334,
+      "grad_norm": 0.07616999163161729,
+      "learning_rate": 1.620553997216023e-05,
+      "loss": 2.3523,
+      "step": 238
+    },
+    {
+      "epoch": 1.9916666666666667,
+      "grad_norm": 0.08241527325980988,
+      "learning_rate": 1.6105842287800046e-05,
+      "loss": 2.2982,
+      "step": 239
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08007891750583127,
+      "learning_rate": 1.600605210828451e-05,
+      "loss": 2.2785,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3910558223724365,
+      "eval_runtime": 83.4904,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 0.311,
+      "step": 240
+    },
+    {
+      "epoch": 2.0083333333333333,
+      "grad_norm": 0.08108687194604622,
+      "learning_rate": 1.5906174407154883e-05,
+      "loss": 2.3367,
+      "step": 241
+    },
+    {
+      "epoch": 2.0166666666666666,
+      "grad_norm": 0.0806511417182259,
+      "learning_rate": 1.5806214162314463e-05,
+      "loss": 2.3011,
+      "step": 242
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.08264392219751603,
+      "learning_rate": 1.5706176355780556e-05,
+      "loss": 2.3036,
+      "step": 243
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.07958409681135217,
+      "learning_rate": 1.5606065973436132e-05,
+      "loss": 2.3056,
+      "step": 244
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.07856642651007223,
+      "learning_rate": 1.550588800478133e-05,
+      "loss": 2.3692,
+      "step": 245
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.08350216798892127,
+      "learning_rate": 1.5405647442684794e-05,
+      "loss": 2.2697,
+      "step": 246
+    },
+    {
+      "epoch": 2.058333333333333,
+      "grad_norm": 0.08390645284684875,
+      "learning_rate": 1.530534928313484e-05,
+      "loss": 2.2425,
+      "step": 247
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.07883358190907572,
+      "learning_rate": 1.5204998524990423e-05,
+      "loss": 2.3281,
+      "step": 248
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.07994560560782488,
+      "learning_rate": 1.5104600169732015e-05,
+      "loss": 2.3285,
+      "step": 249
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.08345016891314849,
+      "learning_rate": 1.5004159221212325e-05,
+      "loss": 2.3252,
+      "step": 250
+    },
+    {
+      "epoch": 2.091666666666667,
+      "grad_norm": 0.0767244585605165,
+      "learning_rate": 1.490368068540692e-05,
+      "loss": 2.3176,
+      "step": 251
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.07853322933102938,
+      "learning_rate": 1.4803169570164703e-05,
+      "loss": 2.286,
+      "step": 252
+    },
+    {
+      "epoch": 2.1083333333333334,
+      "grad_norm": 0.07885223855237164,
+      "learning_rate": 1.4702630884958345e-05,
+      "loss": 2.3293,
+      "step": 253
+    },
+    {
+      "epoch": 2.1166666666666667,
+      "grad_norm": 0.07786083611140765,
+      "learning_rate": 1.4602069640634605e-05,
+      "loss": 2.3241,
+      "step": 254
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.07961379829842732,
+      "learning_rate": 1.4501490849164585e-05,
+      "loss": 2.3218,
+      "step": 255
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.0812119479291348,
+      "learning_rate": 1.4400899523393928e-05,
+      "loss": 2.3101,
+      "step": 256
+    },
+    {
+      "epoch": 2.1416666666666666,
+      "grad_norm": 0.07820228956836967,
+      "learning_rate": 1.4300300676793e-05,
+      "loss": 2.3105,
+      "step": 257
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.0787354321940814,
+      "learning_rate": 1.4199699323207e-05,
+      "loss": 2.2921,
+      "step": 258
+    },
+    {
+      "epoch": 2.158333333333333,
+      "grad_norm": 0.0821168083039209,
+      "learning_rate": 1.4099100476606071e-05,
+      "loss": 2.3449,
+      "step": 259
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.08227570212622978,
+      "learning_rate": 1.3998509150835417e-05,
+      "loss": 2.2804,
+      "step": 260
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.07956552166316343,
+      "learning_rate": 1.3897930359365397e-05,
+      "loss": 2.2798,
+      "step": 261
+    },
+    {
+      "epoch": 2.183333333333333,
+      "grad_norm": 0.08355971196343313,
+      "learning_rate": 1.3797369115041656e-05,
+      "loss": 2.3121,
+      "step": 262
+    },
+    {
+      "epoch": 2.191666666666667,
+      "grad_norm": 0.07664615523847712,
+      "learning_rate": 1.3696830429835303e-05,
+      "loss": 2.3511,
+      "step": 263
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.07875754809310784,
+      "learning_rate": 1.3596319314593088e-05,
+      "loss": 2.276,
+      "step": 264
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.07805417721469433,
+      "learning_rate": 1.3495840778787675e-05,
+      "loss": 2.3156,
+      "step": 265
+    },
+    {
+      "epoch": 2.216666666666667,
+      "grad_norm": 0.08500867883177173,
+      "learning_rate": 1.339539983026799e-05,
+      "loss": 2.3304,
+      "step": 266
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.08575986404103182,
+      "learning_rate": 1.3295001475009578e-05,
+      "loss": 2.3171,
+      "step": 267
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.0796424885760881,
+      "learning_rate": 1.3194650716865163e-05,
+      "loss": 2.3488,
+      "step": 268
+    },
+    {
+      "epoch": 2.2416666666666667,
+      "grad_norm": 0.07791982790558008,
+      "learning_rate": 1.3094352557315207e-05,
+      "loss": 2.3806,
+      "step": 269
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0840055290628465,
+      "learning_rate": 1.299411199521868e-05,
+      "loss": 2.3277,
+      "step": 270
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 2.3895957469940186,
+      "eval_runtime": 83.1157,
+      "eval_samples_per_second": 4.933,
+      "eval_steps_per_second": 0.313,
+      "step": 270
+    },
+    {
+      "epoch": 2.2583333333333333,
+      "grad_norm": 0.07770712903979533,
+      "learning_rate": 1.2893934026563873e-05,
+      "loss": 2.2666,
+      "step": 271
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07846164594226922,
+      "learning_rate": 1.2793823644219445e-05,
+      "loss": 2.2855,
+      "step": 272
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.08498339693180243,
+      "learning_rate": 1.269378583768554e-05,
+      "loss": 2.2733,
+      "step": 273
+    },
+    {
+      "epoch": 2.283333333333333,
+      "grad_norm": 0.07834222258922019,
+      "learning_rate": 1.2593825592845122e-05,
+      "loss": 2.3193,
+      "step": 274
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.08132580954052983,
+      "learning_rate": 1.2493947891715491e-05,
+      "loss": 2.3085,
+      "step": 275
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.07883697009265064,
+      "learning_rate": 1.239415771219996e-05,
+      "loss": 2.3545,
+      "step": 276
+    },
+    {
+      "epoch": 2.3083333333333336,
+      "grad_norm": 0.08023901828387182,
+      "learning_rate": 1.2294460027839779e-05,
+      "loss": 2.3489,
+      "step": 277
+    },
+    {
+      "epoch": 2.3166666666666664,
+      "grad_norm": 0.08930364086676225,
+      "learning_rate": 1.2194859807566216e-05,
+      "loss": 2.2591,
+      "step": 278
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.08343332964333285,
+      "learning_rate": 1.2095362015452961e-05,
+      "loss": 2.3404,
+      "step": 279
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.08292455976075656,
+      "learning_rate": 1.199597161046867e-05,
+      "loss": 2.3028,
+      "step": 280
+    },
+    {
+      "epoch": 2.341666666666667,
+      "grad_norm": 0.08627078651851632,
+      "learning_rate": 1.189669354622982e-05,
+      "loss": 2.343,
+      "step": 281
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.08202097516344958,
+      "learning_rate": 1.1797532770753842e-05,
+      "loss": 2.326,
+      "step": 282
+    },
+    {
+      "epoch": 2.3583333333333334,
+      "grad_norm": 0.08362611496815728,
+      "learning_rate": 1.169849422621248e-05,
+      "loss": 2.3035,
+      "step": 283
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.08888611458113292,
+      "learning_rate": 1.1599582848685506e-05,
+      "loss": 2.2812,
+      "step": 284
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.08217261091117088,
+      "learning_rate": 1.1500803567914671e-05,
+      "loss": 2.3378,
+      "step": 285
+    },
+    {
+      "epoch": 2.3833333333333333,
+      "grad_norm": 0.07985728135451624,
+      "learning_rate": 1.1402161307058047e-05,
+      "loss": 2.3522,
+      "step": 286
+    },
+    {
+      "epoch": 2.3916666666666666,
+      "grad_norm": 0.08014525439116486,
+      "learning_rate": 1.1303660982444624e-05,
+      "loss": 2.2256,
+      "step": 287
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08787593050595495,
+      "learning_rate": 1.1205307503329286e-05,
+      "loss": 2.2974,
+      "step": 288
+    },
+    {
+      "epoch": 2.408333333333333,
+      "grad_norm": 0.08195162040998395,
+      "learning_rate": 1.1107105771648151e-05,
+      "loss": 2.353,
+      "step": 289
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.08267743479386988,
+      "learning_rate": 1.1009060681774236e-05,
+      "loss": 2.3274,
+      "step": 290
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.08798947281948663,
+      "learning_rate": 1.0911177120273537e-05,
+      "loss": 2.3404,
+      "step": 291
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.08828111892887862,
+      "learning_rate": 1.0813459965661489e-05,
+      "loss": 2.3348,
+      "step": 292
+    },
+    {
+      "epoch": 2.4416666666666664,
+      "grad_norm": 0.08102528742267785,
+      "learning_rate": 1.0715914088159789e-05,
+      "loss": 2.2863,
+      "step": 293
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0866645702075036,
+      "learning_rate": 1.06185443494537e-05,
+      "loss": 2.3357,
+      "step": 294
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.08290121294865929,
+      "learning_rate": 1.0521355602449723e-05,
+      "loss": 2.3537,
+      "step": 295
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.08332374744178081,
+      "learning_rate": 1.042435269103374e-05,
+      "loss": 2.3554,
+      "step": 296
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.08367195510948358,
+      "learning_rate": 1.0327540449829583e-05,
+      "loss": 2.3384,
+      "step": 297
+    },
+    {
+      "epoch": 2.4833333333333334,
+      "grad_norm": 0.08673119537467149,
+      "learning_rate": 1.0230923703958083e-05,
+      "loss": 2.2725,
+      "step": 298
+    },
+    {
+      "epoch": 2.4916666666666667,
+      "grad_norm": 0.08235186060858125,
+      "learning_rate": 1.0134507268796605e-05,
+      "loss": 2.328,
+      "step": 299
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08408079009588813,
+      "learning_rate": 1.0038295949739004e-05,
+      "loss": 2.3403,
+      "step": 300
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.3881967067718506,
+      "eval_runtime": 82.1489,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.316,
+      "step": 300
+    },
+    {
+      "epoch": 2.5083333333333333,
+      "grad_norm": 0.07909547450093556,
+      "learning_rate": 9.942294541956169e-06,
+      "loss": 2.3357,
+      "step": 301
+    },
+    {
+      "epoch": 2.5166666666666666,
+      "grad_norm": 0.08766753125589274,
+      "learning_rate": 9.846507830157e-06,
+      "loss": 2.2503,
+      "step": 302
+    },
+    {
+      "epoch": 2.525,
+      "grad_norm": 0.07987208695801865,
+      "learning_rate": 9.75094058834997e-06,
+      "loss": 2.3168,
+      "step": 303
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.08537107163629042,
+      "learning_rate": 9.655597579605152e-06,
+      "loss": 2.3036,
+      "step": 304
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.08251527677113132,
+      "learning_rate": 9.560483555816858e-06,
+      "loss": 2.3419,
+      "step": 305
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.08523777732696665,
+      "learning_rate": 9.465603257466792e-06,
+      "loss": 2.3449,
+      "step": 306
+    },
+    {
+      "epoch": 2.5583333333333336,
+      "grad_norm": 0.0848931418707024,
+      "learning_rate": 9.370961413387778e-06,
+      "loss": 2.2844,
+      "step": 307
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.08156484852737556,
+      "learning_rate": 9.27656274052809e-06,
+      "loss": 2.3485,
+      "step": 308
+    },
+    {
+      "epoch": 2.575,
+      "grad_norm": 0.08185057405642468,
+      "learning_rate": 9.182411943716344e-06,
+      "loss": 2.3748,
+      "step": 309
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.08210521440208327,
+      "learning_rate": 9.088513715427028e-06,
+      "loss": 2.376,
+      "step": 310
+    },
+    {
+      "epoch": 2.591666666666667,
+      "grad_norm": 0.08030540134328207,
+      "learning_rate": 8.9948727355466e-06,
+      "loss": 2.3196,
+      "step": 311
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.08216024303479584,
+      "learning_rate": 8.901493671140283e-06,
+      "loss": 2.3534,
+      "step": 312
+    },
+    {
+      "epoch": 2.6083333333333334,
+      "grad_norm": 0.08105902557687622,
+      "learning_rate": 8.808381176219426e-06,
+      "loss": 2.2729,
+      "step": 313
+    },
+    {
+      "epoch": 2.6166666666666667,
+      "grad_norm": 0.08410998796525411,
+      "learning_rate": 8.71553989150955e-06,
+      "loss": 2.3596,
+      "step": 314
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.08582437979635364,
+      "learning_rate": 8.622974444219076e-06,
+      "loss": 2.3063,
+      "step": 315
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.08419960708603666,
+      "learning_rate": 8.530689447808683e-06,
+      "loss": 2.3468,
+      "step": 316
+    },
+    {
+      "epoch": 2.6416666666666666,
+      "grad_norm": 0.08532017727647645,
+      "learning_rate": 8.438689501761387e-06,
+      "loss": 2.3378,
+      "step": 317
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.08544492639100988,
+      "learning_rate": 8.346979191353288e-06,
+      "loss": 2.2872,
+      "step": 318
+    },
+    {
+      "epoch": 2.658333333333333,
+      "grad_norm": 0.0825611786693761,
+      "learning_rate": 8.255563087425069e-06,
+      "loss": 2.3037,
+      "step": 319
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.07923900030264817,
+      "learning_rate": 8.164445746154141e-06,
+      "loss": 2.2746,
+      "step": 320
+    },
+    {
+      "epoch": 2.675,
+      "grad_norm": 0.0805988851220756,
+      "learning_rate": 8.073631708827614e-06,
+      "loss": 2.3116,
+      "step": 321
+    },
+    {
+      "epoch": 2.6833333333333336,
+      "grad_norm": 0.07902450485255898,
+      "learning_rate": 7.983125501615913e-06,
+      "loss": 2.3253,
+      "step": 322
+    },
+    {
+      "epoch": 2.6916666666666664,
+      "grad_norm": 0.08586994856844313,
+      "learning_rate": 7.892931635347223e-06,
+      "loss": 2.3636,
+      "step": 323
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.08029033935205021,
+      "learning_rate": 7.803054605282652e-06,
+      "loss": 2.3023,
+      "step": 324
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.08041087816983067,
+      "learning_rate": 7.713498890892208e-06,
+      "loss": 2.3629,
+      "step": 325
+    },
+    {
+      "epoch": 2.716666666666667,
+      "grad_norm": 0.08451031313730265,
+      "learning_rate": 7.624268955631531e-06,
+      "loss": 2.2625,
+      "step": 326
+    },
+    {
+      "epoch": 2.725,
+      "grad_norm": 0.07898217475608488,
+      "learning_rate": 7.53536924671942e-06,
+      "loss": 2.3106,
+      "step": 327
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.08283676255780481,
+      "learning_rate": 7.446804194916206e-06,
+      "loss": 2.3576,
+      "step": 328
+    },
+    {
+      "epoch": 2.7416666666666667,
+      "grad_norm": 0.08212231805524588,
+      "learning_rate": 7.358578214302908e-06,
+      "loss": 2.2791,
+      "step": 329
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.08251122557980495,
+      "learning_rate": 7.270695702061248e-06,
+      "loss": 2.3553,
+      "step": 330
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 2.387129783630371,
+      "eval_runtime": 81.7826,
+      "eval_samples_per_second": 5.013,
+      "eval_steps_per_second": 0.318,
+      "step": 330
+    },
+    {
+      "epoch": 2.7583333333333333,
+      "grad_norm": 0.08008513950564178,
+      "learning_rate": 7.1831610382544856e-06,
+      "loss": 2.2737,
+      "step": 331
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.08378397772580942,
+      "learning_rate": 7.095978585609125e-06,
+      "loss": 2.362,
+      "step": 332
+    },
+    {
+      "epoch": 2.775,
+      "grad_norm": 0.08519607549475229,
+      "learning_rate": 7.009152689297463e-06,
+      "loss": 2.2601,
+      "step": 333
+    },
+    {
+      "epoch": 2.783333333333333,
+      "grad_norm": 0.08038464346170233,
+      "learning_rate": 6.9226876767210355e-06,
+      "loss": 2.3434,
+      "step": 334
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.08107258257971683,
+      "learning_rate": 6.83658785729493e-06,
+      "loss": 2.2608,
+      "step": 335
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0801095446046233,
+      "learning_rate": 6.750857522233032e-06,
+      "loss": 2.3562,
+      "step": 336
+    },
+    {
+      "epoch": 2.8083333333333336,
+      "grad_norm": 0.08032953635285699,
+      "learning_rate": 6.665500944334116e-06,
+      "loss": 2.3473,
+      "step": 337
+    },
+    {
+      "epoch": 2.8166666666666664,
+      "grad_norm": 0.08165787890975398,
+      "learning_rate": 6.580522377768902e-06,
+      "loss": 2.3662,
+      "step": 338
+    },
+    {
+      "epoch": 2.825,
+      "grad_norm": 0.08186138228862638,
+      "learning_rate": 6.495926057868045e-06,
+      "loss": 2.3611,
+      "step": 339
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.08409693406516083,
+      "learning_rate": 6.4117162009110105e-06,
+      "loss": 2.3014,
+      "step": 340
+    },
+    {
+      "epoch": 2.841666666666667,
+      "grad_norm": 0.08426043237254878,
+      "learning_rate": 6.327897003915982e-06,
+      "loss": 2.3556,
+      "step": 341
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.07860767709618154,
+      "learning_rate": 6.244472644430632e-06,
+      "loss": 2.3986,
+      "step": 342
+    },
+    {
+      "epoch": 2.8583333333333334,
+      "grad_norm": 0.07913910815896576,
+      "learning_rate": 6.161447280323948e-06,
+      "loss": 2.3041,
+      "step": 343
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.0834686817566552,
+      "learning_rate": 6.078825049578985e-06,
+      "loss": 2.2694,
+      "step": 344
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.09464173421182612,
+      "learning_rate": 5.996610070086646e-06,
+      "loss": 2.3291,
+      "step": 345
+    },
+    {
+      "epoch": 2.8833333333333333,
+      "grad_norm": 0.08924525286993587,
+      "learning_rate": 5.914806439440443e-06,
+      "loss": 2.2425,
+      "step": 346
+    },
+    {
+      "epoch": 2.8916666666666666,
+      "grad_norm": 0.07984144031222275,
+      "learning_rate": 5.833418234732248e-06,
+      "loss": 2.3212,
+      "step": 347
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.08119999485058818,
+      "learning_rate": 5.752449512349119e-06,
+      "loss": 2.3043,
+      "step": 348
+    },
+    {
+      "epoch": 2.908333333333333,
+      "grad_norm": 0.08130268904604636,
+      "learning_rate": 5.671904307771115e-06,
+      "loss": 2.3431,
+      "step": 349
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.0886368269447557,
+      "learning_rate": 5.591786635370193e-06,
+      "loss": 2.2584,
+      "step": 350
+    },
+    {
+      "epoch": 2.925,
+      "grad_norm": 0.08449560278602129,
+      "learning_rate": 5.5121004882100805e-06,
+      "loss": 2.2614,
+      "step": 351
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.0877133422168611,
+      "learning_rate": 5.4328498378473245e-06,
+      "loss": 2.3467,
+      "step": 352
+    },
+    {
+      "epoch": 2.9416666666666664,
+      "grad_norm": 0.0829503072213313,
+      "learning_rate": 5.354038634133295e-06,
+      "loss": 2.2975,
+      "step": 353
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.08436627929472401,
+      "learning_rate": 5.27567080501735e-06,
+      "loss": 2.3115,
+      "step": 354
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.08048623155801396,
+      "learning_rate": 5.197750256351076e-06,
+      "loss": 2.2584,
+      "step": 355
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.08109596859654204,
+      "learning_rate": 5.120280871693596e-06,
+      "loss": 2.3677,
+      "step": 356
+    },
+    {
+      "epoch": 2.975,
+      "grad_norm": 0.081013576151029,
+      "learning_rate": 5.0432665121180266e-06,
+      "loss": 2.3585,
+      "step": 357
+    },
+    {
+      "epoch": 2.9833333333333334,
+      "grad_norm": 0.08546479543984016,
+      "learning_rate": 4.966711016019037e-06,
+      "loss": 2.303,
+      "step": 358
+    },
+    {
+      "epoch": 2.9916666666666667,
+      "grad_norm": 0.08245660024002954,
+      "learning_rate": 4.890618198921555e-06,
+      "loss": 2.3149,
+      "step": 359
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08512068224524219,
+      "learning_rate": 4.814991853290595e-06,
+      "loss": 2.2894,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.386331081390381,
+      "eval_runtime": 82.119,
+      "eval_samples_per_second": 4.993,
+      "eval_steps_per_second": 0.317,
+      "step": 360
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.466444455850803e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-360/training_args.bin b/checkpoint-360/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e71e9ef0b364c8b803828c31c7b34cd4f7001af
--- /dev/null
+++ b/checkpoint-360/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
+size 8504
diff --git a/checkpoint-360/zero_to_fp32.py b/checkpoint-360/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..0e759146cadd92ddfefab3680146c2bd6a2b5c04
--- /dev/null
+++ b/checkpoint-360/zero_to_fp32.py
@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-420/README.md b/checkpoint-420/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1ccd9107504d26ae2d65987b64fc7c79aed7c163
--- /dev/null
+++ b/checkpoint-420/README.md
@@ -0,0 +1,202 @@
+---
+base_model: NewEden/Hamanasu-KTO-V2
+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-420/adapter_config.json b/checkpoint-420/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3d1dc2dbb47a92750a96471a799fbaf0e686ba9d
--- /dev/null
+++ b/checkpoint-420/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-420/adapter_model.safetensors b/checkpoint-420/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3b6876d6d19c9df6c72717339069c7c1e08a036f
--- /dev/null
+++ b/checkpoint-420/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fa37d9c7ab3421ae2b662d0f902689ce2e64e92c4348d941a055be12681c8a
+size 486600536
diff --git a/checkpoint-420/latest b/checkpoint-420/latest
new file mode 100644
index 0000000000000000000000000000000000000000..787484a690ba2c10690302a95f5c7f2ac9458c76
--- /dev/null
+++ b/checkpoint-420/latest
@@ -0,0 +1 @@
+global_step420
\ No newline at end of file
diff --git a/checkpoint-420/rng_state_0.pth b/checkpoint-420/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4896ef8bf6649706d019b05227dc11070a20fbd3
--- /dev/null
+++ b/checkpoint-420/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265918a61a0314e0f11594fea15cc94488f89132a5b6d694ae26646aa63079ad
+size 15024
diff --git a/checkpoint-420/rng_state_1.pth b/checkpoint-420/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6bcc782e17604ad9c339d703698a2a0bfe982f9d
--- /dev/null
+++ b/checkpoint-420/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93e2c7fb83e3faca8947c112fc00f12cfb3e73be0f55d679b281e23123db3ae
+size 15024
diff --git a/checkpoint-420/rng_state_2.pth b/checkpoint-420/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e24299f21a80bed9b4952ec21b99d6a5fd87c089
--- /dev/null
+++ b/checkpoint-420/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df3dbab1a7618f30312de2972ec44d4066f88f75cf720b898007432e17a2a96
+size 15024
diff --git a/checkpoint-420/rng_state_3.pth b/checkpoint-420/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..354837a1619c0ceed80cf48974fc332409359617
--- /dev/null
+++ b/checkpoint-420/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c49799083d1c2eee8103a3275b06480830c78ca81702f633d79806fac560f3
+size 15024
diff --git a/checkpoint-420/scheduler.pt b/checkpoint-420/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7b30c6563e608d12853d857fe89963d622be9588
--- /dev/null
+++ b/checkpoint-420/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7749be1c411bb72e5642b76dd4a581519272a010b19e8263d24eb1b38a5c7eec
+size 1064
diff --git a/checkpoint-420/special_tokens_map.json b/checkpoint-420/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9414f9e36eb995388775c9e63e5588313e7c41d3
--- /dev/null
+++ b/checkpoint-420/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-420/tokenizer.json b/checkpoint-420/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ae94f3cc49ae02ddb8b100e69ba51719000fa01
--- /dev/null
+++ b/checkpoint-420/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884
diff --git a/checkpoint-420/tokenizer_config.json b/checkpoint-420/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c131c4a0f2e6b6f0b564da934a01b86750c6d347
--- /dev/null
+++ b/checkpoint-420/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": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-420/trainer_state.json b/checkpoint-420/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b19afdb20771d8d49acd527874240ca2e9050ebf
--- /dev/null
+++ b/checkpoint-420/trainer_state.json
@@ -0,0 +1,3094 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.5,
+  "eval_steps": 30,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.9462232657835241,
+      "learning_rate": 8.142857142857143e-07,
+      "loss": 2.5443,
+      "step": 1
+    },
+    {
+      "epoch": 0.008333333333333333,
+      "eval_loss": 2.5896365642547607,
+      "eval_runtime": 96.0059,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 0.271,
+      "step": 1
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.9597143397960513,
+      "learning_rate": 1.6285714285714286e-06,
+      "loss": 2.5524,
+      "step": 2
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.9246258453027174,
+      "learning_rate": 2.442857142857143e-06,
+      "loss": 2.5411,
+      "step": 3
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.9822285829186661,
+      "learning_rate": 3.2571428571428572e-06,
+      "loss": 2.5518,
+      "step": 4
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.9044329068814566,
+      "learning_rate": 4.071428571428572e-06,
+      "loss": 2.4922,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9131300887744053,
+      "learning_rate": 4.885714285714286e-06,
+      "loss": 2.5713,
+      "step": 6
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.8336298309675122,
+      "learning_rate": 5.7000000000000005e-06,
+      "loss": 2.4959,
+      "step": 7
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.810775409605909,
+      "learning_rate": 6.5142857142857145e-06,
+      "loss": 2.4943,
+      "step": 8
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.6993505055921954,
+      "learning_rate": 7.3285714285714285e-06,
+      "loss": 2.5022,
+      "step": 9
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.5909140859664664,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 2.468,
+      "step": 10
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.5464791893738283,
+      "learning_rate": 8.957142857142857e-06,
+      "loss": 2.5203,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.41153668995149084,
+      "learning_rate": 9.771428571428571e-06,
+      "loss": 2.4912,
+      "step": 12
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.35433353277028035,
+      "learning_rate": 1.0585714285714287e-05,
+      "loss": 2.4467,
+      "step": 13
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.27579908222756766,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 2.4599,
+      "step": 14
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.22636758420678307,
+      "learning_rate": 1.2214285714285715e-05,
+      "loss": 2.4357,
+      "step": 15
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.22309908436920517,
+      "learning_rate": 1.3028571428571429e-05,
+      "loss": 2.368,
+      "step": 16
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.2384290311446137,
+      "learning_rate": 1.3842857142857143e-05,
+      "loss": 2.4054,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2279055472006466,
+      "learning_rate": 1.4657142857142857e-05,
+      "loss": 2.4162,
+      "step": 18
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.24659885813398136,
+      "learning_rate": 1.547142857142857e-05,
+      "loss": 2.4109,
+      "step": 19
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.21920560481126147,
+      "learning_rate": 1.6285714285714287e-05,
+      "loss": 2.4344,
+      "step": 20
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.21340860355678012,
+      "learning_rate": 1.71e-05,
+      "loss": 2.4532,
+      "step": 21
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.1775246176788835,
+      "learning_rate": 1.7914285714285715e-05,
+      "loss": 2.4398,
+      "step": 22
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.15469100364725502,
+      "learning_rate": 1.872857142857143e-05,
+      "loss": 2.4275,
+      "step": 23
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1261136620302219,
+      "learning_rate": 1.9542857142857143e-05,
+      "loss": 2.3855,
+      "step": 24
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.1251566381945981,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 2.4008,
+      "step": 25
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.12280228065778742,
+      "learning_rate": 2.1171428571428574e-05,
+      "loss": 2.4086,
+      "step": 26
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.1362748806421765,
+      "learning_rate": 2.1985714285714286e-05,
+      "loss": 2.3642,
+      "step": 27
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.12370426656542512,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 2.4168,
+      "step": 28
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.12077140199925576,
+      "learning_rate": 2.3614285714285718e-05,
+      "loss": 2.3502,
+      "step": 29
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.10854652278245232,
+      "learning_rate": 2.442857142857143e-05,
+      "loss": 2.323,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 2.4455511569976807,
+      "eval_runtime": 82.5732,
+      "eval_samples_per_second": 4.965,
+      "eval_steps_per_second": 0.315,
+      "step": 30
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.10286886191993252,
+      "learning_rate": 2.5242857142857142e-05,
+      "loss": 2.4007,
+      "step": 31
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.09687340891245565,
+      "learning_rate": 2.6057142857142858e-05,
+      "loss": 2.4088,
+      "step": 32
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.09653492248714694,
+      "learning_rate": 2.6871428571428574e-05,
+      "loss": 2.3906,
+      "step": 33
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.09022900019263645,
+      "learning_rate": 2.7685714285714286e-05,
+      "loss": 2.4065,
+      "step": 34
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.0912409242342349,
+      "learning_rate": 2.85e-05,
+      "loss": 2.3699,
+      "step": 35
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09592020125185927,
+      "learning_rate": 2.8499644890093217e-05,
+      "loss": 2.3587,
+      "step": 36
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.0907084429462166,
+      "learning_rate": 2.8498579578071537e-05,
+      "loss": 2.4259,
+      "step": 37
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.09390099422567517,
+      "learning_rate": 2.8496804117030106e-05,
+      "loss": 2.3232,
+      "step": 38
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.08704027284958313,
+      "learning_rate": 2.849431859545787e-05,
+      "loss": 2.4027,
+      "step": 39
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.08787482564111378,
+      "learning_rate": 2.849112313723319e-05,
+      "loss": 2.3827,
+      "step": 40
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.08422520058818864,
+      "learning_rate": 2.8487217901617672e-05,
+      "loss": 2.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.07979320980153469,
+      "learning_rate": 2.84826030832482e-05,
+      "loss": 2.3519,
+      "step": 42
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.07814774416810645,
+      "learning_rate": 2.8477278912127266e-05,
+      "loss": 2.3708,
+      "step": 43
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.07237049854036091,
+      "learning_rate": 2.847124565361149e-05,
+      "loss": 2.388,
+      "step": 44
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.07354258492789081,
+      "learning_rate": 2.8464503608398385e-05,
+      "loss": 2.3586,
+      "step": 45
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.0771281784161838,
+      "learning_rate": 2.845705311251141e-05,
+      "loss": 2.3993,
+      "step": 46
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.0763264062020341,
+      "learning_rate": 2.844889453728318e-05,
+      "loss": 2.3838,
+      "step": 47
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07082143620733677,
+      "learning_rate": 2.8440028289336977e-05,
+      "loss": 2.3628,
+      "step": 48
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 0.0715578975320661,
+      "learning_rate": 2.8430454810566477e-05,
+      "loss": 2.361,
+      "step": 49
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.06881630985450242,
+      "learning_rate": 2.8420174578113747e-05,
+      "loss": 2.4392,
+      "step": 50
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.0689279893077156,
+      "learning_rate": 2.8409188104345426e-05,
+      "loss": 2.3519,
+      "step": 51
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.07069081407018309,
+      "learning_rate": 2.8397495936827232e-05,
+      "loss": 2.3981,
+      "step": 52
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 0.07092917277421104,
+      "learning_rate": 2.8385098658296637e-05,
+      "loss": 2.355,
+      "step": 53
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0703607034709259,
+      "learning_rate": 2.8371996886633843e-05,
+      "loss": 2.3793,
+      "step": 54
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.07124199690967324,
+      "learning_rate": 2.8358191274830974e-05,
+      "loss": 2.4275,
+      "step": 55
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.07099804346309355,
+      "learning_rate": 2.8343682510959552e-05,
+      "loss": 2.3323,
+      "step": 56
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.06967632308939245,
+      "learning_rate": 2.8328471318136165e-05,
+      "loss": 2.3883,
+      "step": 57
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.07156300179553134,
+      "learning_rate": 2.831255845448647e-05,
+      "loss": 2.3298,
+      "step": 58
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 0.0704201532980033,
+      "learning_rate": 2.8295944713107387e-05,
+      "loss": 2.331,
+      "step": 59
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.06794782460291071,
+      "learning_rate": 2.8278630922027563e-05,
+      "loss": 2.3776,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.4216628074645996,
+      "eval_runtime": 82.3879,
+      "eval_samples_per_second": 4.976,
+      "eval_steps_per_second": 0.316,
+      "step": 60
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 0.07045949082426937,
+      "learning_rate": 2.8260617944166123e-05,
+      "loss": 2.3319,
+      "step": 61
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 0.0702234192794877,
+      "learning_rate": 2.824190667728965e-05,
+      "loss": 2.3647,
+      "step": 62
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.06946814214632402,
+      "learning_rate": 2.8222498053967434e-05,
+      "loss": 2.3967,
+      "step": 63
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.06563265580127577,
+      "learning_rate": 2.8202393041525005e-05,
+      "loss": 2.3863,
+      "step": 64
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0723770670150652,
+      "learning_rate": 2.8181592641995933e-05,
+      "loss": 2.3823,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06870429029917037,
+      "learning_rate": 2.8160097892071847e-05,
+      "loss": 2.3241,
+      "step": 66
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 0.08615444480664787,
+      "learning_rate": 2.8137909863050806e-05,
+      "loss": 2.3504,
+      "step": 67
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.06980417460436542,
+      "learning_rate": 2.8115029660783887e-05,
+      "loss": 2.3762,
+      "step": 68
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.0691283200064781,
+      "learning_rate": 2.809145842562007e-05,
+      "loss": 2.3202,
+      "step": 69
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.06434433998677834,
+      "learning_rate": 2.8067197332349406e-05,
+      "loss": 2.4117,
+      "step": 70
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 0.06712521054811822,
+      "learning_rate": 2.8042247590144472e-05,
+      "loss": 2.4234,
+      "step": 71
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.07781170630767965,
+      "learning_rate": 2.8016610442500087e-05,
+      "loss": 2.3614,
+      "step": 72
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 0.07179449259884696,
+      "learning_rate": 2.7990287167171357e-05,
+      "loss": 2.327,
+      "step": 73
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.0666012429917219,
+      "learning_rate": 2.7963279076109976e-05,
+      "loss": 2.3606,
+      "step": 74
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07042352420672252,
+      "learning_rate": 2.7935587515398855e-05,
+      "loss": 2.387,
+      "step": 75
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.07141219809062525,
+      "learning_rate": 2.7907213865185014e-05,
+      "loss": 2.3975,
+      "step": 76
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 0.07530038535140655,
+      "learning_rate": 2.787815953961081e-05,
+      "loss": 2.3975,
+      "step": 77
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.06873021297298251,
+      "learning_rate": 2.784842598674345e-05,
+      "loss": 2.3724,
+      "step": 78
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 0.06853494667979494,
+      "learning_rate": 2.781801468850282e-05,
+      "loss": 2.3994,
+      "step": 79
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.07164446612343163,
+      "learning_rate": 2.778692716058762e-05,
+      "loss": 2.3448,
+      "step": 80
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.07112624750325054,
+      "learning_rate": 2.7755164952399844e-05,
+      "loss": 2.2984,
+      "step": 81
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.07679055297227524,
+      "learning_rate": 2.7722729646967527e-05,
+      "loss": 2.3699,
+      "step": 82
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 0.07270378630883641,
+      "learning_rate": 2.768962286086587e-05,
+      "loss": 2.3436,
+      "step": 83
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06869524209312625,
+      "learning_rate": 2.7655846244136654e-05,
+      "loss": 2.3856,
+      "step": 84
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.07006104211903366,
+      "learning_rate": 2.762140148020602e-05,
+      "loss": 2.3852,
+      "step": 85
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.07264285304887648,
+      "learning_rate": 2.758629028580055e-05,
+      "loss": 2.3834,
+      "step": 86
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.07253530482477301,
+      "learning_rate": 2.7550514410861718e-05,
+      "loss": 2.3573,
+      "step": 87
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.07265955522289944,
+      "learning_rate": 2.751407563845866e-05,
+      "loss": 2.3163,
+      "step": 88
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 0.07374626234739601,
+      "learning_rate": 2.747697578469931e-05,
+      "loss": 2.3851,
+      "step": 89
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07255481420091238,
+      "learning_rate": 2.7439216698639904e-05,
+      "loss": 2.3345,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 2.4115521907806396,
+      "eval_runtime": 82.0248,
+      "eval_samples_per_second": 4.998,
+      "eval_steps_per_second": 0.317,
+      "step": 90
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 0.06817548300510701,
+      "learning_rate": 2.7400800262192788e-05,
+      "loss": 2.3449,
+      "step": 91
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.07336990573663302,
+      "learning_rate": 2.7361728390032657e-05,
+      "loss": 2.3448,
+      "step": 92
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.07822885886131264,
+      "learning_rate": 2.732200302950111e-05,
+      "loss": 2.3217,
+      "step": 93
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.07296512071361201,
+      "learning_rate": 2.728162616050959e-05,
+      "loss": 2.3329,
+      "step": 94
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.07367928865175823,
+      "learning_rate": 2.724059979544072e-05,
+      "loss": 2.3208,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.07504139519989858,
+      "learning_rate": 2.719892597904801e-05,
+      "loss": 2.3483,
+      "step": 96
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 0.06790757702451031,
+      "learning_rate": 2.7156606788353906e-05,
+      "loss": 2.4128,
+      "step": 97
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.07011160737870108,
+      "learning_rate": 2.7113644332546336e-05,
+      "loss": 2.3832,
+      "step": 98
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.08077329808935288,
+      "learning_rate": 2.707004075287352e-05,
+      "loss": 2.3308,
+      "step": 99
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.0719496280235162,
+      "learning_rate": 2.7025798222537306e-05,
+      "loss": 2.3254,
+      "step": 100
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 0.07275409855582728,
+      "learning_rate": 2.698091894658483e-05,
+      "loss": 2.3967,
+      "step": 101
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.07201531734077336,
+      "learning_rate": 2.693540516179861e-05,
+      "loss": 2.3346,
+      "step": 102
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 0.0765467775604243,
+      "learning_rate": 2.6889259136585094e-05,
+      "loss": 2.3336,
+      "step": 103
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.077223728318478,
+      "learning_rate": 2.6842483170861568e-05,
+      "loss": 2.3313,
+      "step": 104
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.07639332869289207,
+      "learning_rate": 2.6795079595941553e-05,
+      "loss": 2.4008,
+      "step": 105
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 0.07440505813328589,
+      "learning_rate": 2.6747050774418605e-05,
+      "loss": 2.3425,
+      "step": 106
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 0.06937810484842656,
+      "learning_rate": 2.6698399100048556e-05,
+      "loss": 2.3349,
+      "step": 107
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07336400555418392,
+      "learning_rate": 2.6649126997630225e-05,
+      "loss": 2.3792,
+      "step": 108
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 0.07442564570941794,
+      "learning_rate": 2.6599236922884547e-05,
+      "loss": 2.3683,
+      "step": 109
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.07470689463768693,
+      "learning_rate": 2.65487313623322e-05,
+      "loss": 2.3036,
+      "step": 110
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.07096997017300663,
+      "learning_rate": 2.649761283316966e-05,
+      "loss": 2.3682,
+      "step": 111
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07511821034386772,
+      "learning_rate": 2.6445883883143744e-05,
+      "loss": 2.3346,
+      "step": 112
+    },
+    {
+      "epoch": 0.9416666666666667,
+      "grad_norm": 0.07057540374817312,
+      "learning_rate": 2.639354709042466e-05,
+      "loss": 2.3502,
+      "step": 113
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07300364605060353,
+      "learning_rate": 2.6340605063477456e-05,
+      "loss": 2.3711,
+      "step": 114
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.06925480258849577,
+      "learning_rate": 2.628706044093207e-05,
+      "loss": 2.3816,
+      "step": 115
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.0705107307569524,
+      "learning_rate": 2.623291589145179e-05,
+      "loss": 2.2958,
+      "step": 116
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.07331112076487026,
+      "learning_rate": 2.6178174113600252e-05,
+      "loss": 2.3279,
+      "step": 117
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.06780655482074792,
+      "learning_rate": 2.612283783570695e-05,
+      "loss": 2.4117,
+      "step": 118
+    },
+    {
+      "epoch": 0.9916666666666667,
+      "grad_norm": 0.07485055181125701,
+      "learning_rate": 2.606690981573125e-05,
+      "loss": 2.303,
+      "step": 119
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07276467760742707,
+      "learning_rate": 2.6010392841124932e-05,
+      "loss": 2.3608,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4049572944641113,
+      "eval_runtime": 82.3343,
+      "eval_samples_per_second": 4.98,
+      "eval_steps_per_second": 0.316,
+      "step": 120
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 0.07548790321925977,
+      "learning_rate": 2.5953289728693274e-05,
+      "loss": 2.3185,
+      "step": 121
+    },
+    {
+      "epoch": 1.0166666666666666,
+      "grad_norm": 0.0730570698984131,
+      "learning_rate": 2.5895603324454647e-05,
+      "loss": 2.2877,
+      "step": 122
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.07345139782586493,
+      "learning_rate": 2.5837336503498694e-05,
+      "loss": 2.2836,
+      "step": 123
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.07299378924326991,
+      "learning_rate": 2.5778492169843003e-05,
+      "loss": 2.3436,
+      "step": 124
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.07154250149880004,
+      "learning_rate": 2.5719073256288394e-05,
+      "loss": 2.3822,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0720748804004234,
+      "learning_rate": 2.565908272427274e-05,
+      "loss": 2.2708,
+      "step": 126
+    },
+    {
+      "epoch": 1.0583333333333333,
+      "grad_norm": 0.07269892036621302,
+      "learning_rate": 2.5598523563723373e-05,
+      "loss": 2.3377,
+      "step": 127
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0756770863265576,
+      "learning_rate": 2.5537398792908062e-05,
+      "loss": 2.352,
+      "step": 128
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.07397323539112335,
+      "learning_rate": 2.547571145828459e-05,
+      "loss": 2.3643,
+      "step": 129
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.07438211371538549,
+      "learning_rate": 2.54134646343489e-05,
+      "loss": 2.3387,
+      "step": 130
+    },
+    {
+      "epoch": 1.0916666666666666,
+      "grad_norm": 0.07094248712059498,
+      "learning_rate": 2.5350661423481885e-05,
+      "loss": 2.3221,
+      "step": 131
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.0771622686218861,
+      "learning_rate": 2.5287304955794754e-05,
+      "loss": 2.3183,
+      "step": 132
+    },
+    {
+      "epoch": 1.1083333333333334,
+      "grad_norm": 0.07495056480159959,
+      "learning_rate": 2.5223398388973028e-05,
+      "loss": 2.3697,
+      "step": 133
+    },
+    {
+      "epoch": 1.1166666666666667,
+      "grad_norm": 0.07629199954207538,
+      "learning_rate": 2.515894490811916e-05,
+      "loss": 2.3529,
+      "step": 134
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.0762534542729489,
+      "learning_rate": 2.5093947725593792e-05,
+      "loss": 2.3208,
+      "step": 135
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.07587427933984144,
+      "learning_rate": 2.502841008085565e-05,
+      "loss": 2.3448,
+      "step": 136
+    },
+    {
+      "epoch": 1.1416666666666666,
+      "grad_norm": 0.07490456619530689,
+      "learning_rate": 2.49623352403001e-05,
+      "loss": 2.3435,
+      "step": 137
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.0744781797534131,
+      "learning_rate": 2.4895726497096315e-05,
+      "loss": 2.4,
+      "step": 138
+    },
+    {
+      "epoch": 1.1583333333333332,
+      "grad_norm": 0.07464944817741491,
+      "learning_rate": 2.482858717102319e-05,
+      "loss": 2.318,
+      "step": 139
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.07309033869975678,
+      "learning_rate": 2.4760920608303867e-05,
+      "loss": 2.2891,
+      "step": 140
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.07284517336177344,
+      "learning_rate": 2.469273018143894e-05,
+      "loss": 2.3051,
+      "step": 141
+    },
+    {
+      "epoch": 1.1833333333333333,
+      "grad_norm": 0.07652064520411771,
+      "learning_rate": 2.462401928903839e-05,
+      "loss": 2.3555,
+      "step": 142
+    },
+    {
+      "epoch": 1.1916666666666667,
+      "grad_norm": 0.07701974074136966,
+      "learning_rate": 2.45547913556522e-05,
+      "loss": 2.3015,
+      "step": 143
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.08108352272511765,
+      "learning_rate": 2.448504983159966e-05,
+      "loss": 2.3221,
+      "step": 144
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.07752288456105606,
+      "learning_rate": 2.441479819279742e-05,
+      "loss": 2.3684,
+      "step": 145
+    },
+    {
+      "epoch": 1.2166666666666668,
+      "grad_norm": 0.07881711814524053,
+      "learning_rate": 2.4344039940586235e-05,
+      "loss": 2.3011,
+      "step": 146
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.07757542042787384,
+      "learning_rate": 2.4272778601556472e-05,
+      "loss": 2.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.07228965364348439,
+      "learning_rate": 2.4201017727372336e-05,
+      "loss": 2.3801,
+      "step": 148
+    },
+    {
+      "epoch": 1.2416666666666667,
+      "grad_norm": 0.07389812003829682,
+      "learning_rate": 2.4128760894594853e-05,
+      "loss": 2.3359,
+      "step": 149
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.08146218033856112,
+      "learning_rate": 2.4056011704503633e-05,
+      "loss": 2.3096,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 2.400259494781494,
+      "eval_runtime": 81.604,
+      "eval_samples_per_second": 5.024,
+      "eval_steps_per_second": 0.319,
+      "step": 150
+    },
+    {
+      "epoch": 1.2583333333333333,
+      "grad_norm": 0.07407260421175128,
+      "learning_rate": 2.3982773782917347e-05,
+      "loss": 2.3418,
+      "step": 151
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.07827237096687646,
+      "learning_rate": 2.390905078001306e-05,
+      "loss": 2.2778,
+      "step": 152
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.07699758244967876,
+      "learning_rate": 2.383484637014426e-05,
+      "loss": 2.3245,
+      "step": 153
+    },
+    {
+      "epoch": 1.2833333333333332,
+      "grad_norm": 0.07805943021524937,
+      "learning_rate": 2.3760164251657773e-05,
+      "loss": 2.3782,
+      "step": 154
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.0741687347632035,
+      "learning_rate": 2.368500814670941e-05,
+      "loss": 2.3765,
+      "step": 155
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.07696079818166807,
+      "learning_rate": 2.3609381801078448e-05,
+      "loss": 2.3958,
+      "step": 156
+    },
+    {
+      "epoch": 1.3083333333333333,
+      "grad_norm": 0.08864860865623735,
+      "learning_rate": 2.3533288983980964e-05,
+      "loss": 2.3482,
+      "step": 157
+    },
+    {
+      "epoch": 1.3166666666666667,
+      "grad_norm": 0.07676755572584443,
+      "learning_rate": 2.3456733487881978e-05,
+      "loss": 2.3511,
+      "step": 158
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.07754541163995884,
+      "learning_rate": 2.337971912830641e-05,
+      "loss": 2.3754,
+      "step": 159
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08430746433268149,
+      "learning_rate": 2.3302249743648926e-05,
+      "loss": 2.4063,
+      "step": 160
+    },
+    {
+      "epoch": 1.3416666666666668,
+      "grad_norm": 0.08113759941899056,
+      "learning_rate": 2.322432919498265e-05,
+      "loss": 2.3352,
+      "step": 161
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.08147516272984133,
+      "learning_rate": 2.3145961365866708e-05,
+      "loss": 2.3119,
+      "step": 162
+    },
+    {
+      "epoch": 1.3583333333333334,
+      "grad_norm": 0.07749688842544009,
+      "learning_rate": 2.3067150162152675e-05,
+      "loss": 2.3547,
+      "step": 163
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.08640326754187048,
+      "learning_rate": 2.298789951178992e-05,
+      "loss": 2.3389,
+      "step": 164
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.0795137333109577,
+      "learning_rate": 2.2908213364629812e-05,
+      "loss": 2.3778,
+      "step": 165
+    },
+    {
+      "epoch": 1.3833333333333333,
+      "grad_norm": 0.07739334763959965,
+      "learning_rate": 2.2828095692228886e-05,
+      "loss": 2.3658,
+      "step": 166
+    },
+    {
+      "epoch": 1.3916666666666666,
+      "grad_norm": 0.07783031237693959,
+      "learning_rate": 2.2747550487650887e-05,
+      "loss": 2.3575,
+      "step": 167
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.07682655233706284,
+      "learning_rate": 2.2666581765267758e-05,
+      "loss": 2.2825,
+      "step": 168
+    },
+    {
+      "epoch": 1.4083333333333332,
+      "grad_norm": 0.08359081032268273,
+      "learning_rate": 2.2585193560559563e-05,
+      "loss": 2.261,
+      "step": 169
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.0826940676306091,
+      "learning_rate": 2.250338992991335e-05,
+      "loss": 2.3069,
+      "step": 170
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.08462619097403327,
+      "learning_rate": 2.2421174950421017e-05,
+      "loss": 2.2864,
+      "step": 171
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.07990029642375193,
+      "learning_rate": 2.233855271967606e-05,
+      "loss": 2.3033,
+      "step": 172
+    },
+    {
+      "epoch": 1.4416666666666667,
+      "grad_norm": 0.08051779058857793,
+      "learning_rate": 2.2255527355569372e-05,
+      "loss": 2.3166,
+      "step": 173
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.08604667339713809,
+      "learning_rate": 2.217210299608402e-05,
+      "loss": 2.387,
+      "step": 174
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.07829742536277012,
+      "learning_rate": 2.208828379908899e-05,
+      "loss": 2.311,
+      "step": 175
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.07850219342360719,
+      "learning_rate": 2.200407394213196e-05,
+      "loss": 2.3384,
+      "step": 176
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.08531707041033702,
+      "learning_rate": 2.19194776222311e-05,
+      "loss": 2.3107,
+      "step": 177
+    },
+    {
+      "epoch": 1.4833333333333334,
+      "grad_norm": 0.07652853009760147,
+      "learning_rate": 2.183449905566589e-05,
+      "loss": 2.3494,
+      "step": 178
+    },
+    {
+      "epoch": 1.4916666666666667,
+      "grad_norm": 0.0797336095546633,
+      "learning_rate": 2.1749142477766972e-05,
+      "loss": 2.3291,
+      "step": 179
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.08700079540422817,
+      "learning_rate": 2.166341214270507e-05,
+      "loss": 2.3132,
+      "step": 180
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.3966128826141357,
+      "eval_runtime": 83.184,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 0.313,
+      "step": 180
+    },
+    {
+      "epoch": 1.5083333333333333,
+      "grad_norm": 0.07925581040107615,
+      "learning_rate": 2.157731232327897e-05,
+      "loss": 2.3578,
+      "step": 181
+    },
+    {
+      "epoch": 1.5166666666666666,
+      "grad_norm": 0.07873086864048841,
+      "learning_rate": 2.1490847310702544e-05,
+      "loss": 2.3229,
+      "step": 182
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.07775316849537767,
+      "learning_rate": 2.1404021414390874e-05,
+      "loss": 2.3756,
+      "step": 183
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.07949428482523528,
+      "learning_rate": 2.1316838961745518e-05,
+      "loss": 2.3535,
+      "step": 184
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.08423278187074197,
+      "learning_rate": 2.1229304297938755e-05,
+      "loss": 2.3517,
+      "step": 185
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.07930583119038707,
+      "learning_rate": 2.1141421785697097e-05,
+      "loss": 2.3929,
+      "step": 186
+    },
+    {
+      "epoch": 1.5583333333333333,
+      "grad_norm": 0.07736840323261199,
+      "learning_rate": 2.1053195805083803e-05,
+      "loss": 2.3194,
+      "step": 187
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.08306421066524537,
+      "learning_rate": 2.0964630753280584e-05,
+      "loss": 2.3131,
+      "step": 188
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.0805185815818936,
+      "learning_rate": 2.0875731044368472e-05,
+      "loss": 2.3238,
+      "step": 189
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.07729948838070921,
+      "learning_rate": 2.078650110910779e-05,
+      "loss": 2.3279,
+      "step": 190
+    },
+    {
+      "epoch": 1.5916666666666668,
+      "grad_norm": 0.08053951644296133,
+      "learning_rate": 2.0696945394717355e-05,
+      "loss": 2.3343,
+      "step": 191
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.08184664333069269,
+      "learning_rate": 2.0607068364652783e-05,
+      "loss": 2.3441,
+      "step": 192
+    },
+    {
+      "epoch": 1.6083333333333334,
+      "grad_norm": 0.07894699650259683,
+      "learning_rate": 2.051687449838409e-05,
+      "loss": 2.3384,
+      "step": 193
+    },
+    {
+      "epoch": 1.6166666666666667,
+      "grad_norm": 0.08288692832517489,
+      "learning_rate": 2.042636829117239e-05,
+      "loss": 2.3219,
+      "step": 194
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.09061769591669266,
+      "learning_rate": 2.033555425384586e-05,
+      "loss": 2.3168,
+      "step": 195
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.07607427061534017,
+      "learning_rate": 2.0244436912574938e-05,
+      "loss": 2.3592,
+      "step": 196
+    },
+    {
+      "epoch": 1.6416666666666666,
+      "grad_norm": 0.08827457673533141,
+      "learning_rate": 2.0153020808646715e-05,
+      "loss": 2.3177,
+      "step": 197
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.0757688204165182,
+      "learning_rate": 2.0061310498238618e-05,
+      "loss": 2.2366,
+      "step": 198
+    },
+    {
+      "epoch": 1.6583333333333332,
+      "grad_norm": 0.07815852114026649,
+      "learning_rate": 1.996931055219132e-05,
+      "loss": 2.3161,
+      "step": 199
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.08058901889279678,
+      "learning_rate": 1.9877025555780927e-05,
+      "loss": 2.3749,
+      "step": 200
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.07708027281441528,
+      "learning_rate": 1.978446010849045e-05,
+      "loss": 2.2854,
+      "step": 201
+    },
+    {
+      "epoch": 1.6833333333333333,
+      "grad_norm": 0.08312283019758401,
+      "learning_rate": 1.969161882378058e-05,
+      "loss": 2.3524,
+      "step": 202
+    },
+    {
+      "epoch": 1.6916666666666667,
+      "grad_norm": 0.07784046601849169,
+      "learning_rate": 1.9598506328859717e-05,
+      "loss": 2.3418,
+      "step": 203
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.07906237498578873,
+      "learning_rate": 1.95051272644534e-05,
+      "loss": 2.3514,
+      "step": 204
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.08323464269988524,
+      "learning_rate": 1.9411486284572977e-05,
+      "loss": 2.3133,
+      "step": 205
+    },
+    {
+      "epoch": 1.7166666666666668,
+      "grad_norm": 0.08153670371604982,
+      "learning_rate": 1.931758805628366e-05,
+      "loss": 2.3388,
+      "step": 206
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.08152589045596419,
+      "learning_rate": 1.9223437259471912e-05,
+      "loss": 2.3309,
+      "step": 207
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.08382345786042532,
+      "learning_rate": 1.9129038586612224e-05,
+      "loss": 2.3282,
+      "step": 208
+    },
+    {
+      "epoch": 1.7416666666666667,
+      "grad_norm": 0.0835609429134592,
+      "learning_rate": 1.903439674253321e-05,
+      "loss": 2.3567,
+      "step": 209
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.08252984125014622,
+      "learning_rate": 1.8939516444183143e-05,
+      "loss": 2.3352,
+      "step": 210
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.3933684825897217,
+      "eval_runtime": 83.3063,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 0.312,
+      "step": 210
+    },
+    {
+      "epoch": 1.7583333333333333,
+      "grad_norm": 0.0815481053340795,
+      "learning_rate": 1.884440242039485e-05,
+      "loss": 2.3262,
+      "step": 211
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.08258761118218041,
+      "learning_rate": 1.8749059411650034e-05,
+      "loss": 2.3396,
+      "step": 212
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.0884999967331726,
+      "learning_rate": 1.8653492169843003e-05,
+      "loss": 2.3176,
+      "step": 213
+    },
+    {
+      "epoch": 1.7833333333333332,
+      "grad_norm": 0.0824785010834098,
+      "learning_rate": 1.8557705458043838e-05,
+      "loss": 2.3272,
+      "step": 214
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.08727167025374602,
+      "learning_rate": 1.8461704050261e-05,
+      "loss": 2.2298,
+      "step": 215
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0768016904891171,
+      "learning_rate": 1.8365492731203398e-05,
+      "loss": 2.3554,
+      "step": 216
+    },
+    {
+      "epoch": 1.8083333333333333,
+      "grad_norm": 0.07709533586121158,
+      "learning_rate": 1.8269076296041917e-05,
+      "loss": 2.3702,
+      "step": 217
+    },
+    {
+      "epoch": 1.8166666666666667,
+      "grad_norm": 0.0806446736093232,
+      "learning_rate": 1.8172459550170424e-05,
+      "loss": 2.3585,
+      "step": 218
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.07523532523458193,
+      "learning_rate": 1.8075647308966268e-05,
+      "loss": 2.3609,
+      "step": 219
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.07497201271988578,
+      "learning_rate": 1.797864439755028e-05,
+      "loss": 2.3755,
+      "step": 220
+    },
+    {
+      "epoch": 1.8416666666666668,
+      "grad_norm": 0.08249074177996166,
+      "learning_rate": 1.7881455650546303e-05,
+      "loss": 2.372,
+      "step": 221
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0780160636961897,
+      "learning_rate": 1.7784085911840214e-05,
+      "loss": 2.3823,
+      "step": 222
+    },
+    {
+      "epoch": 1.8583333333333334,
+      "grad_norm": 0.08148680526536918,
+      "learning_rate": 1.7686540034338513e-05,
+      "loss": 2.3314,
+      "step": 223
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0795864595636552,
+      "learning_rate": 1.758882287972646e-05,
+      "loss": 2.2853,
+      "step": 224
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.08198344669246531,
+      "learning_rate": 1.749093931822577e-05,
+      "loss": 2.3605,
+      "step": 225
+    },
+    {
+      "epoch": 1.8833333333333333,
+      "grad_norm": 0.08138145213474299,
+      "learning_rate": 1.739289422835185e-05,
+      "loss": 2.2721,
+      "step": 226
+    },
+    {
+      "epoch": 1.8916666666666666,
+      "grad_norm": 0.08306015511124677,
+      "learning_rate": 1.7294692496670715e-05,
+      "loss": 2.2889,
+      "step": 227
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.07478727556401082,
+      "learning_rate": 1.7196339017555378e-05,
+      "loss": 2.3416,
+      "step": 228
+    },
+    {
+      "epoch": 1.9083333333333332,
+      "grad_norm": 0.08858459574829487,
+      "learning_rate": 1.709783869294196e-05,
+      "loss": 2.3081,
+      "step": 229
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.08175368181940743,
+      "learning_rate": 1.699919643208533e-05,
+      "loss": 2.3304,
+      "step": 230
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.07630479738636474,
+      "learning_rate": 1.6900417151314503e-05,
+      "loss": 2.3454,
+      "step": 231
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.07687273996639293,
+      "learning_rate": 1.6801505773787527e-05,
+      "loss": 2.3901,
+      "step": 232
+    },
+    {
+      "epoch": 1.9416666666666667,
+      "grad_norm": 0.08600269874202937,
+      "learning_rate": 1.670246722924616e-05,
+      "loss": 2.3081,
+      "step": 233
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.07737694968965858,
+      "learning_rate": 1.660330645377018e-05,
+      "loss": 2.3643,
+      "step": 234
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.08165758061569027,
+      "learning_rate": 1.6504028389531333e-05,
+      "loss": 2.355,
+      "step": 235
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.08264378429137093,
+      "learning_rate": 1.640463798454704e-05,
+      "loss": 2.3219,
+      "step": 236
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.0858368818345628,
+      "learning_rate": 1.6305140192433787e-05,
+      "loss": 2.3329,
+      "step": 237
+    },
+    {
+      "epoch": 1.9833333333333334,
+      "grad_norm": 0.07616999163161729,
+      "learning_rate": 1.620553997216023e-05,
+      "loss": 2.3523,
+      "step": 238
+    },
+    {
+      "epoch": 1.9916666666666667,
+      "grad_norm": 0.08241527325980988,
+      "learning_rate": 1.6105842287800046e-05,
+      "loss": 2.2982,
+      "step": 239
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08007891750583127,
+      "learning_rate": 1.600605210828451e-05,
+      "loss": 2.2785,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3910558223724365,
+      "eval_runtime": 83.4904,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 0.311,
+      "step": 240
+    },
+    {
+      "epoch": 2.0083333333333333,
+      "grad_norm": 0.08108687194604622,
+      "learning_rate": 1.5906174407154883e-05,
+      "loss": 2.3367,
+      "step": 241
+    },
+    {
+      "epoch": 2.0166666666666666,
+      "grad_norm": 0.0806511417182259,
+      "learning_rate": 1.5806214162314463e-05,
+      "loss": 2.3011,
+      "step": 242
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.08264392219751603,
+      "learning_rate": 1.5706176355780556e-05,
+      "loss": 2.3036,
+      "step": 243
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.07958409681135217,
+      "learning_rate": 1.5606065973436132e-05,
+      "loss": 2.3056,
+      "step": 244
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.07856642651007223,
+      "learning_rate": 1.550588800478133e-05,
+      "loss": 2.3692,
+      "step": 245
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.08350216798892127,
+      "learning_rate": 1.5405647442684794e-05,
+      "loss": 2.2697,
+      "step": 246
+    },
+    {
+      "epoch": 2.058333333333333,
+      "grad_norm": 0.08390645284684875,
+      "learning_rate": 1.530534928313484e-05,
+      "loss": 2.2425,
+      "step": 247
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.07883358190907572,
+      "learning_rate": 1.5204998524990423e-05,
+      "loss": 2.3281,
+      "step": 248
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.07994560560782488,
+      "learning_rate": 1.5104600169732015e-05,
+      "loss": 2.3285,
+      "step": 249
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.08345016891314849,
+      "learning_rate": 1.5004159221212325e-05,
+      "loss": 2.3252,
+      "step": 250
+    },
+    {
+      "epoch": 2.091666666666667,
+      "grad_norm": 0.0767244585605165,
+      "learning_rate": 1.490368068540692e-05,
+      "loss": 2.3176,
+      "step": 251
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.07853322933102938,
+      "learning_rate": 1.4803169570164703e-05,
+      "loss": 2.286,
+      "step": 252
+    },
+    {
+      "epoch": 2.1083333333333334,
+      "grad_norm": 0.07885223855237164,
+      "learning_rate": 1.4702630884958345e-05,
+      "loss": 2.3293,
+      "step": 253
+    },
+    {
+      "epoch": 2.1166666666666667,
+      "grad_norm": 0.07786083611140765,
+      "learning_rate": 1.4602069640634605e-05,
+      "loss": 2.3241,
+      "step": 254
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.07961379829842732,
+      "learning_rate": 1.4501490849164585e-05,
+      "loss": 2.3218,
+      "step": 255
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.0812119479291348,
+      "learning_rate": 1.4400899523393928e-05,
+      "loss": 2.3101,
+      "step": 256
+    },
+    {
+      "epoch": 2.1416666666666666,
+      "grad_norm": 0.07820228956836967,
+      "learning_rate": 1.4300300676793e-05,
+      "loss": 2.3105,
+      "step": 257
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.0787354321940814,
+      "learning_rate": 1.4199699323207e-05,
+      "loss": 2.2921,
+      "step": 258
+    },
+    {
+      "epoch": 2.158333333333333,
+      "grad_norm": 0.0821168083039209,
+      "learning_rate": 1.4099100476606071e-05,
+      "loss": 2.3449,
+      "step": 259
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.08227570212622978,
+      "learning_rate": 1.3998509150835417e-05,
+      "loss": 2.2804,
+      "step": 260
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.07956552166316343,
+      "learning_rate": 1.3897930359365397e-05,
+      "loss": 2.2798,
+      "step": 261
+    },
+    {
+      "epoch": 2.183333333333333,
+      "grad_norm": 0.08355971196343313,
+      "learning_rate": 1.3797369115041656e-05,
+      "loss": 2.3121,
+      "step": 262
+    },
+    {
+      "epoch": 2.191666666666667,
+      "grad_norm": 0.07664615523847712,
+      "learning_rate": 1.3696830429835303e-05,
+      "loss": 2.3511,
+      "step": 263
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.07875754809310784,
+      "learning_rate": 1.3596319314593088e-05,
+      "loss": 2.276,
+      "step": 264
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.07805417721469433,
+      "learning_rate": 1.3495840778787675e-05,
+      "loss": 2.3156,
+      "step": 265
+    },
+    {
+      "epoch": 2.216666666666667,
+      "grad_norm": 0.08500867883177173,
+      "learning_rate": 1.339539983026799e-05,
+      "loss": 2.3304,
+      "step": 266
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.08575986404103182,
+      "learning_rate": 1.3295001475009578e-05,
+      "loss": 2.3171,
+      "step": 267
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.0796424885760881,
+      "learning_rate": 1.3194650716865163e-05,
+      "loss": 2.3488,
+      "step": 268
+    },
+    {
+      "epoch": 2.2416666666666667,
+      "grad_norm": 0.07791982790558008,
+      "learning_rate": 1.3094352557315207e-05,
+      "loss": 2.3806,
+      "step": 269
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0840055290628465,
+      "learning_rate": 1.299411199521868e-05,
+      "loss": 2.3277,
+      "step": 270
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 2.3895957469940186,
+      "eval_runtime": 83.1157,
+      "eval_samples_per_second": 4.933,
+      "eval_steps_per_second": 0.313,
+      "step": 270
+    },
+    {
+      "epoch": 2.2583333333333333,
+      "grad_norm": 0.07770712903979533,
+      "learning_rate": 1.2893934026563873e-05,
+      "loss": 2.2666,
+      "step": 271
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07846164594226922,
+      "learning_rate": 1.2793823644219445e-05,
+      "loss": 2.2855,
+      "step": 272
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.08498339693180243,
+      "learning_rate": 1.269378583768554e-05,
+      "loss": 2.2733,
+      "step": 273
+    },
+    {
+      "epoch": 2.283333333333333,
+      "grad_norm": 0.07834222258922019,
+      "learning_rate": 1.2593825592845122e-05,
+      "loss": 2.3193,
+      "step": 274
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.08132580954052983,
+      "learning_rate": 1.2493947891715491e-05,
+      "loss": 2.3085,
+      "step": 275
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.07883697009265064,
+      "learning_rate": 1.239415771219996e-05,
+      "loss": 2.3545,
+      "step": 276
+    },
+    {
+      "epoch": 2.3083333333333336,
+      "grad_norm": 0.08023901828387182,
+      "learning_rate": 1.2294460027839779e-05,
+      "loss": 2.3489,
+      "step": 277
+    },
+    {
+      "epoch": 2.3166666666666664,
+      "grad_norm": 0.08930364086676225,
+      "learning_rate": 1.2194859807566216e-05,
+      "loss": 2.2591,
+      "step": 278
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.08343332964333285,
+      "learning_rate": 1.2095362015452961e-05,
+      "loss": 2.3404,
+      "step": 279
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.08292455976075656,
+      "learning_rate": 1.199597161046867e-05,
+      "loss": 2.3028,
+      "step": 280
+    },
+    {
+      "epoch": 2.341666666666667,
+      "grad_norm": 0.08627078651851632,
+      "learning_rate": 1.189669354622982e-05,
+      "loss": 2.343,
+      "step": 281
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.08202097516344958,
+      "learning_rate": 1.1797532770753842e-05,
+      "loss": 2.326,
+      "step": 282
+    },
+    {
+      "epoch": 2.3583333333333334,
+      "grad_norm": 0.08362611496815728,
+      "learning_rate": 1.169849422621248e-05,
+      "loss": 2.3035,
+      "step": 283
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.08888611458113292,
+      "learning_rate": 1.1599582848685506e-05,
+      "loss": 2.2812,
+      "step": 284
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.08217261091117088,
+      "learning_rate": 1.1500803567914671e-05,
+      "loss": 2.3378,
+      "step": 285
+    },
+    {
+      "epoch": 2.3833333333333333,
+      "grad_norm": 0.07985728135451624,
+      "learning_rate": 1.1402161307058047e-05,
+      "loss": 2.3522,
+      "step": 286
+    },
+    {
+      "epoch": 2.3916666666666666,
+      "grad_norm": 0.08014525439116486,
+      "learning_rate": 1.1303660982444624e-05,
+      "loss": 2.2256,
+      "step": 287
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08787593050595495,
+      "learning_rate": 1.1205307503329286e-05,
+      "loss": 2.2974,
+      "step": 288
+    },
+    {
+      "epoch": 2.408333333333333,
+      "grad_norm": 0.08195162040998395,
+      "learning_rate": 1.1107105771648151e-05,
+      "loss": 2.353,
+      "step": 289
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.08267743479386988,
+      "learning_rate": 1.1009060681774236e-05,
+      "loss": 2.3274,
+      "step": 290
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.08798947281948663,
+      "learning_rate": 1.0911177120273537e-05,
+      "loss": 2.3404,
+      "step": 291
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.08828111892887862,
+      "learning_rate": 1.0813459965661489e-05,
+      "loss": 2.3348,
+      "step": 292
+    },
+    {
+      "epoch": 2.4416666666666664,
+      "grad_norm": 0.08102528742267785,
+      "learning_rate": 1.0715914088159789e-05,
+      "loss": 2.2863,
+      "step": 293
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0866645702075036,
+      "learning_rate": 1.06185443494537e-05,
+      "loss": 2.3357,
+      "step": 294
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.08290121294865929,
+      "learning_rate": 1.0521355602449723e-05,
+      "loss": 2.3537,
+      "step": 295
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.08332374744178081,
+      "learning_rate": 1.042435269103374e-05,
+      "loss": 2.3554,
+      "step": 296
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.08367195510948358,
+      "learning_rate": 1.0327540449829583e-05,
+      "loss": 2.3384,
+      "step": 297
+    },
+    {
+      "epoch": 2.4833333333333334,
+      "grad_norm": 0.08673119537467149,
+      "learning_rate": 1.0230923703958083e-05,
+      "loss": 2.2725,
+      "step": 298
+    },
+    {
+      "epoch": 2.4916666666666667,
+      "grad_norm": 0.08235186060858125,
+      "learning_rate": 1.0134507268796605e-05,
+      "loss": 2.328,
+      "step": 299
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08408079009588813,
+      "learning_rate": 1.0038295949739004e-05,
+      "loss": 2.3403,
+      "step": 300
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.3881967067718506,
+      "eval_runtime": 82.1489,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.316,
+      "step": 300
+    },
+    {
+      "epoch": 2.5083333333333333,
+      "grad_norm": 0.07909547450093556,
+      "learning_rate": 9.942294541956169e-06,
+      "loss": 2.3357,
+      "step": 301
+    },
+    {
+      "epoch": 2.5166666666666666,
+      "grad_norm": 0.08766753125589274,
+      "learning_rate": 9.846507830157e-06,
+      "loss": 2.2503,
+      "step": 302
+    },
+    {
+      "epoch": 2.525,
+      "grad_norm": 0.07987208695801865,
+      "learning_rate": 9.75094058834997e-06,
+      "loss": 2.3168,
+      "step": 303
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.08537107163629042,
+      "learning_rate": 9.655597579605152e-06,
+      "loss": 2.3036,
+      "step": 304
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.08251527677113132,
+      "learning_rate": 9.560483555816858e-06,
+      "loss": 2.3419,
+      "step": 305
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.08523777732696665,
+      "learning_rate": 9.465603257466792e-06,
+      "loss": 2.3449,
+      "step": 306
+    },
+    {
+      "epoch": 2.5583333333333336,
+      "grad_norm": 0.0848931418707024,
+      "learning_rate": 9.370961413387778e-06,
+      "loss": 2.2844,
+      "step": 307
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.08156484852737556,
+      "learning_rate": 9.27656274052809e-06,
+      "loss": 2.3485,
+      "step": 308
+    },
+    {
+      "epoch": 2.575,
+      "grad_norm": 0.08185057405642468,
+      "learning_rate": 9.182411943716344e-06,
+      "loss": 2.3748,
+      "step": 309
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.08210521440208327,
+      "learning_rate": 9.088513715427028e-06,
+      "loss": 2.376,
+      "step": 310
+    },
+    {
+      "epoch": 2.591666666666667,
+      "grad_norm": 0.08030540134328207,
+      "learning_rate": 8.9948727355466e-06,
+      "loss": 2.3196,
+      "step": 311
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.08216024303479584,
+      "learning_rate": 8.901493671140283e-06,
+      "loss": 2.3534,
+      "step": 312
+    },
+    {
+      "epoch": 2.6083333333333334,
+      "grad_norm": 0.08105902557687622,
+      "learning_rate": 8.808381176219426e-06,
+      "loss": 2.2729,
+      "step": 313
+    },
+    {
+      "epoch": 2.6166666666666667,
+      "grad_norm": 0.08410998796525411,
+      "learning_rate": 8.71553989150955e-06,
+      "loss": 2.3596,
+      "step": 314
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.08582437979635364,
+      "learning_rate": 8.622974444219076e-06,
+      "loss": 2.3063,
+      "step": 315
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.08419960708603666,
+      "learning_rate": 8.530689447808683e-06,
+      "loss": 2.3468,
+      "step": 316
+    },
+    {
+      "epoch": 2.6416666666666666,
+      "grad_norm": 0.08532017727647645,
+      "learning_rate": 8.438689501761387e-06,
+      "loss": 2.3378,
+      "step": 317
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.08544492639100988,
+      "learning_rate": 8.346979191353288e-06,
+      "loss": 2.2872,
+      "step": 318
+    },
+    {
+      "epoch": 2.658333333333333,
+      "grad_norm": 0.0825611786693761,
+      "learning_rate": 8.255563087425069e-06,
+      "loss": 2.3037,
+      "step": 319
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.07923900030264817,
+      "learning_rate": 8.164445746154141e-06,
+      "loss": 2.2746,
+      "step": 320
+    },
+    {
+      "epoch": 2.675,
+      "grad_norm": 0.0805988851220756,
+      "learning_rate": 8.073631708827614e-06,
+      "loss": 2.3116,
+      "step": 321
+    },
+    {
+      "epoch": 2.6833333333333336,
+      "grad_norm": 0.07902450485255898,
+      "learning_rate": 7.983125501615913e-06,
+      "loss": 2.3253,
+      "step": 322
+    },
+    {
+      "epoch": 2.6916666666666664,
+      "grad_norm": 0.08586994856844313,
+      "learning_rate": 7.892931635347223e-06,
+      "loss": 2.3636,
+      "step": 323
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.08029033935205021,
+      "learning_rate": 7.803054605282652e-06,
+      "loss": 2.3023,
+      "step": 324
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.08041087816983067,
+      "learning_rate": 7.713498890892208e-06,
+      "loss": 2.3629,
+      "step": 325
+    },
+    {
+      "epoch": 2.716666666666667,
+      "grad_norm": 0.08451031313730265,
+      "learning_rate": 7.624268955631531e-06,
+      "loss": 2.2625,
+      "step": 326
+    },
+    {
+      "epoch": 2.725,
+      "grad_norm": 0.07898217475608488,
+      "learning_rate": 7.53536924671942e-06,
+      "loss": 2.3106,
+      "step": 327
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.08283676255780481,
+      "learning_rate": 7.446804194916206e-06,
+      "loss": 2.3576,
+      "step": 328
+    },
+    {
+      "epoch": 2.7416666666666667,
+      "grad_norm": 0.08212231805524588,
+      "learning_rate": 7.358578214302908e-06,
+      "loss": 2.2791,
+      "step": 329
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.08251122557980495,
+      "learning_rate": 7.270695702061248e-06,
+      "loss": 2.3553,
+      "step": 330
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 2.387129783630371,
+      "eval_runtime": 81.7826,
+      "eval_samples_per_second": 5.013,
+      "eval_steps_per_second": 0.318,
+      "step": 330
+    },
+    {
+      "epoch": 2.7583333333333333,
+      "grad_norm": 0.08008513950564178,
+      "learning_rate": 7.1831610382544856e-06,
+      "loss": 2.2737,
+      "step": 331
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.08378397772580942,
+      "learning_rate": 7.095978585609125e-06,
+      "loss": 2.362,
+      "step": 332
+    },
+    {
+      "epoch": 2.775,
+      "grad_norm": 0.08519607549475229,
+      "learning_rate": 7.009152689297463e-06,
+      "loss": 2.2601,
+      "step": 333
+    },
+    {
+      "epoch": 2.783333333333333,
+      "grad_norm": 0.08038464346170233,
+      "learning_rate": 6.9226876767210355e-06,
+      "loss": 2.3434,
+      "step": 334
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.08107258257971683,
+      "learning_rate": 6.83658785729493e-06,
+      "loss": 2.2608,
+      "step": 335
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0801095446046233,
+      "learning_rate": 6.750857522233032e-06,
+      "loss": 2.3562,
+      "step": 336
+    },
+    {
+      "epoch": 2.8083333333333336,
+      "grad_norm": 0.08032953635285699,
+      "learning_rate": 6.665500944334116e-06,
+      "loss": 2.3473,
+      "step": 337
+    },
+    {
+      "epoch": 2.8166666666666664,
+      "grad_norm": 0.08165787890975398,
+      "learning_rate": 6.580522377768902e-06,
+      "loss": 2.3662,
+      "step": 338
+    },
+    {
+      "epoch": 2.825,
+      "grad_norm": 0.08186138228862638,
+      "learning_rate": 6.495926057868045e-06,
+      "loss": 2.3611,
+      "step": 339
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.08409693406516083,
+      "learning_rate": 6.4117162009110105e-06,
+      "loss": 2.3014,
+      "step": 340
+    },
+    {
+      "epoch": 2.841666666666667,
+      "grad_norm": 0.08426043237254878,
+      "learning_rate": 6.327897003915982e-06,
+      "loss": 2.3556,
+      "step": 341
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.07860767709618154,
+      "learning_rate": 6.244472644430632e-06,
+      "loss": 2.3986,
+      "step": 342
+    },
+    {
+      "epoch": 2.8583333333333334,
+      "grad_norm": 0.07913910815896576,
+      "learning_rate": 6.161447280323948e-06,
+      "loss": 2.3041,
+      "step": 343
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.0834686817566552,
+      "learning_rate": 6.078825049578985e-06,
+      "loss": 2.2694,
+      "step": 344
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.09464173421182612,
+      "learning_rate": 5.996610070086646e-06,
+      "loss": 2.3291,
+      "step": 345
+    },
+    {
+      "epoch": 2.8833333333333333,
+      "grad_norm": 0.08924525286993587,
+      "learning_rate": 5.914806439440443e-06,
+      "loss": 2.2425,
+      "step": 346
+    },
+    {
+      "epoch": 2.8916666666666666,
+      "grad_norm": 0.07984144031222275,
+      "learning_rate": 5.833418234732248e-06,
+      "loss": 2.3212,
+      "step": 347
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.08119999485058818,
+      "learning_rate": 5.752449512349119e-06,
+      "loss": 2.3043,
+      "step": 348
+    },
+    {
+      "epoch": 2.908333333333333,
+      "grad_norm": 0.08130268904604636,
+      "learning_rate": 5.671904307771115e-06,
+      "loss": 2.3431,
+      "step": 349
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.0886368269447557,
+      "learning_rate": 5.591786635370193e-06,
+      "loss": 2.2584,
+      "step": 350
+    },
+    {
+      "epoch": 2.925,
+      "grad_norm": 0.08449560278602129,
+      "learning_rate": 5.5121004882100805e-06,
+      "loss": 2.2614,
+      "step": 351
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.0877133422168611,
+      "learning_rate": 5.4328498378473245e-06,
+      "loss": 2.3467,
+      "step": 352
+    },
+    {
+      "epoch": 2.9416666666666664,
+      "grad_norm": 0.0829503072213313,
+      "learning_rate": 5.354038634133295e-06,
+      "loss": 2.2975,
+      "step": 353
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.08436627929472401,
+      "learning_rate": 5.27567080501735e-06,
+      "loss": 2.3115,
+      "step": 354
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.08048623155801396,
+      "learning_rate": 5.197750256351076e-06,
+      "loss": 2.2584,
+      "step": 355
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.08109596859654204,
+      "learning_rate": 5.120280871693596e-06,
+      "loss": 2.3677,
+      "step": 356
+    },
+    {
+      "epoch": 2.975,
+      "grad_norm": 0.081013576151029,
+      "learning_rate": 5.0432665121180266e-06,
+      "loss": 2.3585,
+      "step": 357
+    },
+    {
+      "epoch": 2.9833333333333334,
+      "grad_norm": 0.08546479543984016,
+      "learning_rate": 4.966711016019037e-06,
+      "loss": 2.303,
+      "step": 358
+    },
+    {
+      "epoch": 2.9916666666666667,
+      "grad_norm": 0.08245660024002954,
+      "learning_rate": 4.890618198921555e-06,
+      "loss": 2.3149,
+      "step": 359
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08512068224524219,
+      "learning_rate": 4.814991853290595e-06,
+      "loss": 2.2894,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.386331081390381,
+      "eval_runtime": 82.119,
+      "eval_samples_per_second": 4.993,
+      "eval_steps_per_second": 0.317,
+      "step": 360
+    },
+    {
+      "epoch": 3.0083333333333333,
+      "grad_norm": 0.08558372235748295,
+      "learning_rate": 4.739835748342228e-06,
+      "loss": 2.2984,
+      "step": 361
+    },
+    {
+      "epoch": 3.0166666666666666,
+      "grad_norm": 0.08035880067291258,
+      "learning_rate": 4.665153629855744e-06,
+      "loss": 2.3033,
+      "step": 362
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 0.07959465533779843,
+      "learning_rate": 4.5909492199869445e-06,
+      "loss": 2.3507,
+      "step": 363
+    },
+    {
+      "epoch": 3.033333333333333,
+      "grad_norm": 0.08267174156962717,
+      "learning_rate": 4.517226217082652e-06,
+      "loss": 2.3425,
+      "step": 364
+    },
+    {
+      "epoch": 3.0416666666666665,
+      "grad_norm": 0.07991572961673732,
+      "learning_rate": 4.44398829549637e-06,
+      "loss": 2.3261,
+      "step": 365
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.07847568885444599,
+      "learning_rate": 4.371239105405148e-06,
+      "loss": 2.3477,
+      "step": 366
+    },
+    {
+      "epoch": 3.058333333333333,
+      "grad_norm": 0.08038194746327948,
+      "learning_rate": 4.29898227262767e-06,
+      "loss": 2.2698,
+      "step": 367
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.08253718833393997,
+      "learning_rate": 4.22722139844353e-06,
+      "loss": 2.3652,
+      "step": 368
+    },
+    {
+      "epoch": 3.075,
+      "grad_norm": 0.08516413003066334,
+      "learning_rate": 4.1559600594137686e-06,
+      "loss": 2.3331,
+      "step": 369
+    },
+    {
+      "epoch": 3.0833333333333335,
+      "grad_norm": 0.07953660852824361,
+      "learning_rate": 4.085201807202586e-06,
+      "loss": 2.3689,
+      "step": 370
+    },
+    {
+      "epoch": 3.091666666666667,
+      "grad_norm": 0.08238213712670353,
+      "learning_rate": 4.014950168400341e-06,
+      "loss": 2.308,
+      "step": 371
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.08283454952311556,
+      "learning_rate": 3.945208644347803e-06,
+      "loss": 2.2875,
+      "step": 372
+    },
+    {
+      "epoch": 3.1083333333333334,
+      "grad_norm": 0.08123988730396041,
+      "learning_rate": 3.875980710961609e-06,
+      "loss": 2.2607,
+      "step": 373
+    },
+    {
+      "epoch": 3.1166666666666667,
+      "grad_norm": 0.08112099690166064,
+      "learning_rate": 3.8072698185610614e-06,
+      "loss": 2.3591,
+      "step": 374
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.0792957148134827,
+      "learning_rate": 3.7390793916961342e-06,
+      "loss": 2.3218,
+      "step": 375
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.08349920233794074,
+      "learning_rate": 3.671412828976812e-06,
+      "loss": 2.298,
+      "step": 376
+    },
+    {
+      "epoch": 3.1416666666666666,
+      "grad_norm": 0.07899532707809945,
+      "learning_rate": 3.604273502903688e-06,
+      "loss": 2.3226,
+      "step": 377
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.08573888823467567,
+      "learning_rate": 3.537664759699903e-06,
+      "loss": 2.316,
+      "step": 378
+    },
+    {
+      "epoch": 3.158333333333333,
+      "grad_norm": 0.08115043743007767,
+      "learning_rate": 3.4715899191443483e-06,
+      "loss": 2.2912,
+      "step": 379
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.08268384127740624,
+      "learning_rate": 3.40605227440621e-06,
+      "loss": 2.2777,
+      "step": 380
+    },
+    {
+      "epoch": 3.175,
+      "grad_norm": 0.08106251418915893,
+      "learning_rate": 3.3410550918808443e-06,
+      "loss": 2.3159,
+      "step": 381
+    },
+    {
+      "epoch": 3.183333333333333,
+      "grad_norm": 0.08286464503073644,
+      "learning_rate": 3.276601611026974e-06,
+      "loss": 2.3071,
+      "step": 382
+    },
+    {
+      "epoch": 3.191666666666667,
+      "grad_norm": 0.08199773880110967,
+      "learning_rate": 3.2126950442052483e-06,
+      "loss": 2.3043,
+      "step": 383
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.08187041229316819,
+      "learning_rate": 3.149338576518116e-06,
+      "loss": 2.2955,
+      "step": 384
+    },
+    {
+      "epoch": 3.2083333333333335,
+      "grad_norm": 0.08220875126507468,
+      "learning_rate": 3.0865353656511014e-06,
+      "loss": 2.3141,
+      "step": 385
+    },
+    {
+      "epoch": 3.216666666666667,
+      "grad_norm": 0.08353220855881248,
+      "learning_rate": 3.024288541715413e-06,
+      "loss": 2.3677,
+      "step": 386
+    },
+    {
+      "epoch": 3.225,
+      "grad_norm": 0.07903966810055228,
+      "learning_rate": 2.9626012070919357e-06,
+      "loss": 2.3359,
+      "step": 387
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.08190032494339015,
+      "learning_rate": 2.901476436276628e-06,
+      "loss": 2.2796,
+      "step": 388
+    },
+    {
+      "epoch": 3.2416666666666667,
+      "grad_norm": 0.08161746077320213,
+      "learning_rate": 2.840917275727264e-06,
+      "loss": 2.3368,
+      "step": 389
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.0815574105377222,
+      "learning_rate": 2.780926743711611e-06,
+      "loss": 2.2746,
+      "step": 390
+    },
+    {
+      "epoch": 3.25,
+      "eval_loss": 2.385850667953491,
+      "eval_runtime": 83.443,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 0.312,
+      "step": 390
+    },
+    {
+      "epoch": 3.2583333333333333,
+      "grad_norm": 0.07940368361833833,
+      "learning_rate": 2.7215078301570005e-06,
+      "loss": 2.3239,
+      "step": 391
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.0789092720450855,
+      "learning_rate": 2.6626634965013064e-06,
+      "loss": 2.3485,
+      "step": 392
+    },
+    {
+      "epoch": 3.275,
+      "grad_norm": 0.07860086067453795,
+      "learning_rate": 2.604396675545354e-06,
+      "loss": 2.3022,
+      "step": 393
+    },
+    {
+      "epoch": 3.283333333333333,
+      "grad_norm": 0.0827013915236191,
+      "learning_rate": 2.546710271306732e-06,
+      "loss": 2.3382,
+      "step": 394
+    },
+    {
+      "epoch": 3.2916666666666665,
+      "grad_norm": 0.08392337720938575,
+      "learning_rate": 2.4896071588750746e-06,
+      "loss": 2.2495,
+      "step": 395
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.07896168168173961,
+      "learning_rate": 2.433090184268755e-06,
+      "loss": 2.3413,
+      "step": 396
+    },
+    {
+      "epoch": 3.3083333333333336,
+      "grad_norm": 0.08513092869669563,
+      "learning_rate": 2.3771621642930495e-06,
+      "loss": 2.32,
+      "step": 397
+    },
+    {
+      "epoch": 3.3166666666666664,
+      "grad_norm": 0.08158164066376497,
+      "learning_rate": 2.3218258863997483e-06,
+      "loss": 2.3159,
+      "step": 398
+    },
+    {
+      "epoch": 3.325,
+      "grad_norm": 0.07850245543386242,
+      "learning_rate": 2.2670841085482114e-06,
+      "loss": 2.2892,
+      "step": 399
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.07948289924872026,
+      "learning_rate": 2.2129395590679325e-06,
+      "loss": 2.3183,
+      "step": 400
+    },
+    {
+      "epoch": 3.341666666666667,
+      "grad_norm": 0.08268427645613528,
+      "learning_rate": 2.1593949365225455e-06,
+      "loss": 2.3455,
+      "step": 401
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.0805567434916959,
+      "learning_rate": 2.1064529095753457e-06,
+      "loss": 2.323,
+      "step": 402
+    },
+    {
+      "epoch": 3.3583333333333334,
+      "grad_norm": 0.08055664155765571,
+      "learning_rate": 2.054116116856257e-06,
+      "loss": 2.3334,
+      "step": 403
+    },
+    {
+      "epoch": 3.3666666666666667,
+      "grad_norm": 0.082279494119965,
+      "learning_rate": 2.0023871668303433e-06,
+      "loss": 2.2938,
+      "step": 404
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.08252463940578399,
+      "learning_rate": 1.9512686376678015e-06,
+      "loss": 2.2965,
+      "step": 405
+    },
+    {
+      "epoch": 3.3833333333333333,
+      "grad_norm": 0.08541294452389535,
+      "learning_rate": 1.9007630771154532e-06,
+      "loss": 2.2363,
+      "step": 406
+    },
+    {
+      "epoch": 3.3916666666666666,
+      "grad_norm": 0.08261328178534114,
+      "learning_rate": 1.850873002369778e-06,
+      "loss": 2.3175,
+      "step": 407
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.0830385045862884,
+      "learning_rate": 1.8016008999514467e-06,
+      "loss": 2.2871,
+      "step": 408
+    },
+    {
+      "epoch": 3.408333333333333,
+      "grad_norm": 0.08146738848250283,
+      "learning_rate": 1.7529492255814008e-06,
+      "loss": 2.3198,
+      "step": 409
+    },
+    {
+      "epoch": 3.4166666666666665,
+      "grad_norm": 0.0827275148559704,
+      "learning_rate": 1.704920404058452e-06,
+      "loss": 2.2888,
+      "step": 410
+    },
+    {
+      "epoch": 3.425,
+      "grad_norm": 0.0803715450561763,
+      "learning_rate": 1.6575168291384352e-06,
+      "loss": 2.3405,
+      "step": 411
+    },
+    {
+      "epoch": 3.4333333333333336,
+      "grad_norm": 0.07862601957152224,
+      "learning_rate": 1.6107408634149068e-06,
+      "loss": 2.2978,
+      "step": 412
+    },
+    {
+      "epoch": 3.4416666666666664,
+      "grad_norm": 0.0797822244213719,
+      "learning_rate": 1.5645948382013898e-06,
+      "loss": 2.3701,
+      "step": 413
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 0.07749237550393802,
+      "learning_rate": 1.5190810534151723e-06,
+      "loss": 2.3616,
+      "step": 414
+    },
+    {
+      "epoch": 3.4583333333333335,
+      "grad_norm": 0.07924907970443268,
+      "learning_rate": 1.474201777462696e-06,
+      "loss": 2.2771,
+      "step": 415
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.07962985015963248,
+      "learning_rate": 1.4299592471264814e-06,
+      "loss": 2.3482,
+      "step": 416
+    },
+    {
+      "epoch": 3.475,
+      "grad_norm": 0.08046145953371857,
+      "learning_rate": 1.3863556674536668e-06,
+      "loss": 2.2809,
+      "step": 417
+    },
+    {
+      "epoch": 3.4833333333333334,
+      "grad_norm": 0.08300783210234308,
+      "learning_rate": 1.3433932116460928e-06,
+      "loss": 2.257,
+      "step": 418
+    },
+    {
+      "epoch": 3.4916666666666667,
+      "grad_norm": 0.07975202760505942,
+      "learning_rate": 1.3010740209519938e-06,
+      "loss": 2.2887,
+      "step": 419
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.08236525138293024,
+      "learning_rate": 1.2594002045592805e-06,
+      "loss": 2.3372,
+      "step": 420
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 2.385662794113159,
+      "eval_runtime": 83.0808,
+      "eval_samples_per_second": 4.935,
+      "eval_steps_per_second": 0.313,
+      "step": 420
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.210852912057549e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-420/training_args.bin b/checkpoint-420/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e71e9ef0b364c8b803828c31c7b34cd4f7001af
--- /dev/null
+++ b/checkpoint-420/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
+size 8504
diff --git a/checkpoint-420/zero_to_fp32.py b/checkpoint-420/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..0e759146cadd92ddfefab3680146c2bd6a2b5c04
--- /dev/null
+++ b/checkpoint-420/zero_to_fp32.py
@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/checkpoint-480/adapter_config.json b/checkpoint-480/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3d1dc2dbb47a92750a96471a799fbaf0e686ba9d
--- /dev/null
+++ b/checkpoint-480/adapter_config.json
@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-480/adapter_model.safetensors b/checkpoint-480/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0468018290f56f05a61b7c61f149b4b35460ff46
--- /dev/null
+++ b/checkpoint-480/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f43dab069cfdcacbd2443671997ce7738bb6dc3830c63fa9d0e4d28a5903ffc
+size 486600536
diff --git a/checkpoint-480/latest b/checkpoint-480/latest
new file mode 100644
index 0000000000000000000000000000000000000000..417da84690337adfc654fe11aa696251226ad7ca
--- /dev/null
+++ b/checkpoint-480/latest
@@ -0,0 +1 @@
+global_step480
\ No newline at end of file
diff --git a/checkpoint-480/rng_state_0.pth b/checkpoint-480/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f7989e2388d1493e7cd8168a1bfa1e7eb3ae5233
--- /dev/null
+++ b/checkpoint-480/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1f21026275687a9e2b5ae9fea95182a54e8af40224677482c41ec3d2663b09
+size 15024
diff --git a/checkpoint-480/rng_state_1.pth b/checkpoint-480/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ee731fab6225eafa195f29cb61605d0518a847d
--- /dev/null
+++ b/checkpoint-480/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91fc6ac62a71e41b931c39aec3709464b7c6d441f89f54ded1cc0e0e800ef0a
+size 15024
diff --git a/checkpoint-480/rng_state_2.pth b/checkpoint-480/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ad39e749822fb192d5af87931e232c760d7c2bf7
--- /dev/null
+++ b/checkpoint-480/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44237fb3cacd6e70f1b22605c6649a067f3bcbeaabf7a9b502704cc90341fbc
+size 15024
diff --git a/checkpoint-480/rng_state_3.pth b/checkpoint-480/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..662e435fb6e1d62f6a9074ea7f3897dc73f7fe93
--- /dev/null
+++ b/checkpoint-480/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c58b3ad21e246a883e92a2298ad62fe7606885f6110c0866f4d3949e5c4af82
+size 15024
diff --git a/checkpoint-480/scheduler.pt b/checkpoint-480/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61db6e39b53b33d90ecf2fdf72074ed0c0668808
--- /dev/null
+++ b/checkpoint-480/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f47f08a47a71169a2f267bfc89f4ceb4882943de27e166bc859280fff991882
+size 1064
diff --git a/checkpoint-480/special_tokens_map.json b/checkpoint-480/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9414f9e36eb995388775c9e63e5588313e7c41d3
--- /dev/null
+++ b/checkpoint-480/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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-480/tokenizer.json b/checkpoint-480/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ae94f3cc49ae02ddb8b100e69ba51719000fa01
--- /dev/null
+++ b/checkpoint-480/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884
diff --git a/checkpoint-480/tokenizer_config.json b/checkpoint-480/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c131c4a0f2e6b6f0b564da934a01b86750c6d347
--- /dev/null
+++ b/checkpoint-480/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": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/checkpoint-480/trainer_state.json b/checkpoint-480/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..337aa00b24387b4444497302d1c94c13ed94cc33
--- /dev/null
+++ b/checkpoint-480/trainer_state.json
@@ -0,0 +1,3530 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 30,
+  "global_step": 480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.9462232657835241,
+      "learning_rate": 8.142857142857143e-07,
+      "loss": 2.5443,
+      "step": 1
+    },
+    {
+      "epoch": 0.008333333333333333,
+      "eval_loss": 2.5896365642547607,
+      "eval_runtime": 96.0059,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 0.271,
+      "step": 1
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.9597143397960513,
+      "learning_rate": 1.6285714285714286e-06,
+      "loss": 2.5524,
+      "step": 2
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.9246258453027174,
+      "learning_rate": 2.442857142857143e-06,
+      "loss": 2.5411,
+      "step": 3
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.9822285829186661,
+      "learning_rate": 3.2571428571428572e-06,
+      "loss": 2.5518,
+      "step": 4
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.9044329068814566,
+      "learning_rate": 4.071428571428572e-06,
+      "loss": 2.4922,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9131300887744053,
+      "learning_rate": 4.885714285714286e-06,
+      "loss": 2.5713,
+      "step": 6
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.8336298309675122,
+      "learning_rate": 5.7000000000000005e-06,
+      "loss": 2.4959,
+      "step": 7
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.810775409605909,
+      "learning_rate": 6.5142857142857145e-06,
+      "loss": 2.4943,
+      "step": 8
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.6993505055921954,
+      "learning_rate": 7.3285714285714285e-06,
+      "loss": 2.5022,
+      "step": 9
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.5909140859664664,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 2.468,
+      "step": 10
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.5464791893738283,
+      "learning_rate": 8.957142857142857e-06,
+      "loss": 2.5203,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.41153668995149084,
+      "learning_rate": 9.771428571428571e-06,
+      "loss": 2.4912,
+      "step": 12
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.35433353277028035,
+      "learning_rate": 1.0585714285714287e-05,
+      "loss": 2.4467,
+      "step": 13
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.27579908222756766,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 2.4599,
+      "step": 14
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.22636758420678307,
+      "learning_rate": 1.2214285714285715e-05,
+      "loss": 2.4357,
+      "step": 15
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.22309908436920517,
+      "learning_rate": 1.3028571428571429e-05,
+      "loss": 2.368,
+      "step": 16
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.2384290311446137,
+      "learning_rate": 1.3842857142857143e-05,
+      "loss": 2.4054,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2279055472006466,
+      "learning_rate": 1.4657142857142857e-05,
+      "loss": 2.4162,
+      "step": 18
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.24659885813398136,
+      "learning_rate": 1.547142857142857e-05,
+      "loss": 2.4109,
+      "step": 19
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.21920560481126147,
+      "learning_rate": 1.6285714285714287e-05,
+      "loss": 2.4344,
+      "step": 20
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.21340860355678012,
+      "learning_rate": 1.71e-05,
+      "loss": 2.4532,
+      "step": 21
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.1775246176788835,
+      "learning_rate": 1.7914285714285715e-05,
+      "loss": 2.4398,
+      "step": 22
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.15469100364725502,
+      "learning_rate": 1.872857142857143e-05,
+      "loss": 2.4275,
+      "step": 23
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1261136620302219,
+      "learning_rate": 1.9542857142857143e-05,
+      "loss": 2.3855,
+      "step": 24
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.1251566381945981,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 2.4008,
+      "step": 25
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.12280228065778742,
+      "learning_rate": 2.1171428571428574e-05,
+      "loss": 2.4086,
+      "step": 26
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.1362748806421765,
+      "learning_rate": 2.1985714285714286e-05,
+      "loss": 2.3642,
+      "step": 27
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.12370426656542512,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 2.4168,
+      "step": 28
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.12077140199925576,
+      "learning_rate": 2.3614285714285718e-05,
+      "loss": 2.3502,
+      "step": 29
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.10854652278245232,
+      "learning_rate": 2.442857142857143e-05,
+      "loss": 2.323,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 2.4455511569976807,
+      "eval_runtime": 82.5732,
+      "eval_samples_per_second": 4.965,
+      "eval_steps_per_second": 0.315,
+      "step": 30
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.10286886191993252,
+      "learning_rate": 2.5242857142857142e-05,
+      "loss": 2.4007,
+      "step": 31
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.09687340891245565,
+      "learning_rate": 2.6057142857142858e-05,
+      "loss": 2.4088,
+      "step": 32
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.09653492248714694,
+      "learning_rate": 2.6871428571428574e-05,
+      "loss": 2.3906,
+      "step": 33
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.09022900019263645,
+      "learning_rate": 2.7685714285714286e-05,
+      "loss": 2.4065,
+      "step": 34
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.0912409242342349,
+      "learning_rate": 2.85e-05,
+      "loss": 2.3699,
+      "step": 35
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09592020125185927,
+      "learning_rate": 2.8499644890093217e-05,
+      "loss": 2.3587,
+      "step": 36
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.0907084429462166,
+      "learning_rate": 2.8498579578071537e-05,
+      "loss": 2.4259,
+      "step": 37
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.09390099422567517,
+      "learning_rate": 2.8496804117030106e-05,
+      "loss": 2.3232,
+      "step": 38
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.08704027284958313,
+      "learning_rate": 2.849431859545787e-05,
+      "loss": 2.4027,
+      "step": 39
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.08787482564111378,
+      "learning_rate": 2.849112313723319e-05,
+      "loss": 2.3827,
+      "step": 40
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.08422520058818864,
+      "learning_rate": 2.8487217901617672e-05,
+      "loss": 2.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.07979320980153469,
+      "learning_rate": 2.84826030832482e-05,
+      "loss": 2.3519,
+      "step": 42
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.07814774416810645,
+      "learning_rate": 2.8477278912127266e-05,
+      "loss": 2.3708,
+      "step": 43
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.07237049854036091,
+      "learning_rate": 2.847124565361149e-05,
+      "loss": 2.388,
+      "step": 44
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.07354258492789081,
+      "learning_rate": 2.8464503608398385e-05,
+      "loss": 2.3586,
+      "step": 45
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.0771281784161838,
+      "learning_rate": 2.845705311251141e-05,
+      "loss": 2.3993,
+      "step": 46
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.0763264062020341,
+      "learning_rate": 2.844889453728318e-05,
+      "loss": 2.3838,
+      "step": 47
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07082143620733677,
+      "learning_rate": 2.8440028289336977e-05,
+      "loss": 2.3628,
+      "step": 48
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 0.0715578975320661,
+      "learning_rate": 2.8430454810566477e-05,
+      "loss": 2.361,
+      "step": 49
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.06881630985450242,
+      "learning_rate": 2.8420174578113747e-05,
+      "loss": 2.4392,
+      "step": 50
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.0689279893077156,
+      "learning_rate": 2.8409188104345426e-05,
+      "loss": 2.3519,
+      "step": 51
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.07069081407018309,
+      "learning_rate": 2.8397495936827232e-05,
+      "loss": 2.3981,
+      "step": 52
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 0.07092917277421104,
+      "learning_rate": 2.8385098658296637e-05,
+      "loss": 2.355,
+      "step": 53
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0703607034709259,
+      "learning_rate": 2.8371996886633843e-05,
+      "loss": 2.3793,
+      "step": 54
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.07124199690967324,
+      "learning_rate": 2.8358191274830974e-05,
+      "loss": 2.4275,
+      "step": 55
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.07099804346309355,
+      "learning_rate": 2.8343682510959552e-05,
+      "loss": 2.3323,
+      "step": 56
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.06967632308939245,
+      "learning_rate": 2.8328471318136165e-05,
+      "loss": 2.3883,
+      "step": 57
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.07156300179553134,
+      "learning_rate": 2.831255845448647e-05,
+      "loss": 2.3298,
+      "step": 58
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 0.0704201532980033,
+      "learning_rate": 2.8295944713107387e-05,
+      "loss": 2.331,
+      "step": 59
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.06794782460291071,
+      "learning_rate": 2.8278630922027563e-05,
+      "loss": 2.3776,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.4216628074645996,
+      "eval_runtime": 82.3879,
+      "eval_samples_per_second": 4.976,
+      "eval_steps_per_second": 0.316,
+      "step": 60
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 0.07045949082426937,
+      "learning_rate": 2.8260617944166123e-05,
+      "loss": 2.3319,
+      "step": 61
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 0.0702234192794877,
+      "learning_rate": 2.824190667728965e-05,
+      "loss": 2.3647,
+      "step": 62
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.06946814214632402,
+      "learning_rate": 2.8222498053967434e-05,
+      "loss": 2.3967,
+      "step": 63
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.06563265580127577,
+      "learning_rate": 2.8202393041525005e-05,
+      "loss": 2.3863,
+      "step": 64
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0723770670150652,
+      "learning_rate": 2.8181592641995933e-05,
+      "loss": 2.3823,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.06870429029917037,
+      "learning_rate": 2.8160097892071847e-05,
+      "loss": 2.3241,
+      "step": 66
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 0.08615444480664787,
+      "learning_rate": 2.8137909863050806e-05,
+      "loss": 2.3504,
+      "step": 67
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.06980417460436542,
+      "learning_rate": 2.8115029660783887e-05,
+      "loss": 2.3762,
+      "step": 68
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.0691283200064781,
+      "learning_rate": 2.809145842562007e-05,
+      "loss": 2.3202,
+      "step": 69
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.06434433998677834,
+      "learning_rate": 2.8067197332349406e-05,
+      "loss": 2.4117,
+      "step": 70
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 0.06712521054811822,
+      "learning_rate": 2.8042247590144472e-05,
+      "loss": 2.4234,
+      "step": 71
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.07781170630767965,
+      "learning_rate": 2.8016610442500087e-05,
+      "loss": 2.3614,
+      "step": 72
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 0.07179449259884696,
+      "learning_rate": 2.7990287167171357e-05,
+      "loss": 2.327,
+      "step": 73
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.0666012429917219,
+      "learning_rate": 2.7963279076109976e-05,
+      "loss": 2.3606,
+      "step": 74
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07042352420672252,
+      "learning_rate": 2.7935587515398855e-05,
+      "loss": 2.387,
+      "step": 75
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.07141219809062525,
+      "learning_rate": 2.7907213865185014e-05,
+      "loss": 2.3975,
+      "step": 76
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 0.07530038535140655,
+      "learning_rate": 2.787815953961081e-05,
+      "loss": 2.3975,
+      "step": 77
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.06873021297298251,
+      "learning_rate": 2.784842598674345e-05,
+      "loss": 2.3724,
+      "step": 78
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 0.06853494667979494,
+      "learning_rate": 2.781801468850282e-05,
+      "loss": 2.3994,
+      "step": 79
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.07164446612343163,
+      "learning_rate": 2.778692716058762e-05,
+      "loss": 2.3448,
+      "step": 80
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.07112624750325054,
+      "learning_rate": 2.7755164952399844e-05,
+      "loss": 2.2984,
+      "step": 81
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.07679055297227524,
+      "learning_rate": 2.7722729646967527e-05,
+      "loss": 2.3699,
+      "step": 82
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 0.07270378630883641,
+      "learning_rate": 2.768962286086587e-05,
+      "loss": 2.3436,
+      "step": 83
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06869524209312625,
+      "learning_rate": 2.7655846244136654e-05,
+      "loss": 2.3856,
+      "step": 84
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.07006104211903366,
+      "learning_rate": 2.762140148020602e-05,
+      "loss": 2.3852,
+      "step": 85
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.07264285304887648,
+      "learning_rate": 2.758629028580055e-05,
+      "loss": 2.3834,
+      "step": 86
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.07253530482477301,
+      "learning_rate": 2.7550514410861718e-05,
+      "loss": 2.3573,
+      "step": 87
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.07265955522289944,
+      "learning_rate": 2.751407563845866e-05,
+      "loss": 2.3163,
+      "step": 88
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 0.07374626234739601,
+      "learning_rate": 2.747697578469931e-05,
+      "loss": 2.3851,
+      "step": 89
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07255481420091238,
+      "learning_rate": 2.7439216698639904e-05,
+      "loss": 2.3345,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 2.4115521907806396,
+      "eval_runtime": 82.0248,
+      "eval_samples_per_second": 4.998,
+      "eval_steps_per_second": 0.317,
+      "step": 90
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 0.06817548300510701,
+      "learning_rate": 2.7400800262192788e-05,
+      "loss": 2.3449,
+      "step": 91
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.07336990573663302,
+      "learning_rate": 2.7361728390032657e-05,
+      "loss": 2.3448,
+      "step": 92
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.07822885886131264,
+      "learning_rate": 2.732200302950111e-05,
+      "loss": 2.3217,
+      "step": 93
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.07296512071361201,
+      "learning_rate": 2.728162616050959e-05,
+      "loss": 2.3329,
+      "step": 94
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.07367928865175823,
+      "learning_rate": 2.724059979544072e-05,
+      "loss": 2.3208,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.07504139519989858,
+      "learning_rate": 2.719892597904801e-05,
+      "loss": 2.3483,
+      "step": 96
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 0.06790757702451031,
+      "learning_rate": 2.7156606788353906e-05,
+      "loss": 2.4128,
+      "step": 97
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.07011160737870108,
+      "learning_rate": 2.7113644332546336e-05,
+      "loss": 2.3832,
+      "step": 98
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.08077329808935288,
+      "learning_rate": 2.707004075287352e-05,
+      "loss": 2.3308,
+      "step": 99
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.0719496280235162,
+      "learning_rate": 2.7025798222537306e-05,
+      "loss": 2.3254,
+      "step": 100
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 0.07275409855582728,
+      "learning_rate": 2.698091894658483e-05,
+      "loss": 2.3967,
+      "step": 101
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.07201531734077336,
+      "learning_rate": 2.693540516179861e-05,
+      "loss": 2.3346,
+      "step": 102
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 0.0765467775604243,
+      "learning_rate": 2.6889259136585094e-05,
+      "loss": 2.3336,
+      "step": 103
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.077223728318478,
+      "learning_rate": 2.6842483170861568e-05,
+      "loss": 2.3313,
+      "step": 104
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.07639332869289207,
+      "learning_rate": 2.6795079595941553e-05,
+      "loss": 2.4008,
+      "step": 105
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 0.07440505813328589,
+      "learning_rate": 2.6747050774418605e-05,
+      "loss": 2.3425,
+      "step": 106
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 0.06937810484842656,
+      "learning_rate": 2.6698399100048556e-05,
+      "loss": 2.3349,
+      "step": 107
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07336400555418392,
+      "learning_rate": 2.6649126997630225e-05,
+      "loss": 2.3792,
+      "step": 108
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 0.07442564570941794,
+      "learning_rate": 2.6599236922884547e-05,
+      "loss": 2.3683,
+      "step": 109
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.07470689463768693,
+      "learning_rate": 2.65487313623322e-05,
+      "loss": 2.3036,
+      "step": 110
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.07096997017300663,
+      "learning_rate": 2.649761283316966e-05,
+      "loss": 2.3682,
+      "step": 111
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.07511821034386772,
+      "learning_rate": 2.6445883883143744e-05,
+      "loss": 2.3346,
+      "step": 112
+    },
+    {
+      "epoch": 0.9416666666666667,
+      "grad_norm": 0.07057540374817312,
+      "learning_rate": 2.639354709042466e-05,
+      "loss": 2.3502,
+      "step": 113
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.07300364605060353,
+      "learning_rate": 2.6340605063477456e-05,
+      "loss": 2.3711,
+      "step": 114
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.06925480258849577,
+      "learning_rate": 2.628706044093207e-05,
+      "loss": 2.3816,
+      "step": 115
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.0705107307569524,
+      "learning_rate": 2.623291589145179e-05,
+      "loss": 2.2958,
+      "step": 116
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.07331112076487026,
+      "learning_rate": 2.6178174113600252e-05,
+      "loss": 2.3279,
+      "step": 117
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.06780655482074792,
+      "learning_rate": 2.612283783570695e-05,
+      "loss": 2.4117,
+      "step": 118
+    },
+    {
+      "epoch": 0.9916666666666667,
+      "grad_norm": 0.07485055181125701,
+      "learning_rate": 2.606690981573125e-05,
+      "loss": 2.303,
+      "step": 119
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07276467760742707,
+      "learning_rate": 2.6010392841124932e-05,
+      "loss": 2.3608,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4049572944641113,
+      "eval_runtime": 82.3343,
+      "eval_samples_per_second": 4.98,
+      "eval_steps_per_second": 0.316,
+      "step": 120
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 0.07548790321925977,
+      "learning_rate": 2.5953289728693274e-05,
+      "loss": 2.3185,
+      "step": 121
+    },
+    {
+      "epoch": 1.0166666666666666,
+      "grad_norm": 0.0730570698984131,
+      "learning_rate": 2.5895603324454647e-05,
+      "loss": 2.2877,
+      "step": 122
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.07345139782586493,
+      "learning_rate": 2.5837336503498694e-05,
+      "loss": 2.2836,
+      "step": 123
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.07299378924326991,
+      "learning_rate": 2.5778492169843003e-05,
+      "loss": 2.3436,
+      "step": 124
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.07154250149880004,
+      "learning_rate": 2.5719073256288394e-05,
+      "loss": 2.3822,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0720748804004234,
+      "learning_rate": 2.565908272427274e-05,
+      "loss": 2.2708,
+      "step": 126
+    },
+    {
+      "epoch": 1.0583333333333333,
+      "grad_norm": 0.07269892036621302,
+      "learning_rate": 2.5598523563723373e-05,
+      "loss": 2.3377,
+      "step": 127
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0756770863265576,
+      "learning_rate": 2.5537398792908062e-05,
+      "loss": 2.352,
+      "step": 128
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.07397323539112335,
+      "learning_rate": 2.547571145828459e-05,
+      "loss": 2.3643,
+      "step": 129
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.07438211371538549,
+      "learning_rate": 2.54134646343489e-05,
+      "loss": 2.3387,
+      "step": 130
+    },
+    {
+      "epoch": 1.0916666666666666,
+      "grad_norm": 0.07094248712059498,
+      "learning_rate": 2.5350661423481885e-05,
+      "loss": 2.3221,
+      "step": 131
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.0771622686218861,
+      "learning_rate": 2.5287304955794754e-05,
+      "loss": 2.3183,
+      "step": 132
+    },
+    {
+      "epoch": 1.1083333333333334,
+      "grad_norm": 0.07495056480159959,
+      "learning_rate": 2.5223398388973028e-05,
+      "loss": 2.3697,
+      "step": 133
+    },
+    {
+      "epoch": 1.1166666666666667,
+      "grad_norm": 0.07629199954207538,
+      "learning_rate": 2.515894490811916e-05,
+      "loss": 2.3529,
+      "step": 134
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.0762534542729489,
+      "learning_rate": 2.5093947725593792e-05,
+      "loss": 2.3208,
+      "step": 135
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.07587427933984144,
+      "learning_rate": 2.502841008085565e-05,
+      "loss": 2.3448,
+      "step": 136
+    },
+    {
+      "epoch": 1.1416666666666666,
+      "grad_norm": 0.07490456619530689,
+      "learning_rate": 2.49623352403001e-05,
+      "loss": 2.3435,
+      "step": 137
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.0744781797534131,
+      "learning_rate": 2.4895726497096315e-05,
+      "loss": 2.4,
+      "step": 138
+    },
+    {
+      "epoch": 1.1583333333333332,
+      "grad_norm": 0.07464944817741491,
+      "learning_rate": 2.482858717102319e-05,
+      "loss": 2.318,
+      "step": 139
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.07309033869975678,
+      "learning_rate": 2.4760920608303867e-05,
+      "loss": 2.2891,
+      "step": 140
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.07284517336177344,
+      "learning_rate": 2.469273018143894e-05,
+      "loss": 2.3051,
+      "step": 141
+    },
+    {
+      "epoch": 1.1833333333333333,
+      "grad_norm": 0.07652064520411771,
+      "learning_rate": 2.462401928903839e-05,
+      "loss": 2.3555,
+      "step": 142
+    },
+    {
+      "epoch": 1.1916666666666667,
+      "grad_norm": 0.07701974074136966,
+      "learning_rate": 2.45547913556522e-05,
+      "loss": 2.3015,
+      "step": 143
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.08108352272511765,
+      "learning_rate": 2.448504983159966e-05,
+      "loss": 2.3221,
+      "step": 144
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.07752288456105606,
+      "learning_rate": 2.441479819279742e-05,
+      "loss": 2.3684,
+      "step": 145
+    },
+    {
+      "epoch": 1.2166666666666668,
+      "grad_norm": 0.07881711814524053,
+      "learning_rate": 2.4344039940586235e-05,
+      "loss": 2.3011,
+      "step": 146
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.07757542042787384,
+      "learning_rate": 2.4272778601556472e-05,
+      "loss": 2.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.07228965364348439,
+      "learning_rate": 2.4201017727372336e-05,
+      "loss": 2.3801,
+      "step": 148
+    },
+    {
+      "epoch": 1.2416666666666667,
+      "grad_norm": 0.07389812003829682,
+      "learning_rate": 2.4128760894594853e-05,
+      "loss": 2.3359,
+      "step": 149
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.08146218033856112,
+      "learning_rate": 2.4056011704503633e-05,
+      "loss": 2.3096,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 2.400259494781494,
+      "eval_runtime": 81.604,
+      "eval_samples_per_second": 5.024,
+      "eval_steps_per_second": 0.319,
+      "step": 150
+    },
+    {
+      "epoch": 1.2583333333333333,
+      "grad_norm": 0.07407260421175128,
+      "learning_rate": 2.3982773782917347e-05,
+      "loss": 2.3418,
+      "step": 151
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.07827237096687646,
+      "learning_rate": 2.390905078001306e-05,
+      "loss": 2.2778,
+      "step": 152
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.07699758244967876,
+      "learning_rate": 2.383484637014426e-05,
+      "loss": 2.3245,
+      "step": 153
+    },
+    {
+      "epoch": 1.2833333333333332,
+      "grad_norm": 0.07805943021524937,
+      "learning_rate": 2.3760164251657773e-05,
+      "loss": 2.3782,
+      "step": 154
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.0741687347632035,
+      "learning_rate": 2.368500814670941e-05,
+      "loss": 2.3765,
+      "step": 155
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.07696079818166807,
+      "learning_rate": 2.3609381801078448e-05,
+      "loss": 2.3958,
+      "step": 156
+    },
+    {
+      "epoch": 1.3083333333333333,
+      "grad_norm": 0.08864860865623735,
+      "learning_rate": 2.3533288983980964e-05,
+      "loss": 2.3482,
+      "step": 157
+    },
+    {
+      "epoch": 1.3166666666666667,
+      "grad_norm": 0.07676755572584443,
+      "learning_rate": 2.3456733487881978e-05,
+      "loss": 2.3511,
+      "step": 158
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.07754541163995884,
+      "learning_rate": 2.337971912830641e-05,
+      "loss": 2.3754,
+      "step": 159
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08430746433268149,
+      "learning_rate": 2.3302249743648926e-05,
+      "loss": 2.4063,
+      "step": 160
+    },
+    {
+      "epoch": 1.3416666666666668,
+      "grad_norm": 0.08113759941899056,
+      "learning_rate": 2.322432919498265e-05,
+      "loss": 2.3352,
+      "step": 161
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.08147516272984133,
+      "learning_rate": 2.3145961365866708e-05,
+      "loss": 2.3119,
+      "step": 162
+    },
+    {
+      "epoch": 1.3583333333333334,
+      "grad_norm": 0.07749688842544009,
+      "learning_rate": 2.3067150162152675e-05,
+      "loss": 2.3547,
+      "step": 163
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.08640326754187048,
+      "learning_rate": 2.298789951178992e-05,
+      "loss": 2.3389,
+      "step": 164
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.0795137333109577,
+      "learning_rate": 2.2908213364629812e-05,
+      "loss": 2.3778,
+      "step": 165
+    },
+    {
+      "epoch": 1.3833333333333333,
+      "grad_norm": 0.07739334763959965,
+      "learning_rate": 2.2828095692228886e-05,
+      "loss": 2.3658,
+      "step": 166
+    },
+    {
+      "epoch": 1.3916666666666666,
+      "grad_norm": 0.07783031237693959,
+      "learning_rate": 2.2747550487650887e-05,
+      "loss": 2.3575,
+      "step": 167
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.07682655233706284,
+      "learning_rate": 2.2666581765267758e-05,
+      "loss": 2.2825,
+      "step": 168
+    },
+    {
+      "epoch": 1.4083333333333332,
+      "grad_norm": 0.08359081032268273,
+      "learning_rate": 2.2585193560559563e-05,
+      "loss": 2.261,
+      "step": 169
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.0826940676306091,
+      "learning_rate": 2.250338992991335e-05,
+      "loss": 2.3069,
+      "step": 170
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.08462619097403327,
+      "learning_rate": 2.2421174950421017e-05,
+      "loss": 2.2864,
+      "step": 171
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.07990029642375193,
+      "learning_rate": 2.233855271967606e-05,
+      "loss": 2.3033,
+      "step": 172
+    },
+    {
+      "epoch": 1.4416666666666667,
+      "grad_norm": 0.08051779058857793,
+      "learning_rate": 2.2255527355569372e-05,
+      "loss": 2.3166,
+      "step": 173
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.08604667339713809,
+      "learning_rate": 2.217210299608402e-05,
+      "loss": 2.387,
+      "step": 174
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.07829742536277012,
+      "learning_rate": 2.208828379908899e-05,
+      "loss": 2.311,
+      "step": 175
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.07850219342360719,
+      "learning_rate": 2.200407394213196e-05,
+      "loss": 2.3384,
+      "step": 176
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.08531707041033702,
+      "learning_rate": 2.19194776222311e-05,
+      "loss": 2.3107,
+      "step": 177
+    },
+    {
+      "epoch": 1.4833333333333334,
+      "grad_norm": 0.07652853009760147,
+      "learning_rate": 2.183449905566589e-05,
+      "loss": 2.3494,
+      "step": 178
+    },
+    {
+      "epoch": 1.4916666666666667,
+      "grad_norm": 0.0797336095546633,
+      "learning_rate": 2.1749142477766972e-05,
+      "loss": 2.3291,
+      "step": 179
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.08700079540422817,
+      "learning_rate": 2.166341214270507e-05,
+      "loss": 2.3132,
+      "step": 180
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.3966128826141357,
+      "eval_runtime": 83.184,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 0.313,
+      "step": 180
+    },
+    {
+      "epoch": 1.5083333333333333,
+      "grad_norm": 0.07925581040107615,
+      "learning_rate": 2.157731232327897e-05,
+      "loss": 2.3578,
+      "step": 181
+    },
+    {
+      "epoch": 1.5166666666666666,
+      "grad_norm": 0.07873086864048841,
+      "learning_rate": 2.1490847310702544e-05,
+      "loss": 2.3229,
+      "step": 182
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.07775316849537767,
+      "learning_rate": 2.1404021414390874e-05,
+      "loss": 2.3756,
+      "step": 183
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.07949428482523528,
+      "learning_rate": 2.1316838961745518e-05,
+      "loss": 2.3535,
+      "step": 184
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.08423278187074197,
+      "learning_rate": 2.1229304297938755e-05,
+      "loss": 2.3517,
+      "step": 185
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.07930583119038707,
+      "learning_rate": 2.1141421785697097e-05,
+      "loss": 2.3929,
+      "step": 186
+    },
+    {
+      "epoch": 1.5583333333333333,
+      "grad_norm": 0.07736840323261199,
+      "learning_rate": 2.1053195805083803e-05,
+      "loss": 2.3194,
+      "step": 187
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.08306421066524537,
+      "learning_rate": 2.0964630753280584e-05,
+      "loss": 2.3131,
+      "step": 188
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.0805185815818936,
+      "learning_rate": 2.0875731044368472e-05,
+      "loss": 2.3238,
+      "step": 189
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.07729948838070921,
+      "learning_rate": 2.078650110910779e-05,
+      "loss": 2.3279,
+      "step": 190
+    },
+    {
+      "epoch": 1.5916666666666668,
+      "grad_norm": 0.08053951644296133,
+      "learning_rate": 2.0696945394717355e-05,
+      "loss": 2.3343,
+      "step": 191
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.08184664333069269,
+      "learning_rate": 2.0607068364652783e-05,
+      "loss": 2.3441,
+      "step": 192
+    },
+    {
+      "epoch": 1.6083333333333334,
+      "grad_norm": 0.07894699650259683,
+      "learning_rate": 2.051687449838409e-05,
+      "loss": 2.3384,
+      "step": 193
+    },
+    {
+      "epoch": 1.6166666666666667,
+      "grad_norm": 0.08288692832517489,
+      "learning_rate": 2.042636829117239e-05,
+      "loss": 2.3219,
+      "step": 194
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.09061769591669266,
+      "learning_rate": 2.033555425384586e-05,
+      "loss": 2.3168,
+      "step": 195
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.07607427061534017,
+      "learning_rate": 2.0244436912574938e-05,
+      "loss": 2.3592,
+      "step": 196
+    },
+    {
+      "epoch": 1.6416666666666666,
+      "grad_norm": 0.08827457673533141,
+      "learning_rate": 2.0153020808646715e-05,
+      "loss": 2.3177,
+      "step": 197
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.0757688204165182,
+      "learning_rate": 2.0061310498238618e-05,
+      "loss": 2.2366,
+      "step": 198
+    },
+    {
+      "epoch": 1.6583333333333332,
+      "grad_norm": 0.07815852114026649,
+      "learning_rate": 1.996931055219132e-05,
+      "loss": 2.3161,
+      "step": 199
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.08058901889279678,
+      "learning_rate": 1.9877025555780927e-05,
+      "loss": 2.3749,
+      "step": 200
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.07708027281441528,
+      "learning_rate": 1.978446010849045e-05,
+      "loss": 2.2854,
+      "step": 201
+    },
+    {
+      "epoch": 1.6833333333333333,
+      "grad_norm": 0.08312283019758401,
+      "learning_rate": 1.969161882378058e-05,
+      "loss": 2.3524,
+      "step": 202
+    },
+    {
+      "epoch": 1.6916666666666667,
+      "grad_norm": 0.07784046601849169,
+      "learning_rate": 1.9598506328859717e-05,
+      "loss": 2.3418,
+      "step": 203
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.07906237498578873,
+      "learning_rate": 1.95051272644534e-05,
+      "loss": 2.3514,
+      "step": 204
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.08323464269988524,
+      "learning_rate": 1.9411486284572977e-05,
+      "loss": 2.3133,
+      "step": 205
+    },
+    {
+      "epoch": 1.7166666666666668,
+      "grad_norm": 0.08153670371604982,
+      "learning_rate": 1.931758805628366e-05,
+      "loss": 2.3388,
+      "step": 206
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.08152589045596419,
+      "learning_rate": 1.9223437259471912e-05,
+      "loss": 2.3309,
+      "step": 207
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.08382345786042532,
+      "learning_rate": 1.9129038586612224e-05,
+      "loss": 2.3282,
+      "step": 208
+    },
+    {
+      "epoch": 1.7416666666666667,
+      "grad_norm": 0.0835609429134592,
+      "learning_rate": 1.903439674253321e-05,
+      "loss": 2.3567,
+      "step": 209
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.08252984125014622,
+      "learning_rate": 1.8939516444183143e-05,
+      "loss": 2.3352,
+      "step": 210
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.3933684825897217,
+      "eval_runtime": 83.3063,
+      "eval_samples_per_second": 4.922,
+      "eval_steps_per_second": 0.312,
+      "step": 210
+    },
+    {
+      "epoch": 1.7583333333333333,
+      "grad_norm": 0.0815481053340795,
+      "learning_rate": 1.884440242039485e-05,
+      "loss": 2.3262,
+      "step": 211
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.08258761118218041,
+      "learning_rate": 1.8749059411650034e-05,
+      "loss": 2.3396,
+      "step": 212
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.0884999967331726,
+      "learning_rate": 1.8653492169843003e-05,
+      "loss": 2.3176,
+      "step": 213
+    },
+    {
+      "epoch": 1.7833333333333332,
+      "grad_norm": 0.0824785010834098,
+      "learning_rate": 1.8557705458043838e-05,
+      "loss": 2.3272,
+      "step": 214
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.08727167025374602,
+      "learning_rate": 1.8461704050261e-05,
+      "loss": 2.2298,
+      "step": 215
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0768016904891171,
+      "learning_rate": 1.8365492731203398e-05,
+      "loss": 2.3554,
+      "step": 216
+    },
+    {
+      "epoch": 1.8083333333333333,
+      "grad_norm": 0.07709533586121158,
+      "learning_rate": 1.8269076296041917e-05,
+      "loss": 2.3702,
+      "step": 217
+    },
+    {
+      "epoch": 1.8166666666666667,
+      "grad_norm": 0.0806446736093232,
+      "learning_rate": 1.8172459550170424e-05,
+      "loss": 2.3585,
+      "step": 218
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.07523532523458193,
+      "learning_rate": 1.8075647308966268e-05,
+      "loss": 2.3609,
+      "step": 219
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.07497201271988578,
+      "learning_rate": 1.797864439755028e-05,
+      "loss": 2.3755,
+      "step": 220
+    },
+    {
+      "epoch": 1.8416666666666668,
+      "grad_norm": 0.08249074177996166,
+      "learning_rate": 1.7881455650546303e-05,
+      "loss": 2.372,
+      "step": 221
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0780160636961897,
+      "learning_rate": 1.7784085911840214e-05,
+      "loss": 2.3823,
+      "step": 222
+    },
+    {
+      "epoch": 1.8583333333333334,
+      "grad_norm": 0.08148680526536918,
+      "learning_rate": 1.7686540034338513e-05,
+      "loss": 2.3314,
+      "step": 223
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0795864595636552,
+      "learning_rate": 1.758882287972646e-05,
+      "loss": 2.2853,
+      "step": 224
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.08198344669246531,
+      "learning_rate": 1.749093931822577e-05,
+      "loss": 2.3605,
+      "step": 225
+    },
+    {
+      "epoch": 1.8833333333333333,
+      "grad_norm": 0.08138145213474299,
+      "learning_rate": 1.739289422835185e-05,
+      "loss": 2.2721,
+      "step": 226
+    },
+    {
+      "epoch": 1.8916666666666666,
+      "grad_norm": 0.08306015511124677,
+      "learning_rate": 1.7294692496670715e-05,
+      "loss": 2.2889,
+      "step": 227
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.07478727556401082,
+      "learning_rate": 1.7196339017555378e-05,
+      "loss": 2.3416,
+      "step": 228
+    },
+    {
+      "epoch": 1.9083333333333332,
+      "grad_norm": 0.08858459574829487,
+      "learning_rate": 1.709783869294196e-05,
+      "loss": 2.3081,
+      "step": 229
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.08175368181940743,
+      "learning_rate": 1.699919643208533e-05,
+      "loss": 2.3304,
+      "step": 230
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.07630479738636474,
+      "learning_rate": 1.6900417151314503e-05,
+      "loss": 2.3454,
+      "step": 231
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.07687273996639293,
+      "learning_rate": 1.6801505773787527e-05,
+      "loss": 2.3901,
+      "step": 232
+    },
+    {
+      "epoch": 1.9416666666666667,
+      "grad_norm": 0.08600269874202937,
+      "learning_rate": 1.670246722924616e-05,
+      "loss": 2.3081,
+      "step": 233
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.07737694968965858,
+      "learning_rate": 1.660330645377018e-05,
+      "loss": 2.3643,
+      "step": 234
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.08165758061569027,
+      "learning_rate": 1.6504028389531333e-05,
+      "loss": 2.355,
+      "step": 235
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.08264378429137093,
+      "learning_rate": 1.640463798454704e-05,
+      "loss": 2.3219,
+      "step": 236
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.0858368818345628,
+      "learning_rate": 1.6305140192433787e-05,
+      "loss": 2.3329,
+      "step": 237
+    },
+    {
+      "epoch": 1.9833333333333334,
+      "grad_norm": 0.07616999163161729,
+      "learning_rate": 1.620553997216023e-05,
+      "loss": 2.3523,
+      "step": 238
+    },
+    {
+      "epoch": 1.9916666666666667,
+      "grad_norm": 0.08241527325980988,
+      "learning_rate": 1.6105842287800046e-05,
+      "loss": 2.2982,
+      "step": 239
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08007891750583127,
+      "learning_rate": 1.600605210828451e-05,
+      "loss": 2.2785,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.3910558223724365,
+      "eval_runtime": 83.4904,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 0.311,
+      "step": 240
+    },
+    {
+      "epoch": 2.0083333333333333,
+      "grad_norm": 0.08108687194604622,
+      "learning_rate": 1.5906174407154883e-05,
+      "loss": 2.3367,
+      "step": 241
+    },
+    {
+      "epoch": 2.0166666666666666,
+      "grad_norm": 0.0806511417182259,
+      "learning_rate": 1.5806214162314463e-05,
+      "loss": 2.3011,
+      "step": 242
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.08264392219751603,
+      "learning_rate": 1.5706176355780556e-05,
+      "loss": 2.3036,
+      "step": 243
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.07958409681135217,
+      "learning_rate": 1.5606065973436132e-05,
+      "loss": 2.3056,
+      "step": 244
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.07856642651007223,
+      "learning_rate": 1.550588800478133e-05,
+      "loss": 2.3692,
+      "step": 245
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.08350216798892127,
+      "learning_rate": 1.5405647442684794e-05,
+      "loss": 2.2697,
+      "step": 246
+    },
+    {
+      "epoch": 2.058333333333333,
+      "grad_norm": 0.08390645284684875,
+      "learning_rate": 1.530534928313484e-05,
+      "loss": 2.2425,
+      "step": 247
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.07883358190907572,
+      "learning_rate": 1.5204998524990423e-05,
+      "loss": 2.3281,
+      "step": 248
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.07994560560782488,
+      "learning_rate": 1.5104600169732015e-05,
+      "loss": 2.3285,
+      "step": 249
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.08345016891314849,
+      "learning_rate": 1.5004159221212325e-05,
+      "loss": 2.3252,
+      "step": 250
+    },
+    {
+      "epoch": 2.091666666666667,
+      "grad_norm": 0.0767244585605165,
+      "learning_rate": 1.490368068540692e-05,
+      "loss": 2.3176,
+      "step": 251
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.07853322933102938,
+      "learning_rate": 1.4803169570164703e-05,
+      "loss": 2.286,
+      "step": 252
+    },
+    {
+      "epoch": 2.1083333333333334,
+      "grad_norm": 0.07885223855237164,
+      "learning_rate": 1.4702630884958345e-05,
+      "loss": 2.3293,
+      "step": 253
+    },
+    {
+      "epoch": 2.1166666666666667,
+      "grad_norm": 0.07786083611140765,
+      "learning_rate": 1.4602069640634605e-05,
+      "loss": 2.3241,
+      "step": 254
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.07961379829842732,
+      "learning_rate": 1.4501490849164585e-05,
+      "loss": 2.3218,
+      "step": 255
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.0812119479291348,
+      "learning_rate": 1.4400899523393928e-05,
+      "loss": 2.3101,
+      "step": 256
+    },
+    {
+      "epoch": 2.1416666666666666,
+      "grad_norm": 0.07820228956836967,
+      "learning_rate": 1.4300300676793e-05,
+      "loss": 2.3105,
+      "step": 257
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.0787354321940814,
+      "learning_rate": 1.4199699323207e-05,
+      "loss": 2.2921,
+      "step": 258
+    },
+    {
+      "epoch": 2.158333333333333,
+      "grad_norm": 0.0821168083039209,
+      "learning_rate": 1.4099100476606071e-05,
+      "loss": 2.3449,
+      "step": 259
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.08227570212622978,
+      "learning_rate": 1.3998509150835417e-05,
+      "loss": 2.2804,
+      "step": 260
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.07956552166316343,
+      "learning_rate": 1.3897930359365397e-05,
+      "loss": 2.2798,
+      "step": 261
+    },
+    {
+      "epoch": 2.183333333333333,
+      "grad_norm": 0.08355971196343313,
+      "learning_rate": 1.3797369115041656e-05,
+      "loss": 2.3121,
+      "step": 262
+    },
+    {
+      "epoch": 2.191666666666667,
+      "grad_norm": 0.07664615523847712,
+      "learning_rate": 1.3696830429835303e-05,
+      "loss": 2.3511,
+      "step": 263
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.07875754809310784,
+      "learning_rate": 1.3596319314593088e-05,
+      "loss": 2.276,
+      "step": 264
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.07805417721469433,
+      "learning_rate": 1.3495840778787675e-05,
+      "loss": 2.3156,
+      "step": 265
+    },
+    {
+      "epoch": 2.216666666666667,
+      "grad_norm": 0.08500867883177173,
+      "learning_rate": 1.339539983026799e-05,
+      "loss": 2.3304,
+      "step": 266
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.08575986404103182,
+      "learning_rate": 1.3295001475009578e-05,
+      "loss": 2.3171,
+      "step": 267
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.0796424885760881,
+      "learning_rate": 1.3194650716865163e-05,
+      "loss": 2.3488,
+      "step": 268
+    },
+    {
+      "epoch": 2.2416666666666667,
+      "grad_norm": 0.07791982790558008,
+      "learning_rate": 1.3094352557315207e-05,
+      "loss": 2.3806,
+      "step": 269
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0840055290628465,
+      "learning_rate": 1.299411199521868e-05,
+      "loss": 2.3277,
+      "step": 270
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 2.3895957469940186,
+      "eval_runtime": 83.1157,
+      "eval_samples_per_second": 4.933,
+      "eval_steps_per_second": 0.313,
+      "step": 270
+    },
+    {
+      "epoch": 2.2583333333333333,
+      "grad_norm": 0.07770712903979533,
+      "learning_rate": 1.2893934026563873e-05,
+      "loss": 2.2666,
+      "step": 271
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07846164594226922,
+      "learning_rate": 1.2793823644219445e-05,
+      "loss": 2.2855,
+      "step": 272
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.08498339693180243,
+      "learning_rate": 1.269378583768554e-05,
+      "loss": 2.2733,
+      "step": 273
+    },
+    {
+      "epoch": 2.283333333333333,
+      "grad_norm": 0.07834222258922019,
+      "learning_rate": 1.2593825592845122e-05,
+      "loss": 2.3193,
+      "step": 274
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.08132580954052983,
+      "learning_rate": 1.2493947891715491e-05,
+      "loss": 2.3085,
+      "step": 275
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.07883697009265064,
+      "learning_rate": 1.239415771219996e-05,
+      "loss": 2.3545,
+      "step": 276
+    },
+    {
+      "epoch": 2.3083333333333336,
+      "grad_norm": 0.08023901828387182,
+      "learning_rate": 1.2294460027839779e-05,
+      "loss": 2.3489,
+      "step": 277
+    },
+    {
+      "epoch": 2.3166666666666664,
+      "grad_norm": 0.08930364086676225,
+      "learning_rate": 1.2194859807566216e-05,
+      "loss": 2.2591,
+      "step": 278
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.08343332964333285,
+      "learning_rate": 1.2095362015452961e-05,
+      "loss": 2.3404,
+      "step": 279
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.08292455976075656,
+      "learning_rate": 1.199597161046867e-05,
+      "loss": 2.3028,
+      "step": 280
+    },
+    {
+      "epoch": 2.341666666666667,
+      "grad_norm": 0.08627078651851632,
+      "learning_rate": 1.189669354622982e-05,
+      "loss": 2.343,
+      "step": 281
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.08202097516344958,
+      "learning_rate": 1.1797532770753842e-05,
+      "loss": 2.326,
+      "step": 282
+    },
+    {
+      "epoch": 2.3583333333333334,
+      "grad_norm": 0.08362611496815728,
+      "learning_rate": 1.169849422621248e-05,
+      "loss": 2.3035,
+      "step": 283
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.08888611458113292,
+      "learning_rate": 1.1599582848685506e-05,
+      "loss": 2.2812,
+      "step": 284
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.08217261091117088,
+      "learning_rate": 1.1500803567914671e-05,
+      "loss": 2.3378,
+      "step": 285
+    },
+    {
+      "epoch": 2.3833333333333333,
+      "grad_norm": 0.07985728135451624,
+      "learning_rate": 1.1402161307058047e-05,
+      "loss": 2.3522,
+      "step": 286
+    },
+    {
+      "epoch": 2.3916666666666666,
+      "grad_norm": 0.08014525439116486,
+      "learning_rate": 1.1303660982444624e-05,
+      "loss": 2.2256,
+      "step": 287
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08787593050595495,
+      "learning_rate": 1.1205307503329286e-05,
+      "loss": 2.2974,
+      "step": 288
+    },
+    {
+      "epoch": 2.408333333333333,
+      "grad_norm": 0.08195162040998395,
+      "learning_rate": 1.1107105771648151e-05,
+      "loss": 2.353,
+      "step": 289
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.08267743479386988,
+      "learning_rate": 1.1009060681774236e-05,
+      "loss": 2.3274,
+      "step": 290
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.08798947281948663,
+      "learning_rate": 1.0911177120273537e-05,
+      "loss": 2.3404,
+      "step": 291
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.08828111892887862,
+      "learning_rate": 1.0813459965661489e-05,
+      "loss": 2.3348,
+      "step": 292
+    },
+    {
+      "epoch": 2.4416666666666664,
+      "grad_norm": 0.08102528742267785,
+      "learning_rate": 1.0715914088159789e-05,
+      "loss": 2.2863,
+      "step": 293
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0866645702075036,
+      "learning_rate": 1.06185443494537e-05,
+      "loss": 2.3357,
+      "step": 294
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.08290121294865929,
+      "learning_rate": 1.0521355602449723e-05,
+      "loss": 2.3537,
+      "step": 295
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.08332374744178081,
+      "learning_rate": 1.042435269103374e-05,
+      "loss": 2.3554,
+      "step": 296
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.08367195510948358,
+      "learning_rate": 1.0327540449829583e-05,
+      "loss": 2.3384,
+      "step": 297
+    },
+    {
+      "epoch": 2.4833333333333334,
+      "grad_norm": 0.08673119537467149,
+      "learning_rate": 1.0230923703958083e-05,
+      "loss": 2.2725,
+      "step": 298
+    },
+    {
+      "epoch": 2.4916666666666667,
+      "grad_norm": 0.08235186060858125,
+      "learning_rate": 1.0134507268796605e-05,
+      "loss": 2.328,
+      "step": 299
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08408079009588813,
+      "learning_rate": 1.0038295949739004e-05,
+      "loss": 2.3403,
+      "step": 300
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.3881967067718506,
+      "eval_runtime": 82.1489,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.316,
+      "step": 300
+    },
+    {
+      "epoch": 2.5083333333333333,
+      "grad_norm": 0.07909547450093556,
+      "learning_rate": 9.942294541956169e-06,
+      "loss": 2.3357,
+      "step": 301
+    },
+    {
+      "epoch": 2.5166666666666666,
+      "grad_norm": 0.08766753125589274,
+      "learning_rate": 9.846507830157e-06,
+      "loss": 2.2503,
+      "step": 302
+    },
+    {
+      "epoch": 2.525,
+      "grad_norm": 0.07987208695801865,
+      "learning_rate": 9.75094058834997e-06,
+      "loss": 2.3168,
+      "step": 303
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.08537107163629042,
+      "learning_rate": 9.655597579605152e-06,
+      "loss": 2.3036,
+      "step": 304
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.08251527677113132,
+      "learning_rate": 9.560483555816858e-06,
+      "loss": 2.3419,
+      "step": 305
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.08523777732696665,
+      "learning_rate": 9.465603257466792e-06,
+      "loss": 2.3449,
+      "step": 306
+    },
+    {
+      "epoch": 2.5583333333333336,
+      "grad_norm": 0.0848931418707024,
+      "learning_rate": 9.370961413387778e-06,
+      "loss": 2.2844,
+      "step": 307
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.08156484852737556,
+      "learning_rate": 9.27656274052809e-06,
+      "loss": 2.3485,
+      "step": 308
+    },
+    {
+      "epoch": 2.575,
+      "grad_norm": 0.08185057405642468,
+      "learning_rate": 9.182411943716344e-06,
+      "loss": 2.3748,
+      "step": 309
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.08210521440208327,
+      "learning_rate": 9.088513715427028e-06,
+      "loss": 2.376,
+      "step": 310
+    },
+    {
+      "epoch": 2.591666666666667,
+      "grad_norm": 0.08030540134328207,
+      "learning_rate": 8.9948727355466e-06,
+      "loss": 2.3196,
+      "step": 311
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.08216024303479584,
+      "learning_rate": 8.901493671140283e-06,
+      "loss": 2.3534,
+      "step": 312
+    },
+    {
+      "epoch": 2.6083333333333334,
+      "grad_norm": 0.08105902557687622,
+      "learning_rate": 8.808381176219426e-06,
+      "loss": 2.2729,
+      "step": 313
+    },
+    {
+      "epoch": 2.6166666666666667,
+      "grad_norm": 0.08410998796525411,
+      "learning_rate": 8.71553989150955e-06,
+      "loss": 2.3596,
+      "step": 314
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.08582437979635364,
+      "learning_rate": 8.622974444219076e-06,
+      "loss": 2.3063,
+      "step": 315
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.08419960708603666,
+      "learning_rate": 8.530689447808683e-06,
+      "loss": 2.3468,
+      "step": 316
+    },
+    {
+      "epoch": 2.6416666666666666,
+      "grad_norm": 0.08532017727647645,
+      "learning_rate": 8.438689501761387e-06,
+      "loss": 2.3378,
+      "step": 317
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.08544492639100988,
+      "learning_rate": 8.346979191353288e-06,
+      "loss": 2.2872,
+      "step": 318
+    },
+    {
+      "epoch": 2.658333333333333,
+      "grad_norm": 0.0825611786693761,
+      "learning_rate": 8.255563087425069e-06,
+      "loss": 2.3037,
+      "step": 319
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.07923900030264817,
+      "learning_rate": 8.164445746154141e-06,
+      "loss": 2.2746,
+      "step": 320
+    },
+    {
+      "epoch": 2.675,
+      "grad_norm": 0.0805988851220756,
+      "learning_rate": 8.073631708827614e-06,
+      "loss": 2.3116,
+      "step": 321
+    },
+    {
+      "epoch": 2.6833333333333336,
+      "grad_norm": 0.07902450485255898,
+      "learning_rate": 7.983125501615913e-06,
+      "loss": 2.3253,
+      "step": 322
+    },
+    {
+      "epoch": 2.6916666666666664,
+      "grad_norm": 0.08586994856844313,
+      "learning_rate": 7.892931635347223e-06,
+      "loss": 2.3636,
+      "step": 323
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.08029033935205021,
+      "learning_rate": 7.803054605282652e-06,
+      "loss": 2.3023,
+      "step": 324
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.08041087816983067,
+      "learning_rate": 7.713498890892208e-06,
+      "loss": 2.3629,
+      "step": 325
+    },
+    {
+      "epoch": 2.716666666666667,
+      "grad_norm": 0.08451031313730265,
+      "learning_rate": 7.624268955631531e-06,
+      "loss": 2.2625,
+      "step": 326
+    },
+    {
+      "epoch": 2.725,
+      "grad_norm": 0.07898217475608488,
+      "learning_rate": 7.53536924671942e-06,
+      "loss": 2.3106,
+      "step": 327
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.08283676255780481,
+      "learning_rate": 7.446804194916206e-06,
+      "loss": 2.3576,
+      "step": 328
+    },
+    {
+      "epoch": 2.7416666666666667,
+      "grad_norm": 0.08212231805524588,
+      "learning_rate": 7.358578214302908e-06,
+      "loss": 2.2791,
+      "step": 329
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.08251122557980495,
+      "learning_rate": 7.270695702061248e-06,
+      "loss": 2.3553,
+      "step": 330
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 2.387129783630371,
+      "eval_runtime": 81.7826,
+      "eval_samples_per_second": 5.013,
+      "eval_steps_per_second": 0.318,
+      "step": 330
+    },
+    {
+      "epoch": 2.7583333333333333,
+      "grad_norm": 0.08008513950564178,
+      "learning_rate": 7.1831610382544856e-06,
+      "loss": 2.2737,
+      "step": 331
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.08378397772580942,
+      "learning_rate": 7.095978585609125e-06,
+      "loss": 2.362,
+      "step": 332
+    },
+    {
+      "epoch": 2.775,
+      "grad_norm": 0.08519607549475229,
+      "learning_rate": 7.009152689297463e-06,
+      "loss": 2.2601,
+      "step": 333
+    },
+    {
+      "epoch": 2.783333333333333,
+      "grad_norm": 0.08038464346170233,
+      "learning_rate": 6.9226876767210355e-06,
+      "loss": 2.3434,
+      "step": 334
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.08107258257971683,
+      "learning_rate": 6.83658785729493e-06,
+      "loss": 2.2608,
+      "step": 335
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0801095446046233,
+      "learning_rate": 6.750857522233032e-06,
+      "loss": 2.3562,
+      "step": 336
+    },
+    {
+      "epoch": 2.8083333333333336,
+      "grad_norm": 0.08032953635285699,
+      "learning_rate": 6.665500944334116e-06,
+      "loss": 2.3473,
+      "step": 337
+    },
+    {
+      "epoch": 2.8166666666666664,
+      "grad_norm": 0.08165787890975398,
+      "learning_rate": 6.580522377768902e-06,
+      "loss": 2.3662,
+      "step": 338
+    },
+    {
+      "epoch": 2.825,
+      "grad_norm": 0.08186138228862638,
+      "learning_rate": 6.495926057868045e-06,
+      "loss": 2.3611,
+      "step": 339
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.08409693406516083,
+      "learning_rate": 6.4117162009110105e-06,
+      "loss": 2.3014,
+      "step": 340
+    },
+    {
+      "epoch": 2.841666666666667,
+      "grad_norm": 0.08426043237254878,
+      "learning_rate": 6.327897003915982e-06,
+      "loss": 2.3556,
+      "step": 341
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.07860767709618154,
+      "learning_rate": 6.244472644430632e-06,
+      "loss": 2.3986,
+      "step": 342
+    },
+    {
+      "epoch": 2.8583333333333334,
+      "grad_norm": 0.07913910815896576,
+      "learning_rate": 6.161447280323948e-06,
+      "loss": 2.3041,
+      "step": 343
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.0834686817566552,
+      "learning_rate": 6.078825049578985e-06,
+      "loss": 2.2694,
+      "step": 344
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.09464173421182612,
+      "learning_rate": 5.996610070086646e-06,
+      "loss": 2.3291,
+      "step": 345
+    },
+    {
+      "epoch": 2.8833333333333333,
+      "grad_norm": 0.08924525286993587,
+      "learning_rate": 5.914806439440443e-06,
+      "loss": 2.2425,
+      "step": 346
+    },
+    {
+      "epoch": 2.8916666666666666,
+      "grad_norm": 0.07984144031222275,
+      "learning_rate": 5.833418234732248e-06,
+      "loss": 2.3212,
+      "step": 347
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.08119999485058818,
+      "learning_rate": 5.752449512349119e-06,
+      "loss": 2.3043,
+      "step": 348
+    },
+    {
+      "epoch": 2.908333333333333,
+      "grad_norm": 0.08130268904604636,
+      "learning_rate": 5.671904307771115e-06,
+      "loss": 2.3431,
+      "step": 349
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.0886368269447557,
+      "learning_rate": 5.591786635370193e-06,
+      "loss": 2.2584,
+      "step": 350
+    },
+    {
+      "epoch": 2.925,
+      "grad_norm": 0.08449560278602129,
+      "learning_rate": 5.5121004882100805e-06,
+      "loss": 2.2614,
+      "step": 351
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.0877133422168611,
+      "learning_rate": 5.4328498378473245e-06,
+      "loss": 2.3467,
+      "step": 352
+    },
+    {
+      "epoch": 2.9416666666666664,
+      "grad_norm": 0.0829503072213313,
+      "learning_rate": 5.354038634133295e-06,
+      "loss": 2.2975,
+      "step": 353
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.08436627929472401,
+      "learning_rate": 5.27567080501735e-06,
+      "loss": 2.3115,
+      "step": 354
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.08048623155801396,
+      "learning_rate": 5.197750256351076e-06,
+      "loss": 2.2584,
+      "step": 355
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.08109596859654204,
+      "learning_rate": 5.120280871693596e-06,
+      "loss": 2.3677,
+      "step": 356
+    },
+    {
+      "epoch": 2.975,
+      "grad_norm": 0.081013576151029,
+      "learning_rate": 5.0432665121180266e-06,
+      "loss": 2.3585,
+      "step": 357
+    },
+    {
+      "epoch": 2.9833333333333334,
+      "grad_norm": 0.08546479543984016,
+      "learning_rate": 4.966711016019037e-06,
+      "loss": 2.303,
+      "step": 358
+    },
+    {
+      "epoch": 2.9916666666666667,
+      "grad_norm": 0.08245660024002954,
+      "learning_rate": 4.890618198921555e-06,
+      "loss": 2.3149,
+      "step": 359
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08512068224524219,
+      "learning_rate": 4.814991853290595e-06,
+      "loss": 2.2894,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.386331081390381,
+      "eval_runtime": 82.119,
+      "eval_samples_per_second": 4.993,
+      "eval_steps_per_second": 0.317,
+      "step": 360
+    },
+    {
+      "epoch": 3.0083333333333333,
+      "grad_norm": 0.08558372235748295,
+      "learning_rate": 4.739835748342228e-06,
+      "loss": 2.2984,
+      "step": 361
+    },
+    {
+      "epoch": 3.0166666666666666,
+      "grad_norm": 0.08035880067291258,
+      "learning_rate": 4.665153629855744e-06,
+      "loss": 2.3033,
+      "step": 362
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 0.07959465533779843,
+      "learning_rate": 4.5909492199869445e-06,
+      "loss": 2.3507,
+      "step": 363
+    },
+    {
+      "epoch": 3.033333333333333,
+      "grad_norm": 0.08267174156962717,
+      "learning_rate": 4.517226217082652e-06,
+      "loss": 2.3425,
+      "step": 364
+    },
+    {
+      "epoch": 3.0416666666666665,
+      "grad_norm": 0.07991572961673732,
+      "learning_rate": 4.44398829549637e-06,
+      "loss": 2.3261,
+      "step": 365
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.07847568885444599,
+      "learning_rate": 4.371239105405148e-06,
+      "loss": 2.3477,
+      "step": 366
+    },
+    {
+      "epoch": 3.058333333333333,
+      "grad_norm": 0.08038194746327948,
+      "learning_rate": 4.29898227262767e-06,
+      "loss": 2.2698,
+      "step": 367
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.08253718833393997,
+      "learning_rate": 4.22722139844353e-06,
+      "loss": 2.3652,
+      "step": 368
+    },
+    {
+      "epoch": 3.075,
+      "grad_norm": 0.08516413003066334,
+      "learning_rate": 4.1559600594137686e-06,
+      "loss": 2.3331,
+      "step": 369
+    },
+    {
+      "epoch": 3.0833333333333335,
+      "grad_norm": 0.07953660852824361,
+      "learning_rate": 4.085201807202586e-06,
+      "loss": 2.3689,
+      "step": 370
+    },
+    {
+      "epoch": 3.091666666666667,
+      "grad_norm": 0.08238213712670353,
+      "learning_rate": 4.014950168400341e-06,
+      "loss": 2.308,
+      "step": 371
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.08283454952311556,
+      "learning_rate": 3.945208644347803e-06,
+      "loss": 2.2875,
+      "step": 372
+    },
+    {
+      "epoch": 3.1083333333333334,
+      "grad_norm": 0.08123988730396041,
+      "learning_rate": 3.875980710961609e-06,
+      "loss": 2.2607,
+      "step": 373
+    },
+    {
+      "epoch": 3.1166666666666667,
+      "grad_norm": 0.08112099690166064,
+      "learning_rate": 3.8072698185610614e-06,
+      "loss": 2.3591,
+      "step": 374
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.0792957148134827,
+      "learning_rate": 3.7390793916961342e-06,
+      "loss": 2.3218,
+      "step": 375
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.08349920233794074,
+      "learning_rate": 3.671412828976812e-06,
+      "loss": 2.298,
+      "step": 376
+    },
+    {
+      "epoch": 3.1416666666666666,
+      "grad_norm": 0.07899532707809945,
+      "learning_rate": 3.604273502903688e-06,
+      "loss": 2.3226,
+      "step": 377
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.08573888823467567,
+      "learning_rate": 3.537664759699903e-06,
+      "loss": 2.316,
+      "step": 378
+    },
+    {
+      "epoch": 3.158333333333333,
+      "grad_norm": 0.08115043743007767,
+      "learning_rate": 3.4715899191443483e-06,
+      "loss": 2.2912,
+      "step": 379
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.08268384127740624,
+      "learning_rate": 3.40605227440621e-06,
+      "loss": 2.2777,
+      "step": 380
+    },
+    {
+      "epoch": 3.175,
+      "grad_norm": 0.08106251418915893,
+      "learning_rate": 3.3410550918808443e-06,
+      "loss": 2.3159,
+      "step": 381
+    },
+    {
+      "epoch": 3.183333333333333,
+      "grad_norm": 0.08286464503073644,
+      "learning_rate": 3.276601611026974e-06,
+      "loss": 2.3071,
+      "step": 382
+    },
+    {
+      "epoch": 3.191666666666667,
+      "grad_norm": 0.08199773880110967,
+      "learning_rate": 3.2126950442052483e-06,
+      "loss": 2.3043,
+      "step": 383
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.08187041229316819,
+      "learning_rate": 3.149338576518116e-06,
+      "loss": 2.2955,
+      "step": 384
+    },
+    {
+      "epoch": 3.2083333333333335,
+      "grad_norm": 0.08220875126507468,
+      "learning_rate": 3.0865353656511014e-06,
+      "loss": 2.3141,
+      "step": 385
+    },
+    {
+      "epoch": 3.216666666666667,
+      "grad_norm": 0.08353220855881248,
+      "learning_rate": 3.024288541715413e-06,
+      "loss": 2.3677,
+      "step": 386
+    },
+    {
+      "epoch": 3.225,
+      "grad_norm": 0.07903966810055228,
+      "learning_rate": 2.9626012070919357e-06,
+      "loss": 2.3359,
+      "step": 387
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.08190032494339015,
+      "learning_rate": 2.901476436276628e-06,
+      "loss": 2.2796,
+      "step": 388
+    },
+    {
+      "epoch": 3.2416666666666667,
+      "grad_norm": 0.08161746077320213,
+      "learning_rate": 2.840917275727264e-06,
+      "loss": 2.3368,
+      "step": 389
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.0815574105377222,
+      "learning_rate": 2.780926743711611e-06,
+      "loss": 2.2746,
+      "step": 390
+    },
+    {
+      "epoch": 3.25,
+      "eval_loss": 2.385850667953491,
+      "eval_runtime": 83.443,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 0.312,
+      "step": 390
+    },
+    {
+      "epoch": 3.2583333333333333,
+      "grad_norm": 0.07940368361833833,
+      "learning_rate": 2.7215078301570005e-06,
+      "loss": 2.3239,
+      "step": 391
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.0789092720450855,
+      "learning_rate": 2.6626634965013064e-06,
+      "loss": 2.3485,
+      "step": 392
+    },
+    {
+      "epoch": 3.275,
+      "grad_norm": 0.07860086067453795,
+      "learning_rate": 2.604396675545354e-06,
+      "loss": 2.3022,
+      "step": 393
+    },
+    {
+      "epoch": 3.283333333333333,
+      "grad_norm": 0.0827013915236191,
+      "learning_rate": 2.546710271306732e-06,
+      "loss": 2.3382,
+      "step": 394
+    },
+    {
+      "epoch": 3.2916666666666665,
+      "grad_norm": 0.08392337720938575,
+      "learning_rate": 2.4896071588750746e-06,
+      "loss": 2.2495,
+      "step": 395
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.07896168168173961,
+      "learning_rate": 2.433090184268755e-06,
+      "loss": 2.3413,
+      "step": 396
+    },
+    {
+      "epoch": 3.3083333333333336,
+      "grad_norm": 0.08513092869669563,
+      "learning_rate": 2.3771621642930495e-06,
+      "loss": 2.32,
+      "step": 397
+    },
+    {
+      "epoch": 3.3166666666666664,
+      "grad_norm": 0.08158164066376497,
+      "learning_rate": 2.3218258863997483e-06,
+      "loss": 2.3159,
+      "step": 398
+    },
+    {
+      "epoch": 3.325,
+      "grad_norm": 0.07850245543386242,
+      "learning_rate": 2.2670841085482114e-06,
+      "loss": 2.2892,
+      "step": 399
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.07948289924872026,
+      "learning_rate": 2.2129395590679325e-06,
+      "loss": 2.3183,
+      "step": 400
+    },
+    {
+      "epoch": 3.341666666666667,
+      "grad_norm": 0.08268427645613528,
+      "learning_rate": 2.1593949365225455e-06,
+      "loss": 2.3455,
+      "step": 401
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.0805567434916959,
+      "learning_rate": 2.1064529095753457e-06,
+      "loss": 2.323,
+      "step": 402
+    },
+    {
+      "epoch": 3.3583333333333334,
+      "grad_norm": 0.08055664155765571,
+      "learning_rate": 2.054116116856257e-06,
+      "loss": 2.3334,
+      "step": 403
+    },
+    {
+      "epoch": 3.3666666666666667,
+      "grad_norm": 0.082279494119965,
+      "learning_rate": 2.0023871668303433e-06,
+      "loss": 2.2938,
+      "step": 404
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.08252463940578399,
+      "learning_rate": 1.9512686376678015e-06,
+      "loss": 2.2965,
+      "step": 405
+    },
+    {
+      "epoch": 3.3833333333333333,
+      "grad_norm": 0.08541294452389535,
+      "learning_rate": 1.9007630771154532e-06,
+      "loss": 2.2363,
+      "step": 406
+    },
+    {
+      "epoch": 3.3916666666666666,
+      "grad_norm": 0.08261328178534114,
+      "learning_rate": 1.850873002369778e-06,
+      "loss": 2.3175,
+      "step": 407
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.0830385045862884,
+      "learning_rate": 1.8016008999514467e-06,
+      "loss": 2.2871,
+      "step": 408
+    },
+    {
+      "epoch": 3.408333333333333,
+      "grad_norm": 0.08146738848250283,
+      "learning_rate": 1.7529492255814008e-06,
+      "loss": 2.3198,
+      "step": 409
+    },
+    {
+      "epoch": 3.4166666666666665,
+      "grad_norm": 0.0827275148559704,
+      "learning_rate": 1.704920404058452e-06,
+      "loss": 2.2888,
+      "step": 410
+    },
+    {
+      "epoch": 3.425,
+      "grad_norm": 0.0803715450561763,
+      "learning_rate": 1.6575168291384352e-06,
+      "loss": 2.3405,
+      "step": 411
+    },
+    {
+      "epoch": 3.4333333333333336,
+      "grad_norm": 0.07862601957152224,
+      "learning_rate": 1.6107408634149068e-06,
+      "loss": 2.2978,
+      "step": 412
+    },
+    {
+      "epoch": 3.4416666666666664,
+      "grad_norm": 0.0797822244213719,
+      "learning_rate": 1.5645948382013898e-06,
+      "loss": 2.3701,
+      "step": 413
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 0.07749237550393802,
+      "learning_rate": 1.5190810534151723e-06,
+      "loss": 2.3616,
+      "step": 414
+    },
+    {
+      "epoch": 3.4583333333333335,
+      "grad_norm": 0.07924907970443268,
+      "learning_rate": 1.474201777462696e-06,
+      "loss": 2.2771,
+      "step": 415
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.07962985015963248,
+      "learning_rate": 1.4299592471264814e-06,
+      "loss": 2.3482,
+      "step": 416
+    },
+    {
+      "epoch": 3.475,
+      "grad_norm": 0.08046145953371857,
+      "learning_rate": 1.3863556674536668e-06,
+      "loss": 2.2809,
+      "step": 417
+    },
+    {
+      "epoch": 3.4833333333333334,
+      "grad_norm": 0.08300783210234308,
+      "learning_rate": 1.3433932116460928e-06,
+      "loss": 2.257,
+      "step": 418
+    },
+    {
+      "epoch": 3.4916666666666667,
+      "grad_norm": 0.07975202760505942,
+      "learning_rate": 1.3010740209519938e-06,
+      "loss": 2.2887,
+      "step": 419
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.08236525138293024,
+      "learning_rate": 1.2594002045592805e-06,
+      "loss": 2.3372,
+      "step": 420
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 2.385662794113159,
+      "eval_runtime": 83.0808,
+      "eval_samples_per_second": 4.935,
+      "eval_steps_per_second": 0.313,
+      "step": 420
+    },
+    {
+      "epoch": 3.5083333333333333,
+      "grad_norm": 0.0770785839751936,
+      "learning_rate": 1.2183738394904125e-06,
+      "loss": 2.316,
+      "step": 421
+    },
+    {
+      "epoch": 3.5166666666666666,
+      "grad_norm": 0.08097460244560037,
+      "learning_rate": 1.1779969704988948e-06,
+      "loss": 2.2975,
+      "step": 422
+    },
+    {
+      "epoch": 3.525,
+      "grad_norm": 0.07940694057270696,
+      "learning_rate": 1.1382716099673468e-06,
+      "loss": 2.2899,
+      "step": 423
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.07624395089449575,
+      "learning_rate": 1.099199737807215e-06,
+      "loss": 2.269,
+      "step": 424
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 0.08303520654580664,
+      "learning_rate": 1.0607833013601008e-06,
+      "loss": 2.2388,
+      "step": 425
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 0.08044700838476601,
+      "learning_rate": 1.0230242153006902e-06,
+      "loss": 2.2696,
+      "step": 426
+    },
+    {
+      "epoch": 3.5583333333333336,
+      "grad_norm": 0.08344501586117684,
+      "learning_rate": 9.85924361541343e-07,
+      "loss": 2.3153,
+      "step": 427
+    },
+    {
+      "epoch": 3.5666666666666664,
+      "grad_norm": 0.08179619120507588,
+      "learning_rate": 9.494855891382835e-07,
+      "loss": 2.3233,
+      "step": 428
+    },
+    {
+      "epoch": 3.575,
+      "grad_norm": 0.07850084483291209,
+      "learning_rate": 9.137097141994495e-07,
+      "loss": 2.3087,
+      "step": 429
+    },
+    {
+      "epoch": 3.5833333333333335,
+      "grad_norm": 0.08111699262929621,
+      "learning_rate": 8.785985197939802e-07,
+      "loss": 2.3543,
+      "step": 430
+    },
+    {
+      "epoch": 3.591666666666667,
+      "grad_norm": 0.07923257497320196,
+      "learning_rate": 8.441537558633456e-07,
+      "loss": 2.2727,
+      "step": 431
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.08295454182298913,
+      "learning_rate": 8.103771391341333e-07,
+      "loss": 2.2947,
+      "step": 432
+    },
+    {
+      "epoch": 3.6083333333333334,
+      "grad_norm": 0.08330165750451879,
+      "learning_rate": 7.772703530324758e-07,
+      "loss": 2.2726,
+      "step": 433
+    },
+    {
+      "epoch": 3.6166666666666667,
+      "grad_norm": 0.08825135153749371,
+      "learning_rate": 7.448350476001587e-07,
+      "loss": 2.3293,
+      "step": 434
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.07936800616322473,
+      "learning_rate": 7.130728394123811e-07,
+      "loss": 2.3361,
+      "step": 435
+    },
+    {
+      "epoch": 3.6333333333333333,
+      "grad_norm": 0.08092774191682904,
+      "learning_rate": 6.819853114971846e-07,
+      "loss": 2.2896,
+      "step": 436
+    },
+    {
+      "epoch": 3.6416666666666666,
+      "grad_norm": 0.0847047278961897,
+      "learning_rate": 6.515740132565501e-07,
+      "loss": 2.3467,
+      "step": 437
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.08396765360593379,
+      "learning_rate": 6.218404603891905e-07,
+      "loss": 2.3158,
+      "step": 438
+    },
+    {
+      "epoch": 3.658333333333333,
+      "grad_norm": 0.08429525429703029,
+      "learning_rate": 5.927861348149875e-07,
+      "loss": 2.3163,
+      "step": 439
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.08234598100556376,
+      "learning_rate": 5.644124846011458e-07,
+      "loss": 2.267,
+      "step": 440
+    },
+    {
+      "epoch": 3.675,
+      "grad_norm": 0.08146900548133754,
+      "learning_rate": 5.367209238900246e-07,
+      "loss": 2.2648,
+      "step": 441
+    },
+    {
+      "epoch": 3.6833333333333336,
+      "grad_norm": 0.08208680327943706,
+      "learning_rate": 5.097128328286468e-07,
+      "loss": 2.3259,
+      "step": 442
+    },
+    {
+      "epoch": 3.6916666666666664,
+      "grad_norm": 0.0797527104636109,
+      "learning_rate": 4.833895574999158e-07,
+      "loss": 2.3253,
+      "step": 443
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.08665834276318864,
+      "learning_rate": 4.577524098555302e-07,
+      "loss": 2.2622,
+      "step": 444
+    },
+    {
+      "epoch": 3.7083333333333335,
+      "grad_norm": 0.07997688422980546,
+      "learning_rate": 4.328026676505935e-07,
+      "loss": 2.3534,
+      "step": 445
+    },
+    {
+      "epoch": 3.716666666666667,
+      "grad_norm": 0.07828547467180325,
+      "learning_rate": 4.085415743799311e-07,
+      "loss": 2.3496,
+      "step": 446
+    },
+    {
+      "epoch": 3.725,
+      "grad_norm": 0.08026091990691622,
+      "learning_rate": 3.849703392161145e-07,
+      "loss": 2.268,
+      "step": 447
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.07786907236541515,
+      "learning_rate": 3.620901369491971e-07,
+      "loss": 2.287,
+      "step": 448
+    },
+    {
+      "epoch": 3.7416666666666667,
+      "grad_norm": 0.08181636690118672,
+      "learning_rate": 3.3990210792815556e-07,
+      "loss": 2.3515,
+      "step": 449
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.07917094030405644,
+      "learning_rate": 3.184073580040699e-07,
+      "loss": 2.3202,
+      "step": 450
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 2.3855926990509033,
+      "eval_runtime": 83.2872,
+      "eval_samples_per_second": 4.923,
+      "eval_steps_per_second": 0.312,
+      "step": 450
+    },
+    {
+      "epoch": 3.7583333333333333,
+      "grad_norm": 0.07910995296958116,
+      "learning_rate": 2.976069584749945e-07,
+      "loss": 2.3408,
+      "step": 451
+    },
+    {
+      "epoch": 3.7666666666666666,
+      "grad_norm": 0.08190829338924943,
+      "learning_rate": 2.775019460325717e-07,
+      "loss": 2.342,
+      "step": 452
+    },
+    {
+      "epoch": 3.775,
+      "grad_norm": 0.07897395505824549,
+      "learning_rate": 2.580933227103546e-07,
+      "loss": 2.3585,
+      "step": 453
+    },
+    {
+      "epoch": 3.783333333333333,
+      "grad_norm": 0.07574550298881826,
+      "learning_rate": 2.3938205583387747e-07,
+      "loss": 2.3582,
+      "step": 454
+    },
+    {
+      "epoch": 3.7916666666666665,
+      "grad_norm": 0.07850140630528783,
+      "learning_rate": 2.2136907797243712e-07,
+      "loss": 2.3041,
+      "step": 455
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.07649287404720032,
+      "learning_rate": 2.0405528689261514e-07,
+      "loss": 2.2674,
+      "step": 456
+    },
+    {
+      "epoch": 3.8083333333333336,
+      "grad_norm": 0.08096951270830731,
+      "learning_rate": 1.874415455135306e-07,
+      "loss": 2.2864,
+      "step": 457
+    },
+    {
+      "epoch": 3.8166666666666664,
+      "grad_norm": 0.0793447282503826,
+      "learning_rate": 1.715286818638379e-07,
+      "loss": 2.2997,
+      "step": 458
+    },
+    {
+      "epoch": 3.825,
+      "grad_norm": 0.08240373350552549,
+      "learning_rate": 1.563174890404522e-07,
+      "loss": 2.2679,
+      "step": 459
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 0.08609998518111264,
+      "learning_rate": 1.4180872516902617e-07,
+      "loss": 2.2403,
+      "step": 460
+    },
+    {
+      "epoch": 3.841666666666667,
+      "grad_norm": 0.08167728612673658,
+      "learning_rate": 1.280031133661591e-07,
+      "loss": 2.3446,
+      "step": 461
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.0805979419664327,
+      "learning_rate": 1.149013417033655e-07,
+      "loss": 2.3297,
+      "step": 462
+    },
+    {
+      "epoch": 3.8583333333333334,
+      "grad_norm": 0.08611631443079958,
+      "learning_rate": 1.0250406317276928e-07,
+      "loss": 2.3336,
+      "step": 463
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 0.08143966447727025,
+      "learning_rate": 9.081189565457504e-08,
+      "loss": 2.2744,
+      "step": 464
+    },
+    {
+      "epoch": 3.875,
+      "grad_norm": 0.08488722225095564,
+      "learning_rate": 7.982542188625722e-08,
+      "loss": 2.3295,
+      "step": 465
+    },
+    {
+      "epoch": 3.8833333333333333,
+      "grad_norm": 0.07853979984810681,
+      "learning_rate": 6.954518943352283e-08,
+      "loss": 2.344,
+      "step": 466
+    },
+    {
+      "epoch": 3.8916666666666666,
+      "grad_norm": 0.07862078924318884,
+      "learning_rate": 5.99717106630256e-08,
+      "loss": 2.3355,
+      "step": 467
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.08377975012300021,
+      "learning_rate": 5.110546271682018e-08,
+      "loss": 2.3136,
+      "step": 468
+    },
+    {
+      "epoch": 3.908333333333333,
+      "grad_norm": 0.07944977947348907,
+      "learning_rate": 4.294688748859016e-08,
+      "loss": 2.2962,
+      "step": 469
+    },
+    {
+      "epoch": 3.9166666666666665,
+      "grad_norm": 0.0833522759120961,
+      "learning_rate": 3.549639160161608e-08,
+      "loss": 2.308,
+      "step": 470
+    },
+    {
+      "epoch": 3.925,
+      "grad_norm": 0.08140602305245098,
+      "learning_rate": 2.8754346388515512e-08,
+      "loss": 2.2746,
+      "step": 471
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 0.07858129028297453,
+      "learning_rate": 2.2721087872736023e-08,
+      "loss": 2.3202,
+      "step": 472
+    },
+    {
+      "epoch": 3.9416666666666664,
+      "grad_norm": 0.08607576848964471,
+      "learning_rate": 1.739691675180108e-08,
+      "loss": 2.2951,
+      "step": 473
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 0.08333546885762359,
+      "learning_rate": 1.2782098382329438e-08,
+      "loss": 2.3083,
+      "step": 474
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 0.07846414060719181,
+      "learning_rate": 8.876862766810657e-09,
+      "loss": 2.3477,
+      "step": 475
+    },
+    {
+      "epoch": 3.966666666666667,
+      "grad_norm": 0.0843173916539748,
+      "learning_rate": 5.681404542133506e-09,
+      "loss": 2.3153,
+      "step": 476
+    },
+    {
+      "epoch": 3.975,
+      "grad_norm": 0.08182426750859544,
+      "learning_rate": 3.195882969897396e-09,
+      "loss": 2.3014,
+      "step": 477
+    },
+    {
+      "epoch": 3.9833333333333334,
+      "grad_norm": 0.08152323272955077,
+      "learning_rate": 1.4204219284608965e-09,
+      "loss": 2.2305,
+      "step": 478
+    },
+    {
+      "epoch": 3.9916666666666667,
+      "grad_norm": 0.08125023609849888,
+      "learning_rate": 3.5510990678433443e-10,
+      "loss": 2.3295,
+      "step": 479
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.08005084236686048,
+      "learning_rate": 0.0,
+      "loss": 2.3509,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.3855347633361816,
+      "eval_runtime": 81.8722,
+      "eval_samples_per_second": 5.008,
+      "eval_steps_per_second": 0.318,
+      "step": 480
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.955261368264294e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-480/training_args.bin b/checkpoint-480/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e71e9ef0b364c8b803828c31c7b34cd4f7001af
--- /dev/null
+++ b/checkpoint-480/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
+size 8504
diff --git a/checkpoint-480/zero_to_fp32.py b/checkpoint-480/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..0e759146cadd92ddfefab3680146c2bd6a2b5c04
--- /dev/null
+++ b/checkpoint-480/zero_to_fp32.py
@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa8641624470ab4b16c917c3738ed17b1fcd4292
--- /dev/null
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128019,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "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": "4.50.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..9414f9e36eb995388775c9e63e5588313e7c41d3
--- /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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ae94f3cc49ae02ddb8b100e69ba51719000fa01
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c131c4a0f2e6b6f0b564da934a01b86750c6d347
--- /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": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e71e9ef0b364c8b803828c31c7b34cd4f7001af
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
+size 8504