Upload task output goof-intercode-synth

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen3-4B-Instruct-2507
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61593e9727bbb1e9ad307c6b6b0fdf3b053e8ea7f2b28e5a562f5e2500749d40
+size 1057033224

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

loss.txt

@@ -0,0 +1 @@
+927,no_eval

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1699 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9989224137931034,
+  "eval_steps": 500,
+  "global_step": 927,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005387931034482759,
+      "grad_norm": 12.1968412399292,
+      "learning_rate": 3.0395136778115497e-06,
+      "loss": 1.8873,
+      "mean_token_accuracy": 0.6897695422172546,
+      "num_tokens": 400768.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.010775862068965518,
+      "grad_norm": 3.8057918548583984,
+      "learning_rate": 6.838905775075987e-06,
+      "loss": 1.5876,
+      "mean_token_accuracy": 0.7044613480567932,
+      "num_tokens": 802093.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.016163793103448277,
+      "grad_norm": 2.502718448638916,
+      "learning_rate": 1.0638297872340424e-05,
+      "loss": 1.1671,
+      "mean_token_accuracy": 0.7444040536880493,
+      "num_tokens": 1204371.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.021551724137931036,
+      "grad_norm": 2.530015707015991,
+      "learning_rate": 1.4437689969604861e-05,
+      "loss": 0.7662,
+      "mean_token_accuracy": 0.8218989968299866,
+      "num_tokens": 1605926.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02693965517241379,
+      "grad_norm": 1.6813504695892334,
+      "learning_rate": 1.8237082066869297e-05,
+      "loss": 0.3334,
+      "mean_token_accuracy": 0.9192753791809082,
+      "num_tokens": 2008520.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.032327586206896554,
+      "grad_norm": 0.39220893383026123,
+      "learning_rate": 2.2036474164133735e-05,
+      "loss": 0.1079,
+      "mean_token_accuracy": 0.9747061133384705,
+      "num_tokens": 2411286.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03771551724137931,
+      "grad_norm": 0.292656809091568,
+      "learning_rate": 2.5835866261398174e-05,
+      "loss": 0.0539,
+      "mean_token_accuracy": 0.9869680643081665,
+      "num_tokens": 2812384.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 0.19993343949317932,
+      "learning_rate": 2.963525835866261e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9947868347167969,
+      "num_tokens": 3214237.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04849137931034483,
+      "grad_norm": 0.08813618868589401,
+      "learning_rate": 3.343465045592705e-05,
+      "loss": 0.0126,
+      "mean_token_accuracy": 0.9972272276878357,
+      "num_tokens": 3615584.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05387931034482758,
+      "grad_norm": 0.08378174901008606,
+      "learning_rate": 3.5713945110618356e-05,
+      "loss": 0.0101,
+      "mean_token_accuracy": 0.9976756691932678,
+      "num_tokens": 4017174.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.059267241379310345,
+      "grad_norm": 0.040304359048604965,
+      "learning_rate": 3.5710113518316467e-05,
+      "loss": 0.0086,
+      "mean_token_accuracy": 0.9979347348213196,
+      "num_tokens": 4419005.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.06465517241379311,
+      "grad_norm": 0.0402657724916935,
+      "learning_rate": 3.570202580121256e-05,
+      "loss": 0.0067,
+      "mean_token_accuracy": 0.9984693050384521,
+      "num_tokens": 4822335.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07004310344827586,
+      "grad_norm": 0.042970675975084305,
+      "learning_rate": 3.568968453030844e-05,
+      "loss": 0.0081,
+      "mean_token_accuracy": 0.9980570435523987,
+      "num_tokens": 5223110.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07543103448275862,
+      "grad_norm": 0.01980830542743206,
+      "learning_rate": 3.5673093628766804e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.9986111402511597,
+      "num_tokens": 5625737.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.08081896551724138,
+      "grad_norm": 0.028515689074993134,
+      "learning_rate": 3.565225837066405e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.9985626578330994,
+      "num_tokens": 6027745.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 0.03216356039047241,
+      "learning_rate": 3.562718537931378e-05,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.9981380701065063,
+      "num_tokens": 6428386.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.09159482758620689,
+      "grad_norm": 0.025963930413126945,
+      "learning_rate": 3.559788262516122e-05,
+      "loss": 0.007,
+      "mean_token_accuracy": 0.998262357711792,
+      "num_tokens": 6829296.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.09698275862068965,
+      "grad_norm": 0.030876589938998222,
+      "learning_rate": 3.55643594232496e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.998642098903656,
+      "num_tokens": 7231383.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.10237068965517242,
+      "grad_norm": 0.05387759208679199,
+      "learning_rate": 3.5526626430258894e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9989140748977661,
+      "num_tokens": 7634181.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.10775862068965517,
+      "grad_norm": 0.04550587758421898,
+      "learning_rate": 3.5484695641118264e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.9984101295471192,
+      "num_tokens": 8034986.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.11314655172413793,
+      "grad_norm": 0.04244628921151161,
+      "learning_rate": 3.543858038519294e-05,
+      "loss": 0.0059,
+      "mean_token_accuracy": 0.998475968837738,
+      "num_tokens": 8435724.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.11853448275862069,
+      "grad_norm": 0.033975739032030106,
+      "learning_rate": 3.538829532204697e-05,
+      "loss": 0.0055,
+      "mean_token_accuracy": 0.9984067916870117,
+      "num_tokens": 8836433.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.12392241379310345,
+      "grad_norm": 0.027840062975883484,
+      "learning_rate": 3.533385643678309e-05,
+      "loss": 0.0049,
+      "mean_token_accuracy": 0.9984710574150085,
+      "num_tokens": 9237426.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 0.032441090792417526,
+      "learning_rate": 3.527528103496123e-05,
+      "loss": 0.0043,
+      "mean_token_accuracy": 0.9987731218338013,
+      "num_tokens": 9639785.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.13469827586206898,
+      "grad_norm": 1.1890063285827637,
+      "learning_rate": 3.521258773709726e-05,
+      "loss": 0.0091,
+      "mean_token_accuracy": 0.9984417676925659,
+      "num_tokens": 10041859.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.1400862068965517,
+      "grad_norm": 0.5110039710998535,
+      "learning_rate": 3.514579647274372e-05,
+      "loss": 0.0072,
+      "mean_token_accuracy": 0.9981804013252258,
+      "num_tokens": 10444169.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.14547413793103448,
+      "grad_norm": 0.051610980182886124,
+      "learning_rate": 3.5074928474154395e-05,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9986317992210388,
+      "num_tokens": 10845781.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.15086206896551724,
+      "grad_norm": 0.04819732531905174,
+      "learning_rate": 3.500000626953483e-05,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9987854123115539,
+      "num_tokens": 11247814.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.04421250522136688,
+      "learning_rate": 3.492105367588084e-05,
+      "loss": 0.0057,
+      "mean_token_accuracy": 0.9981728672981263,
+      "num_tokens": 11647231.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.16163793103448276,
+      "grad_norm": 0.028427110984921455,
+      "learning_rate": 3.4838095791407325e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9986980438232422,
+      "num_tokens": 12048822.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.16702586206896552,
+      "grad_norm": 0.0242963545024395,
+      "learning_rate": 3.4751158987569807e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.998879075050354,
+      "num_tokens": 12451451.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.036968301981687546,
+      "learning_rate": 3.4660270900681224e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.998667573928833,
+      "num_tokens": 12853407.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.17780172413793102,
+      "grad_norm": 0.026654532179236412,
+      "learning_rate": 3.456546042312664e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9989476799964905,
+      "num_tokens": 13256199.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.18318965517241378,
+      "grad_norm": 0.030982624739408493,
+      "learning_rate": 3.446675769417862e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.998691463470459,
+      "num_tokens": 13657432.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.18857758620689655,
+      "grad_norm": 0.027644401416182518,
+      "learning_rate": 3.4364194090416284e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989338278770447,
+      "num_tokens": 14059944.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1939655172413793,
+      "grad_norm": 0.028662100434303284,
+      "learning_rate": 3.425780221575104e-05,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.9985748648643493,
+      "num_tokens": 14460963.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.19935344827586207,
+      "grad_norm": 0.016480762511491776,
+      "learning_rate": 3.414761589106212e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990429401397705,
+      "num_tokens": 14864395.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.20474137931034483,
+      "grad_norm": 0.029979556798934937,
+      "learning_rate": 3.403367014344524e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988659739494323,
+      "num_tokens": 15266900.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2101293103448276,
+      "grad_norm": 0.027647046372294426,
+      "learning_rate": 3.3916001195077896e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988864541053772,
+      "num_tokens": 15669225.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 0.028145747259259224,
+      "learning_rate": 3.379464645170468e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9988593935966492,
+      "num_tokens": 16071024.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.2209051724137931,
+      "grad_norm": 0.023499226197600365,
+      "learning_rate": 3.36696444907464e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9987353444099426,
+      "num_tokens": 16472951.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.22629310344827586,
+      "grad_norm": 0.022392505779862404,
+      "learning_rate": 3.3541035049036674e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989378809928894,
+      "num_tokens": 16875413.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.23168103448275862,
+      "grad_norm": 0.03322723135352135,
+      "learning_rate": 3.340885901019005e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988948225975036,
+      "num_tokens": 17277289.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.23706896551724138,
+      "grad_norm": 0.023486241698265076,
+      "learning_rate": 3.327315839160552e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989814162254333,
+      "num_tokens": 17680132.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.24245689655172414,
+      "grad_norm": 0.022162310779094696,
+      "learning_rate": 3.3133976331109576e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988259553909302,
+      "num_tokens": 18082263.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.2478448275862069,
+      "grad_norm": 0.02749790996313095,
+      "learning_rate": 3.299135707324319e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987885236740113,
+      "num_tokens": 18483839.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.25323275862068967,
+      "grad_norm": 0.026179060339927673,
+      "learning_rate": 3.2845345955196925e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988064408302307,
+      "num_tokens": 18884764.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 0.024499984458088875,
+      "learning_rate": 3.2695989392398675e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988564133644104,
+      "num_tokens": 19286945.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2640086206896552,
+      "grad_norm": 0.030282603576779366,
+      "learning_rate": 3.254333486375871e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988001465797425,
+      "num_tokens": 19688183.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.26939655172413796,
+      "grad_norm": 0.025260329246520996,
+      "learning_rate": 3.238743089657662e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988892674446106,
+      "num_tokens": 20090284.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.27478448275862066,
+      "grad_norm": 0.021427838131785393,
+      "learning_rate": 3.222832705111498e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988217949867249,
+      "num_tokens": 20492129.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.2801724137931034,
+      "grad_norm": 0.025272101163864136,
+      "learning_rate": 3.206607390484465e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988567233085632,
+      "num_tokens": 20894270.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2855603448275862,
+      "grad_norm": 0.029396332800388336,
+      "learning_rate": 3.190072303636671e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989629626274109,
+      "num_tokens": 21296742.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.29094827586206895,
+      "grad_norm": 0.024497823789715767,
+      "learning_rate": 3.1732327009016207e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9986671328544616,
+      "num_tokens": 21697099.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.2963362068965517,
+      "grad_norm": 0.025028323754668236,
+      "learning_rate": 3.1560939354152733e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987683653831482,
+      "num_tokens": 22098085.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 0.04323757439851761,
+      "learning_rate": 3.138661455414342e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987198233604431,
+      "num_tokens": 22499299.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.30711206896551724,
+      "grad_norm": 0.03109692595899105,
+      "learning_rate": 3.120940802504353e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990125894546509,
+      "num_tokens": 22902840.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.02269172854721546,
+      "learning_rate": 3.102937609898027e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.998817777633667,
+      "num_tokens": 23304365.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.31788793103448276,
+      "grad_norm": 0.030877182260155678,
+      "learning_rate": 3.084657600624539e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9986727714538575,
+      "num_tokens": 23704949.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.3232758620689655,
+      "grad_norm": 0.029980527237057686,
+      "learning_rate": 3.066106585710227e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988664746284485,
+      "num_tokens": 24106884.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.3286637931034483,
+      "grad_norm": 0.029696747660636902,
+      "learning_rate": 3.0472904623313255e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9985985040664673,
+      "num_tokens": 24507350.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.33405172413793105,
+      "grad_norm": 0.028655147179961205,
+      "learning_rate": 3.028215211939314e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988056421279907,
+      "num_tokens": 24908360.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.3394396551724138,
+      "grad_norm": 0.02250654809176922,
+      "learning_rate": 3.0088868983594765e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988771677017212,
+      "num_tokens": 25309887.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.02577587589621544,
+      "learning_rate": 2.9893116658632732e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988795518875122,
+      "num_tokens": 25711811.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.35021551724137934,
+      "grad_norm": 0.018826596438884735,
+      "learning_rate": 2.9694957372151408e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9987824082374572,
+      "num_tokens": 26113834.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.35560344827586204,
+      "grad_norm": 0.01912921853363514,
+      "learning_rate": 2.9494454116943372e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988623023033142,
+      "num_tokens": 26515468.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3609913793103448,
+      "grad_norm": 0.025108449161052704,
+      "learning_rate": 2.92916706309247e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9985854864120484,
+      "num_tokens": 26914860.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.36637931034482757,
+      "grad_norm": 0.027960950508713722,
+      "learning_rate": 2.9086671376873294e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987654566764832,
+      "num_tokens": 27315883.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.37176724137931033,
+      "grad_norm": 0.03099741041660309,
+      "learning_rate": 2.887952152193688e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988365650177002,
+      "num_tokens": 27717295.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.3771551724137931,
+      "grad_norm": 0.03361531347036362,
+      "learning_rate": 2.8670286916916988e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9987235307693482,
+      "num_tokens": 28118485.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.38254310344827586,
+      "grad_norm": 0.02108229137957096,
+      "learning_rate": 2.84590340753357e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9987129092216491,
+      "num_tokens": 28518536.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 0.01629681885242462,
+      "learning_rate": 2.8245830152291688e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990845441818237,
+      "num_tokens": 28921172.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3933189655172414,
+      "grad_norm": 0.018096312880516052,
+      "learning_rate": 2.8030742923112265e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990448117256164,
+      "num_tokens": 29323757.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.39870689655172414,
+      "grad_norm": 0.020383162423968315,
+      "learning_rate": 2.7813840761808355e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988522887229919,
+      "num_tokens": 29725160.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.4040948275862069,
+      "grad_norm": 0.02313813753426075,
+      "learning_rate": 2.7595192619339067e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989789724349976,
+      "num_tokens": 30127047.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.40948275862068967,
+      "grad_norm": 0.01893896609544754,
+      "learning_rate": 2.7374868001692914e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988893032073974,
+      "num_tokens": 30528443.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.41487068965517243,
+      "grad_norm": 0.02219376526772976,
+      "learning_rate": 2.7152936947792565e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991058945655823,
+      "num_tokens": 30931610.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.4202586206896552,
+      "grad_norm": 0.023286934942007065,
+      "learning_rate": 2.69294700072302e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988597512245179,
+      "num_tokens": 31333168.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.42564655172413796,
+      "grad_norm": 0.02829907275736332,
+      "learning_rate": 2.6704538217840525e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987843632698059,
+      "num_tokens": 31734174.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 0.022872034460306168,
+      "learning_rate": 2.6478213083118573e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999057388305664,
+      "num_tokens": 32137321.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.4364224137931034,
+      "grad_norm": 0.019009580835700035,
+      "learning_rate": 2.6250566549489473e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989295959472656,
+      "num_tokens": 32538924.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.4418103448275862,
+      "grad_norm": 0.024119965732097626,
+      "learning_rate": 2.6021670983437456e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988219618797303,
+      "num_tokens": 32940096.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.44719827586206895,
+      "grad_norm": 0.015429486520588398,
+      "learning_rate": 2.5791599148501243e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990504860877991,
+      "num_tokens": 33342584.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.4525862068965517,
+      "grad_norm": 0.015945369377732277,
+      "learning_rate": 2.5560424182143315e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989794135093689,
+      "num_tokens": 33744543.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.4579741379310345,
+      "grad_norm": 0.02112257108092308,
+      "learning_rate": 2.5328219572500253e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988049507141114,
+      "num_tokens": 34145921.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.46336206896551724,
+      "grad_norm": 0.024047503247857094,
+      "learning_rate": 2.5095059135021593e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.998953115940094,
+      "num_tokens": 34548234.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.024766026064753532,
+      "learning_rate": 2.4861016989004707e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991255521774292,
+      "num_tokens": 34951217.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 0.021735843271017075,
+      "learning_rate": 2.4626167534032994e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991132974624634,
+      "num_tokens": 35354444.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4795258620689655,
+      "grad_norm": 0.024870026856660843,
+      "learning_rate": 2.439058542632504e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989467620849609,
+      "num_tokens": 35756337.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.4849137931034483,
+      "grad_norm": 0.03170805424451828,
+      "learning_rate": 2.415434555500219e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990429520606995,
+      "num_tokens": 36158903.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.49030172413793105,
+      "grad_norm": 0.02606450952589512,
+      "learning_rate": 2.3917523018282043e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988895416259765,
+      "num_tokens": 36560305.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.4956896551724138,
+      "grad_norm": 0.019804656505584717,
+      "learning_rate": 2.3680193099605526e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989361643791199,
+      "num_tokens": 36962098.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.5010775862068966,
+      "grad_norm": 0.0203046053647995,
+      "learning_rate": 2.3442431243705042e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988129019737244,
+      "num_tokens": 37362831.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.5064655172413793,
+      "grad_norm": 0.024860316887497902,
+      "learning_rate": 2.3204313032621397e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.998871922492981,
+      "num_tokens": 37764399.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.5118534482758621,
+      "grad_norm": 0.017818594351410866,
+      "learning_rate": 2.2965914161677012e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987210273742676,
+      "num_tokens": 38164578.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.025839868932962418,
+      "learning_rate": 2.2727310415413196e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999123215675354,
+      "num_tokens": 38568107.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.5226293103448276,
+      "grad_norm": 0.03040791116654873,
+      "learning_rate": 2.2488577643499015e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9986463069915772,
+      "num_tokens": 38968204.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.5280172413793104,
+      "grad_norm": 0.01823345199227333,
+      "learning_rate": 2.2249791736619445e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9987418293952942,
+      "num_tokens": 39368748.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.5334051724137931,
+      "grad_norm": 0.017456430941820145,
+      "learning_rate": 2.201102860235052e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989594459533692,
+      "num_tokens": 39771148.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.5387931034482759,
+      "grad_norm": 0.011293855495750904,
+      "learning_rate": 2.17723641410291e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9989207744598388,
+      "num_tokens": 40172936.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.5441810344827587,
+      "grad_norm": 0.02168232947587967,
+      "learning_rate": 2.153387422162493e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988669872283935,
+      "num_tokens": 40574321.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.5495689655172413,
+      "grad_norm": 0.022194452583789825,
+      "learning_rate": 2.1295634657622692e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990811824798584,
+      "num_tokens": 40977332.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5549568965517241,
+      "grad_norm": 0.02700430154800415,
+      "learning_rate": 2.1057721182921658e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987297415733337,
+      "num_tokens": 41377361.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 0.01630469039082527,
+      "learning_rate": 2.0820209427760667e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9991111278533935,
+      "num_tokens": 41780206.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5657327586206896,
+      "grad_norm": 0.01802549883723259,
+      "learning_rate": 2.058317489467608e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.999023711681366,
+      "num_tokens": 42182533.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.5711206896551724,
+      "grad_norm": 0.018393119797110558,
+      "learning_rate": 2.0346692934500267e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987900257110596,
+      "num_tokens": 42583411.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5765086206896551,
+      "grad_norm": 0.030562814325094223,
+      "learning_rate": 2.011083872240839e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989658832550049,
+      "num_tokens": 42986211.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.5818965517241379,
+      "grad_norm": 0.01817888766527176,
+      "learning_rate": 1.987568723402096e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990274429321289,
+      "num_tokens": 43388450.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5872844827586207,
+      "grad_norm": 0.03097994066774845,
+      "learning_rate": 1.9641313221569873e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987420558929443,
+      "num_tokens": 43789193.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.5926724137931034,
+      "grad_norm": 0.03705303370952606,
+      "learning_rate": 1.9407791190135443e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988808393478393,
+      "num_tokens": 44190262.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5980603448275862,
+      "grad_norm": 0.02740267850458622,
+      "learning_rate": 1.917519537396203e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990205049514771,
+      "num_tokens": 44592899.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.020006787031888962,
+      "learning_rate": 1.8943599712859686e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989693641662598,
+      "num_tokens": 44994842.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.6088362068965517,
+      "grad_norm": 0.018442636355757713,
+      "learning_rate": 1.8713077828699518e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9991243004798889,
+      "num_tokens": 45398071.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.6142241379310345,
+      "grad_norm": 0.018633628264069557,
+      "learning_rate": 1.8483703002009994e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989421129226684,
+      "num_tokens": 45799996.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.6196120689655172,
+      "grad_norm": 0.018919259309768677,
+      "learning_rate": 1.8255548148681885e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987382292747498,
+      "num_tokens": 46200521.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.02536233887076378,
+      "learning_rate": 1.8028685796788967e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990259528160095,
+      "num_tokens": 46602910.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.6303879310344828,
+      "grad_norm": 0.0378764346241951,
+      "learning_rate": 1.7803188063532184e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989383459091187,
+      "num_tokens": 47004490.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.6357758620689655,
+      "grad_norm": 0.016049856320023537,
+      "learning_rate": 1.7579126632314283e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.998798668384552,
+      "num_tokens": 47405554.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.6411637931034483,
+      "grad_norm": 0.0242848452180624,
+      "learning_rate": 1.7356572729952424e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989304065704345,
+      "num_tokens": 47807115.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 0.017967503517866135,
+      "learning_rate": 1.713559710403587e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988836526870728,
+      "num_tokens": 48208645.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6519396551724138,
+      "grad_norm": 0.017399689182639122,
+      "learning_rate": 1.6916270000436114e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989873170852661,
+      "num_tokens": 48611213.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.6573275862068966,
+      "grad_norm": 0.021693337708711624,
+      "learning_rate": 1.6698661140976403e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990190029144287,
+      "num_tokens": 49013618.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6627155172413793,
+      "grad_norm": 0.01829269900918007,
+      "learning_rate": 1.6482839701267902e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.998821759223938,
+      "num_tokens": 49414231.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.6681034482758621,
+      "grad_norm": 0.0219797994941473,
+      "learning_rate": 1.626887428871947e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988946676254272,
+      "num_tokens": 49815839.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6734913793103449,
+      "grad_norm": 0.039269037544727325,
+      "learning_rate": 1.6056832920728103e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990034341812134,
+      "num_tokens": 50218362.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.6788793103448276,
+      "grad_norm": 0.017020177096128464,
+      "learning_rate": 1.5846783003056866e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988498330116272,
+      "num_tokens": 50619518.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.6842672413793104,
+      "grad_norm": 0.02394365519285202,
+      "learning_rate": 1.5638791308407327e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988521933555603,
+      "num_tokens": 51021046.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.021199658513069153,
+      "learning_rate": 1.5432923955193175e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.999006700515747,
+      "num_tokens": 51422849.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.6950431034482759,
+      "grad_norm": 0.02825820818543434,
+      "learning_rate": 1.5229246386521894e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989290356636047,
+      "num_tokens": 51824411.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.7004310344827587,
+      "grad_norm": 0.02520933374762535,
+      "learning_rate": 1.502782334939104e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.998921251296997,
+      "num_tokens": 52226246.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.7058189655172413,
+      "grad_norm": 0.01974504068493843,
+      "learning_rate": 1.4828718874105872e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988064289093017,
+      "num_tokens": 52627376.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.7112068965517241,
+      "grad_norm": 0.019875643774867058,
+      "learning_rate": 1.4631996253924749e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9991117596626282,
+      "num_tokens": 53029842.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.7165948275862069,
+      "grad_norm": 0.02502973936498165,
+      "learning_rate": 1.4437718024938859e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989853501319885,
+      "num_tokens": 53431813.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.7219827586206896,
+      "grad_norm": 0.019360193982720375,
+      "learning_rate": 1.4245945946192675e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990947246551514,
+      "num_tokens": 53834644.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.7273706896551724,
+      "grad_norm": 0.023955252021551132,
+      "learning_rate": 1.4056740980051348e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989283204078674,
+      "num_tokens": 54236164.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 0.02692730724811554,
+      "learning_rate": 1.3870163272821422e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9990485668182373,
+      "num_tokens": 54638824.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.7381465517241379,
+      "grad_norm": 0.02147173322737217,
+      "learning_rate": 1.3686272135630939e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987776398658752,
+      "num_tokens": 55039338.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.7435344827586207,
+      "grad_norm": 0.019535936415195465,
+      "learning_rate": 1.3505126025575055e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987868070602417,
+      "num_tokens": 55440205.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.7489224137931034,
+      "grad_norm": 0.03529336303472519,
+      "learning_rate": 1.3326782527133116e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987475514411926,
+      "num_tokens": 55840842.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.7543103448275862,
+      "grad_norm": 0.025773324072360992,
+      "learning_rate": 1.3151298333863147e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988975048065185,
+      "num_tokens": 56242938.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.759698275862069,
+      "grad_norm": 0.02031223475933075,
+      "learning_rate": 1.2978729230379578e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999043345451355,
+      "num_tokens": 56645521.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.7650862068965517,
+      "grad_norm": 0.019422592595219612,
+      "learning_rate": 1.2809130074619848e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990111470222474,
+      "num_tokens": 57047701.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7704741379310345,
+      "grad_norm": 0.02163652516901493,
+      "learning_rate": 1.2642554780405692e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.998817241191864,
+      "num_tokens": 57448557.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.0820826068520546,
+      "learning_rate": 1.2479056300304417e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989529132843018,
+      "num_tokens": 57850078.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.023449266329407692,
+      "learning_rate": 1.2318686608795911e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990583896636963,
+      "num_tokens": 58252482.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.7866379310344828,
+      "grad_norm": 0.017454233020544052,
+      "learning_rate": 1.216149668575042e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989933013916016,
+      "num_tokens": 58654206.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7920258620689655,
+      "grad_norm": 0.048610441386699677,
+      "learning_rate": 1.2007536500222625e-05,
+      "loss": 0.0024,
+      "mean_token_accuracy": 0.9991249680519104,
+      "num_tokens": 59057296.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.7974137931034483,
+      "grad_norm": 0.020494062453508377,
+      "learning_rate": 1.1856854994566963e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987275719642639,
+      "num_tokens": 59457386.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.802801724137931,
+      "grad_norm": 0.025657858699560165,
+      "learning_rate": 1.170950006887937e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998903775215149,
+      "num_tokens": 59858294.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.8081896551724138,
+      "grad_norm": 0.023894695565104485,
+      "learning_rate": 1.1565518565770333e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988603472709656,
+      "num_tokens": 60259023.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.8135775862068966,
+      "grad_norm": 0.02173379436135292,
+      "learning_rate": 1.1424956255474115e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989583969116211,
+      "num_tokens": 60660452.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.02115975134074688,
+      "learning_rate": 1.128785782129885e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9989435195922851,
+      "num_tokens": 61063319.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.8243534482758621,
+      "grad_norm": 0.01883304864168167,
+      "learning_rate": 1.1154266845422202e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989779353141784,
+      "num_tokens": 61464875.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.8297413793103449,
+      "grad_norm": 0.018032465130090714,
+      "learning_rate": 1.1024225795037032e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989536046981812,
+      "num_tokens": 61866596.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.8351293103448276,
+      "grad_norm": 0.027652721852064133,
+      "learning_rate": 1.089777600885151e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9988827228546142,
+      "num_tokens": 62268237.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.8405172413793104,
+      "grad_norm": 0.019578590989112854,
+      "learning_rate": 1.077495768394797e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998927652835846,
+      "num_tokens": 62669305.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.8459051724137931,
+      "grad_norm": 0.0217635165899992,
+      "learning_rate": 1.065580986300468e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.998993194103241,
+      "num_tokens": 63070895.0,
+      "step": 785
+    },
+    {
+      "epoch": 0.8512931034482759,
+      "grad_norm": 0.0335141085088253,
+      "learning_rate": 1.0540370421884568e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989400029182434,
+      "num_tokens": 63472239.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.8566810344827587,
+      "grad_norm": 0.045086249709129333,
+      "learning_rate": 1.0428676057594878e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990049242973328,
+      "num_tokens": 63874106.0,
+      "step": 795
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.017286602407693863,
+      "learning_rate": 1.0320762276621562e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989065647125244,
+      "num_tokens": 64275413.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8674568965517241,
+      "grad_norm": 0.017771046608686447,
+      "learning_rate": 1.0216663383642168e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9989452719688415,
+      "num_tokens": 64677195.0,
+      "step": 805
+    },
+    {
+      "epoch": 0.8728448275862069,
+      "grad_norm": 0.02480809949338436,
+      "learning_rate": 1.0116412470620679e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991085529327393,
+      "num_tokens": 65079992.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.8782327586206896,
+      "grad_norm": 0.016402944922447205,
+      "learning_rate": 1.0020041406287986e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989410161972045,
+      "num_tokens": 65481578.0,
+      "step": 815
+    },
+    {
+      "epoch": 0.8836206896551724,
+      "grad_norm": 0.020128078758716583,
+      "learning_rate": 9.927580826011085e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9991302847862243,
+      "num_tokens": 65884403.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.8890086206896551,
+      "grad_norm": 0.021842217072844505,
+      "learning_rate": 9.839060122054454e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9989564180374145,
+      "num_tokens": 66285831.0,
+      "step": 825
+    },
+    {
+      "epoch": 0.8943965517241379,
+      "grad_norm": 0.026447417214512825,
+      "learning_rate": 9.75450743423654e-06,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9987640976905823,
+      "num_tokens": 66685786.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.8997844827586207,
+      "grad_norm": 0.022103259339928627,
+      "learning_rate": 9.673949640984395e-06,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988175153732299,
+      "num_tokens": 67086671.0,
+      "step": 835
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 0.019495461136102676,
+      "learning_rate": 9.597412350789308e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9991957783699036,
+      "num_tokens": 67489546.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.9105603448275862,
+      "grad_norm": 0.024082858115434647,
+      "learning_rate": 9.52491989406613e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989072203636169,
+      "num_tokens": 67890580.0,
+      "step": 845
+    },
+    {
+      "epoch": 0.915948275862069,
+      "grad_norm": 0.02223868854343891,
+      "learning_rate": 9.456495315418894e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989860415458679,
+      "num_tokens": 68291991.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.9213362068965517,
+      "grad_norm": 0.027163589373230934,
+      "learning_rate": 9.392160366315146e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989891409873962,
+      "num_tokens": 68693639.0,
+      "step": 855
+    },
+    {
+      "epoch": 0.9267241379310345,
+      "grad_norm": 0.020333966240286827,
+      "learning_rate": 9.331935498171415e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989105701446533,
+      "num_tokens": 69094631.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.9321120689655172,
+      "grad_norm": 0.028376305475831032,
+      "learning_rate": 9.275839855851889e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990219831466675,
+      "num_tokens": 69496289.0,
+      "step": 865
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.020459886640310287,
+      "learning_rate": 9.223891271582473e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989444851875305,
+      "num_tokens": 69897569.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.9428879310344828,
+      "grad_norm": 0.026060640811920166,
+      "learning_rate": 9.176106259282111e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989287614822387,
+      "num_tokens": 70299003.0,
+      "step": 875
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.02536623924970627,
+      "learning_rate": 9.132500009313176e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989724516868591,
+      "num_tokens": 70700394.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.9536637931034483,
+      "grad_norm": 0.021408097818493843,
+      "learning_rate": 9.093086383652602e-06,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9987998485565186,
+      "num_tokens": 71100777.0,
+      "step": 885
+    },
+    {
+      "epoch": 0.959051724137931,
+      "grad_norm": 0.025553466752171516,
+      "learning_rate": 9.057877911485328e-06,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990517139434815,
+      "num_tokens": 71502841.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.9644396551724138,
+      "grad_norm": 0.02613006718456745,
+      "learning_rate": 9.026885785221381e-06,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988353490829468,
+      "num_tokens": 71903621.0,
+      "step": 895
+    },
+    {
+      "epoch": 0.9698275862068966,
+      "grad_norm": 0.0313388854265213,
+      "learning_rate": 9.000119856937926e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989818334579468,
+      "num_tokens": 72304967.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.9752155172413793,
+      "grad_norm": 0.0230126790702343,
+      "learning_rate": 8.977588635247394e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.998962688446045,
+      "num_tokens": 72706360.0,
+      "step": 905
+    },
+    {
+      "epoch": 0.9806034482758621,
+      "grad_norm": 0.027466285973787308,
+      "learning_rate": 8.95929928259269e-06,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9992066025733948,
+      "num_tokens": 73109586.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.9859913793103449,
+      "grad_norm": 0.027096059173345566,
+      "learning_rate": 8.945257612970317e-06,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9990667819976806,
+      "num_tokens": 73511828.0,
+      "step": 915
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.026896227151155472,
+      "learning_rate": 8.935468090082163e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998914110660553,
+      "num_tokens": 73912645.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9967672413793104,
+      "grad_norm": 0.031491924077272415,
+      "learning_rate": 8.929933825916554e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989247798919678,
+      "num_tokens": 74313996.0,
+      "step": 925
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 928,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7417116445069804e+18,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43938dad9ffe3ff1401a6f96d8c5e2d32ebd574f42cda6ca5b10cb89d513be87
+size 6545