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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "q_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:eeaed67547f317f6591a26e6a1ec515fa0b27d563a12926d0112e9b6c5cf0622
+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": 11.358600616455078,
+      "learning_rate": 3.0395136778115497e-06,
+      "loss": 1.9178,
+      "mean_token_accuracy": 0.6784796357154846,
+      "num_tokens": 400768.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.010775862068965518,
+      "grad_norm": 3.644407033920288,
+      "learning_rate": 6.838905775075987e-06,
+      "loss": 1.6268,
+      "mean_token_accuracy": 0.6908416032791138,
+      "num_tokens": 802094.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.016163793103448277,
+      "grad_norm": 2.4331142902374268,
+      "learning_rate": 1.0638297872340424e-05,
+      "loss": 1.2037,
+      "mean_token_accuracy": 0.7343859195709228,
+      "num_tokens": 1204372.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.021551724137931036,
+      "grad_norm": 2.40728497505188,
+      "learning_rate": 1.4437689969604861e-05,
+      "loss": 0.7993,
+      "mean_token_accuracy": 0.8154044389724732,
+      "num_tokens": 1605927.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02693965517241379,
+      "grad_norm": 1.5771023035049438,
+      "learning_rate": 1.8237082066869297e-05,
+      "loss": 0.3527,
+      "mean_token_accuracy": 0.914470088481903,
+      "num_tokens": 2008521.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.032327586206896554,
+      "grad_norm": 0.5942408442497253,
+      "learning_rate": 2.2036474164133735e-05,
+      "loss": 0.1246,
+      "mean_token_accuracy": 0.9693703055381775,
+      "num_tokens": 2411283.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03771551724137931,
+      "grad_norm": 0.49840110540390015,
+      "learning_rate": 2.5835866261398174e-05,
+      "loss": 0.0648,
+      "mean_token_accuracy": 0.9832711696624756,
+      "num_tokens": 2812381.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 0.1990126520395279,
+      "learning_rate": 2.963525835866261e-05,
+      "loss": 0.0325,
+      "mean_token_accuracy": 0.9908363938331604,
+      "num_tokens": 3214234.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04849137931034483,
+      "grad_norm": 0.1390412151813507,
+      "learning_rate": 3.343465045592705e-05,
+      "loss": 0.0239,
+      "mean_token_accuracy": 0.993123197555542,
+      "num_tokens": 3615581.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05387931034482758,
+      "grad_norm": 0.05990126356482506,
+      "learning_rate": 3.5713945110618356e-05,
+      "loss": 0.0216,
+      "mean_token_accuracy": 0.9935235619544983,
+      "num_tokens": 4017171.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.059267241379310345,
+      "grad_norm": 0.05641232803463936,
+      "learning_rate": 3.5710113518316467e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.993712043762207,
+      "num_tokens": 4419002.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.06465517241379311,
+      "grad_norm": 0.06281889975070953,
+      "learning_rate": 3.570202580121256e-05,
+      "loss": 0.0183,
+      "mean_token_accuracy": 0.9941544771194458,
+      "num_tokens": 4822332.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07004310344827586,
+      "grad_norm": 0.05587254464626312,
+      "learning_rate": 3.568968453030844e-05,
+      "loss": 0.0194,
+      "mean_token_accuracy": 0.9937392830848694,
+      "num_tokens": 5223107.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07543103448275862,
+      "grad_norm": 0.04280732572078705,
+      "learning_rate": 3.5673093628766804e-05,
+      "loss": 0.0171,
+      "mean_token_accuracy": 0.9943207740783692,
+      "num_tokens": 5625734.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.08081896551724138,
+      "grad_norm": 0.0779673308134079,
+      "learning_rate": 3.565225837066405e-05,
+      "loss": 0.0177,
+      "mean_token_accuracy": 0.9942807674407959,
+      "num_tokens": 6027742.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 0.057991866022348404,
+      "learning_rate": 3.562718537931378e-05,
+      "loss": 0.0187,
+      "mean_token_accuracy": 0.9939850211143494,
+      "num_tokens": 6428384.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.09159482758620689,
+      "grad_norm": 0.0478542186319828,
+      "learning_rate": 3.559788262516122e-05,
+      "loss": 0.018,
+      "mean_token_accuracy": 0.9940856099128723,
+      "num_tokens": 6829293.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.09698275862068965,
+      "grad_norm": 0.05062701553106308,
+      "learning_rate": 3.55643594232496e-05,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9943302392959594,
+      "num_tokens": 7231379.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.10237068965517242,
+      "grad_norm": 0.06459315121173859,
+      "learning_rate": 3.5526626430258894e-05,
+      "loss": 0.0151,
+      "mean_token_accuracy": 0.9947145700454711,
+      "num_tokens": 7634176.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.10775862068965517,
+      "grad_norm": 0.25823408365249634,
+      "learning_rate": 3.5484695641118264e-05,
+      "loss": 0.016,
+      "mean_token_accuracy": 0.9943834066390991,
+      "num_tokens": 8034981.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.11314655172413793,
+      "grad_norm": 0.0566800981760025,
+      "learning_rate": 3.543858038519294e-05,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9943542599678039,
+      "num_tokens": 8435719.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.11853448275862069,
+      "grad_norm": 0.0464828722178936,
+      "learning_rate": 3.538829532204697e-05,
+      "loss": 0.0164,
+      "mean_token_accuracy": 0.9941744804382324,
+      "num_tokens": 8836428.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.12392241379310345,
+      "grad_norm": 0.049051329493522644,
+      "learning_rate": 3.533385643678309e-05,
+      "loss": 0.0159,
+      "mean_token_accuracy": 0.9941733956336976,
+      "num_tokens": 9237421.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 0.06364122033119202,
+      "learning_rate": 3.527528103496123e-05,
+      "loss": 0.0152,
+      "mean_token_accuracy": 0.9945533514022827,
+      "num_tokens": 9639778.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.13469827586206898,
+      "grad_norm": 0.04338002949953079,
+      "learning_rate": 3.521258773709726e-05,
+      "loss": 0.0155,
+      "mean_token_accuracy": 0.9944260716438293,
+      "num_tokens": 10041852.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.1400862068965517,
+      "grad_norm": 0.04522588849067688,
+      "learning_rate": 3.514579647274372e-05,
+      "loss": 0.0155,
+      "mean_token_accuracy": 0.9944804668426513,
+      "num_tokens": 10444159.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.14547413793103448,
+      "grad_norm": 0.1478981226682663,
+      "learning_rate": 3.5074928474154395e-05,
+      "loss": 0.0149,
+      "mean_token_accuracy": 0.9946131467819214,
+      "num_tokens": 10845771.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.15086206896551724,
+      "grad_norm": 1.2337453365325928,
+      "learning_rate": 3.500000626953483e-05,
+      "loss": 0.0151,
+      "mean_token_accuracy": 0.994551134109497,
+      "num_tokens": 11247804.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.3259663581848145,
+      "learning_rate": 3.492105367588084e-05,
+      "loss": 0.0161,
+      "mean_token_accuracy": 0.9942270040512085,
+      "num_tokens": 11647222.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.16163793103448276,
+      "grad_norm": 0.11509668081998825,
+      "learning_rate": 3.4838095791407325e-05,
+      "loss": 0.0171,
+      "mean_token_accuracy": 0.9939950346946717,
+      "num_tokens": 12048813.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.16702586206896552,
+      "grad_norm": 0.049369506537914276,
+      "learning_rate": 3.4751158987569807e-05,
+      "loss": 0.0152,
+      "mean_token_accuracy": 0.9944715738296509,
+      "num_tokens": 12451442.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.08355387300252914,
+      "learning_rate": 3.4660270900681224e-05,
+      "loss": 0.0151,
+      "mean_token_accuracy": 0.9943839192390442,
+      "num_tokens": 12853398.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.17780172413793102,
+      "grad_norm": 0.062434665858745575,
+      "learning_rate": 3.456546042312664e-05,
+      "loss": 0.0147,
+      "mean_token_accuracy": 0.9945378303527832,
+      "num_tokens": 13256187.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.18318965517241378,
+      "grad_norm": 0.05102328583598137,
+      "learning_rate": 3.446675769417862e-05,
+      "loss": 0.0151,
+      "mean_token_accuracy": 0.9944287657737731,
+      "num_tokens": 13657420.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.18857758620689655,
+      "grad_norm": 0.044247303158044815,
+      "learning_rate": 3.4364194090416284e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9946641683578491,
+      "num_tokens": 14059932.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1939655172413793,
+      "grad_norm": 0.046152565628290176,
+      "learning_rate": 3.425780221575104e-05,
+      "loss": 0.0148,
+      "mean_token_accuracy": 0.9944445013999939,
+      "num_tokens": 14460951.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.19935344827586207,
+      "grad_norm": 0.08260088413953781,
+      "learning_rate": 3.414761589106212e-05,
+      "loss": 0.0146,
+      "mean_token_accuracy": 0.9944788217544556,
+      "num_tokens": 14864383.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.20474137931034483,
+      "grad_norm": 0.058555666357278824,
+      "learning_rate": 3.403367014344524e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9944794178009033,
+      "num_tokens": 15266886.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2101293103448276,
+      "grad_norm": 0.05130434036254883,
+      "learning_rate": 3.3916001195077896e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.9946597218513489,
+      "num_tokens": 15669207.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 0.06096741557121277,
+      "learning_rate": 3.379464645170468e-05,
+      "loss": 0.0143,
+      "mean_token_accuracy": 0.994647204875946,
+      "num_tokens": 16071006.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.2209051724137931,
+      "grad_norm": 0.04882777854800224,
+      "learning_rate": 3.36696444907464e-05,
+      "loss": 0.0148,
+      "mean_token_accuracy": 0.9945741534233093,
+      "num_tokens": 16472933.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.22629310344827586,
+      "grad_norm": 0.039595477283000946,
+      "learning_rate": 3.3541035049036674e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947598457336426,
+      "num_tokens": 16875395.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.23168103448275862,
+      "grad_norm": 0.04643889516592026,
+      "learning_rate": 3.340885901019005e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9945803761482239,
+      "num_tokens": 17277271.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.23706896551724138,
+      "grad_norm": 0.039959874004125595,
+      "learning_rate": 3.327315839160552e-05,
+      "loss": 0.0143,
+      "mean_token_accuracy": 0.9946106910705567,
+      "num_tokens": 17680114.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.24245689655172414,
+      "grad_norm": 0.031239081174135208,
+      "learning_rate": 3.3133976331109576e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9945644021034241,
+      "num_tokens": 18082245.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.2478448275862069,
+      "grad_norm": 0.04183759540319443,
+      "learning_rate": 3.299135707324319e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9946491479873657,
+      "num_tokens": 18483821.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.25323275862068967,
+      "grad_norm": 0.0487377867102623,
+      "learning_rate": 3.2845345955196925e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9947177767753601,
+      "num_tokens": 18884746.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 0.030534762889146805,
+      "learning_rate": 3.2695989392398675e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9946200132369996,
+      "num_tokens": 19286927.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2640086206896552,
+      "grad_norm": 0.04179931804537773,
+      "learning_rate": 3.254333486375871e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9946305751800537,
+      "num_tokens": 19688165.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.26939655172413796,
+      "grad_norm": 0.03564748913049698,
+      "learning_rate": 3.238743089657662e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9946931838989258,
+      "num_tokens": 20090262.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.27478448275862066,
+      "grad_norm": 0.03191967308521271,
+      "learning_rate": 3.222832705111498e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9946922659873962,
+      "num_tokens": 20492107.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.2801724137931034,
+      "grad_norm": 0.048875682055950165,
+      "learning_rate": 3.206607390484465e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9947479844093323,
+      "num_tokens": 20894248.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2855603448275862,
+      "grad_norm": 0.05810167267918587,
+      "learning_rate": 3.190072303636671e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9946684122085572,
+      "num_tokens": 21296720.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.29094827586206895,
+      "grad_norm": 0.035630956292152405,
+      "learning_rate": 3.1732327009016207e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9946584820747375,
+      "num_tokens": 21697077.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.2963362068965517,
+      "grad_norm": 0.036733414977788925,
+      "learning_rate": 3.1560939354152733e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9946447968482971,
+      "num_tokens": 22098063.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 0.052511196583509445,
+      "learning_rate": 3.138661455414342e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9946583271026611,
+      "num_tokens": 22499277.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.30711206896551724,
+      "grad_norm": 0.042709656059741974,
+      "learning_rate": 3.120940802504353e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9947189092636108,
+      "num_tokens": 22902818.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.04298898205161095,
+      "learning_rate": 3.102937609898027e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9947368025779724,
+      "num_tokens": 23304341.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.31788793103448276,
+      "grad_norm": 0.03954196348786354,
+      "learning_rate": 3.084657600624539e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9945488214492798,
+      "num_tokens": 23704925.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.3232758620689655,
+      "grad_norm": 0.03840317949652672,
+      "learning_rate": 3.066106585710227e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.994524884223938,
+      "num_tokens": 24106861.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.3286637931034483,
+      "grad_norm": 0.03564877063035965,
+      "learning_rate": 3.0472904623313255e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9945776104927063,
+      "num_tokens": 24507326.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.33405172413793105,
+      "grad_norm": 0.03882898762822151,
+      "learning_rate": 3.028215211939314e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9946590304374695,
+      "num_tokens": 24908336.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.3394396551724138,
+      "grad_norm": 0.06508338451385498,
+      "learning_rate": 3.0088868983594765e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9946718215942383,
+      "num_tokens": 25309863.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.05758961662650108,
+      "learning_rate": 2.9893116658632732e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948211431503295,
+      "num_tokens": 25711787.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.35021551724137934,
+      "grad_norm": 0.054873988032341,
+      "learning_rate": 2.9694957372151408e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9945468068122864,
+      "num_tokens": 26113810.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.35560344827586204,
+      "grad_norm": 0.036844588816165924,
+      "learning_rate": 2.9494454116943372e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9945004224777222,
+      "num_tokens": 26515442.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3609913793103448,
+      "grad_norm": 0.0447879433631897,
+      "learning_rate": 2.92916706309247e-05,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9946565389633178,
+      "num_tokens": 26914834.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.36637931034482757,
+      "grad_norm": 0.05034846439957619,
+      "learning_rate": 2.9086671376873294e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.994661021232605,
+      "num_tokens": 27315857.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.37176724137931033,
+      "grad_norm": 0.04919150099158287,
+      "learning_rate": 2.887952152193688e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948759317398072,
+      "num_tokens": 27717269.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.3771551724137931,
+      "grad_norm": 0.03395334631204605,
+      "learning_rate": 2.8670286916916988e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.994801688194275,
+      "num_tokens": 28118459.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.38254310344827586,
+      "grad_norm": 0.05123238265514374,
+      "learning_rate": 2.84590340753357e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9947862744331359,
+      "num_tokens": 28518510.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 0.03627648577094078,
+      "learning_rate": 2.8245830152291688e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9946453213691712,
+      "num_tokens": 28921146.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3933189655172414,
+      "grad_norm": 0.035906147211790085,
+      "learning_rate": 2.8030742923112265e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947586536407471,
+      "num_tokens": 29323731.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.39870689655172414,
+      "grad_norm": 0.03345450013875961,
+      "learning_rate": 2.7813840761808355e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948821663856506,
+      "num_tokens": 29725134.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.4040948275862069,
+      "grad_norm": 0.03122451901435852,
+      "learning_rate": 2.7595192619339067e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.994830584526062,
+      "num_tokens": 30127021.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.40948275862068967,
+      "grad_norm": 0.04287945479154587,
+      "learning_rate": 2.7374868001692914e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.994744873046875,
+      "num_tokens": 30528417.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.41487068965517243,
+      "grad_norm": 0.03291918337345123,
+      "learning_rate": 2.7152936947792565e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948456525802613,
+      "num_tokens": 30931584.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.4202586206896552,
+      "grad_norm": 0.027440782636404037,
+      "learning_rate": 2.69294700072302e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.994544506072998,
+      "num_tokens": 31333142.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.42564655172413796,
+      "grad_norm": 0.037700895220041275,
+      "learning_rate": 2.6704538217840525e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9947353482246399,
+      "num_tokens": 31734148.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 0.0358114056289196,
+      "learning_rate": 2.6478213083118573e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948834419250489,
+      "num_tokens": 32137295.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.4364224137931034,
+      "grad_norm": 0.03803620487451553,
+      "learning_rate": 2.6250566549489473e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9947781920433044,
+      "num_tokens": 32538896.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.4418103448275862,
+      "grad_norm": 0.037323955446481705,
+      "learning_rate": 2.6021670983437456e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9946366667747497,
+      "num_tokens": 32940068.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.44719827586206895,
+      "grad_norm": 0.030287249013781548,
+      "learning_rate": 2.5791599148501243e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948618412017822,
+      "num_tokens": 33342556.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.4525862068965517,
+      "grad_norm": 0.026962261646986008,
+      "learning_rate": 2.5560424182143315e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948041200637817,
+      "num_tokens": 33744513.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.4579741379310345,
+      "grad_norm": 0.03837694600224495,
+      "learning_rate": 2.5328219572500253e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9946581721305847,
+      "num_tokens": 34145891.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.46336206896551724,
+      "grad_norm": 0.057087261229753494,
+      "learning_rate": 2.5095059135021593e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9946252107620239,
+      "num_tokens": 34548204.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.04009949788451195,
+      "learning_rate": 2.4861016989004707e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9949546933174134,
+      "num_tokens": 34951187.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 0.03429457172751427,
+      "learning_rate": 2.4626167534032994e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947332978248596,
+      "num_tokens": 35354414.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4795258620689655,
+      "grad_norm": 0.02866434119641781,
+      "learning_rate": 2.439058542632504e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9946959257125855,
+      "num_tokens": 35756305.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.4849137931034483,
+      "grad_norm": 0.04517655074596405,
+      "learning_rate": 2.415434555500219e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948800444602967,
+      "num_tokens": 36158871.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.49030172413793105,
+      "grad_norm": 0.03420615196228027,
+      "learning_rate": 2.3917523018282043e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9947355508804321,
+      "num_tokens": 36560269.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.4956896551724138,
+      "grad_norm": 0.03990909829735756,
+      "learning_rate": 2.3680193099605526e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948008775711059,
+      "num_tokens": 36962062.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.5010775862068966,
+      "grad_norm": 0.029747340828180313,
+      "learning_rate": 2.3442431243705042e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948464274406433,
+      "num_tokens": 37362795.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.5064655172413793,
+      "grad_norm": 0.030703416094183922,
+      "learning_rate": 2.3204313032621397e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.994754946231842,
+      "num_tokens": 37764363.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.5118534482758621,
+      "grad_norm": 0.028925905004143715,
+      "learning_rate": 2.2965914161677012e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9947946190834045,
+      "num_tokens": 38164542.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.03919248282909393,
+      "learning_rate": 2.2727310415413196e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9949039578437805,
+      "num_tokens": 38568071.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.5226293103448276,
+      "grad_norm": 0.04291438311338425,
+      "learning_rate": 2.2488577643499015e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.99475177526474,
+      "num_tokens": 38968166.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.5280172413793104,
+      "grad_norm": 0.03157598897814751,
+      "learning_rate": 2.2249791736619445e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9948109865188599,
+      "num_tokens": 39368710.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.5334051724137931,
+      "grad_norm": 0.047276876866817474,
+      "learning_rate": 2.201102860235052e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947322010993958,
+      "num_tokens": 39771110.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.5387931034482759,
+      "grad_norm": 0.02039233036339283,
+      "learning_rate": 2.17723641410291e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948310494422913,
+      "num_tokens": 40172898.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.5441810344827587,
+      "grad_norm": 0.027669690549373627,
+      "learning_rate": 2.153387422162493e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9947868824005127,
+      "num_tokens": 40574281.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.5495689655172413,
+      "grad_norm": 0.030390165746212006,
+      "learning_rate": 2.1295634657622692e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9949378609657288,
+      "num_tokens": 40977292.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5549568965517241,
+      "grad_norm": 0.03699078410863876,
+      "learning_rate": 2.1057721182921658e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9947897791862488,
+      "num_tokens": 41377321.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 0.02632001042366028,
+      "learning_rate": 2.0820209427760667e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9949733495712281,
+      "num_tokens": 41780166.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5657327586206896,
+      "grad_norm": 0.04134310409426689,
+      "learning_rate": 2.058317489467608e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947456240653991,
+      "num_tokens": 42182491.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.5711206896551724,
+      "grad_norm": 0.10398031771183014,
+      "learning_rate": 2.0346692934500267e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948503613471985,
+      "num_tokens": 42583369.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5765086206896551,
+      "grad_norm": 0.06951781362295151,
+      "learning_rate": 2.011083872240839e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9946800589561462,
+      "num_tokens": 42986169.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.5818965517241379,
+      "grad_norm": 0.0338253527879715,
+      "learning_rate": 1.987568723402096e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947983860969544,
+      "num_tokens": 43388408.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5872844827586207,
+      "grad_norm": 0.043899111449718475,
+      "learning_rate": 1.9641313221569873e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9946236848831177,
+      "num_tokens": 43789151.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.5926724137931034,
+      "grad_norm": 0.037070490419864655,
+      "learning_rate": 1.9407791190135443e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9947730422019958,
+      "num_tokens": 44190220.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5980603448275862,
+      "grad_norm": 0.0317143052816391,
+      "learning_rate": 1.917519537396203e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.994796097278595,
+      "num_tokens": 44592857.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.03147880360484123,
+      "learning_rate": 1.8943599712859686e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947721242904664,
+      "num_tokens": 44994800.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.6088362068965517,
+      "grad_norm": 0.024809807538986206,
+      "learning_rate": 1.8713077828699518e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.994830334186554,
+      "num_tokens": 45398025.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.6142241379310345,
+      "grad_norm": 0.029903240501880646,
+      "learning_rate": 1.8483703002009994e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9947473049163819,
+      "num_tokens": 45799951.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.6196120689655172,
+      "grad_norm": 0.02878548949956894,
+      "learning_rate": 1.8255548148681885e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948133111000061,
+      "num_tokens": 46200476.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.03262052685022354,
+      "learning_rate": 1.8028685796788967e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948443055152894,
+      "num_tokens": 46602865.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.6303879310344828,
+      "grad_norm": 0.037397563457489014,
+      "learning_rate": 1.7803188063532184e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9950237035751343,
+      "num_tokens": 47004445.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.6357758620689655,
+      "grad_norm": 0.02558806724846363,
+      "learning_rate": 1.7579126632314283e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9947809338569641,
+      "num_tokens": 47405509.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.6411637931034483,
+      "grad_norm": 0.03402222320437431,
+      "learning_rate": 1.7356572729952424e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.994775903224945,
+      "num_tokens": 47807070.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 0.041079867631196976,
+      "learning_rate": 1.713559710403587e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9946501970291137,
+      "num_tokens": 48208600.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6519396551724138,
+      "grad_norm": 0.034396298229694366,
+      "learning_rate": 1.6916270000436114e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948722124099731,
+      "num_tokens": 48611166.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.6573275862068966,
+      "grad_norm": 0.03436857834458351,
+      "learning_rate": 1.6698661140976403e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948982000350952,
+      "num_tokens": 49013571.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6627155172413793,
+      "grad_norm": 0.03140538930892944,
+      "learning_rate": 1.6482839701267902e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9947989225387573,
+      "num_tokens": 49414184.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.6681034482758621,
+      "grad_norm": 0.05165150761604309,
+      "learning_rate": 1.626887428871947e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947850465774536,
+      "num_tokens": 49815792.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6734913793103449,
+      "grad_norm": 0.04548334330320358,
+      "learning_rate": 1.6056832920728103e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949025988578797,
+      "num_tokens": 50218315.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.6788793103448276,
+      "grad_norm": 0.033490464091300964,
+      "learning_rate": 1.5846783003056866e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9946399450302124,
+      "num_tokens": 50619471.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.6842672413793104,
+      "grad_norm": 0.028969909995794296,
+      "learning_rate": 1.5638791308407327e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948153138160706,
+      "num_tokens": 51020999.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.027664504945278168,
+      "learning_rate": 1.5432923955193175e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9948143601417542,
+      "num_tokens": 51422802.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.6950431034482759,
+      "grad_norm": 0.03504246845841408,
+      "learning_rate": 1.5229246386521894e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948045015335083,
+      "num_tokens": 51824364.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.7004310344827587,
+      "grad_norm": 0.050419677048921585,
+      "learning_rate": 1.502782334939104e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949135184288025,
+      "num_tokens": 52226195.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.7058189655172413,
+      "grad_norm": 0.028731906786561012,
+      "learning_rate": 1.4828718874105872e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948068141937256,
+      "num_tokens": 52627325.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.7112068965517241,
+      "grad_norm": 0.04866371676325798,
+      "learning_rate": 1.4631996253924749e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.994967234134674,
+      "num_tokens": 53029791.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.7165948275862069,
+      "grad_norm": 0.031085016205906868,
+      "learning_rate": 1.4437718024938859e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950807452201843,
+      "num_tokens": 53431762.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.7219827586206896,
+      "grad_norm": 0.029772335663437843,
+      "learning_rate": 1.4245945946192675e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947867870330811,
+      "num_tokens": 53834592.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.7273706896551724,
+      "grad_norm": 0.042420390993356705,
+      "learning_rate": 1.4056740980051348e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9948947906494141,
+      "num_tokens": 54236113.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 0.04056272655725479,
+      "learning_rate": 1.3870163272821422e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9950251102447509,
+      "num_tokens": 54638773.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.7381465517241379,
+      "grad_norm": 0.02548728883266449,
+      "learning_rate": 1.3686272135630939e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949590563774109,
+      "num_tokens": 55039287.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.7435344827586207,
+      "grad_norm": 0.02634035237133503,
+      "learning_rate": 1.3505126025575055e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948865652084351,
+      "num_tokens": 55440154.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.7489224137931034,
+      "grad_norm": 0.035474665462970734,
+      "learning_rate": 1.3326782527133116e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947669029235839,
+      "num_tokens": 55840791.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.7543103448275862,
+      "grad_norm": 0.03327346593141556,
+      "learning_rate": 1.3151298333863147e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947926640510559,
+      "num_tokens": 56242887.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.759698275862069,
+      "grad_norm": 0.027285410091280937,
+      "learning_rate": 1.2978729230379578e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9950402617454529,
+      "num_tokens": 56645470.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.7650862068965517,
+      "grad_norm": 0.025033418089151382,
+      "learning_rate": 1.2809130074619848e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9947838306427002,
+      "num_tokens": 57047650.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7704741379310345,
+      "grad_norm": 0.036593757569789886,
+      "learning_rate": 1.2642554780405692e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949217319488526,
+      "num_tokens": 57448504.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.05492115020751953,
+      "learning_rate": 1.2479056300304417e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948967695236206,
+      "num_tokens": 57850023.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.02926582470536232,
+      "learning_rate": 1.2318686608795911e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948256611824036,
+      "num_tokens": 58252427.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.7866379310344828,
+      "grad_norm": 0.0516173429787159,
+      "learning_rate": 1.216149668575042e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948697447776794,
+      "num_tokens": 58654151.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7920258620689655,
+      "grad_norm": 0.031214216724038124,
+      "learning_rate": 1.2007536500222625e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948197126388549,
+      "num_tokens": 59057239.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.7974137931034483,
+      "grad_norm": 0.19109757244586945,
+      "learning_rate": 1.1856854994566963e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948896765708923,
+      "num_tokens": 59457329.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.802801724137931,
+      "grad_norm": 0.07098083943128586,
+      "learning_rate": 1.170950006887937e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.994968032836914,
+      "num_tokens": 59858237.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.8081896551724138,
+      "grad_norm": 0.029992876574397087,
+      "learning_rate": 1.1565518565770333e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947031497955322,
+      "num_tokens": 60258966.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.8135775862068966,
+      "grad_norm": 0.02831091545522213,
+      "learning_rate": 1.1424956255474115e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949681520462036,
+      "num_tokens": 60660391.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.03193649649620056,
+      "learning_rate": 1.128785782129885e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948087692260742,
+      "num_tokens": 61063253.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.8243534482758621,
+      "grad_norm": 0.03372105956077576,
+      "learning_rate": 1.1154266845422202e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948907732963562,
+      "num_tokens": 61464810.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.8297413793103449,
+      "grad_norm": 0.03639473393559456,
+      "learning_rate": 1.1024225795037032e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948284268379212,
+      "num_tokens": 61866531.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.8351293103448276,
+      "grad_norm": 0.028340987861156464,
+      "learning_rate": 1.089777600885151e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949876070022583,
+      "num_tokens": 62268172.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.8405172413793104,
+      "grad_norm": 0.027911396697163582,
+      "learning_rate": 1.077495768394797e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949463605880737,
+      "num_tokens": 62669240.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.8459051724137931,
+      "grad_norm": 0.0304352268576622,
+      "learning_rate": 1.065580986300468e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9947375655174255,
+      "num_tokens": 63070830.0,
+      "step": 785
+    },
+    {
+      "epoch": 0.8512931034482759,
+      "grad_norm": 0.03557021915912628,
+      "learning_rate": 1.0540370421884568e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949083209037781,
+      "num_tokens": 63472170.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.8566810344827587,
+      "grad_norm": 0.04443613067269325,
+      "learning_rate": 1.0428676057594878e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9950238466262817,
+      "num_tokens": 63874037.0,
+      "step": 795
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.024053096771240234,
+      "learning_rate": 1.0320762276621562e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949499011039734,
+      "num_tokens": 64275344.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8674568965517241,
+      "grad_norm": 0.03015071339905262,
+      "learning_rate": 1.0216663383642168e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948014855384827,
+      "num_tokens": 64677126.0,
+      "step": 805
+    },
+    {
+      "epoch": 0.8728448275862069,
+      "grad_norm": 0.031103769317269325,
+      "learning_rate": 1.0116412470620679e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950470447540283,
+      "num_tokens": 65079920.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.8782327586206896,
+      "grad_norm": 0.03264924883842468,
+      "learning_rate": 1.0020041406287986e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948317050933838,
+      "num_tokens": 65481506.0,
+      "step": 815
+    },
+    {
+      "epoch": 0.8836206896551724,
+      "grad_norm": 0.02971888706088066,
+      "learning_rate": 9.927580826011085e-06,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9949733018875122,
+      "num_tokens": 65884331.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.8890086206896551,
+      "grad_norm": 0.03420015424489975,
+      "learning_rate": 9.839060122054454e-06,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9949661493301392,
+      "num_tokens": 66285759.0,
+      "step": 825
+    },
+    {
+      "epoch": 0.8943965517241379,
+      "grad_norm": 0.045038193464279175,
+      "learning_rate": 9.75450743423654e-06,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948656320571899,
+      "num_tokens": 66685714.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.8997844827586207,
+      "grad_norm": 0.035762231796979904,
+      "learning_rate": 9.673949640984395e-06,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9948834419250489,
+      "num_tokens": 67086597.0,
+      "step": 835
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 0.03386284038424492,
+      "learning_rate": 9.597412350789308e-06,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949593067169189,
+      "num_tokens": 67489472.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.9105603448275862,
+      "grad_norm": 0.02994493395090103,
+      "learning_rate": 9.52491989406613e-06,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9949299573898316,
+      "num_tokens": 67890506.0,
+      "step": 845
+    },
+    {
+      "epoch": 0.915948275862069,
+      "grad_norm": 0.030689487233757973,
+      "learning_rate": 9.456495315418894e-06,
+      "loss": 0.0126,
+      "mean_token_accuracy": 0.9950518608093262,
+      "num_tokens": 68291917.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.9213362068965517,
+      "grad_norm": 0.0423220731317997,
+      "learning_rate": 9.392160366315146e-06,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9946566700935364,
+      "num_tokens": 68693565.0,
+      "step": 855
+    },
+    {
+      "epoch": 0.9267241379310345,
+      "grad_norm": 0.0269051231443882,
+      "learning_rate": 9.331935498171415e-06,
+      "loss": 0.0126,
+      "mean_token_accuracy": 0.9951117157936096,
+      "num_tokens": 69094557.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.9321120689655172,
+      "grad_norm": 0.03736714646220207,
+      "learning_rate": 9.275839855851889e-06,
+      "loss": 0.0126,
+      "mean_token_accuracy": 0.9950791954994201,
+      "num_tokens": 69496215.0,
+      "step": 865
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.038321010768413544,
+      "learning_rate": 9.223891271582473e-06,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9950317859649658,
+      "num_tokens": 69897495.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.9428879310344828,
+      "grad_norm": 0.03330431133508682,
+      "learning_rate": 9.176106259282111e-06,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949549078941345,
+      "num_tokens": 70298929.0,
+      "step": 875
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.03637678548693657,
+      "learning_rate": 9.132500009313176e-06,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949822068214417,
+      "num_tokens": 70700320.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.9536637931034483,
+      "grad_norm": 0.02678218111395836,
+      "learning_rate": 9.093086383652602e-06,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9948176503181457,
+      "num_tokens": 71100703.0,
+      "step": 885
+    },
+    {
+      "epoch": 0.959051724137931,
+      "grad_norm": 0.040675800293684006,
+      "learning_rate": 9.057877911485328e-06,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9950784921646119,
+      "num_tokens": 71502763.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.9644396551724138,
+      "grad_norm": 0.03423236683011055,
+      "learning_rate": 9.026885785221381e-06,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9948654890060424,
+      "num_tokens": 71903543.0,
+      "step": 895
+    },
+    {
+      "epoch": 0.9698275862068966,
+      "grad_norm": 0.04655428230762482,
+      "learning_rate": 9.000119856937926e-06,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950368642807007,
+      "num_tokens": 72304889.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.9752155172413793,
+      "grad_norm": 0.0383138544857502,
+      "learning_rate": 8.977588635247394e-06,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9947501182556152,
+      "num_tokens": 72706282.0,
+      "step": 905
+    },
+    {
+      "epoch": 0.9806034482758621,
+      "grad_norm": 0.03898213803768158,
+      "learning_rate": 8.95929928259269e-06,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949674487113953,
+      "num_tokens": 73109508.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.9859913793103449,
+      "grad_norm": 0.03106722980737686,
+      "learning_rate": 8.945257612970317e-06,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9950725197792053,
+      "num_tokens": 73511750.0,
+      "step": 915
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.03446138650178909,
+      "learning_rate": 8.935468090082163e-06,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950355887413025,
+      "num_tokens": 73912567.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9967672413793104,
+      "grad_norm": 0.04413456842303276,
+      "learning_rate": 8.929933825916554e-06,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9949971795082092,
+      "num_tokens": 74313918.0,
+      "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": 1.7417098212933632e+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 sha256:0772abe9029080643354dff6a5ca3fc9494d60ba351b840bfc518cd89fe774d1
+size 6545