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": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_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:b694d6e881a14aaa9b9500200cf483b480ac262ff5cce39cae218aff37f8672b
+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": 11.118752479553223,
+      "learning_rate": 3.0395136778115497e-06,
+      "loss": 1.8415,
+      "mean_token_accuracy": 0.6949578166007996,
+      "num_tokens": 400768.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.010775862068965518,
+      "grad_norm": 3.6559956073760986,
+      "learning_rate": 6.838905775075987e-06,
+      "loss": 1.5636,
+      "mean_token_accuracy": 0.7073541164398194,
+      "num_tokens": 802094.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.016163793103448277,
+      "grad_norm": 2.47355318069458,
+      "learning_rate": 1.0638297872340424e-05,
+      "loss": 1.1447,
+      "mean_token_accuracy": 0.7477938294410705,
+      "num_tokens": 1204372.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.021551724137931036,
+      "grad_norm": 2.6038503646850586,
+      "learning_rate": 1.4437689969604861e-05,
+      "loss": 0.7431,
+      "mean_token_accuracy": 0.8272091269493103,
+      "num_tokens": 1605927.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02693965517241379,
+      "grad_norm": 1.5864155292510986,
+      "learning_rate": 1.8237082066869297e-05,
+      "loss": 0.3175,
+      "mean_token_accuracy": 0.9232812523841858,
+      "num_tokens": 2008521.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.032327586206896554,
+      "grad_norm": 0.40001317858695984,
+      "learning_rate": 2.2036474164133735e-05,
+      "loss": 0.1035,
+      "mean_token_accuracy": 0.9760098576545715,
+      "num_tokens": 2411283.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03771551724137931,
+      "grad_norm": 0.37432125210762024,
+      "learning_rate": 2.5835866261398174e-05,
+      "loss": 0.0492,
+      "mean_token_accuracy": 0.9880791783332825,
+      "num_tokens": 2812381.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 0.12147562205791473,
+      "learning_rate": 2.963525835866261e-05,
+      "loss": 0.0203,
+      "mean_token_accuracy": 0.9950897693634033,
+      "num_tokens": 3214234.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04849137931034483,
+      "grad_norm": 0.07509531080722809,
+      "learning_rate": 3.343465045592705e-05,
+      "loss": 0.0121,
+      "mean_token_accuracy": 0.9974198818206788,
+      "num_tokens": 3615581.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05387931034482758,
+      "grad_norm": 4.481222629547119,
+      "learning_rate": 3.5713945110618356e-05,
+      "loss": 0.0156,
+      "mean_token_accuracy": 0.9971701502799988,
+      "num_tokens": 4017171.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.059267241379310345,
+      "grad_norm": 1.3098348379135132,
+      "learning_rate": 3.5710113518316467e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9971798539161683,
+      "num_tokens": 4419002.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.06465517241379311,
+      "grad_norm": 0.07002394646406174,
+      "learning_rate": 3.570202580121256e-05,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.9981415390968322,
+      "num_tokens": 4822332.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07004310344827586,
+      "grad_norm": 0.05212470144033432,
+      "learning_rate": 3.568968453030844e-05,
+      "loss": 0.0094,
+      "mean_token_accuracy": 0.9978966236114502,
+      "num_tokens": 5223107.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07543103448275862,
+      "grad_norm": 0.02627100795507431,
+      "learning_rate": 3.5673093628766804e-05,
+      "loss": 0.0062,
+      "mean_token_accuracy": 0.9985594034194947,
+      "num_tokens": 5625734.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.08081896551724138,
+      "grad_norm": 0.0241162721067667,
+      "learning_rate": 3.565225837066405e-05,
+      "loss": 0.0071,
+      "mean_token_accuracy": 0.9983980655670166,
+      "num_tokens": 6027742.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 0.03432080149650574,
+      "learning_rate": 3.562718537931378e-05,
+      "loss": 0.0084,
+      "mean_token_accuracy": 0.9979879975318908,
+      "num_tokens": 6428384.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.09159482758620689,
+      "grad_norm": 0.028015699237585068,
+      "learning_rate": 3.559788262516122e-05,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.9981574892997742,
+      "num_tokens": 6829293.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.09698275862068965,
+      "grad_norm": 0.0296330489218235,
+      "learning_rate": 3.55643594232496e-05,
+      "loss": 0.0061,
+      "mean_token_accuracy": 0.9985599040985107,
+      "num_tokens": 7231379.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.10237068965517242,
+      "grad_norm": 0.027567585930228233,
+      "learning_rate": 3.5526626430258894e-05,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9988541007041931,
+      "num_tokens": 7634176.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.10775862068965517,
+      "grad_norm": 0.03464515879750252,
+      "learning_rate": 3.5484695641118264e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.998340117931366,
+      "num_tokens": 8034981.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.11314655172413793,
+      "grad_norm": 0.03444606438279152,
+      "learning_rate": 3.543858038519294e-05,
+      "loss": 0.0063,
+      "mean_token_accuracy": 0.9984558463096619,
+      "num_tokens": 8435719.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.11853448275862069,
+      "grad_norm": 0.02906894125044346,
+      "learning_rate": 3.538829532204697e-05,
+      "loss": 0.0059,
+      "mean_token_accuracy": 0.9984469652175904,
+      "num_tokens": 8836428.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.12392241379310345,
+      "grad_norm": 0.026567254215478897,
+      "learning_rate": 3.533385643678309e-05,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9984662294387817,
+      "num_tokens": 9237421.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 0.028587114065885544,
+      "learning_rate": 3.527528103496123e-05,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9987730145454407,
+      "num_tokens": 9639778.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.13469827586206898,
+      "grad_norm": 0.02611548639833927,
+      "learning_rate": 3.521258773709726e-05,
+      "loss": 0.005,
+      "mean_token_accuracy": 0.9985883116722107,
+      "num_tokens": 10041852.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.1400862068965517,
+      "grad_norm": 0.028025874868035316,
+      "learning_rate": 3.514579647274372e-05,
+      "loss": 0.0049,
+      "mean_token_accuracy": 0.998680031299591,
+      "num_tokens": 10444159.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.14547413793103448,
+      "grad_norm": 0.04556312412023544,
+      "learning_rate": 3.5074928474154395e-05,
+      "loss": 0.0044,
+      "mean_token_accuracy": 0.9987163543701172,
+      "num_tokens": 10845771.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.15086206896551724,
+      "grad_norm": 0.04252542927861214,
+      "learning_rate": 3.500000626953483e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9987828731536865,
+      "num_tokens": 11247804.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.039127446711063385,
+      "learning_rate": 3.492105367588084e-05,
+      "loss": 0.0057,
+      "mean_token_accuracy": 0.9981782674789429,
+      "num_tokens": 11647222.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.16163793103448276,
+      "grad_norm": 0.02822212316095829,
+      "learning_rate": 3.4838095791407325e-05,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.998698377609253,
+      "num_tokens": 12048813.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.16702586206896552,
+      "grad_norm": 0.021515976637601852,
+      "learning_rate": 3.4751158987569807e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988813161849975,
+      "num_tokens": 12451442.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.04444750025868416,
+      "learning_rate": 3.4660270900681224e-05,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.998634934425354,
+      "num_tokens": 12853398.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.17780172413793102,
+      "grad_norm": 0.0250164233148098,
+      "learning_rate": 3.456546042312664e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9989552855491638,
+      "num_tokens": 13256187.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.18318965517241378,
+      "grad_norm": 0.029835877940058708,
+      "learning_rate": 3.446675769417862e-05,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9987164378166199,
+      "num_tokens": 13657420.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.18857758620689655,
+      "grad_norm": 0.02986965700984001,
+      "learning_rate": 3.4364194090416284e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9989364504814148,
+      "num_tokens": 14059932.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1939655172413793,
+      "grad_norm": 0.028351912274956703,
+      "learning_rate": 3.425780221575104e-05,
+      "loss": 0.0043,
+      "mean_token_accuracy": 0.9985925316810608,
+      "num_tokens": 14460951.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.19935344827586207,
+      "grad_norm": 0.016597596928477287,
+      "learning_rate": 3.414761589106212e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990380048751831,
+      "num_tokens": 14864383.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.20474137931034483,
+      "grad_norm": 0.031333401799201965,
+      "learning_rate": 3.403367014344524e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988710880279541,
+      "num_tokens": 15266886.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2101293103448276,
+      "grad_norm": 0.02912697196006775,
+      "learning_rate": 3.3916001195077896e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.998849093914032,
+      "num_tokens": 15669207.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 0.029591375961899757,
+      "learning_rate": 3.379464645170468e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988542199134827,
+      "num_tokens": 16071006.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.2209051724137931,
+      "grad_norm": 0.02394878678023815,
+      "learning_rate": 3.36696444907464e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9987379312515259,
+      "num_tokens": 16472933.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.22629310344827586,
+      "grad_norm": 0.023629413917660713,
+      "learning_rate": 3.3541035049036674e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989330530166626,
+      "num_tokens": 16875395.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.23168103448275862,
+      "grad_norm": 0.032314199954271317,
+      "learning_rate": 3.340885901019005e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9989269018173218,
+      "num_tokens": 17277271.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.23706896551724138,
+      "grad_norm": 0.0229765884578228,
+      "learning_rate": 3.327315839160552e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989865899085999,
+      "num_tokens": 17680114.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.24245689655172414,
+      "grad_norm": 0.024461975321173668,
+      "learning_rate": 3.3133976331109576e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9988359451293946,
+      "num_tokens": 18082245.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.2478448275862069,
+      "grad_norm": 0.026213262230157852,
+      "learning_rate": 3.299135707324319e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987861156463623,
+      "num_tokens": 18483821.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.25323275862068967,
+      "grad_norm": 0.032358359545469284,
+      "learning_rate": 3.2845345955196925e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987888932228088,
+      "num_tokens": 18884746.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 0.021628115326166153,
+      "learning_rate": 3.2695989392398675e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988565802574157,
+      "num_tokens": 19286927.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2640086206896552,
+      "grad_norm": 0.032560136169195175,
+      "learning_rate": 3.254333486375871e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.998822295665741,
+      "num_tokens": 19688165.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.26939655172413796,
+      "grad_norm": 0.026628414168953896,
+      "learning_rate": 3.238743089657662e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988994359970093,
+      "num_tokens": 20090262.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.27478448275862066,
+      "grad_norm": 0.021604420617222786,
+      "learning_rate": 3.222832705111498e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988043308258057,
+      "num_tokens": 20492107.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.2801724137931034,
+      "grad_norm": 0.027409082278609276,
+      "learning_rate": 3.206607390484465e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988442182540893,
+      "num_tokens": 20894248.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2855603448275862,
+      "grad_norm": 0.031035037711262703,
+      "learning_rate": 3.190072303636671e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989655137062072,
+      "num_tokens": 21296720.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.29094827586206895,
+      "grad_norm": 0.025560248643159866,
+      "learning_rate": 3.1732327009016207e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9986896753311157,
+      "num_tokens": 21697077.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.2963362068965517,
+      "grad_norm": 0.027044419199228287,
+      "learning_rate": 3.1560939354152733e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987533926963806,
+      "num_tokens": 22098063.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 0.04460646212100983,
+      "learning_rate": 3.138661455414342e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987125039100647,
+      "num_tokens": 22499277.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.30711206896551724,
+      "grad_norm": 0.02684149332344532,
+      "learning_rate": 3.120940802504353e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990176081657409,
+      "num_tokens": 22902818.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.025129975751042366,
+      "learning_rate": 3.102937609898027e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9988201856613159,
+      "num_tokens": 23304341.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.31788793103448276,
+      "grad_norm": 0.03148937597870827,
+      "learning_rate": 3.084657600624539e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9986629009246826,
+      "num_tokens": 23704925.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.3232758620689655,
+      "grad_norm": 0.030350444838404655,
+      "learning_rate": 3.066106585710227e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988539814949036,
+      "num_tokens": 24106861.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.3286637931034483,
+      "grad_norm": 0.027379781007766724,
+      "learning_rate": 3.0472904623313255e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9986437201499939,
+      "num_tokens": 24507326.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.33405172413793105,
+      "grad_norm": 0.028325095772743225,
+      "learning_rate": 3.028215211939314e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988056659698487,
+      "num_tokens": 24908336.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.3394396551724138,
+      "grad_norm": 0.022994231432676315,
+      "learning_rate": 3.0088868983594765e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988773822784424,
+      "num_tokens": 25309863.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.02782243676483631,
+      "learning_rate": 2.9893116658632732e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988821387290955,
+      "num_tokens": 25711787.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.35021551724137934,
+      "grad_norm": 0.01946713961660862,
+      "learning_rate": 2.9694957372151408e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9987824201583863,
+      "num_tokens": 26113810.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.35560344827586204,
+      "grad_norm": 0.02599230408668518,
+      "learning_rate": 2.9494454116943372e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988673329353333,
+      "num_tokens": 26515442.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3609913793103448,
+      "grad_norm": 0.0248300451785326,
+      "learning_rate": 2.92916706309247e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9985779404640198,
+      "num_tokens": 26914834.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.36637931034482757,
+      "grad_norm": 0.028298387303948402,
+      "learning_rate": 2.9086671376873294e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.998742938041687,
+      "num_tokens": 27315857.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.37176724137931033,
+      "grad_norm": 0.03281069174408913,
+      "learning_rate": 2.887952152193688e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988440275192261,
+      "num_tokens": 27717269.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.3771551724137931,
+      "grad_norm": 0.03256155177950859,
+      "learning_rate": 2.8670286916916988e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9987234234809875,
+      "num_tokens": 28118459.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.38254310344827586,
+      "grad_norm": 0.022085973992943764,
+      "learning_rate": 2.84590340753357e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987329363822937,
+      "num_tokens": 28518510.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 0.017243554815649986,
+      "learning_rate": 2.8245830152291688e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990796089172364,
+      "num_tokens": 28921146.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3933189655172414,
+      "grad_norm": 0.018972132354974747,
+      "learning_rate": 2.8030742923112265e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990222811698913,
+      "num_tokens": 29323731.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.39870689655172414,
+      "grad_norm": 0.02033703401684761,
+      "learning_rate": 2.7813840761808355e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988647699356079,
+      "num_tokens": 29725134.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.4040948275862069,
+      "grad_norm": 0.02075575664639473,
+      "learning_rate": 2.7595192619339067e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998983871936798,
+      "num_tokens": 30127021.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.40948275862068967,
+      "grad_norm": 0.01936476305127144,
+      "learning_rate": 2.7374868001692914e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988717794418335,
+      "num_tokens": 30528417.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.41487068965517243,
+      "grad_norm": 0.022590680047869682,
+      "learning_rate": 2.7152936947792565e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991134643554688,
+      "num_tokens": 30931584.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.4202586206896552,
+      "grad_norm": 0.029338538646697998,
+      "learning_rate": 2.69294700072302e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988523483276367,
+      "num_tokens": 31333142.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.42564655172413796,
+      "grad_norm": 0.028044741600751877,
+      "learning_rate": 2.6704538217840525e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987943410873413,
+      "num_tokens": 31734148.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 0.02476726658642292,
+      "learning_rate": 2.6478213083118573e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990673303604126,
+      "num_tokens": 32137295.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.4364224137931034,
+      "grad_norm": 0.021439680829644203,
+      "learning_rate": 2.6250566549489473e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9989170432090759,
+      "num_tokens": 32538896.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.4418103448275862,
+      "grad_norm": 0.027145177125930786,
+      "learning_rate": 2.6021670983437456e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987870693206787,
+      "num_tokens": 32940068.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.44719827586206895,
+      "grad_norm": 0.015717459842562675,
+      "learning_rate": 2.5791599148501243e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990354537963867,
+      "num_tokens": 33342556.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.4525862068965517,
+      "grad_norm": 0.016596542671322823,
+      "learning_rate": 2.5560424182143315e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989644050598144,
+      "num_tokens": 33744513.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.4579741379310345,
+      "grad_norm": 0.022335536777973175,
+      "learning_rate": 2.5328219572500253e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987898945808411,
+      "num_tokens": 34145891.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.46336206896551724,
+      "grad_norm": 0.026606585830450058,
+      "learning_rate": 2.5095059135021593e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989604115486145,
+      "num_tokens": 34548204.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.022704385221004486,
+      "learning_rate": 2.4861016989004707e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991106033325196,
+      "num_tokens": 34951187.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 0.04150070250034332,
+      "learning_rate": 2.4626167534032994e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991032481193542,
+      "num_tokens": 35354414.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4795258620689655,
+      "grad_norm": 0.02489551343023777,
+      "learning_rate": 2.439058542632504e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989043354988099,
+      "num_tokens": 35756305.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.4849137931034483,
+      "grad_norm": 0.027949925512075424,
+      "learning_rate": 2.415434555500219e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990329504013061,
+      "num_tokens": 36158871.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.49030172413793105,
+      "grad_norm": 0.02412698045372963,
+      "learning_rate": 2.3917523018282043e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988869667053223,
+      "num_tokens": 36560269.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.4956896551724138,
+      "grad_norm": 0.02200850285589695,
+      "learning_rate": 2.3680193099605526e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989560723304749,
+      "num_tokens": 36962062.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.5010775862068966,
+      "grad_norm": 0.01985372044146061,
+      "learning_rate": 2.3442431243705042e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988078117370606,
+      "num_tokens": 37362795.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.5064655172413793,
+      "grad_norm": 0.0251405481249094,
+      "learning_rate": 2.3204313032621397e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988798141479492,
+      "num_tokens": 37764363.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.5118534482758621,
+      "grad_norm": 0.017319003120064735,
+      "learning_rate": 2.2965914161677012e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987285256385803,
+      "num_tokens": 38164542.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.02730216644704342,
+      "learning_rate": 2.2727310415413196e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999100661277771,
+      "num_tokens": 38568071.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.5226293103448276,
+      "grad_norm": 0.02837636135518551,
+      "learning_rate": 2.2488577643499015e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9986386775970459,
+      "num_tokens": 38968166.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.5280172413793104,
+      "grad_norm": 0.02115839347243309,
+      "learning_rate": 2.2249791736619445e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987141489982605,
+      "num_tokens": 39368710.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.5334051724137931,
+      "grad_norm": 0.01951654814183712,
+      "learning_rate": 2.201102860235052e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989643692970276,
+      "num_tokens": 39771110.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.5387931034482759,
+      "grad_norm": 0.011981317773461342,
+      "learning_rate": 2.17723641410291e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988933444023133,
+      "num_tokens": 40172898.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.5441810344827587,
+      "grad_norm": 0.018850047141313553,
+      "learning_rate": 2.153387422162493e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988592743873597,
+      "num_tokens": 40574281.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.5495689655172413,
+      "grad_norm": 0.018220078200101852,
+      "learning_rate": 2.1295634657622692e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9991109728813171,
+      "num_tokens": 40977292.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5549568965517241,
+      "grad_norm": 0.02601587027311325,
+      "learning_rate": 2.1057721182921658e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987223386764527,
+      "num_tokens": 41377321.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 0.017099367454648018,
+      "learning_rate": 2.0820209427760667e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9991111755371094,
+      "num_tokens": 41780166.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5657327586206896,
+      "grad_norm": 0.01895494945347309,
+      "learning_rate": 2.058317489467608e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990185737609864,
+      "num_tokens": 42182491.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.5711206896551724,
+      "grad_norm": 0.019429514184594154,
+      "learning_rate": 2.0346692934500267e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9987874507904053,
+      "num_tokens": 42583369.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5765086206896551,
+      "grad_norm": 0.029150033369660378,
+      "learning_rate": 2.011083872240839e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989708065986633,
+      "num_tokens": 42986169.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.5818965517241379,
+      "grad_norm": 0.01646232232451439,
+      "learning_rate": 1.987568723402096e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990198969841003,
+      "num_tokens": 43388408.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5872844827586207,
+      "grad_norm": 0.029317881911993027,
+      "learning_rate": 1.9641313221569873e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987244963645935,
+      "num_tokens": 43789151.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.5926724137931034,
+      "grad_norm": 0.026302972808480263,
+      "learning_rate": 1.9407791190135443e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988860845565796,
+      "num_tokens": 44190220.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5980603448275862,
+      "grad_norm": 0.02601112239062786,
+      "learning_rate": 1.917519537396203e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990330338478088,
+      "num_tokens": 44592857.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.019996047019958496,
+      "learning_rate": 1.8943599712859686e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989817619323731,
+      "num_tokens": 44994800.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.6088362068965517,
+      "grad_norm": 0.015889732167124748,
+      "learning_rate": 1.8713077828699518e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991264820098877,
+      "num_tokens": 45398025.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.6142241379310345,
+      "grad_norm": 0.01739376410841942,
+      "learning_rate": 1.8483703002009994e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989471673965454,
+      "num_tokens": 45799951.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.6196120689655172,
+      "grad_norm": 0.019734220579266548,
+      "learning_rate": 1.8255548148681885e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987558484077453,
+      "num_tokens": 46200476.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.028406864032149315,
+      "learning_rate": 1.8028685796788967e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9990233540534973,
+      "num_tokens": 46602865.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.6303879310344828,
+      "grad_norm": 0.029668040573596954,
+      "learning_rate": 1.7803188063532184e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989258170127868,
+      "num_tokens": 47004445.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.6357758620689655,
+      "grad_norm": 0.017754795029759407,
+      "learning_rate": 1.7579126632314283e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.998816168308258,
+      "num_tokens": 47405509.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.6411637931034483,
+      "grad_norm": 0.023762712255120277,
+      "learning_rate": 1.7356572729952424e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9989230871200562,
+      "num_tokens": 47807070.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 0.019800549373030663,
+      "learning_rate": 1.713559710403587e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988937497138977,
+      "num_tokens": 48208600.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6519396551724138,
+      "grad_norm": 0.0168940257281065,
+      "learning_rate": 1.6916270000436114e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.998992097377777,
+      "num_tokens": 48611166.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.6573275862068966,
+      "grad_norm": 0.020920807495713234,
+      "learning_rate": 1.6698661140976403e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990215063095093,
+      "num_tokens": 49013571.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6627155172413793,
+      "grad_norm": 0.01899370178580284,
+      "learning_rate": 1.6482839701267902e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9987942934036255,
+      "num_tokens": 49414184.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.6681034482758621,
+      "grad_norm": 0.021047541871666908,
+      "learning_rate": 1.626887428871947e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988746643066406,
+      "num_tokens": 49815792.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6734913793103449,
+      "grad_norm": 0.03720097616314888,
+      "learning_rate": 1.6056832920728103e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.998986005783081,
+      "num_tokens": 50218315.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.6788793103448276,
+      "grad_norm": 0.018089212477207184,
+      "learning_rate": 1.5846783003056866e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988272428512573,
+      "num_tokens": 50619471.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.6842672413793104,
+      "grad_norm": 0.01994973048567772,
+      "learning_rate": 1.5638791308407327e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988573670387269,
+      "num_tokens": 51020999.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.022940637543797493,
+      "learning_rate": 1.5432923955193175e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989816308021545,
+      "num_tokens": 51422802.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.6950431034482759,
+      "grad_norm": 0.02870994061231613,
+      "learning_rate": 1.5229246386521894e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989091634750367,
+      "num_tokens": 51824364.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.7004310344827587,
+      "grad_norm": 0.02485145442187786,
+      "learning_rate": 1.502782334939104e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988964319229126,
+      "num_tokens": 52226195.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.7058189655172413,
+      "grad_norm": 0.018746523186564445,
+      "learning_rate": 1.4828718874105872e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988164305686951,
+      "num_tokens": 52627325.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.7112068965517241,
+      "grad_norm": 0.021077096462249756,
+      "learning_rate": 1.4631996253924749e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999091649055481,
+      "num_tokens": 53029791.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.7165948275862069,
+      "grad_norm": 0.023125356063246727,
+      "learning_rate": 1.4437718024938859e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989755392074585,
+      "num_tokens": 53431762.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.7219827586206896,
+      "grad_norm": 0.021164370700716972,
+      "learning_rate": 1.4245945946192675e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990996837615966,
+      "num_tokens": 53834592.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.7273706896551724,
+      "grad_norm": 0.023194963112473488,
+      "learning_rate": 1.4056740980051348e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989457607269288,
+      "num_tokens": 54236113.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 0.027318745851516724,
+      "learning_rate": 1.3870163272821422e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.999036180973053,
+      "num_tokens": 54638773.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.7381465517241379,
+      "grad_norm": 0.02111695520579815,
+      "learning_rate": 1.3686272135630939e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9988025784492492,
+      "num_tokens": 55039287.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.7435344827586207,
+      "grad_norm": 0.021133102476596832,
+      "learning_rate": 1.3505126025575055e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987844109535218,
+      "num_tokens": 55440154.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.7489224137931034,
+      "grad_norm": 0.02764318138360977,
+      "learning_rate": 1.3326782527133116e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9987500309944153,
+      "num_tokens": 55840791.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.7543103448275862,
+      "grad_norm": 0.024941669777035713,
+      "learning_rate": 1.3151298333863147e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988775968551635,
+      "num_tokens": 56242887.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.759698275862069,
+      "grad_norm": 0.020666925236582756,
+      "learning_rate": 1.2978729230379578e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990407824516296,
+      "num_tokens": 56645470.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.7650862068965517,
+      "grad_norm": 0.020904364064335823,
+      "learning_rate": 1.2809130074619848e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.998978590965271,
+      "num_tokens": 57047650.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7704741379310345,
+      "grad_norm": 0.03892960771918297,
+      "learning_rate": 1.2642554780405692e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987773180007935,
+      "num_tokens": 57448504.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.019465629011392593,
+      "learning_rate": 1.2479056300304417e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989529132843018,
+      "num_tokens": 57850023.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.022766010835766792,
+      "learning_rate": 1.2318686608795911e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990706324577332,
+      "num_tokens": 58252427.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.7866379310344828,
+      "grad_norm": 0.01826990395784378,
+      "learning_rate": 1.216149668575042e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989858031272888,
+      "num_tokens": 58654151.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7920258620689655,
+      "grad_norm": 0.024694079533219337,
+      "learning_rate": 1.2007536500222625e-05,
+      "loss": 0.0024,
+      "mean_token_accuracy": 0.9991173863410949,
+      "num_tokens": 59057239.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.7974137931034483,
+      "grad_norm": 0.024528369307518005,
+      "learning_rate": 1.1856854994566963e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987176299095154,
+      "num_tokens": 59457329.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.802801724137931,
+      "grad_norm": 0.023563502356410027,
+      "learning_rate": 1.170950006887937e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9988890886306763,
+      "num_tokens": 59858237.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.8081896551724138,
+      "grad_norm": 0.022601908072829247,
+      "learning_rate": 1.1565518565770333e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988453388214111,
+      "num_tokens": 60258966.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.8135775862068966,
+      "grad_norm": 0.02289353311061859,
+      "learning_rate": 1.1424956255474115e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989407777786254,
+      "num_tokens": 60660391.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.022011511027812958,
+      "learning_rate": 1.128785782129885e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9989583969116211,
+      "num_tokens": 61063253.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.8243534482758621,
+      "grad_norm": 0.016875440254807472,
+      "learning_rate": 1.1154266845422202e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989829182624816,
+      "num_tokens": 61464810.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.8297413793103449,
+      "grad_norm": 0.019241346046328545,
+      "learning_rate": 1.1024225795037032e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989438533782959,
+      "num_tokens": 61866531.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.8351293103448276,
+      "grad_norm": 0.02377363108098507,
+      "learning_rate": 1.089777600885151e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989052176475525,
+      "num_tokens": 62268172.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.8405172413793104,
+      "grad_norm": 0.020043199881911278,
+      "learning_rate": 1.077495768394797e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989200592041015,
+      "num_tokens": 62669240.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.8459051724137931,
+      "grad_norm": 0.021909885108470917,
+      "learning_rate": 1.065580986300468e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990006566047669,
+      "num_tokens": 63070830.0,
+      "step": 785
+    },
+    {
+      "epoch": 0.8512931034482759,
+      "grad_norm": 0.022637179121375084,
+      "learning_rate": 1.0540370421884568e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989096641540527,
+      "num_tokens": 63472170.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.8566810344827587,
+      "grad_norm": 0.024955401197075844,
+      "learning_rate": 1.0428676057594878e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.998984956741333,
+      "num_tokens": 63874037.0,
+      "step": 795
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.01749681495130062,
+      "learning_rate": 1.0320762276621562e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9988763809204102,
+      "num_tokens": 64275344.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8674568965517241,
+      "grad_norm": 0.027656937018036842,
+      "learning_rate": 1.0216663383642168e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.998952853679657,
+      "num_tokens": 64677126.0,
+      "step": 805
+    },
+    {
+      "epoch": 0.8728448275862069,
+      "grad_norm": 0.023702535778284073,
+      "learning_rate": 1.0116412470620679e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9990836262702942,
+      "num_tokens": 65079920.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.8782327586206896,
+      "grad_norm": 0.01650397479534149,
+      "learning_rate": 1.0020041406287986e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989512085914611,
+      "num_tokens": 65481506.0,
+      "step": 815
+    },
+    {
+      "epoch": 0.8836206896551724,
+      "grad_norm": 0.020977003499865532,
+      "learning_rate": 9.927580826011085e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9991203188896179,
+      "num_tokens": 65884331.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.8890086206896551,
+      "grad_norm": 0.024442242458462715,
+      "learning_rate": 9.839060122054454e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.998936676979065,
+      "num_tokens": 66285759.0,
+      "step": 825
+    },
+    {
+      "epoch": 0.8943965517241379,
+      "grad_norm": 0.026786241680383682,
+      "learning_rate": 9.75450743423654e-06,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.998736298084259,
+      "num_tokens": 66685714.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.8997844827586207,
+      "grad_norm": 0.02032666653394699,
+      "learning_rate": 9.673949640984395e-06,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9987974643707276,
+      "num_tokens": 67086597.0,
+      "step": 835
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 0.018526580184698105,
+      "learning_rate": 9.597412350789308e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9991434216499329,
+      "num_tokens": 67489472.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.9105603448275862,
+      "grad_norm": 0.02303580939769745,
+      "learning_rate": 9.52491989406613e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998892092704773,
+      "num_tokens": 67890506.0,
+      "step": 845
+    },
+    {
+      "epoch": 0.915948275862069,
+      "grad_norm": 0.02187165431678295,
+      "learning_rate": 9.456495315418894e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.998983633518219,
+      "num_tokens": 68291917.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.9213362068965517,
+      "grad_norm": 0.024225406348705292,
+      "learning_rate": 9.392160366315146e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989516019821167,
+      "num_tokens": 68693565.0,
+      "step": 855
+    },
+    {
+      "epoch": 0.9267241379310345,
+      "grad_norm": 0.02186994068324566,
+      "learning_rate": 9.331935498171415e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9988806962966919,
+      "num_tokens": 69094557.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.9321120689655172,
+      "grad_norm": 0.028275199234485626,
+      "learning_rate": 9.275839855851889e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9990072846412659,
+      "num_tokens": 69496215.0,
+      "step": 865
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.023129276931285858,
+      "learning_rate": 9.223891271582473e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.99894700050354,
+      "num_tokens": 69897495.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.9428879310344828,
+      "grad_norm": 0.026557613164186478,
+      "learning_rate": 9.176106259282111e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.998926043510437,
+      "num_tokens": 70298929.0,
+      "step": 875
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.026480358093976974,
+      "learning_rate": 9.132500009313176e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989673137664795,
+      "num_tokens": 70700320.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.9536637931034483,
+      "grad_norm": 0.020785316824913025,
+      "learning_rate": 9.093086383652602e-06,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9987948417663575,
+      "num_tokens": 71100703.0,
+      "step": 885
+    },
+    {
+      "epoch": 0.959051724137931,
+      "grad_norm": 0.024656957015395164,
+      "learning_rate": 9.057877911485328e-06,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9990541458129882,
+      "num_tokens": 71502763.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.9644396551724138,
+      "grad_norm": 0.023979607969522476,
+      "learning_rate": 9.026885785221381e-06,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988475799560547,
+      "num_tokens": 71903543.0,
+      "step": 895
+    },
+    {
+      "epoch": 0.9698275862068966,
+      "grad_norm": 0.03244682401418686,
+      "learning_rate": 9.000119856937926e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989493727684021,
+      "num_tokens": 72304889.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.9752155172413793,
+      "grad_norm": 0.021832207217812538,
+      "learning_rate": 8.977588635247394e-06,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.998972749710083,
+      "num_tokens": 72706282.0,
+      "step": 905
+    },
+    {
+      "epoch": 0.9806034482758621,
+      "grad_norm": 0.027536118403077126,
+      "learning_rate": 8.95929928259269e-06,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9991941571235656,
+      "num_tokens": 73109508.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.9859913793103449,
+      "grad_norm": 0.0195818729698658,
+      "learning_rate": 8.945257612970317e-06,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9990817308425903,
+      "num_tokens": 73511750.0,
+      "step": 915
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.02713189646601677,
+      "learning_rate": 8.935468090082163e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9989341139793396,
+      "num_tokens": 73912567.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9967672413793104,
+      "grad_norm": 0.027518320828676224,
+      "learning_rate": 8.929933825916554e-06,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9989198088645935,
+      "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 sha256:7a6501df599ca2d094d2fc23c96912793a2eea8e543411f6ed466537e49e36f3
+size 6545