Upload task output goof-intercode

.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: Jordansky/augmented-f560e4e6ee71e78d
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Jordansky--augmented-f560e4e6ee71e78d
+- 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": "Jordansky/augmented-f560e4e6ee71e78d",
+  "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": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_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 sha256:3b4b3091b6ccfa96b03bf8f0e06ae4616fe4e7b52fe087299d246cf5f418ebc2
+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 @@
+783,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 +1,1438 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47512135922330095,
+  "eval_steps": 500,
+  "global_step": 783,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003033980582524272,
+      "grad_norm": 12.881993293762207,
+      "learning_rate": 1.7209638554216869e-06,
+      "loss": 1.8952,
+      "mean_token_accuracy": 0.6737864851951599,
+      "num_tokens": 407386.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006067961165048544,
+      "grad_norm": 5.927900791168213,
+      "learning_rate": 3.872168674698796e-06,
+      "loss": 1.7501,
+      "mean_token_accuracy": 0.6814195275306701,
+      "num_tokens": 814608.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.009101941747572815,
+      "grad_norm": 3.0456957817077637,
+      "learning_rate": 6.023373493975903e-06,
+      "loss": 1.4337,
+      "mean_token_accuracy": 0.704640793800354,
+      "num_tokens": 1221103.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.012135922330097087,
+      "grad_norm": 2.4085395336151123,
+      "learning_rate": 8.174578313253012e-06,
+      "loss": 1.0971,
+      "mean_token_accuracy": 0.7540878534317017,
+      "num_tokens": 1628633.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.01516990291262136,
+      "grad_norm": 3.0483357906341553,
+      "learning_rate": 1.0325783132530121e-05,
+      "loss": 0.7505,
+      "mean_token_accuracy": 0.8266023993492126,
+      "num_tokens": 2035802.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.01820388349514563,
+      "grad_norm": 2.5269112586975098,
+      "learning_rate": 1.247698795180723e-05,
+      "loss": 0.413,
+      "mean_token_accuracy": 0.8993165135383606,
+      "num_tokens": 2442910.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.021237864077669904,
+      "grad_norm": 0.5028864741325378,
+      "learning_rate": 1.4628192771084337e-05,
+      "loss": 0.1641,
+      "mean_token_accuracy": 0.9638293981552124,
+      "num_tokens": 2849002.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.024271844660194174,
+      "grad_norm": 0.32503458857536316,
+      "learning_rate": 1.6779397590361448e-05,
+      "loss": 0.0904,
+      "mean_token_accuracy": 0.9782682418823242,
+      "num_tokens": 3256206.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.027305825242718445,
+      "grad_norm": 0.3155650794506073,
+      "learning_rate": 1.8930602409638557e-05,
+      "loss": 0.0543,
+      "mean_token_accuracy": 0.986135733127594,
+      "num_tokens": 3663246.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.03033980582524272,
+      "grad_norm": 0.18562550842761993,
+      "learning_rate": 2.1081807228915663e-05,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9897839546203613,
+      "num_tokens": 4069706.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.03337378640776699,
+      "grad_norm": 0.120665542781353,
+      "learning_rate": 2.3233012048192772e-05,
+      "loss": 0.028,
+      "mean_token_accuracy": 0.9917330026626587,
+      "num_tokens": 4476831.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.03640776699029126,
+      "grad_norm": 0.08647274225950241,
+      "learning_rate": 2.538421686746988e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.9926599621772766,
+      "num_tokens": 4883779.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.03944174757281554,
+      "grad_norm": 0.07028564810752869,
+      "learning_rate": 2.753542168674699e-05,
+      "loss": 0.0242,
+      "mean_token_accuracy": 0.9927438616752624,
+      "num_tokens": 5290679.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.04247572815533981,
+      "grad_norm": 0.10383659601211548,
+      "learning_rate": 2.96866265060241e-05,
+      "loss": 0.0237,
+      "mean_token_accuracy": 0.992747163772583,
+      "num_tokens": 5697620.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.04550970873786408,
+      "grad_norm": 0.09976121038198471,
+      "learning_rate": 3.183783132530121e-05,
+      "loss": 0.0278,
+      "mean_token_accuracy": 0.991703736782074,
+      "num_tokens": 6104413.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.04854368932038835,
+      "grad_norm": 0.06832871586084366,
+      "learning_rate": 3.3989036144578313e-05,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.992477285861969,
+      "num_tokens": 6510558.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.05157766990291262,
+      "grad_norm": 0.06535604596138,
+      "learning_rate": 3.570997301875174e-05,
+      "loss": 0.0248,
+      "mean_token_accuracy": 0.9922604560852051,
+      "num_tokens": 6917082.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.05461165048543689,
+      "grad_norm": 0.10271787643432617,
+      "learning_rate": 3.570902868647871e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9928990721702575,
+      "num_tokens": 7324254.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.05764563106796117,
+      "grad_norm": 0.10438171029090881,
+      "learning_rate": 3.5706735400516436e-05,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.9923665881156921,
+      "num_tokens": 7731206.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.06067961165048544,
+      "grad_norm": 0.04581941291689873,
+      "learning_rate": 3.570309339189348e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9928493976593018,
+      "num_tokens": 8137840.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.06371359223300971,
+      "grad_norm": 0.05334591865539551,
+      "learning_rate": 3.569810302751041e-05,
+      "loss": 0.0248,
+      "mean_token_accuracy": 0.9923072218894958,
+      "num_tokens": 8544534.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.06674757281553398,
+      "grad_norm": 0.052358437329530716,
+      "learning_rate": 3.569176481010288e-05,
+      "loss": 0.0239,
+      "mean_token_accuracy": 0.9925079822540284,
+      "num_tokens": 8951215.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.06978155339805825,
+      "grad_norm": 0.08001242578029633,
+      "learning_rate": 3.568407937819095e-05,
+      "loss": 0.0264,
+      "mean_token_accuracy": 0.9917665481567383,
+      "num_tokens": 9357839.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.07281553398058252,
+      "grad_norm": 0.05479741096496582,
+      "learning_rate": 3.5675047506014815e-05,
+      "loss": 0.0242,
+      "mean_token_accuracy": 0.9923253774642944,
+      "num_tokens": 9764643.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.07584951456310679,
+      "grad_norm": 0.05963903293013573,
+      "learning_rate": 3.566467010345674e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9926764607429505,
+      "num_tokens": 10170675.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.07888349514563107,
+      "grad_norm": 0.057525910437107086,
+      "learning_rate": 3.5652948215949454e-05,
+      "loss": 0.0223,
+      "mean_token_accuracy": 0.9926943898200988,
+      "num_tokens": 10577296.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.08191747572815535,
+      "grad_norm": 0.059444062411785126,
+      "learning_rate": 3.56398830243708e-05,
+      "loss": 0.0228,
+      "mean_token_accuracy": 0.9926655173301697,
+      "num_tokens": 10983842.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.08495145631067962,
+      "grad_norm": 0.10497656464576721,
+      "learning_rate": 3.562547584492477e-05,
+      "loss": 0.021,
+      "mean_token_accuracy": 0.9932034730911254,
+      "num_tokens": 11391523.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.08798543689320389,
+      "grad_norm": 0.04242556169629097,
+      "learning_rate": 3.5609728129008934e-05,
+      "loss": 0.0212,
+      "mean_token_accuracy": 0.9929630875587463,
+      "num_tokens": 11798319.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.09101941747572816,
+      "grad_norm": 0.03587333485484123,
+      "learning_rate": 3.5592641463068204e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9929973602294921,
+      "num_tokens": 12204367.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.09405339805825243,
+      "grad_norm": 0.03362417593598366,
+      "learning_rate": 3.557421756843501e-05,
+      "loss": 0.022,
+      "mean_token_accuracy": 0.9928773045539856,
+      "num_tokens": 12611691.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 0.05092537775635719,
+      "learning_rate": 3.555445830115592e-05,
+      "loss": 0.019,
+      "mean_token_accuracy": 0.9936353206634522,
+      "num_tokens": 13019316.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.10012135922330097,
+      "grad_norm": 0.051133450120687485,
+      "learning_rate": 3.5533365651804625e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9924604773521424,
+      "num_tokens": 13426273.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.10315533980582524,
+      "grad_norm": 0.0654042586684227,
+      "learning_rate": 3.5510941745281405e-05,
+      "loss": 0.0234,
+      "mean_token_accuracy": 0.9927022099494934,
+      "num_tokens": 13832090.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.10618932038834951,
+      "grad_norm": 0.05316481739282608,
+      "learning_rate": 3.548718884059912e-05,
+      "loss": 0.0173,
+      "mean_token_accuracy": 0.9940166115760803,
+      "num_tokens": 14239146.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.10922330097087378,
+      "grad_norm": 0.0432591438293457,
+      "learning_rate": 3.5462109330655545e-05,
+      "loss": 0.0226,
+      "mean_token_accuracy": 0.9927533149719239,
+      "num_tokens": 14645842.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.11225728155339806,
+      "grad_norm": 0.040612801909446716,
+      "learning_rate": 3.5435705741992395e-05,
+      "loss": 0.0228,
+      "mean_token_accuracy": 0.9925273418426513,
+      "num_tokens": 15052978.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.11529126213592233,
+      "grad_norm": 0.03967801108956337,
+      "learning_rate": 3.540798073454075e-05,
+      "loss": 0.0215,
+      "mean_token_accuracy": 0.9930168747901916,
+      "num_tokens": 15459755.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.1183252427184466,
+      "grad_norm": 0.06023363396525383,
+      "learning_rate": 3.5378937101353065e-05,
+      "loss": 0.0227,
+      "mean_token_accuracy": 0.9926756858825684,
+      "num_tokens": 15866485.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.12135922330097088,
+      "grad_norm": 0.028881069272756577,
+      "learning_rate": 3.534857776832187e-05,
+      "loss": 0.0194,
+      "mean_token_accuracy": 0.9934703350067139,
+      "num_tokens": 16274029.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.12439320388349515,
+      "grad_norm": 0.04172505810856819,
+      "learning_rate": 3.5316905793884944e-05,
+      "loss": 0.0217,
+      "mean_token_accuracy": 0.9927970051765442,
+      "num_tokens": 16681849.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.12742718446601942,
+      "grad_norm": 0.047556426376104355,
+      "learning_rate": 3.528392436871724e-05,
+      "loss": 0.0213,
+      "mean_token_accuracy": 0.992992353439331,
+      "num_tokens": 17089757.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.1304611650485437,
+      "grad_norm": 0.053197335451841354,
+      "learning_rate": 3.5249636815409434e-05,
+      "loss": 0.0233,
+      "mean_token_accuracy": 0.9926238298416138,
+      "num_tokens": 17496241.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.13349514563106796,
+      "grad_norm": 0.040444646030664444,
+      "learning_rate": 3.5214046588133205e-05,
+      "loss": 0.0242,
+      "mean_token_accuracy": 0.992365038394928,
+      "num_tokens": 17902466.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.13652912621359223,
+      "grad_norm": 0.07247660309076309,
+      "learning_rate": 3.5177157272293284e-05,
+      "loss": 0.0217,
+      "mean_token_accuracy": 0.9929222345352173,
+      "num_tokens": 18308520.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.1395631067961165,
+      "grad_norm": 0.3286735713481903,
+      "learning_rate": 3.513897258416623e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9928990960121155,
+      "num_tokens": 18715808.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.14259708737864077,
+      "grad_norm": 1.6682692766189575,
+      "learning_rate": 3.509949637052602e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.9931188821792603,
+      "num_tokens": 19122927.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.14563106796116504,
+      "grad_norm": 0.3066796362400055,
+      "learning_rate": 3.505873260825659e-05,
+      "loss": 0.0223,
+      "mean_token_accuracy": 0.9929746747016907,
+      "num_tokens": 19530080.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.1486650485436893,
+      "grad_norm": 0.09548434615135193,
+      "learning_rate": 3.5016685403951156e-05,
+      "loss": 0.0215,
+      "mean_token_accuracy": 0.9930257797241211,
+      "num_tokens": 19936885.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.15169902912621358,
+      "grad_norm": 0.04770074412226677,
+      "learning_rate": 3.4973358993498494e-05,
+      "loss": 0.0206,
+      "mean_token_accuracy": 0.993126392364502,
+      "num_tokens": 20342832.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.15473300970873785,
+      "grad_norm": 0.07485935091972351,
+      "learning_rate": 3.492875774165625e-05,
+      "loss": 0.0232,
+      "mean_token_accuracy": 0.9926700353622436,
+      "num_tokens": 20748938.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.15776699029126215,
+      "grad_norm": 0.04704100638628006,
+      "learning_rate": 3.48828861416112e-05,
+      "loss": 0.0203,
+      "mean_token_accuracy": 0.9931455612182617,
+      "num_tokens": 21156249.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.16080097087378642,
+      "grad_norm": 0.04121704027056694,
+      "learning_rate": 3.4835748814526635e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9925450682640076,
+      "num_tokens": 21562911.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.1638349514563107,
+      "grad_norm": 0.28638556599617004,
+      "learning_rate": 3.478735050907677e-05,
+      "loss": 0.0212,
+      "mean_token_accuracy": 0.9931713461875915,
+      "num_tokens": 21968979.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.16686893203883496,
+      "grad_norm": 0.12565217912197113,
+      "learning_rate": 3.473769610096839e-05,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9920137882232666,
+      "num_tokens": 22375386.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.16990291262135923,
+      "grad_norm": 0.22467869520187378,
+      "learning_rate": 3.468679059244967e-05,
+      "loss": 0.022,
+      "mean_token_accuracy": 0.9929057478904724,
+      "num_tokens": 22782306.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.1729368932038835,
+      "grad_norm": 0.0678594633936882,
+      "learning_rate": 3.463463911180622e-05,
+      "loss": 0.023,
+      "mean_token_accuracy": 0.9927614450454711,
+      "num_tokens": 23188938.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.17597087378640777,
+      "grad_norm": 0.05392945557832718,
+      "learning_rate": 3.458124691284445e-05,
+      "loss": 0.0205,
+      "mean_token_accuracy": 0.9933057188987732,
+      "num_tokens": 23595074.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.17900485436893204,
+      "grad_norm": 0.058865759521722794,
+      "learning_rate": 3.452661937436235e-05,
+      "loss": 0.0216,
+      "mean_token_accuracy": 0.9929778814315796,
+      "num_tokens": 24001568.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.1820388349514563,
+      "grad_norm": 0.05121828243136406,
+      "learning_rate": 3.447076199960755e-05,
+      "loss": 0.0223,
+      "mean_token_accuracy": 0.9928174257278443,
+      "num_tokens": 24407977.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.18507281553398058,
+      "grad_norm": 0.046074215322732925,
+      "learning_rate": 3.4413680415722955e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9932069063186646,
+      "num_tokens": 24813624.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.18810679611650485,
+      "grad_norm": 0.03264041990041733,
+      "learning_rate": 3.435538037317986e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.9931853413581848,
+      "num_tokens": 25219688.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.19114077669902912,
+      "grad_norm": 0.03584812954068184,
+      "learning_rate": 3.429586774519863e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9934399485588074,
+      "num_tokens": 25626392.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.03796568140387535,
+      "learning_rate": 3.423514852715701e-05,
+      "loss": 0.0198,
+      "mean_token_accuracy": 0.9932878255844116,
+      "num_tokens": 26033554.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.19720873786407767,
+      "grad_norm": 0.030003419145941734,
+      "learning_rate": 3.417322883598621e-05,
+      "loss": 0.0183,
+      "mean_token_accuracy": 0.9937293291091919,
+      "num_tokens": 26439949.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.20024271844660194,
+      "grad_norm": 0.03972536325454712,
+      "learning_rate": 3.411011490955457e-05,
+      "loss": 0.0215,
+      "mean_token_accuracy": 0.9929001450538635,
+      "num_tokens": 26847039.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.2032766990291262,
+      "grad_norm": 0.04523684084415436,
+      "learning_rate": 3.4045813106039256e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9929434895515442,
+      "num_tokens": 27253524.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.20631067961165048,
+      "grad_norm": 0.05554588511586189,
+      "learning_rate": 3.398032990328565e-05,
+      "loss": 0.0198,
+      "mean_token_accuracy": 0.9933468461036682,
+      "num_tokens": 27660579.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.20934466019417475,
+      "grad_norm": 0.0418703593313694,
+      "learning_rate": 3.3913671898154795e-05,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9919080615043641,
+      "num_tokens": 28066764.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.21237864077669902,
+      "grad_norm": 0.03904140740633011,
+      "learning_rate": 3.384584580585883e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.9925149798393249,
+      "num_tokens": 28474314.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.2154126213592233,
+      "grad_norm": 0.036088310182094574,
+      "learning_rate": 3.377685845928448e-05,
+      "loss": 0.0208,
+      "mean_token_accuracy": 0.9931179046630859,
+      "num_tokens": 28881394.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.21844660194174756,
+      "grad_norm": 0.04056026414036751,
+      "learning_rate": 3.370671680830471e-05,
+      "loss": 0.0218,
+      "mean_token_accuracy": 0.992766273021698,
+      "num_tokens": 29287460.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.22148058252427186,
+      "grad_norm": 0.0464637354016304,
+      "learning_rate": 3.363542791907854e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.993265700340271,
+      "num_tokens": 29694534.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.22451456310679613,
+      "grad_norm": 0.036997150629758835,
+      "learning_rate": 3.356299897333927e-05,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.9928918242454529,
+      "num_tokens": 30101092.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.2275485436893204,
+      "grad_norm": 0.04870880767703056,
+      "learning_rate": 3.348943726767093e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.9932775974273682,
+      "num_tokens": 30507917.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.23058252427184467,
+      "grad_norm": 0.07872658967971802,
+      "learning_rate": 3.3414750212773206e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9932668089866639,
+      "num_tokens": 30914865.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.23361650485436894,
+      "grad_norm": 0.03615431487560272,
+      "learning_rate": 3.333894533271491e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9935308218002319,
+      "num_tokens": 31321893.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.2366504854368932,
+      "grad_norm": 0.033446334302425385,
+      "learning_rate": 3.326203026417599e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9932949662208557,
+      "num_tokens": 31729278.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.23968446601941748,
+      "grad_norm": 0.03931819647550583,
+      "learning_rate": 3.3184012755678186e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9932982683181762,
+      "num_tokens": 32135795.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 0.036338433623313904,
+      "learning_rate": 3.310490066680442e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9924678921699523,
+      "num_tokens": 32542773.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.24575242718446602,
+      "grad_norm": 0.033566638827323914,
+      "learning_rate": 3.302470196740707e-05,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9934674024581909,
+      "num_tokens": 32949527.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.2487864077669903,
+      "grad_norm": 0.044052544981241226,
+      "learning_rate": 3.2943424736805e-05,
+      "loss": 0.0208,
+      "mean_token_accuracy": 0.9930399060249329,
+      "num_tokens": 33356981.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.2518203883495146,
+      "grad_norm": 0.0594814233481884,
+      "learning_rate": 3.28610771629697e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9934720158576965,
+      "num_tokens": 33763975.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.25485436893203883,
+      "grad_norm": 0.06194014474749565,
+      "learning_rate": 3.2777667541700405e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.9930955171585083,
+      "num_tokens": 34171521.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.25788834951456313,
+      "grad_norm": 0.03647923097014427,
+      "learning_rate": 3.269320427578833e-05,
+      "loss": 0.0217,
+      "mean_token_accuracy": 0.9928809881210328,
+      "num_tokens": 34578265.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.2609223300970874,
+      "grad_norm": 0.06534451991319656,
+      "learning_rate": 3.260769587417021e-05,
+      "loss": 0.0203,
+      "mean_token_accuracy": 0.9933925867080688,
+      "num_tokens": 34984780.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.26395631067961167,
+      "grad_norm": 0.03720612823963165,
+      "learning_rate": 3.252115095107108e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.9927129507064819,
+      "num_tokens": 35390481.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.2669902912621359,
+      "grad_norm": 0.052582353353500366,
+      "learning_rate": 3.243357822513647e-05,
+      "loss": 0.0206,
+      "mean_token_accuracy": 0.9931320190429688,
+      "num_tokens": 35797895.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.2700242718446602,
+      "grad_norm": 0.035469647496938705,
+      "learning_rate": 3.234498651855404e-05,
+      "loss": 0.0227,
+      "mean_token_accuracy": 0.9924560546875,
+      "num_tokens": 36205302.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.27305825242718446,
+      "grad_norm": 0.030852986499667168,
+      "learning_rate": 3.2255384756164905e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9932003140449523,
+      "num_tokens": 36611860.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.27609223300970875,
+      "grad_norm": 0.03644876554608345,
+      "learning_rate": 3.216478196456445e-05,
+      "loss": 0.019,
+      "mean_token_accuracy": 0.9935380101203919,
+      "num_tokens": 37018765.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.279126213592233,
+      "grad_norm": 0.037993211299180984,
+      "learning_rate": 3.207318727119302e-05,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.992822015285492,
+      "num_tokens": 37426212.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.2821601941747573,
+      "grad_norm": 0.03461167588829994,
+      "learning_rate": 3.1980609903416415e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9932843446731567,
+      "num_tokens": 37832810.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.28519417475728154,
+      "grad_norm": 0.03228127583861351,
+      "learning_rate": 3.1887059187596306e-05,
+      "loss": 0.0223,
+      "mean_token_accuracy": 0.992818820476532,
+      "num_tokens": 38239386.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.28822815533980584,
+      "grad_norm": 0.04857522249221802,
+      "learning_rate": 3.179254454815066e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9930593371391296,
+      "num_tokens": 38646309.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.04640183225274086,
+      "learning_rate": 3.1697075506604365e-05,
+      "loss": 0.0205,
+      "mean_token_accuracy": 0.9930596828460694,
+      "num_tokens": 39054017.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.2942961165048544,
+      "grad_norm": 0.07724732160568237,
+      "learning_rate": 3.160066168062996e-05,
+      "loss": 0.0184,
+      "mean_token_accuracy": 0.9936440348625183,
+      "num_tokens": 39461269.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.2973300970873786,
+      "grad_norm": 0.02800828032195568,
+      "learning_rate": 3.150331278307879e-05,
+      "loss": 0.0221,
+      "mean_token_accuracy": 0.99279283285141,
+      "num_tokens": 39868650.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.3003640776699029,
+      "grad_norm": 0.037310052663087845,
+      "learning_rate": 3.140503862100249e-05,
+      "loss": 0.0201,
+      "mean_token_accuracy": 0.9932762980461121,
+      "num_tokens": 40274804.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.30339805825242716,
+      "grad_norm": 0.06045287847518921,
+      "learning_rate": 3.130584909466502e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9927901029586792,
+      "num_tokens": 40680743.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.30643203883495146,
+      "grad_norm": 0.037607740610837936,
+      "learning_rate": 3.1205754196545294e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.9926772832870483,
+      "num_tokens": 41087347.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.3094660194174757,
+      "grad_norm": 0.036764051765203476,
+      "learning_rate": 3.110476401033054e-05,
+      "loss": 0.0217,
+      "mean_token_accuracy": 0.9927445411682129,
+      "num_tokens": 41494644.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.03375716134905815,
+      "learning_rate": 3.100288870990043e-05,
+      "loss": 0.0196,
+      "mean_token_accuracy": 0.9934267640113831,
+      "num_tokens": 41902084.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.3155339805825243,
+      "grad_norm": 0.03154360502958298,
+      "learning_rate": 3.0900138558302194e-05,
+      "loss": 0.0191,
+      "mean_token_accuracy": 0.9935309648513794,
+      "num_tokens": 42309300.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.31856796116504854,
+      "grad_norm": 0.025135209783911705,
+      "learning_rate": 3.079652390671665e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9934475421905518,
+      "num_tokens": 42716542.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.32160194174757284,
+      "grad_norm": 0.03982224315404892,
+      "learning_rate": 3.069205519341546e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9934385299682618,
+      "num_tokens": 43123256.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.3246359223300971,
+      "grad_norm": 0.04023640230298042,
+      "learning_rate": 3.058674294270955e-05,
+      "loss": 0.0186,
+      "mean_token_accuracy": 0.9937353134155273,
+      "num_tokens": 43529652.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.3276699029126214,
+      "grad_norm": 0.028163542971014977,
+      "learning_rate": 3.0480597763888863e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.993327522277832,
+      "num_tokens": 43935601.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.3307038834951456,
+      "grad_norm": 0.03361319378018379,
+      "learning_rate": 3.0373630350153597e-05,
+      "loss": 0.0175,
+      "mean_token_accuracy": 0.993952751159668,
+      "num_tokens": 44342453.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.3337378640776699,
+      "grad_norm": 0.035180699080228806,
+      "learning_rate": 3.026585147753692e-05,
+      "loss": 0.0226,
+      "mean_token_accuracy": 0.9926326274871826,
+      "num_tokens": 44748951.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.33677184466019416,
+      "grad_norm": 0.04069613292813301,
+      "learning_rate": 3.0157272003819414e-05,
+      "loss": 0.0207,
+      "mean_token_accuracy": 0.9931874632835388,
+      "num_tokens": 45155188.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.33980582524271846,
+      "grad_norm": 0.029416020959615707,
+      "learning_rate": 3.0047902867435223e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9927819728851318,
+      "num_tokens": 45561807.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.3428398058252427,
+      "grad_norm": 0.035775549709796906,
+      "learning_rate": 2.993775508637012e-05,
+      "loss": 0.0227,
+      "mean_token_accuracy": 0.9924745202064514,
+      "num_tokens": 45968255.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.345873786407767,
+      "grad_norm": 0.039437539875507355,
+      "learning_rate": 2.9826839757051526e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9934724569320679,
+      "num_tokens": 46375144.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.34890776699029125,
+      "grad_norm": 0.03149618208408356,
+      "learning_rate": 2.971516805323066e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.992820394039154,
+      "num_tokens": 46782323.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.35194174757281554,
+      "grad_norm": 0.03710157796740532,
+      "learning_rate": 2.9602751224856852e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9933429002761841,
+      "num_tokens": 47188896.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.3549757281553398,
+      "grad_norm": 0.03251684457063675,
+      "learning_rate": 2.9489600596944236e-05,
+      "loss": 0.0198,
+      "mean_token_accuracy": 0.9933558225631713,
+      "num_tokens": 47595402.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.3580097087378641,
+      "grad_norm": 0.024846093729138374,
+      "learning_rate": 2.937572756843084e-05,
+      "loss": 0.0208,
+      "mean_token_accuracy": 0.9929834604263306,
+      "num_tokens": 48002676.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.36104368932038833,
+      "grad_norm": 0.03847256675362587,
+      "learning_rate": 2.9261143611030253e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9932600855827332,
+      "num_tokens": 48408909.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.3640776699029126,
+      "grad_norm": 0.03794528916478157,
+      "learning_rate": 2.914586026807594e-05,
+      "loss": 0.0201,
+      "mean_token_accuracy": 0.9932417273521423,
+      "num_tokens": 48816050.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.36711165048543687,
+      "grad_norm": 0.03913505747914314,
+      "learning_rate": 2.902988915335836e-05,
+      "loss": 0.0207,
+      "mean_token_accuracy": 0.9929919958114624,
+      "num_tokens": 49223367.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.37014563106796117,
+      "grad_norm": 0.03473582863807678,
+      "learning_rate": 2.8913241949954957e-05,
+      "loss": 0.0221,
+      "mean_token_accuracy": 0.9925926566123963,
+      "num_tokens": 49630760.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.3731796116504854,
+      "grad_norm": 0.027801785618066788,
+      "learning_rate": 2.8795930409053225e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9932288885116577,
+      "num_tokens": 50037598.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.3762135922330097,
+      "grad_norm": 0.0316888689994812,
+      "learning_rate": 2.867796634876686e-05,
+      "loss": 0.0184,
+      "mean_token_accuracy": 0.9937638401985168,
+      "num_tokens": 50444771.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.379247572815534,
+      "grad_norm": 0.07504960894584656,
+      "learning_rate": 2.8559361652945176e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9932967185974121,
+      "num_tokens": 50851588.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.38228155339805825,
+      "grad_norm": 0.045697640627622604,
+      "learning_rate": 2.8440128269975945e-05,
+      "loss": 0.0187,
+      "mean_token_accuracy": 0.9934902310371398,
+      "num_tokens": 51258940.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.38531553398058255,
+      "grad_norm": 0.03645659238100052,
+      "learning_rate": 2.8320278211581675e-05,
+      "loss": 0.0208,
+      "mean_token_accuracy": 0.9932755589485168,
+      "num_tokens": 51665862.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.03291779011487961,
+      "learning_rate": 2.8199823551609523e-05,
+      "loss": 0.0242,
+      "mean_token_accuracy": 0.9920920610427857,
+      "num_tokens": 52072805.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.3913834951456311,
+      "grad_norm": 0.03070950135588646,
+      "learning_rate": 2.8078776424815e-05,
+      "loss": 0.0209,
+      "mean_token_accuracy": 0.9930874943733216,
+      "num_tokens": 52479343.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.39441747572815533,
+      "grad_norm": 0.040879931300878525,
+      "learning_rate": 2.7957149025639455e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9928395271301269,
+      "num_tokens": 52886647.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.39745145631067963,
+      "grad_norm": 0.035599879920482635,
+      "learning_rate": 2.7834953606981647e-05,
+      "loss": 0.0213,
+      "mean_token_accuracy": 0.9928174138069152,
+      "num_tokens": 53292846.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.40048543689320387,
+      "grad_norm": 0.03400155529379845,
+      "learning_rate": 2.77122024789633e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9932538151741028,
+      "num_tokens": 53700258.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.40351941747572817,
+      "grad_norm": 0.028687704354524612,
+      "learning_rate": 2.7588908007689038e-05,
+      "loss": 0.0186,
+      "mean_token_accuracy": 0.9934426546096802,
+      "num_tokens": 54107958.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.4065533980582524,
+      "grad_norm": 0.03738875687122345,
+      "learning_rate": 2.7465082614000553e-05,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9925989031791687,
+      "num_tokens": 54514336.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.4095873786407767,
+      "grad_norm": 0.03134342283010483,
+      "learning_rate": 2.734073877222535e-05,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9933988332748414,
+      "num_tokens": 54921552.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.41262135922330095,
+      "grad_norm": 0.026389850303530693,
+      "learning_rate": 2.7215889008920038e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9930248975753784,
+      "num_tokens": 55327241.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.41565533980582525,
+      "grad_norm": 0.022707246243953705,
+      "learning_rate": 2.7090545901608423e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9931993603706359,
+      "num_tokens": 55734366.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.4186893203883495,
+      "grad_norm": 0.042725060135126114,
+      "learning_rate": 2.6964722077514394e-05,
+      "loss": 0.024,
+      "mean_token_accuracy": 0.9923825621604919,
+      "num_tokens": 56140445.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.4217233009708738,
+      "grad_norm": 0.055999163538217545,
+      "learning_rate": 2.6838430212289874e-05,
+      "loss": 0.0236,
+      "mean_token_accuracy": 0.9923421740531921,
+      "num_tokens": 56546727.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.42475728155339804,
+      "grad_norm": 0.09104075282812119,
+      "learning_rate": 2.6711683028737836e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9931105375289917,
+      "num_tokens": 56953430.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.42779126213592233,
+      "grad_norm": 0.03057127818465233,
+      "learning_rate": 2.6584493295530605e-05,
+      "loss": 0.0195,
+      "mean_token_accuracy": 0.9935212850570678,
+      "num_tokens": 57359890.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.4308252427184466,
+      "grad_norm": 0.039992984384298325,
+      "learning_rate": 2.6456873825923518e-05,
+      "loss": 0.0203,
+      "mean_token_accuracy": 0.9931409597396851,
+      "num_tokens": 57766561.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.4338592233009709,
+      "grad_norm": 0.03372696414589882,
+      "learning_rate": 2.63288374764641e-05,
+      "loss": 0.0205,
+      "mean_token_accuracy": 0.9930363297462463,
+      "num_tokens": 58173113.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.4368932038834951,
+      "grad_norm": 0.020909098908305168,
+      "learning_rate": 2.620039714569688e-05,
+      "loss": 0.0194,
+      "mean_token_accuracy": 0.9933443427085876,
+      "num_tokens": 58580501.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.4399271844660194,
+      "grad_norm": 0.02915063500404358,
+      "learning_rate": 2.6071565772863995e-05,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9934536218643188,
+      "num_tokens": 58986906.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.4429611650485437,
+      "grad_norm": 0.03697626665234566,
+      "learning_rate": 2.594235633660163e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9925421714782715,
+      "num_tokens": 59393310.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.44599514563106796,
+      "grad_norm": 0.028796004131436348,
+      "learning_rate": 2.5812781853632587e-05,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.9928050398826599,
+      "num_tokens": 59799208.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.44902912621359226,
+      "grad_norm": 0.03447737544775009,
+      "learning_rate": 2.5682855377454918e-05,
+      "loss": 0.0184,
+      "mean_token_accuracy": 0.9936539769172669,
+      "num_tokens": 60206416.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.4520631067961165,
+      "grad_norm": 0.09332480281591415,
+      "learning_rate": 2.555258999702692e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.992510449886322,
+      "num_tokens": 60612501.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.4550970873786408,
+      "grad_norm": 0.13943925499916077,
+      "learning_rate": 2.5421998835448545e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9927754759788513,
+      "num_tokens": 61019113.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.45813106796116504,
+      "grad_norm": 0.029267804697155952,
+      "learning_rate": 2.5291095048639348e-05,
+      "loss": 0.019,
+      "mean_token_accuracy": 0.9934199333190918,
+      "num_tokens": 61425726.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.46116504854368934,
+      "grad_norm": 0.03230291232466698,
+      "learning_rate": 2.5159891824013134e-05,
+      "loss": 0.0218,
+      "mean_token_accuracy": 0.9925872683525085,
+      "num_tokens": 61831973.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.4641990291262136,
+      "grad_norm": 0.024981655180454254,
+      "learning_rate": 2.502840237914948e-05,
+      "loss": 0.0189,
+      "mean_token_accuracy": 0.9935161352157593,
+      "num_tokens": 62238418.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.4672330097087379,
+      "grad_norm": 0.022092267870903015,
+      "learning_rate": 2.4896639960462126e-05,
+      "loss": 0.0185,
+      "mean_token_accuracy": 0.9936355710029602,
+      "num_tokens": 62645878.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.4702669902912621,
+      "grad_norm": 0.03437012434005737,
+      "learning_rate": 2.476461784186456e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9932804703712463,
+      "num_tokens": 63053187.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.4733009708737864,
+      "grad_norm": 0.039246056228876114,
+      "learning_rate": 2.463234932343276e-05,
+      "loss": 0.022,
+      "mean_token_accuracy": 0.9929169893264771,
+      "num_tokens": 63459015.0,
+      "step": 780
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1648,
+  "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": 1.4897968655735194e+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 sha256:8dd6e15e67e417e411eb66432e277f8b640c229df7a98e9555061cff4d04bfd8
+size 6545