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: 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": [
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_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 sha256:8e5efbe2fb6b87404299f3d57ef22f8a7a151cca8e31db7e0d12a2999b023a6d
+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 @@
+500,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 +1,934 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32786885245901637,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003278688524590164,
+      "grad_norm": 11.864808082580566,
+      "learning_rate": 1.8550649350649352e-06,
+      "loss": 1.8825,
+      "mean_token_accuracy": 0.6717052340507508,
+      "num_tokens": 408217.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006557377049180328,
+      "grad_norm": 5.262256622314453,
+      "learning_rate": 4.173896103896104e-06,
+      "loss": 1.7165,
+      "mean_token_accuracy": 0.6818771481513977,
+      "num_tokens": 816357.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.009836065573770493,
+      "grad_norm": 2.965733289718628,
+      "learning_rate": 6.492727272727273e-06,
+      "loss": 1.3829,
+      "mean_token_accuracy": 0.70808926820755,
+      "num_tokens": 1224772.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.013114754098360656,
+      "grad_norm": 2.455183982849121,
+      "learning_rate": 8.811558441558442e-06,
+      "loss": 1.0236,
+      "mean_token_accuracy": 0.7685024738311768,
+      "num_tokens": 1633483.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 10.492952346801758,
+      "learning_rate": 1.113038961038961e-05,
+      "loss": 0.6499,
+      "mean_token_accuracy": 0.8449655532836914,
+      "num_tokens": 2042159.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.019672131147540985,
+      "grad_norm": 2.165491819381714,
+      "learning_rate": 1.344922077922078e-05,
+      "loss": 0.289,
+      "mean_token_accuracy": 0.9292097449302673,
+      "num_tokens": 2450648.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.022950819672131147,
+      "grad_norm": 0.3516330122947693,
+      "learning_rate": 1.5768051948051948e-05,
+      "loss": 0.0746,
+      "mean_token_accuracy": 0.9830971240997315,
+      "num_tokens": 2859130.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.02622950819672131,
+      "grad_norm": 0.2468341439962387,
+      "learning_rate": 1.8086883116883115e-05,
+      "loss": 0.0381,
+      "mean_token_accuracy": 0.9902603626251221,
+      "num_tokens": 3268040.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.029508196721311476,
+      "grad_norm": 0.23932884633541107,
+      "learning_rate": 2.0405714285714284e-05,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.9884509086608887,
+      "num_tokens": 3676141.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.03278688524590164,
+      "grad_norm": 0.1291441023349762,
+      "learning_rate": 2.2724545454545454e-05,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.9916678190231323,
+      "num_tokens": 4084717.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.036065573770491806,
+      "grad_norm": 0.11761873215436935,
+      "learning_rate": 2.5043376623376624e-05,
+      "loss": 0.0248,
+      "mean_token_accuracy": 0.9925343513488769,
+      "num_tokens": 4492938.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.03934426229508197,
+      "grad_norm": 0.057177335023880005,
+      "learning_rate": 2.7362207792207794e-05,
+      "loss": 0.0178,
+      "mean_token_accuracy": 0.9940186262130737,
+      "num_tokens": 4901795.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.04262295081967213,
+      "grad_norm": 0.09501975029706955,
+      "learning_rate": 2.9681038961038964e-05,
+      "loss": 0.0159,
+      "mean_token_accuracy": 0.9943653583526612,
+      "num_tokens": 5310849.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.04590163934426229,
+      "grad_norm": 0.09123346954584122,
+      "learning_rate": 3.199987012987013e-05,
+      "loss": 0.0166,
+      "mean_token_accuracy": 0.9942219018936157,
+      "num_tokens": 5719518.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 0.08542507886886597,
+      "learning_rate": 3.43187012987013e-05,
+      "loss": 0.0157,
+      "mean_token_accuracy": 0.9944955110549927,
+      "num_tokens": 6127881.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.05245901639344262,
+      "grad_norm": 0.04323630407452583,
+      "learning_rate": 3.570987392962234e-05,
+      "loss": 0.0147,
+      "mean_token_accuracy": 0.9947323679924012,
+      "num_tokens": 6536261.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.05573770491803279,
+      "grad_norm": 0.08876936882734299,
+      "learning_rate": 3.570845566513458e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.9947437524795533,
+      "num_tokens": 6945150.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.05901639344262295,
+      "grad_norm": 0.05356862023472786,
+      "learning_rate": 3.5705461715643066e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.9947035908699036,
+      "num_tokens": 7353980.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.06229508196721312,
+      "grad_norm": 0.0856458991765976,
+      "learning_rate": 3.5700892433472276e-05,
+      "loss": 0.0153,
+      "mean_token_accuracy": 0.9945327043533325,
+      "num_tokens": 7762104.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 0.038863301277160645,
+      "learning_rate": 3.569474835633004e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.994780158996582,
+      "num_tokens": 8170451.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.06885245901639345,
+      "grad_norm": 0.04703042283654213,
+      "learning_rate": 3.56870302072442e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9946265578269958,
+      "num_tokens": 8579349.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.07213114754098361,
+      "grad_norm": 0.036843106150627136,
+      "learning_rate": 3.5677738894477597e-05,
+      "loss": 0.015,
+      "mean_token_accuracy": 0.9946633577346802,
+      "num_tokens": 8987188.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.07540983606557378,
+      "grad_norm": 0.032964933663606644,
+      "learning_rate": 3.56668755114211e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9949539065361023,
+      "num_tokens": 9396028.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.07868852459016394,
+      "grad_norm": 0.02178327925503254,
+      "learning_rate": 3.565444133646502e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.994755208492279,
+      "num_tokens": 9804877.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 0.0296860970556736,
+      "learning_rate": 3.56404378328486e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9949416399002076,
+      "num_tokens": 10213751.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.08524590163934426,
+      "grad_norm": 0.0411427803337574,
+      "learning_rate": 3.562486664848789e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9947504162788391,
+      "num_tokens": 10622374.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.08852459016393442,
+      "grad_norm": 0.03543432801961899,
+      "learning_rate": 3.560772961578175e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9947629570960999,
+      "num_tokens": 11031043.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.09180327868852459,
+      "grad_norm": 0.059530045837163925,
+      "learning_rate": 3.5589028751396305e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9950087666511536,
+      "num_tokens": 11439772.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.09508196721311475,
+      "grad_norm": 0.07755406200885773,
+      "learning_rate": 3.556876625602752e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9948176383972168,
+      "num_tokens": 11848505.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 0.04126143455505371,
+      "learning_rate": 3.5546944514142315e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948662519454956,
+      "num_tokens": 12257305.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.10163934426229508,
+      "grad_norm": 0.03997291252017021,
+      "learning_rate": 3.5523566093697924e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9949190497398377,
+      "num_tokens": 12666302.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 0.040034219622612,
+      "learning_rate": 3.5498633745839686e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9949692964553833,
+      "num_tokens": 13075215.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.10819672131147541,
+      "grad_norm": 0.03907650709152222,
+      "learning_rate": 3.547215040457733e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9948561072349549,
+      "num_tokens": 13484075.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.11147540983606558,
+      "grad_norm": 0.04138929769396782,
+      "learning_rate": 3.544411918643969e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9949599266052246,
+      "num_tokens": 13892435.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.11475409836065574,
+      "grad_norm": 0.05110432580113411,
+      "learning_rate": 3.541454339010794e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9946610331535339,
+      "num_tokens": 14301183.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1180327868852459,
+      "grad_norm": 0.031282778829336166,
+      "learning_rate": 3.5383426496027415e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9948694586753846,
+      "num_tokens": 14709806.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.12131147540983607,
+      "grad_norm": 0.02924703061580658,
+      "learning_rate": 3.5350772165998065e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9947750806808472,
+      "num_tokens": 15118488.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.12459016393442623,
+      "grad_norm": 0.03491539880633354,
+      "learning_rate": 3.5316584242743505e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9948323130607605,
+      "num_tokens": 15526810.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.12786885245901639,
+      "grad_norm": 0.05004236847162247,
+      "learning_rate": 3.52808667494588e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9948232173919678,
+      "num_tokens": 15934808.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 0.059048738330602646,
+      "learning_rate": 3.524362388933707e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9948498249053955,
+      "num_tokens": 16342813.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.13442622950819672,
+      "grad_norm": 0.04443388804793358,
+      "learning_rate": 3.520486004507482e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9949076414108277,
+      "num_tokens": 16751499.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.1377049180327869,
+      "grad_norm": 0.034815456718206406,
+      "learning_rate": 3.516457977835619e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9949151515960694,
+      "num_tokens": 17159608.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.14098360655737704,
+      "grad_norm": 0.051543693989515305,
+      "learning_rate": 3.512278782931617e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9949401617050171,
+      "num_tokens": 17568139.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.14426229508196722,
+      "grad_norm": 0.05390683189034462,
+      "learning_rate": 3.507948911598274e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9949264645576477,
+      "num_tokens": 17977007.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "grad_norm": 0.06902962177991867,
+      "learning_rate": 3.50346887336982e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9947143077850342,
+      "num_tokens": 18385375.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.15081967213114755,
+      "grad_norm": 0.02893741987645626,
+      "learning_rate": 3.498839195451947e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.994857931137085,
+      "num_tokens": 18793771.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.1540983606557377,
+      "grad_norm": 0.02865167334675789,
+      "learning_rate": 3.494060422659772e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949785351753235,
+      "num_tokens": 19202621.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.15737704918032788,
+      "grad_norm": 0.04375935345888138,
+      "learning_rate": 3.489133117353724e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9947228193283081,
+      "num_tokens": 19611057.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.16065573770491803,
+      "grad_norm": 0.02420743554830551,
+      "learning_rate": 3.4840578593733666e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9950337886810303,
+      "num_tokens": 20019638.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 0.05214788392186165,
+      "learning_rate": 3.4788352459691614e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9949548959732055,
+      "num_tokens": 20428003.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.16721311475409836,
+      "grad_norm": 0.04234194755554199,
+      "learning_rate": 3.473465891732185e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9947700738906861,
+      "num_tokens": 20837020.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.17049180327868851,
+      "grad_norm": 0.034778088331222534,
+      "learning_rate": 3.4679504285218047e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947812557220459,
+      "num_tokens": 21245246.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.1737704918032787,
+      "grad_norm": 0.03974767401814461,
+      "learning_rate": 3.4622895053913217e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9948418736457825,
+      "num_tokens": 21653778.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.17704918032786884,
+      "grad_norm": 0.052754733711481094,
+      "learning_rate": 3.456483788511593e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948596477508544,
+      "num_tokens": 22062154.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.18032786885245902,
+      "grad_norm": 0.047448959201574326,
+      "learning_rate": 3.450533961092634e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9950472474098205,
+      "num_tokens": 22470813.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.18360655737704917,
+      "grad_norm": 0.09723605960607529,
+      "learning_rate": 3.444440723303221e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.994795274734497,
+      "num_tokens": 22879476.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.18688524590163935,
+      "grad_norm": 0.08869442343711853,
+      "learning_rate": 3.4382047921884984e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.994783091545105,
+      "num_tokens": 23287593.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.1901639344262295,
+      "grad_norm": 0.06632116436958313,
+      "learning_rate": 3.431826901585592e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9947378635406494,
+      "num_tokens": 23695847.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.19344262295081968,
+      "grad_norm": 0.03997300565242767,
+      "learning_rate": 3.4253078020372585e-05,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9951478004455566,
+      "num_tokens": 24104934.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 0.03351575508713722,
+      "learning_rate": 3.418648260703555e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9948622226715088,
+      "num_tokens": 24513848.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.04181559756398201,
+      "learning_rate": 3.41184906127157e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9950374960899353,
+      "num_tokens": 24921760.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.20327868852459016,
+      "grad_norm": 0.044396817684173584,
+      "learning_rate": 3.40491100386319e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9949706077575684,
+      "num_tokens": 25329955.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.20655737704918034,
+      "grad_norm": 0.02727290242910385,
+      "learning_rate": 3.39783490494095e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9948286771774292,
+      "num_tokens": 25738012.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.2098360655737705,
+      "grad_norm": 0.04054737091064453,
+      "learning_rate": 3.390621597211947e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948787569999695,
+      "num_tokens": 26146499.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.21311475409836064,
+      "grad_norm": 0.03496871143579483,
+      "learning_rate": 3.3832719295298546e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9949335575103759,
+      "num_tokens": 26554662.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.21639344262295082,
+      "grad_norm": 0.07436609268188477,
+      "learning_rate": 3.375786766795025e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949586033821106,
+      "num_tokens": 26963118.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.21967213114754097,
+      "grad_norm": 0.03663641959428787,
+      "learning_rate": 3.368166989852709e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9948944687843323,
+      "num_tokens": 27371149.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.22295081967213115,
+      "grad_norm": 0.03990248590707779,
+      "learning_rate": 3.3604134953894047e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949881911277771,
+      "num_tokens": 27779612.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.2262295081967213,
+      "grad_norm": 0.05796727165579796,
+      "learning_rate": 3.352527195827331e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9949235558509827,
+      "num_tokens": 28188222.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.22950819672131148,
+      "grad_norm": 0.05331377312541008,
+      "learning_rate": 3.344509019217057e-05,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.994888699054718,
+      "num_tokens": 28596553.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.23278688524590163,
+      "grad_norm": 0.04629578813910484,
+      "learning_rate": 3.336359909128287e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949244379997253,
+      "num_tokens": 29004751.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.2360655737704918,
+      "grad_norm": 0.034980956465005875,
+      "learning_rate": 3.328080824538829e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9950591683387756,
+      "num_tokens": 29413216.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.23934426229508196,
+      "grad_norm": 0.049879077821969986,
+      "learning_rate": 3.3196727397217355e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9946274876594543,
+      "num_tokens": 29820939.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.24262295081967214,
+      "grad_norm": 0.03049667924642563,
+      "learning_rate": 3.311136644130658e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949459671974182,
+      "num_tokens": 30229737.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 0.03131835535168648,
+      "learning_rate": 3.3024735422834075e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.995038378238678,
+      "num_tokens": 30638060.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.24918032786885247,
+      "grad_norm": 0.10647476464509964,
+      "learning_rate": 3.2936844536437424e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9952004551887512,
+      "num_tokens": 31046393.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.25245901639344265,
+      "grad_norm": 0.03366782143712044,
+      "learning_rate": 3.2847704125014004e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9949777960777283,
+      "num_tokens": 31455002.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.25573770491803277,
+      "grad_norm": 0.04673784226179123,
+      "learning_rate": 3.2757324678503855e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9947427630424499,
+      "num_tokens": 31863601.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.25901639344262295,
+      "grad_norm": 0.05322699621319771,
+      "learning_rate": 3.266571683265521e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.994936466217041,
+      "num_tokens": 32272638.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 0.09595732390880585,
+      "learning_rate": 3.257289136777294e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9950599074363708,
+      "num_tokens": 32681386.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.26557377049180325,
+      "grad_norm": 0.04479283094406128,
+      "learning_rate": 3.2478859207449874e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.994804859161377,
+      "num_tokens": 33089486.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.26885245901639343,
+      "grad_norm": 0.030818136408925056,
+      "learning_rate": 3.2383631417281374e-05,
+      "loss": 0.0126,
+      "mean_token_accuracy": 0.995081651210785,
+      "num_tokens": 33498149.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.2721311475409836,
+      "grad_norm": 0.041336897760629654,
+      "learning_rate": 3.228721920356313e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950200915336609,
+      "num_tokens": 33906426.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.2754098360655738,
+      "grad_norm": 0.02350839041173458,
+      "learning_rate": 3.218963391197243e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9947636127471924,
+      "num_tokens": 34314986.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.2786885245901639,
+      "grad_norm": 0.02138645388185978,
+      "learning_rate": 3.209088702623298e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948771834373474,
+      "num_tokens": 34723179.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.2819672131147541,
+      "grad_norm": 0.041177183389663696,
+      "learning_rate": 3.1990990166763574e-05,
+      "loss": 0.0127,
+      "mean_token_accuracy": 0.9951212167739868,
+      "num_tokens": 35132085.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.28524590163934427,
+      "grad_norm": 0.04491574689745903,
+      "learning_rate": 3.188995508931052e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948252081871033,
+      "num_tokens": 35540424.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.28852459016393445,
+      "grad_norm": 0.03420275077223778,
+      "learning_rate": 3.178779368356435e-05,
+      "loss": 0.0125,
+      "mean_token_accuracy": 0.9952936053276062,
+      "num_tokens": 35948584.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.29180327868852457,
+      "grad_norm": 0.02960294671356678,
+      "learning_rate": 3.1684517971760586e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9950698137283325,
+      "num_tokens": 36356683.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 0.03503751382231712,
+      "learning_rate": 3.158014010726497e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9947447061538697,
+      "num_tokens": 36765639.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.2983606557377049,
+      "grad_norm": 0.12213002890348434,
+      "learning_rate": 3.1474672373143325e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949376940727234,
+      "num_tokens": 37174367.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.3016393442622951,
+      "grad_norm": 0.026703471317887306,
+      "learning_rate": 3.136812718071603e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.995039415359497,
+      "num_tokens": 37582693.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.30491803278688523,
+      "grad_norm": 0.04152139276266098,
+      "learning_rate": 3.126051706809753e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9950154423713684,
+      "num_tokens": 37991765.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.3081967213114754,
+      "grad_norm": 0.03578517958521843,
+      "learning_rate": 3.115185469872084e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9947016477584839,
+      "num_tokens": 38400227.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.3114754098360656,
+      "grad_norm": 0.02464434690773487,
+      "learning_rate": 3.1042152859847324e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9948673963546752,
+      "num_tokens": 38807929.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.31475409836065577,
+      "grad_norm": 0.03423834592103958,
+      "learning_rate": 3.093142446106189e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9949305653572083,
+      "num_tokens": 39216673.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.3180327868852459,
+      "grad_norm": 0.03287561610341072,
+      "learning_rate": 3.0819682532753864e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9948360681533813,
+      "num_tokens": 39625104.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.32131147540983607,
+      "grad_norm": 0.031057024374604225,
+      "learning_rate": 3.070694022458351e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9948514938354492,
+      "num_tokens": 40033992.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.32459016393442625,
+      "grad_norm": 0.03567773476243019,
+      "learning_rate": 3.059321080393464e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.9949483275413513,
+      "num_tokens": 40442234.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.03349795937538147,
+      "learning_rate": 3.0478507654353334e-05,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9948728799819946,
+      "num_tokens": 40850853.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1525,
+  "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": 9.553592302509752e+17,
+  "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 sha256:0b68ff855da0fd32d34b4d9b70e0e9844f6715dcf088005911b756b49b024914
+size 6545