Upload folder using huggingface_hub

.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
+r16_checkpoint-164/tokenizer.json filter=lfs diff=lfs merge=lfs -text

r16_checkpoint-164/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B
+- 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

r16_checkpoint-164/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

r16_checkpoint-164/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd9f19caaecf27d962eb5bcee72a36837414c930f0de5f490753d9561ea97cd
+size 1685299160

r16_checkpoint-164/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
+}

r16_checkpoint-164/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- 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" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

r16_checkpoint-164/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0be9fd1911383e41ca1d4625bcc6ea2c36917678651f4bfe7eef802e7225b2b
+size 264673227

r16_checkpoint-164/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a7e86f79847e5024055001f3bb35e40be5e072cbe245b0d830613eb9fa4eae
+size 14645

r16_checkpoint-164/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb36d3229eed0b0116f2c721940a1737e2cbe34e2f9b0ad4b1d55f2545f74b4f
+size 1465

r16_checkpoint-164/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
+  }
+}

r16_checkpoint-164/tokenizer.json

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

r16_checkpoint-164/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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

r16_checkpoint-164/trainer_state.json

@@ -0,0 +1,1674 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 164,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8626787662506104,
+      "epoch": 0.012195121951219513,
+      "grad_norm": 1.093520998954773,
+      "learning_rate": 0.0,
+      "loss": 1.6278,
+      "mean_token_accuracy": 0.6077101826667786,
+      "num_tokens": 16384.0,
+      "step": 1
+    },
+    {
+      "entropy": 0.8334736227989197,
+      "epoch": 0.024390243902439025,
+      "grad_norm": 1.1227993965148926,
+      "learning_rate": 2e-05,
+      "loss": 1.6238,
+      "mean_token_accuracy": 0.6236559152603149,
+      "num_tokens": 32768.0,
+      "step": 2
+    },
+    {
+      "entropy": 0.843785285949707,
+      "epoch": 0.036585365853658534,
+      "grad_norm": 1.0835614204406738,
+      "learning_rate": 4e-05,
+      "loss": 1.6063,
+      "mean_token_accuracy": 0.6162023544311523,
+      "num_tokens": 49152.0,
+      "step": 3
+    },
+    {
+      "entropy": 0.8779809474945068,
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.9354265928268433,
+      "learning_rate": 6e-05,
+      "loss": 1.5604,
+      "mean_token_accuracy": 0.6130865216255188,
+      "num_tokens": 65536.0,
+      "step": 4
+    },
+    {
+      "entropy": 0.9051678776741028,
+      "epoch": 0.06097560975609756,
+      "grad_norm": 0.7520043253898621,
+      "learning_rate": 8e-05,
+      "loss": 1.4806,
+      "mean_token_accuracy": 0.618462860584259,
+      "num_tokens": 81920.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.9353162050247192,
+      "epoch": 0.07317073170731707,
+      "grad_norm": 0.608469545841217,
+      "learning_rate": 0.0001,
+      "loss": 1.4196,
+      "mean_token_accuracy": 0.6241446733474731,
+      "num_tokens": 98304.0,
+      "step": 6
+    },
+    {
+      "entropy": 0.9815650582313538,
+      "epoch": 0.08536585365853659,
+      "grad_norm": 0.5623904466629028,
+      "learning_rate": 9.999024041442456e-05,
+      "loss": 1.3894,
+      "mean_token_accuracy": 0.6333699822425842,
+      "num_tokens": 114688.0,
+      "step": 7
+    },
+    {
+      "entropy": 1.0563855171203613,
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.39273801445961,
+      "learning_rate": 9.99609654676786e-05,
+      "loss": 1.3009,
+      "mean_token_accuracy": 0.6317204236984253,
+      "num_tokens": 131072.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.1101257801055908,
+      "epoch": 0.10975609756097561,
+      "grad_norm": 0.37761062383651733,
+      "learning_rate": 9.991218658821608e-05,
+      "loss": 1.2618,
+      "mean_token_accuracy": 0.6392350792884827,
+      "num_tokens": 147456.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.195725679397583,
+      "epoch": 0.12195121951219512,
+      "grad_norm": 0.3863956034183502,
+      "learning_rate": 9.984392281850293e-05,
+      "loss": 1.2558,
+      "mean_token_accuracy": 0.6326979398727417,
+      "num_tokens": 163840.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.2094194889068604,
+      "epoch": 0.13414634146341464,
+      "grad_norm": 0.36058974266052246,
+      "learning_rate": 9.97562008075832e-05,
+      "loss": 1.2465,
+      "mean_token_accuracy": 0.6655669808387756,
+      "num_tokens": 180224.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.2624375820159912,
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.34076783061027527,
+      "learning_rate": 9.964905480067586e-05,
+      "loss": 1.2181,
+      "mean_token_accuracy": 0.6512096524238586,
+      "num_tokens": 196608.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.2377264499664307,
+      "epoch": 0.15853658536585366,
+      "grad_norm": 0.3092578053474426,
+      "learning_rate": 9.952252662580579e-05,
+      "loss": 1.1554,
+      "mean_token_accuracy": 0.6719208359718323,
+      "num_tokens": 212992.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.1959787607192993,
+      "epoch": 0.17073170731707318,
+      "grad_norm": 0.3330951929092407,
+      "learning_rate": 9.937666567747501e-05,
+      "loss": 1.0803,
+      "mean_token_accuracy": 0.6903714537620544,
+      "num_tokens": 229376.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.244974970817566,
+      "epoch": 0.18292682926829268,
+      "grad_norm": 0.3327937126159668,
+      "learning_rate": 9.921152889737984e-05,
+      "loss": 1.1151,
+      "mean_token_accuracy": 0.6904325485229492,
+      "num_tokens": 245760.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.2253583669662476,
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.3638331890106201,
+      "learning_rate": 9.902718075218176e-05,
+      "loss": 1.0701,
+      "mean_token_accuracy": 0.6973973512649536,
+      "num_tokens": 262144.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.2277535200119019,
+      "epoch": 0.2073170731707317,
+      "grad_norm": 0.34471285343170166,
+      "learning_rate": 9.882369320834069e-05,
+      "loss": 1.0763,
+      "mean_token_accuracy": 0.7006964683532715,
+      "num_tokens": 278528.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.1190669536590576,
+      "epoch": 0.21951219512195122,
+      "grad_norm": 0.31308990716934204,
+      "learning_rate": 9.860114570402054e-05,
+      "loss": 1.0033,
+      "mean_token_accuracy": 0.6972751617431641,
+      "num_tokens": 294912.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.0731631517410278,
+      "epoch": 0.23170731707317074,
+      "grad_norm": 0.28365620970726013,
+      "learning_rate": 9.835962511807786e-05,
+      "loss": 0.9789,
+      "mean_token_accuracy": 0.6879276633262634,
+      "num_tokens": 311296.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.0539000034332275,
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.2581247091293335,
+      "learning_rate": 9.809922573614569e-05,
+      "loss": 0.9533,
+      "mean_token_accuracy": 0.7093108296394348,
+      "num_tokens": 327680.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.0733942985534668,
+      "epoch": 0.25609756097560976,
+      "grad_norm": 0.25778359174728394,
+      "learning_rate": 9.782004921382612e-05,
+      "loss": 0.9808,
+      "mean_token_accuracy": 0.7142595052719116,
+      "num_tokens": 344064.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.005030870437622,
+      "epoch": 0.2682926829268293,
+      "grad_norm": 0.24065329134464264,
+      "learning_rate": 9.752220453700556e-05,
+      "loss": 0.9526,
+      "mean_token_accuracy": 0.7184750437736511,
+      "num_tokens": 360448.0,
+      "step": 22
+    },
+    {
+      "entropy": 0.9591503143310547,
+      "epoch": 0.2804878048780488,
+      "grad_norm": 0.22566185891628265,
+      "learning_rate": 9.720580797930845e-05,
+      "loss": 0.9023,
+      "mean_token_accuracy": 0.7219575047492981,
+      "num_tokens": 376832.0,
+      "step": 23
+    },
+    {
+      "entropy": 0.9062448740005493,
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.21324659883975983,
+      "learning_rate": 9.687098305670605e-05,
+      "loss": 0.863,
+      "mean_token_accuracy": 0.7317326664924622,
+      "num_tokens": 393216.0,
+      "step": 24
+    },
+    {
+      "entropy": 0.8665833473205566,
+      "epoch": 0.3048780487804878,
+      "grad_norm": 0.21358917653560638,
+      "learning_rate": 9.651786047929773e-05,
+      "loss": 0.8513,
+      "mean_token_accuracy": 0.7454789876937866,
+      "num_tokens": 409600.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.8195997476577759,
+      "epoch": 0.3170731707317073,
+      "grad_norm": 0.20360076427459717,
+      "learning_rate": 9.614657810028402e-05,
+      "loss": 0.8183,
+      "mean_token_accuracy": 0.7438294291496277,
+      "num_tokens": 425984.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.8189018964767456,
+      "epoch": 0.32926829268292684,
+      "grad_norm": 0.1878810077905655,
+      "learning_rate": 9.575728086215092e-05,
+      "loss": 0.8251,
+      "mean_token_accuracy": 0.7345430254936218,
+      "num_tokens": 442368.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.8264307379722595,
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.1862117052078247,
+      "learning_rate": 9.535012074008687e-05,
+      "loss": 0.8499,
+      "mean_token_accuracy": 0.738575279712677,
+      "num_tokens": 458752.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.809086263179779,
+      "epoch": 0.35365853658536583,
+      "grad_norm": 0.18720269203186035,
+      "learning_rate": 9.492525668265399e-05,
+      "loss": 0.8427,
+      "mean_token_accuracy": 0.7409579753875732,
+      "num_tokens": 475136.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.8115344047546387,
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.18687783181667328,
+      "learning_rate": 9.448285454973738e-05,
+      "loss": 0.8283,
+      "mean_token_accuracy": 0.7388196587562561,
+      "num_tokens": 491520.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8720694780349731,
+      "epoch": 0.3780487804878049,
+      "grad_norm": 0.19463640451431274,
+      "learning_rate": 9.402308704779599e-05,
+      "loss": 0.9073,
+      "mean_token_accuracy": 0.7170698642730713,
+      "num_tokens": 507904.0,
+      "step": 31
+    },
+    {
+      "entropy": 0.7934220433235168,
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.2061900645494461,
+      "learning_rate": 9.354613366244108e-05,
+      "loss": 0.8354,
+      "mean_token_accuracy": 0.7403470277786255,
+      "num_tokens": 524288.0,
+      "step": 32
+    },
+    {
+      "entropy": 0.8034217357635498,
+      "epoch": 0.4024390243902439,
+      "grad_norm": 0.18652082979679108,
+      "learning_rate": 9.305218058836778e-05,
+      "loss": 0.8198,
+      "mean_token_accuracy": 0.7371701002120972,
+      "num_tokens": 540672.0,
+      "step": 33
+    },
+    {
+      "entropy": 0.7859891057014465,
+      "epoch": 0.4146341463414634,
+      "grad_norm": 0.18425549566745758,
+      "learning_rate": 9.254142065666801e-05,
+      "loss": 0.8052,
+      "mean_token_accuracy": 0.7403470277786255,
+      "num_tokens": 557056.0,
+      "step": 34
+    },
+    {
+      "entropy": 0.8217732310295105,
+      "epoch": 0.4268292682926829,
+      "grad_norm": 0.1789712905883789,
+      "learning_rate": 9.201405325955221e-05,
+      "loss": 0.8289,
+      "mean_token_accuracy": 0.7328934669494629,
+      "num_tokens": 573440.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.919280469417572,
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.20816408097743988,
+      "learning_rate": 9.14702842725101e-05,
+      "loss": 0.937,
+      "mean_token_accuracy": 0.725256621837616,
+      "num_tokens": 589824.0,
+      "step": 36
+    },
+    {
+      "entropy": 0.8575299978256226,
+      "epoch": 0.45121951219512196,
+      "grad_norm": 0.17666810750961304,
+      "learning_rate": 9.091032597394012e-05,
+      "loss": 0.8453,
+      "mean_token_accuracy": 0.7242180109024048,
+      "num_tokens": 606208.0,
+      "step": 37
+    },
+    {
+      "entropy": 0.852461040019989,
+      "epoch": 0.4634146341463415,
+      "grad_norm": 0.19314983487129211,
+      "learning_rate": 9.033439696227965e-05,
+      "loss": 0.8383,
+      "mean_token_accuracy": 0.7425464391708374,
+      "num_tokens": 622592.0,
+      "step": 38
+    },
+    {
+      "entropy": 0.9019465446472168,
+      "epoch": 0.47560975609756095,
+      "grad_norm": 0.5123350620269775,
+      "learning_rate": 8.974272207066767e-05,
+      "loss": 0.8832,
+      "mean_token_accuracy": 0.7297165393829346,
+      "num_tokens": 638976.0,
+      "step": 39
+    },
+    {
+      "entropy": 0.8627578020095825,
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.17488670349121094,
+      "learning_rate": 8.913553227917367e-05,
+      "loss": 0.8428,
+      "mean_token_accuracy": 0.7358260154724121,
+      "num_tokens": 655360.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.856721043586731,
+      "epoch": 0.5,
+      "grad_norm": 0.18452906608581543,
+      "learning_rate": 8.851306462462688e-05,
+      "loss": 0.8303,
+      "mean_token_accuracy": 0.7369868159294128,
+      "num_tokens": 671744.0,
+      "step": 41
+    },
+    {
+      "entropy": 0.8949995040893555,
+      "epoch": 0.5121951219512195,
+      "grad_norm": 0.18721207976341248,
+      "learning_rate": 8.787556210808101e-05,
+      "loss": 0.8737,
+      "mean_token_accuracy": 0.7280669808387756,
+      "num_tokens": 688128.0,
+      "step": 42
+    },
+    {
+      "entropy": 0.8572060465812683,
+      "epoch": 0.524390243902439,
+      "grad_norm": 0.2125820517539978,
+      "learning_rate": 8.722327359995064e-05,
+      "loss": 0.8289,
+      "mean_token_accuracy": 0.7305718660354614,
+      "num_tokens": 704512.0,
+      "step": 43
+    },
+    {
+      "entropy": 0.8431792855262756,
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.16261345148086548,
+      "learning_rate": 8.655645374285637e-05,
+      "loss": 0.8324,
+      "mean_token_accuracy": 0.7467008829116821,
+      "num_tokens": 720896.0,
+      "step": 44
+    },
+    {
+      "entropy": 0.8569008111953735,
+      "epoch": 0.5487804878048781,
+      "grad_norm": 0.16756756603717804,
+      "learning_rate": 8.587536285221656e-05,
+      "loss": 0.8385,
+      "mean_token_accuracy": 0.7399193644523621,
+      "num_tokens": 737280.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.8784096240997314,
+      "epoch": 0.5609756097560976,
+      "grad_norm": 0.1637604683637619,
+      "learning_rate": 8.518026681462448e-05,
+      "loss": 0.8758,
+      "mean_token_accuracy": 0.7420576810836792,
+      "num_tokens": 753664.0,
+      "step": 46
+    },
+    {
+      "entropy": 0.8060196042060852,
+      "epoch": 0.573170731707317,
+      "grad_norm": 0.1424463987350464,
+      "learning_rate": 8.44714369840506e-05,
+      "loss": 0.7857,
+      "mean_token_accuracy": 0.7453567981719971,
+      "num_tokens": 770048.0,
+      "step": 47
+    },
+    {
+      "entropy": 0.8206385374069214,
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.16366063058376312,
+      "learning_rate": 8.374915007591053e-05,
+      "loss": 0.8108,
+      "mean_token_accuracy": 0.7399804592132568,
+      "num_tokens": 786432.0,
+      "step": 48
+    },
+    {
+      "entropy": 0.7763859629631042,
+      "epoch": 0.5975609756097561,
+      "grad_norm": 0.15812788903713226,
+      "learning_rate": 8.301368805903988e-05,
+      "loss": 0.7664,
+      "mean_token_accuracy": 0.7501221895217896,
+      "num_tokens": 802816.0,
+      "step": 49
+    },
+    {
+      "entropy": 0.8081514835357666,
+      "epoch": 0.6097560975609756,
+      "grad_norm": 0.13794690370559692,
+      "learning_rate": 8.226533804561827e-05,
+      "loss": 0.7941,
+      "mean_token_accuracy": 0.7362536787986755,
+      "num_tokens": 819200.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7959892153739929,
+      "epoch": 0.6219512195121951,
+      "grad_norm": 0.15148861706256866,
+      "learning_rate": 8.150439217908556e-05,
+      "loss": 0.7991,
+      "mean_token_accuracy": 0.7465175986289978,
+      "num_tokens": 835584.0,
+      "step": 51
+    },
+    {
+      "entropy": 0.7600486874580383,
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.15204936265945435,
+      "learning_rate": 8.073114752009387e-05,
+      "loss": 0.7455,
+      "mean_token_accuracy": 0.7529325485229492,
+      "num_tokens": 851968.0,
+      "step": 52
+    },
+    {
+      "entropy": 0.7730528116226196,
+      "epoch": 0.6463414634146342,
+      "grad_norm": 0.16175110638141632,
+      "learning_rate": 7.994590593054001e-05,
+      "loss": 0.7712,
+      "mean_token_accuracy": 0.7553763389587402,
+      "num_tokens": 868352.0,
+      "step": 53
+    },
+    {
+      "entropy": 0.723149299621582,
+      "epoch": 0.6585365853658537,
+      "grad_norm": 0.1428563892841339,
+      "learning_rate": 7.91489739557236e-05,
+      "loss": 0.7223,
+      "mean_token_accuracy": 0.7581256031990051,
+      "num_tokens": 884736.0,
+      "step": 54
+    },
+    {
+      "entropy": 0.8479559421539307,
+      "epoch": 0.6707317073170732,
+      "grad_norm": 0.15264202654361725,
+      "learning_rate": 7.83406627046769e-05,
+      "loss": 0.8563,
+      "mean_token_accuracy": 0.7294110655784607,
+      "num_tokens": 901120.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.8442703485488892,
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.16407510638237,
+      "learning_rate": 7.752128772871292e-05,
+      "loss": 0.8483,
+      "mean_token_accuracy": 0.7380865216255188,
+      "num_tokens": 917504.0,
+      "step": 56
+    },
+    {
+      "entropy": 0.8123852014541626,
+      "epoch": 0.6951219512195121,
+      "grad_norm": 0.2425997406244278,
+      "learning_rate": 7.669116889823955e-05,
+      "loss": 0.8099,
+      "mean_token_accuracy": 0.7432795763015747,
+      "num_tokens": 933888.0,
+      "step": 57
+    },
+    {
+      "entropy": 0.8269070386886597,
+      "epoch": 0.7073170731707317,
+      "grad_norm": 0.17707492411136627,
+      "learning_rate": 7.585063027788731e-05,
+      "loss": 0.8236,
+      "mean_token_accuracy": 0.7399193644523621,
+      "num_tokens": 950272.0,
+      "step": 58
+    },
+    {
+      "entropy": 0.8299212455749512,
+      "epoch": 0.7195121951219512,
+      "grad_norm": 0.18594571948051453,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8269,
+      "mean_token_accuracy": 0.7259286642074585,
+      "num_tokens": 966656.0,
+      "step": 59
+    },
+    {
+      "entropy": 0.7739796042442322,
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.1970595121383667,
+      "learning_rate": 7.413961013653726e-05,
+      "loss": 0.7692,
+      "mean_token_accuracy": 0.7574535608291626,
+      "num_tokens": 983040.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7878926396369934,
+      "epoch": 0.7439024390243902,
+      "grad_norm": 0.15815742313861847,
+      "learning_rate": 7.326979656943906e-05,
+      "loss": 0.782,
+      "mean_token_accuracy": 0.7506109476089478,
+      "num_tokens": 999424.0,
+      "step": 61
+    },
+    {
+      "entropy": 0.7709231376647949,
+      "epoch": 0.7560975609756098,
+      "grad_norm": 0.15482768416404724,
+      "learning_rate": 7.239089885950316e-05,
+      "loss": 0.7644,
+      "mean_token_accuracy": 0.7500610947608948,
+      "num_tokens": 1015808.0,
+      "step": 62
+    },
+    {
+      "entropy": 0.8151384592056274,
+      "epoch": 0.7682926829268293,
+      "grad_norm": 0.18697461485862732,
+      "learning_rate": 7.150326011382604e-05,
+      "loss": 0.8341,
+      "mean_token_accuracy": 0.748900294303894,
+      "num_tokens": 1032192.0,
+      "step": 63
+    },
+    {
+      "entropy": 0.7922771573066711,
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.1754199117422104,
+      "learning_rate": 7.060722685185961e-05,
+      "loss": 0.7985,
+      "mean_token_accuracy": 0.7541544437408447,
+      "num_tokens": 1048576.0,
+      "step": 64
+    },
+    {
+      "entropy": 0.7848575711250305,
+      "epoch": 0.7926829268292683,
+      "grad_norm": 0.15173719823360443,
+      "learning_rate": 6.970314887013584e-05,
+      "loss": 0.7815,
+      "mean_token_accuracy": 0.7364980578422546,
+      "num_tokens": 1064960.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.8392961025238037,
+      "epoch": 0.8048780487804879,
+      "grad_norm": 0.15754099190235138,
+      "learning_rate": 6.879137910571191e-05,
+      "loss": 0.8434,
+      "mean_token_accuracy": 0.7264785170555115,
+      "num_tokens": 1081344.0,
+      "step": 66
+    },
+    {
+      "entropy": 0.8158323764801025,
+      "epoch": 0.8170731707317073,
+      "grad_norm": 0.15918175876140594,
+      "learning_rate": 6.787227349838947e-05,
+      "loss": 0.822,
+      "mean_token_accuracy": 0.7360703945159912,
+      "num_tokens": 1097728.0,
+      "step": 67
+    },
+    {
+      "entropy": 0.8016376495361328,
+      "epoch": 0.8292682926829268,
+      "grad_norm": 0.16510061919689178,
+      "learning_rate": 6.694619085176159e-05,
+      "loss": 0.7931,
+      "mean_token_accuracy": 0.7269061803817749,
+      "num_tokens": 1114112.0,
+      "step": 68
+    },
+    {
+      "entropy": 0.8735076189041138,
+      "epoch": 0.8414634146341463,
+      "grad_norm": 0.17883004248142242,
+      "learning_rate": 6.601349269314188e-05,
+      "loss": 0.8698,
+      "mean_token_accuracy": 0.738025426864624,
+      "num_tokens": 1130496.0,
+      "step": 69
+    },
+    {
+      "entropy": 0.7732913494110107,
+      "epoch": 0.8536585365853658,
+      "grad_norm": 0.15874753892421722,
+      "learning_rate": 6.507454313243015e-05,
+      "loss": 0.7788,
+      "mean_token_accuracy": 0.7560483813285828,
+      "num_tokens": 1146880.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8275507688522339,
+      "epoch": 0.8658536585365854,
+      "grad_norm": 0.21345174312591553,
+      "learning_rate": 6.412970871996995e-05,
+      "loss": 0.832,
+      "mean_token_accuracy": 0.732587993144989,
+      "num_tokens": 1163264.0,
+      "step": 71
+    },
+    {
+      "entropy": 0.7750837802886963,
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.19833992421627045,
+      "learning_rate": 6.317935830345338e-05,
+      "loss": 0.7663,
+      "mean_token_accuracy": 0.7450513243675232,
+      "num_tokens": 1179648.0,
+      "step": 72
+    },
+    {
+      "entropy": 0.7952277064323425,
+      "epoch": 0.8902439024390244,
+      "grad_norm": 0.15775804221630096,
+      "learning_rate": 6.222386288392913e-05,
+      "loss": 0.7877,
+      "mean_token_accuracy": 0.7415078282356262,
+      "num_tokens": 1196032.0,
+      "step": 73
+    },
+    {
+      "entropy": 0.7806995511054993,
+      "epoch": 0.9024390243902439,
+      "grad_norm": 0.14973501861095428,
+      "learning_rate": 6.126359547096975e-05,
+      "loss": 0.7856,
+      "mean_token_accuracy": 0.7389418482780457,
+      "num_tokens": 1212416.0,
+      "step": 74
+    },
+    {
+      "entropy": 0.7249821424484253,
+      "epoch": 0.9146341463414634,
+      "grad_norm": 0.14249767363071442,
+      "learning_rate": 6.029893093705492e-05,
+      "loss": 0.7337,
+      "mean_token_accuracy": 0.7622189521789551,
+      "num_tokens": 1228800.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.844130277633667,
+      "epoch": 0.926829268292683,
+      "grad_norm": 0.14792245626449585,
+      "learning_rate": 5.9330245871227454e-05,
+      "loss": 0.8473,
+      "mean_token_accuracy": 0.7195137143135071,
+      "num_tokens": 1245184.0,
+      "step": 76
+    },
+    {
+      "entropy": 0.8064289689064026,
+      "epoch": 0.9390243902439024,
+      "grad_norm": 0.1545572131872177,
+      "learning_rate": 5.835791843207916e-05,
+      "loss": 0.8022,
+      "mean_token_accuracy": 0.7437072396278381,
+      "num_tokens": 1261568.0,
+      "step": 77
+    },
+    {
+      "entropy": 0.7663623094558716,
+      "epoch": 0.9512195121951219,
+      "grad_norm": 0.14488399028778076,
+      "learning_rate": 5.738232820012407e-05,
+      "loss": 0.7681,
+      "mean_token_accuracy": 0.7433406710624695,
+      "num_tokens": 1277952.0,
+      "step": 78
+    },
+    {
+      "entropy": 0.7927509546279907,
+      "epoch": 0.9634146341463414,
+      "grad_norm": 0.14524520933628082,
+      "learning_rate": 5.640385602961634e-05,
+      "loss": 0.779,
+      "mean_token_accuracy": 0.7425464391708374,
+      "num_tokens": 1294336.0,
+      "step": 79
+    },
+    {
+      "entropy": 0.8146692514419556,
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.18617865443229675,
+      "learning_rate": 5.5422883899871284e-05,
+      "loss": 0.8285,
+      "mean_token_accuracy": 0.7455400824546814,
+      "num_tokens": 1310720.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7783186435699463,
+      "epoch": 0.9878048780487805,
+      "grad_norm": 0.18682421743869781,
+      "learning_rate": 5.4439794766146746e-05,
+      "loss": 0.7739,
+      "mean_token_accuracy": 0.7502443790435791,
+      "num_tokens": 1327104.0,
+      "step": 81
+    },
+    {
+      "entropy": 0.81927490234375,
+      "epoch": 1.0,
+      "grad_norm": 0.17351913452148438,
+      "learning_rate": 5.34549724101439e-05,
+      "loss": 0.8139,
+      "mean_token_accuracy": 0.7457152009010315,
+      "num_tokens": 1342464.0,
+      "step": 82
+    },
+    {
+      "entropy": 0.8127053380012512,
+      "epoch": 1.0121951219512195,
+      "grad_norm": 0.18688295781612396,
+      "learning_rate": 5.246880129018516e-05,
+      "loss": 0.7941,
+      "mean_token_accuracy": 0.7455400824546814,
+      "num_tokens": 1358848.0,
+      "step": 83
+    },
+    {
+      "entropy": 0.8702384233474731,
+      "epoch": 1.024390243902439,
+      "grad_norm": 0.16337597370147705,
+      "learning_rate": 5.148166639112799e-05,
+      "loss": 0.8607,
+      "mean_token_accuracy": 0.7197580933570862,
+      "num_tokens": 1375232.0,
+      "step": 84
+    },
+    {
+      "entropy": 0.8485889434814453,
+      "epoch": 1.0365853658536586,
+      "grad_norm": 0.156337171792984,
+      "learning_rate": 5.049395307407329e-05,
+      "loss": 0.8541,
+      "mean_token_accuracy": 0.7224462628364563,
+      "num_tokens": 1391616.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.813921332359314,
+      "epoch": 1.048780487804878,
+      "grad_norm": 0.1604459583759308,
+      "learning_rate": 4.950604692592672e-05,
+      "loss": 0.8029,
+      "mean_token_accuracy": 0.7431573867797852,
+      "num_tokens": 1408000.0,
+      "step": 86
+    },
+    {
+      "entropy": 0.7519501447677612,
+      "epoch": 1.0609756097560976,
+      "grad_norm": 0.15572917461395264,
+      "learning_rate": 4.851833360887201e-05,
+      "loss": 0.7536,
+      "mean_token_accuracy": 0.7580645084381104,
+      "num_tokens": 1424384.0,
+      "step": 87
+    },
+    {
+      "entropy": 0.8007060289382935,
+      "epoch": 1.0731707317073171,
+      "grad_norm": 0.165048286318779,
+      "learning_rate": 4.7531198709814854e-05,
+      "loss": 0.7925,
+      "mean_token_accuracy": 0.7437683343887329,
+      "num_tokens": 1440768.0,
+      "step": 88
+    },
+    {
+      "entropy": 0.7244361042976379,
+      "epoch": 1.0853658536585367,
+      "grad_norm": 0.153402641415596,
+      "learning_rate": 4.654502758985611e-05,
+      "loss": 0.7212,
+      "mean_token_accuracy": 0.7533602118492126,
+      "num_tokens": 1457152.0,
+      "step": 89
+    },
+    {
+      "entropy": 0.7844712734222412,
+      "epoch": 1.0975609756097562,
+      "grad_norm": 0.17439647018909454,
+      "learning_rate": 4.5560205233853266e-05,
+      "loss": 0.7909,
+      "mean_token_accuracy": 0.7572702765464783,
+      "num_tokens": 1473536.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.8085858225822449,
+      "epoch": 1.1097560975609757,
+      "grad_norm": 0.16895566880702972,
+      "learning_rate": 4.4577116100128735e-05,
+      "loss": 0.8054,
+      "mean_token_accuracy": 0.7484115362167358,
+      "num_tokens": 1489920.0,
+      "step": 91
+    },
+    {
+      "entropy": 0.8172082304954529,
+      "epoch": 1.1219512195121952,
+      "grad_norm": 0.16507022082805634,
+      "learning_rate": 4.3596143970383664e-05,
+      "loss": 0.8126,
+      "mean_token_accuracy": 0.7358871102333069,
+      "num_tokens": 1506304.0,
+      "step": 92
+    },
+    {
+      "entropy": 0.804606020450592,
+      "epoch": 1.1341463414634148,
+      "grad_norm": 0.17114119231700897,
+      "learning_rate": 4.2617671799875944e-05,
+      "loss": 0.8043,
+      "mean_token_accuracy": 0.7403470277786255,
+      "num_tokens": 1522688.0,
+      "step": 93
+    },
+    {
+      "entropy": 0.8033316135406494,
+      "epoch": 1.146341463414634,
+      "grad_norm": 0.16593089699745178,
+      "learning_rate": 4.1642081567920846e-05,
+      "loss": 0.7935,
+      "mean_token_accuracy": 0.7421798706054688,
+      "num_tokens": 1539072.0,
+      "step": 94
+    },
+    {
+      "entropy": 0.7842370271682739,
+      "epoch": 1.1585365853658536,
+      "grad_norm": 0.1647975593805313,
+      "learning_rate": 4.066975412877255e-05,
+      "loss": 0.7744,
+      "mean_token_accuracy": 0.7479838728904724,
+      "num_tokens": 1555456.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.7931013107299805,
+      "epoch": 1.170731707317073,
+      "grad_norm": 0.16263936460018158,
+      "learning_rate": 3.970106906294509e-05,
+      "loss": 0.7807,
+      "mean_token_accuracy": 0.7437683343887329,
+      "num_tokens": 1571840.0,
+      "step": 96
+    },
+    {
+      "entropy": 0.8188630938529968,
+      "epoch": 1.1829268292682926,
+      "grad_norm": 0.16917824745178223,
+      "learning_rate": 3.873640452903026e-05,
+      "loss": 0.8164,
+      "mean_token_accuracy": 0.7358260154724121,
+      "num_tokens": 1588224.0,
+      "step": 97
+    },
+    {
+      "entropy": 0.7913827896118164,
+      "epoch": 1.1951219512195121,
+      "grad_norm": 0.18289069831371307,
+      "learning_rate": 3.777613711607087e-05,
+      "loss": 0.7873,
+      "mean_token_accuracy": 0.7564760446548462,
+      "num_tokens": 1604608.0,
+      "step": 98
+    },
+    {
+      "entropy": 0.7935872673988342,
+      "epoch": 1.2073170731707317,
+      "grad_norm": 0.17263023555278778,
+      "learning_rate": 3.682064169654663e-05,
+      "loss": 0.7804,
+      "mean_token_accuracy": 0.7444403767585754,
+      "num_tokens": 1620992.0,
+      "step": 99
+    },
+    {
+      "entropy": 0.7222156524658203,
+      "epoch": 1.2195121951219512,
+      "grad_norm": 0.17958715558052063,
+      "learning_rate": 3.587029128003006e-05,
+      "loss": 0.7201,
+      "mean_token_accuracy": 0.7591031193733215,
+      "num_tokens": 1637376.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7649905681610107,
+      "epoch": 1.2317073170731707,
+      "grad_norm": 0.18006746470928192,
+      "learning_rate": 3.492545686756986e-05,
+      "loss": 0.76,
+      "mean_token_accuracy": 0.7514662742614746,
+      "num_tokens": 1653760.0,
+      "step": 101
+    },
+    {
+      "entropy": 0.7939061522483826,
+      "epoch": 1.2439024390243902,
+      "grad_norm": 0.18951010704040527,
+      "learning_rate": 3.3986507306858125e-05,
+      "loss": 0.7959,
+      "mean_token_accuracy": 0.7506720423698425,
+      "num_tokens": 1670144.0,
+      "step": 102
+    },
+    {
+      "entropy": 0.7376015186309814,
+      "epoch": 1.2560975609756098,
+      "grad_norm": 0.17339089512825012,
+      "learning_rate": 3.3053809148238426e-05,
+      "loss": 0.7364,
+      "mean_token_accuracy": 0.7612414360046387,
+      "num_tokens": 1686528.0,
+      "step": 103
+    },
+    {
+      "entropy": 0.7750467658042908,
+      "epoch": 1.2682926829268293,
+      "grad_norm": 0.18979544937610626,
+      "learning_rate": 3.212772650161056e-05,
+      "loss": 0.7805,
+      "mean_token_accuracy": 0.741568922996521,
+      "num_tokens": 1702912.0,
+      "step": 104
+    },
+    {
+      "entropy": 0.7754949927330017,
+      "epoch": 1.2804878048780488,
+      "grad_norm": 0.17050911486148834,
+      "learning_rate": 3.12086208942881e-05,
+      "loss": 0.77,
+      "mean_token_accuracy": 0.7531158328056335,
+      "num_tokens": 1719296.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.7592970728874207,
+      "epoch": 1.2926829268292683,
+      "grad_norm": 0.1680549532175064,
+      "learning_rate": 3.0296851129864168e-05,
+      "loss": 0.7623,
+      "mean_token_accuracy": 0.7492057681083679,
+      "num_tokens": 1735680.0,
+      "step": 106
+    },
+    {
+      "entropy": 0.7648909687995911,
+      "epoch": 1.3048780487804879,
+      "grad_norm": 0.1712636798620224,
+      "learning_rate": 2.9392773148140408e-05,
+      "loss": 0.7583,
+      "mean_token_accuracy": 0.7597751617431641,
+      "num_tokens": 1752064.0,
+      "step": 107
+    },
+    {
+      "entropy": 0.7280970811843872,
+      "epoch": 1.3170731707317074,
+      "grad_norm": 0.17362791299819946,
+      "learning_rate": 2.8496739886173995e-05,
+      "loss": 0.7274,
+      "mean_token_accuracy": 0.7643572688102722,
+      "num_tokens": 1768448.0,
+      "step": 108
+    },
+    {
+      "entropy": 0.7840908169746399,
+      "epoch": 1.329268292682927,
+      "grad_norm": 0.17845657467842102,
+      "learning_rate": 2.7609101140496863e-05,
+      "loss": 0.7865,
+      "mean_token_accuracy": 0.7373533844947815,
+      "num_tokens": 1784832.0,
+      "step": 109
+    },
+    {
+      "entropy": 0.7682303190231323,
+      "epoch": 1.3414634146341464,
+      "grad_norm": 0.16712307929992676,
+      "learning_rate": 2.6730203430560947e-05,
+      "loss": 0.7645,
+      "mean_token_accuracy": 0.7514662742614746,
+      "num_tokens": 1801216.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.7741588354110718,
+      "epoch": 1.3536585365853657,
+      "grad_norm": 0.19137173891067505,
+      "learning_rate": 2.5860389863462765e-05,
+      "loss": 0.7812,
+      "mean_token_accuracy": 0.7571480870246887,
+      "num_tokens": 1817600.0,
+      "step": 111
+    },
+    {
+      "entropy": 0.7963957786560059,
+      "epoch": 1.3658536585365852,
+      "grad_norm": 0.15832075476646423,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7837,
+      "mean_token_accuracy": 0.7305107712745667,
+      "num_tokens": 1833984.0,
+      "step": 112
+    },
+    {
+      "entropy": 0.8067537546157837,
+      "epoch": 1.3780487804878048,
+      "grad_norm": 0.16905173659324646,
+      "learning_rate": 2.414936972211272e-05,
+      "loss": 0.814,
+      "mean_token_accuracy": 0.7300220131874084,
+      "num_tokens": 1850368.0,
+      "step": 113
+    },
+    {
+      "entropy": 0.7220765948295593,
+      "epoch": 1.3902439024390243,
+      "grad_norm": 0.17643025517463684,
+      "learning_rate": 2.3308831101760486e-05,
+      "loss": 0.7213,
+      "mean_token_accuracy": 0.7626466155052185,
+      "num_tokens": 1866752.0,
+      "step": 114
+    },
+    {
+      "entropy": 0.7335401177406311,
+      "epoch": 1.4024390243902438,
+      "grad_norm": 0.18172410130500793,
+      "learning_rate": 2.247871227128709e-05,
+      "loss": 0.7447,
+      "mean_token_accuracy": 0.7695503234863281,
+      "num_tokens": 1883136.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.777027428150177,
+      "epoch": 1.4146341463414633,
+      "grad_norm": 0.18086431920528412,
+      "learning_rate": 2.1659337295323118e-05,
+      "loss": 0.7786,
+      "mean_token_accuracy": 0.75,
+      "num_tokens": 1899520.0,
+      "step": 116
+    },
+    {
+      "entropy": 0.7760388851165771,
+      "epoch": 1.4268292682926829,
+      "grad_norm": 0.1816961169242859,
+      "learning_rate": 2.0851026044276406e-05,
+      "loss": 0.7689,
+      "mean_token_accuracy": 0.7526270747184753,
+      "num_tokens": 1915904.0,
+      "step": 117
+    },
+    {
+      "entropy": 0.765831470489502,
+      "epoch": 1.4390243902439024,
+      "grad_norm": 0.17442217469215393,
+      "learning_rate": 2.005409406946e-05,
+      "loss": 0.7516,
+      "mean_token_accuracy": 0.7539711594581604,
+      "num_tokens": 1932288.0,
+      "step": 118
+    },
+    {
+      "entropy": 0.7737946510314941,
+      "epoch": 1.451219512195122,
+      "grad_norm": 0.20942705869674683,
+      "learning_rate": 1.9268852479906147e-05,
+      "loss": 0.7698,
+      "mean_token_accuracy": 0.7565982341766357,
+      "num_tokens": 1948672.0,
+      "step": 119
+    },
+    {
+      "entropy": 0.7546911835670471,
+      "epoch": 1.4634146341463414,
+      "grad_norm": 0.16106529533863068,
+      "learning_rate": 1.849560782091445e-05,
+      "loss": 0.7484,
+      "mean_token_accuracy": 0.7628909945487976,
+      "num_tokens": 1965056.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.7773269414901733,
+      "epoch": 1.475609756097561,
+      "grad_norm": 0.16608163714408875,
+      "learning_rate": 1.7734661954381754e-05,
+      "loss": 0.7635,
+      "mean_token_accuracy": 0.7425464391708374,
+      "num_tokens": 1981440.0,
+      "step": 121
+    },
+    {
+      "entropy": 0.8382898569107056,
+      "epoch": 1.4878048780487805,
+      "grad_norm": 0.18340705335140228,
+      "learning_rate": 1.6986311940960147e-05,
+      "loss": 0.8307,
+      "mean_token_accuracy": 0.7344208359718323,
+      "num_tokens": 1997824.0,
+      "step": 122
+    },
+    {
+      "entropy": 0.8073008060455322,
+      "epoch": 1.5,
+      "grad_norm": 0.20171548426151276,
+      "learning_rate": 1.6250849924089484e-05,
+      "loss": 0.8129,
+      "mean_token_accuracy": 0.7513440847396851,
+      "num_tokens": 2014208.0,
+      "step": 123
+    },
+    {
+      "entropy": 0.7637985348701477,
+      "epoch": 1.5121951219512195,
+      "grad_norm": 0.1743263453245163,
+      "learning_rate": 1.552856301594942e-05,
+      "loss": 0.7717,
+      "mean_token_accuracy": 0.7518328428268433,
+      "num_tokens": 2030592.0,
+      "step": 124
+    },
+    {
+      "entropy": 0.7066326141357422,
+      "epoch": 1.524390243902439,
+      "grad_norm": 0.1779520958662033,
+      "learning_rate": 1.4819733185375534e-05,
+      "loss": 0.7039,
+      "mean_token_accuracy": 0.7751099467277527,
+      "num_tokens": 2046976.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.8327795267105103,
+      "epoch": 1.5365853658536586,
+      "grad_norm": 0.19776591658592224,
+      "learning_rate": 1.4124637147783432e-05,
+      "loss": 0.8315,
+      "mean_token_accuracy": 0.7443181872367859,
+      "num_tokens": 2063360.0,
+      "step": 126
+    },
+    {
+      "entropy": 0.7843926548957825,
+      "epoch": 1.548780487804878,
+      "grad_norm": 0.18373773992061615,
+      "learning_rate": 1.3443546257143624e-05,
+      "loss": 0.794,
+      "mean_token_accuracy": 0.7397360801696777,
+      "num_tokens": 2079744.0,
+      "step": 127
+    },
+    {
+      "entropy": 0.762474536895752,
+      "epoch": 1.5609756097560976,
+      "grad_norm": 0.17974597215652466,
+      "learning_rate": 1.277672640004936e-05,
+      "loss": 0.7467,
+      "mean_token_accuracy": 0.7536045908927917,
+      "num_tokens": 2096128.0,
+      "step": 128
+    },
+    {
+      "entropy": 0.8016952872276306,
+      "epoch": 1.5731707317073171,
+      "grad_norm": 0.15986624360084534,
+      "learning_rate": 1.2124437891918993e-05,
+      "loss": 0.8016,
+      "mean_token_accuracy": 0.7256842851638794,
+      "num_tokens": 2112512.0,
+      "step": 129
+    },
+    {
+      "entropy": 0.7332467436790466,
+      "epoch": 1.5853658536585367,
+      "grad_norm": 0.18568632006645203,
+      "learning_rate": 1.1486935375373126e-05,
+      "loss": 0.7322,
+      "mean_token_accuracy": 0.7613025307655334,
+      "num_tokens": 2128896.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.7486759424209595,
+      "epoch": 1.5975609756097562,
+      "grad_norm": 0.1953137218952179,
+      "learning_rate": 1.0864467720826343e-05,
+      "loss": 0.7477,
+      "mean_token_accuracy": 0.7516495585441589,
+      "num_tokens": 2145280.0,
+      "step": 131
+    },
+    {
+      "entropy": 0.7888240218162537,
+      "epoch": 1.6097560975609757,
+      "grad_norm": 0.175430566072464,
+      "learning_rate": 1.0257277929332332e-05,
+      "loss": 0.7963,
+      "mean_token_accuracy": 0.747556209564209,
+      "num_tokens": 2161664.0,
+      "step": 132
+    },
+    {
+      "entropy": 0.7990193963050842,
+      "epoch": 1.6219512195121952,
+      "grad_norm": 0.1816466748714447,
+      "learning_rate": 9.66560303772035e-06,
+      "loss": 0.8,
+      "mean_token_accuracy": 0.7457844614982605,
+      "num_tokens": 2178048.0,
+      "step": 133
+    },
+    {
+      "entropy": 0.7559850811958313,
+      "epoch": 1.6341463414634148,
+      "grad_norm": 0.162869393825531,
+      "learning_rate": 9.08967402605988e-06,
+      "loss": 0.7528,
+      "mean_token_accuracy": 0.7514662742614746,
+      "num_tokens": 2194432.0,
+      "step": 134
+    },
+    {
+      "entropy": 0.7820285558700562,
+      "epoch": 1.6463414634146343,
+      "grad_norm": 0.17867934703826904,
+      "learning_rate": 8.529715727489912e-06,
+      "loss": 0.7747,
+      "mean_token_accuracy": 0.7536656856536865,
+      "num_tokens": 2210816.0,
+      "step": 135
+    },
+    {
+      "entropy": 0.7722501754760742,
+      "epoch": 1.6585365853658538,
+      "grad_norm": 0.17919929325580597,
+      "learning_rate": 7.985946740447791e-06,
+      "loss": 0.7788,
+      "mean_token_accuracy": 0.7443792819976807,
+      "num_tokens": 2227200.0,
+      "step": 136
+    },
+    {
+      "entropy": 0.8223711848258972,
+      "epoch": 1.6707317073170733,
+      "grad_norm": 0.18295317888259888,
+      "learning_rate": 7.458579343331995e-06,
+      "loss": 0.8167,
+      "mean_token_accuracy": 0.7397971749305725,
+      "num_tokens": 2243584.0,
+      "step": 137
+    },
+    {
+      "entropy": 0.800744354724884,
+      "epoch": 1.6829268292682928,
+      "grad_norm": 0.18576347827911377,
+      "learning_rate": 6.947819411632223e-06,
+      "loss": 0.7968,
+      "mean_token_accuracy": 0.7408968806266785,
+      "num_tokens": 2259968.0,
+      "step": 138
+    },
+    {
+      "entropy": 0.7550928592681885,
+      "epoch": 1.6951219512195121,
+      "grad_norm": 0.2127634733915329,
+      "learning_rate": 6.45386633755894e-06,
+      "loss": 0.7554,
+      "mean_token_accuracy": 0.7423631548881531,
+      "num_tokens": 2276352.0,
+      "step": 139
+    },
+    {
+      "entropy": 0.7064895033836365,
+      "epoch": 1.7073170731707317,
+      "grad_norm": 0.17422887682914734,
+      "learning_rate": 5.976912952204017e-06,
+      "loss": 0.7094,
+      "mean_token_accuracy": 0.7641128897666931,
+      "num_tokens": 2292736.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.7777723073959351,
+      "epoch": 1.7195121951219512,
+      "grad_norm": 0.18271087110042572,
+      "learning_rate": 5.51714545026264e-06,
+      "loss": 0.781,
+      "mean_token_accuracy": 0.7472507357597351,
+      "num_tokens": 2309120.0,
+      "step": 141
+    },
+    {
+      "entropy": 0.7698872089385986,
+      "epoch": 1.7317073170731707,
+      "grad_norm": 0.17317108809947968,
+      "learning_rate": 5.074743317346009e-06,
+      "loss": 0.7609,
+      "mean_token_accuracy": 0.7498167157173157,
+      "num_tokens": 2325504.0,
+      "step": 142
+    },
+    {
+      "entropy": 0.7984127402305603,
+      "epoch": 1.7439024390243902,
+      "grad_norm": 0.17088834941387177,
+      "learning_rate": 4.649879259913137e-06,
+      "loss": 0.7915,
+      "mean_token_accuracy": 0.7412023544311523,
+      "num_tokens": 2341888.0,
+      "step": 143
+    },
+    {
+      "entropy": 0.7539505958557129,
+      "epoch": 1.7560975609756098,
+      "grad_norm": 0.20175665616989136,
+      "learning_rate": 4.242719137849077e-06,
+      "loss": 0.7497,
+      "mean_token_accuracy": 0.7550097703933716,
+      "num_tokens": 2358272.0,
+      "step": 144
+    },
+    {
+      "entropy": 0.7771869897842407,
+      "epoch": 1.7682926829268293,
+      "grad_norm": 0.16837109625339508,
+      "learning_rate": 3.853421899715992e-06,
+      "loss": 0.7727,
+      "mean_token_accuracy": 0.7457844614982605,
+      "num_tokens": 2374656.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.7660170793533325,
+      "epoch": 1.7804878048780488,
+      "grad_norm": 0.19410550594329834,
+      "learning_rate": 3.4821395207022766e-06,
+      "loss": 0.7658,
+      "mean_token_accuracy": 0.7619134783744812,
+      "num_tokens": 2391040.0,
+      "step": 146
+    },
+    {
+      "entropy": 0.8108944892883301,
+      "epoch": 1.7926829268292683,
+      "grad_norm": 0.17104439437389374,
+      "learning_rate": 3.1290169432939553e-06,
+      "loss": 0.8056,
+      "mean_token_accuracy": 0.7399193644523621,
+      "num_tokens": 2407424.0,
+      "step": 147
+    },
+    {
+      "entropy": 0.7316269874572754,
+      "epoch": 1.8048780487804879,
+      "grad_norm": 0.18812088668346405,
+      "learning_rate": 2.794192020691544e-06,
+      "loss": 0.7328,
+      "mean_token_accuracy": 0.7670454382896423,
+      "num_tokens": 2423808.0,
+      "step": 148
+    },
+    {
+      "entropy": 0.7689571380615234,
+      "epoch": 1.8170731707317072,
+      "grad_norm": 0.178997203707695,
+      "learning_rate": 2.4777954629944477e-06,
+      "loss": 0.7693,
+      "mean_token_accuracy": 0.757331371307373,
+      "num_tokens": 2440192.0,
+      "step": 149
+    },
+    {
+      "entropy": 0.7423138618469238,
+      "epoch": 1.8292682926829267,
+      "grad_norm": 0.18085432052612305,
+      "learning_rate": 2.179950786173879e-06,
+      "loss": 0.7428,
+      "mean_token_accuracy": 0.7474951148033142,
+      "num_tokens": 2456576.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7876198887825012,
+      "epoch": 1.8414634146341462,
+      "grad_norm": 0.16444949805736542,
+      "learning_rate": 1.9007742638543102e-06,
+      "loss": 0.7773,
+      "mean_token_accuracy": 0.7408357858657837,
+      "num_tokens": 2472960.0,
+      "step": 151
+    },
+    {
+      "entropy": 0.7868691682815552,
+      "epoch": 1.8536585365853657,
+      "grad_norm": 0.1716119349002838,
+      "learning_rate": 1.6403748819221466e-06,
+      "loss": 0.7792,
+      "mean_token_accuracy": 0.7418133020401001,
+      "num_tokens": 2489344.0,
+      "step": 152
+    },
+    {
+      "entropy": 0.7834361791610718,
+      "epoch": 1.8658536585365852,
+      "grad_norm": 0.17245984077453613,
+      "learning_rate": 1.3988542959794627e-06,
+      "loss": 0.7799,
+      "mean_token_accuracy": 0.7481671571731567,
+      "num_tokens": 2505728.0,
+      "step": 153
+    },
+    {
+      "entropy": 0.7828064560890198,
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.16838686168193817,
+      "learning_rate": 1.1763067916593262e-06,
+      "loss": 0.7771,
+      "mean_token_accuracy": 0.7446847558021545,
+      "num_tokens": 2522112.0,
+      "step": 154
+    },
+    {
+      "entropy": 0.7719861268997192,
+      "epoch": 1.8902439024390243,
+      "grad_norm": 0.17695309221744537,
+      "learning_rate": 9.728192478182574e-07,
+      "loss": 0.7782,
+      "mean_token_accuracy": 0.742668628692627,
+      "num_tokens": 2538496.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.7589446306228638,
+      "epoch": 1.9024390243902438,
+      "grad_norm": 0.17181237041950226,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 0.7545,
+      "mean_token_accuracy": 0.7368035316467285,
+      "num_tokens": 2554880.0,
+      "step": 156
+    },
+    {
+      "entropy": 0.7770121097564697,
+      "epoch": 1.9146341463414633,
+      "grad_norm": 0.19122466444969177,
+      "learning_rate": 6.233343225249933e-07,
+      "loss": 0.7929,
+      "mean_token_accuracy": 0.7547653913497925,
+      "num_tokens": 2571264.0,
+      "step": 157
+    },
+    {
+      "entropy": 0.7677299380302429,
+      "epoch": 1.9268292682926829,
+      "grad_norm": 0.17084810137748718,
+      "learning_rate": 4.774733741942206e-07,
+      "loss": 0.7609,
+      "mean_token_accuracy": 0.7466397881507874,
+      "num_tokens": 2587648.0,
+      "step": 158
+    },
+    {
+      "entropy": 0.7504435777664185,
+      "epoch": 1.9390243902439024,
+      "grad_norm": 0.18960894644260406,
+      "learning_rate": 3.5094519932415417e-07,
+      "loss": 0.7408,
+      "mean_token_accuracy": 0.7562927603721619,
+      "num_tokens": 2604032.0,
+      "step": 159
+    },
+    {
+      "entropy": 0.8061732053756714,
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.1871030181646347,
+      "learning_rate": 2.437991924167937e-07,
+      "loss": 0.7982,
+      "mean_token_accuracy": 0.7414467334747314,
+      "num_tokens": 2620416.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7523500919342041,
+      "epoch": 1.9634146341463414,
+      "grad_norm": 0.17688721418380737,
+      "learning_rate": 1.560771814970885e-07,
+      "loss": 0.7481,
+      "mean_token_accuracy": 0.7507942318916321,
+      "num_tokens": 2636800.0,
+      "step": 161
+    },
+    {
+      "entropy": 0.776507556438446,
+      "epoch": 1.975609756097561,
+      "grad_norm": 0.19538748264312744,
+      "learning_rate": 8.781341178393244e-08,
+      "loss": 0.7691,
+      "mean_token_accuracy": 0.7580034136772156,
+      "num_tokens": 2653184.0,
+      "step": 162
+    },
+    {
+      "entropy": 0.7280100584030151,
+      "epoch": 1.9878048780487805,
+      "grad_norm": 0.1717352569103241,
+      "learning_rate": 3.9034532321408076e-08,
+      "loss": 0.7301,
+      "mean_token_accuracy": 0.7578201293945312,
+      "num_tokens": 2669568.0,
+      "step": 163
+    },
+    {
+      "entropy": 0.7388795018196106,
+      "epoch": 2.0,
+      "grad_norm": 0.18290187418460846,
+      "learning_rate": 9.75958557545842e-09,
+      "loss": 0.7391,
+      "mean_token_accuracy": 0.7640925645828247,
+      "num_tokens": 2684928.0,
+      "step": 164
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.906640896262144e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

r16_checkpoint-164/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04a4f7546a5520db95ed52a6c6b4a8204653e8385dd6dde6dba55331d70f28d
+size 6225