Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+r32_checkpoint-164/tokenizer.json filter=lfs diff=lfs merge=lfs -text

r32_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

r32_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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

r32_checkpoint-164/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4fa177a2dc0f148f83c355817fc6d792e0a66041a3447110f1f95affc40709
+size 1817420168

r32_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
+}

r32_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 %}

r32_checkpoint-164/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fd3ea8aa138b69d019a42a1deb365c98b052d8a145daf14c2a00ef1fc1b0e2
+size 528915403

r32_checkpoint-164/rng_state.pth

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

r32_checkpoint-164/scheduler.pt

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

r32_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
+  }
+}

r32_checkpoint-164/tokenizer.json

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

r32_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
+}

r32_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": 1.5963459014892578,
+      "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": 1.6390712261199951,
+      "learning_rate": 2e-05,
+      "loss": 1.6238,
+      "mean_token_accuracy": 0.6236559152603149,
+      "num_tokens": 32768.0,
+      "step": 2
+    },
+    {
+      "entropy": 0.8494130373001099,
+      "epoch": 0.036585365853658534,
+      "grad_norm": 1.530470609664917,
+      "learning_rate": 4e-05,
+      "loss": 1.5979,
+      "mean_token_accuracy": 0.6152859330177307,
+      "num_tokens": 49152.0,
+      "step": 3
+    },
+    {
+      "entropy": 0.9093179106712341,
+      "epoch": 0.04878048780487805,
+      "grad_norm": 1.4252384901046753,
+      "learning_rate": 6e-05,
+      "loss": 1.5182,
+      "mean_token_accuracy": 0.6146138906478882,
+      "num_tokens": 65536.0,
+      "step": 4
+    },
+    {
+      "entropy": 0.9616245031356812,
+      "epoch": 0.06097560975609756,
+      "grad_norm": 0.7481213212013245,
+      "learning_rate": 8e-05,
+      "loss": 1.4084,
+      "mean_token_accuracy": 0.6196847558021545,
+      "num_tokens": 81920.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.0191116333007812,
+      "epoch": 0.07317073170731707,
+      "grad_norm": 0.5280348062515259,
+      "learning_rate": 0.0001,
+      "loss": 1.3238,
+      "mean_token_accuracy": 0.6318426132202148,
+      "num_tokens": 98304.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.1041736602783203,
+      "epoch": 0.08536585365853659,
+      "grad_norm": 0.4979991316795349,
+      "learning_rate": 9.999024041442456e-05,
+      "loss": 1.2856,
+      "mean_token_accuracy": 0.648949146270752,
+      "num_tokens": 114688.0,
+      "step": 7
+    },
+    {
+      "entropy": 1.1686979532241821,
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.48847347497940063,
+      "learning_rate": 9.99609654676786e-05,
+      "loss": 1.1952,
+      "mean_token_accuracy": 0.6550586223602295,
+      "num_tokens": 131072.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.2216129302978516,
+      "epoch": 0.10975609756097561,
+      "grad_norm": 0.417371541261673,
+      "learning_rate": 9.991218658821608e-05,
+      "loss": 1.1544,
+      "mean_token_accuracy": 0.6692937612533569,
+      "num_tokens": 147456.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.2579982280731201,
+      "epoch": 0.12195121951219512,
+      "grad_norm": 0.4322424530982971,
+      "learning_rate": 9.984392281850293e-05,
+      "loss": 1.1366,
+      "mean_token_accuracy": 0.6645283699035645,
+      "num_tokens": 163840.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.290279507637024,
+      "epoch": 0.13414634146341464,
+      "grad_norm": 0.3934442102909088,
+      "learning_rate": 9.97562008075832e-05,
+      "loss": 1.1393,
+      "mean_token_accuracy": 0.6884164214134216,
+      "num_tokens": 180224.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.2753918170928955,
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.387364000082016,
+      "learning_rate": 9.964905480067586e-05,
+      "loss": 1.1095,
+      "mean_token_accuracy": 0.6788245439529419,
+      "num_tokens": 196608.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.2127259969711304,
+      "epoch": 0.15853658536585366,
+      "grad_norm": 0.36151859164237976,
+      "learning_rate": 9.952252662580579e-05,
+      "loss": 1.0552,
+      "mean_token_accuracy": 0.6963587403297424,
+      "num_tokens": 212992.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.1111319065093994,
+      "epoch": 0.17073170731707318,
+      "grad_norm": 0.39386796951293945,
+      "learning_rate": 9.937666567747501e-05,
+      "loss": 0.9736,
+      "mean_token_accuracy": 0.7115713357925415,
+      "num_tokens": 229376.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.1253695487976074,
+      "epoch": 0.18292682926829268,
+      "grad_norm": 0.32668980956077576,
+      "learning_rate": 9.921152889737984e-05,
+      "loss": 1.0039,
+      "mean_token_accuracy": 0.7135874629020691,
+      "num_tokens": 245760.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.0578031539916992,
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.3212492763996124,
+      "learning_rate": 9.902718075218176e-05,
+      "loss": 0.9497,
+      "mean_token_accuracy": 0.7187805771827698,
+      "num_tokens": 262144.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.0252618789672852,
+      "epoch": 0.2073170731707317,
+      "grad_norm": 0.2713640630245209,
+      "learning_rate": 9.882369320834069e-05,
+      "loss": 0.9598,
+      "mean_token_accuracy": 0.7245845794677734,
+      "num_tokens": 278528.0,
+      "step": 17
+    },
+    {
+      "entropy": 0.9348979592323303,
+      "epoch": 0.21951219512195122,
+      "grad_norm": 0.22841602563858032,
+      "learning_rate": 9.860114570402054e-05,
+      "loss": 0.8984,
+      "mean_token_accuracy": 0.7200635671615601,
+      "num_tokens": 294912.0,
+      "step": 18
+    },
+    {
+      "entropy": 0.907302975654602,
+      "epoch": 0.23170731707317074,
+      "grad_norm": 0.2066853642463684,
+      "learning_rate": 9.835962511807786e-05,
+      "loss": 0.8834,
+      "mean_token_accuracy": 0.7054007649421692,
+      "num_tokens": 311296.0,
+      "step": 19
+    },
+    {
+      "entropy": 0.8672784566879272,
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.21688124537467957,
+      "learning_rate": 9.809922573614569e-05,
+      "loss": 0.8693,
+      "mean_token_accuracy": 0.7228739261627197,
+      "num_tokens": 327680.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.8820980787277222,
+      "epoch": 0.25609756097560976,
+      "grad_norm": 0.22094115614891052,
+      "learning_rate": 9.782004921382612e-05,
+      "loss": 0.9005,
+      "mean_token_accuracy": 0.7296554446220398,
+      "num_tokens": 344064.0,
+      "step": 21
+    },
+    {
+      "entropy": 0.8203250169754028,
+      "epoch": 0.2682926829268293,
+      "grad_norm": 0.23713326454162598,
+      "learning_rate": 9.752220453700556e-05,
+      "loss": 0.8812,
+      "mean_token_accuracy": 0.7346652150154114,
+      "num_tokens": 360448.0,
+      "step": 22
+    },
+    {
+      "entropy": 0.8203630447387695,
+      "epoch": 0.2804878048780488,
+      "grad_norm": 0.20235033333301544,
+      "learning_rate": 9.720580797930845e-05,
+      "loss": 0.8422,
+      "mean_token_accuracy": 0.7298998236656189,
+      "num_tokens": 376832.0,
+      "step": 23
+    },
+    {
+      "entropy": 0.7894142270088196,
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.19894097745418549,
+      "learning_rate": 9.687098305670605e-05,
+      "loss": 0.811,
+      "mean_token_accuracy": 0.7418743968009949,
+      "num_tokens": 393216.0,
+      "step": 24
+    },
+    {
+      "entropy": 0.7657908201217651,
+      "epoch": 0.3048780487804878,
+      "grad_norm": 0.21109017729759216,
+      "learning_rate": 9.651786047929773e-05,
+      "loss": 0.7989,
+      "mean_token_accuracy": 0.7545210123062134,
+      "num_tokens": 409600.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.7561244368553162,
+      "epoch": 0.3170731707317073,
+      "grad_norm": 0.19815832376480103,
+      "learning_rate": 9.614657810028402e-05,
+      "loss": 0.7742,
+      "mean_token_accuracy": 0.7501832842826843,
+      "num_tokens": 425984.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.7754881978034973,
+      "epoch": 0.32926829268292684,
+      "grad_norm": 0.1786530464887619,
+      "learning_rate": 9.575728086215092e-05,
+      "loss": 0.7837,
+      "mean_token_accuracy": 0.7402859330177307,
+      "num_tokens": 442368.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.8024546504020691,
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.18607085943222046,
+      "learning_rate": 9.535012074008687e-05,
+      "loss": 0.8114,
+      "mean_token_accuracy": 0.7430962920188904,
+      "num_tokens": 458752.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.8002961277961731,
+      "epoch": 0.35365853658536583,
+      "grad_norm": 0.18757443130016327,
+      "learning_rate": 9.492525668265399e-05,
+      "loss": 0.8114,
+      "mean_token_accuracy": 0.7425464391708374,
+      "num_tokens": 475136.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.8088508248329163,
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.15429729223251343,
+      "learning_rate": 9.448285454973738e-05,
+      "loss": 0.7985,
+      "mean_token_accuracy": 0.7435850501060486,
+      "num_tokens": 491520.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8867294192314148,
+      "epoch": 0.3780487804878049,
+      "grad_norm": 0.1645601987838745,
+      "learning_rate": 9.402308704779599e-05,
+      "loss": 0.8753,
+      "mean_token_accuracy": 0.7231183052062988,
+      "num_tokens": 507904.0,
+      "step": 31
+    },
+    {
+      "entropy": 0.8072658777236938,
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.15431220829486847,
+      "learning_rate": 9.354613366244108e-05,
+      "loss": 0.8023,
+      "mean_token_accuracy": 0.7437683343887329,
+      "num_tokens": 524288.0,
+      "step": 32
+    },
+    {
+      "entropy": 0.8136405944824219,
+      "epoch": 0.4024390243902439,
+      "grad_norm": 0.15425367653369904,
+      "learning_rate": 9.305218058836778e-05,
+      "loss": 0.7937,
+      "mean_token_accuracy": 0.7411412596702576,
+      "num_tokens": 540672.0,
+      "step": 33
+    },
+    {
+      "entropy": 0.7860234379768372,
+      "epoch": 0.4146341463414634,
+      "grad_norm": 0.1481509953737259,
+      "learning_rate": 9.254142065666801e-05,
+      "loss": 0.7793,
+      "mean_token_accuracy": 0.745662271976471,
+      "num_tokens": 557056.0,
+      "step": 34
+    },
+    {
+      "entropy": 0.8171625137329102,
+      "epoch": 0.4268292682926829,
+      "grad_norm": 0.16634202003479004,
+      "learning_rate": 9.201405325955221e-05,
+      "loss": 0.8049,
+      "mean_token_accuracy": 0.7364980578422546,
+      "num_tokens": 573440.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.9218671321868896,
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.18720214068889618,
+      "learning_rate": 9.14702842725101e-05,
+      "loss": 0.9101,
+      "mean_token_accuracy": 0.7291055917739868,
+      "num_tokens": 589824.0,
+      "step": 36
+    },
+    {
+      "entropy": 0.8412395715713501,
+      "epoch": 0.45121951219512196,
+      "grad_norm": 0.8126994967460632,
+      "learning_rate": 9.091032597394012e-05,
+      "loss": 0.8208,
+      "mean_token_accuracy": 0.7296554446220398,
+      "num_tokens": 606208.0,
+      "step": 37
+    },
+    {
+      "entropy": 0.8284791707992554,
+      "epoch": 0.4634146341463415,
+      "grad_norm": 0.1619691252708435,
+      "learning_rate": 9.033439696227965e-05,
+      "loss": 0.8143,
+      "mean_token_accuracy": 0.7478616833686829,
+      "num_tokens": 622592.0,
+      "step": 38
+    },
+    {
+      "entropy": 0.8680922389030457,
+      "epoch": 0.47560975609756095,
+      "grad_norm": 0.17583687603473663,
+      "learning_rate": 8.974272207066767e-05,
+      "loss": 0.8632,
+      "mean_token_accuracy": 0.734237551689148,
+      "num_tokens": 638976.0,
+      "step": 39
+    },
+    {
+      "entropy": 0.8237974047660828,
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.16230465471744537,
+      "learning_rate": 8.913553227917367e-05,
+      "loss": 0.8211,
+      "mean_token_accuracy": 0.7407135963439941,
+      "num_tokens": 655360.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8138308525085449,
+      "epoch": 0.5,
+      "grad_norm": 0.1973644644021988,
+      "learning_rate": 8.851306462462688e-05,
+      "loss": 0.809,
+      "mean_token_accuracy": 0.7399193644523621,
+      "num_tokens": 671744.0,
+      "step": 41
+    },
+    {
+      "entropy": 0.8491259813308716,
+      "epoch": 0.5121951219512195,
+      "grad_norm": 0.19937394559383392,
+      "learning_rate": 8.787556210808101e-05,
+      "loss": 0.8538,
+      "mean_token_accuracy": 0.7324047088623047,
+      "num_tokens": 688128.0,
+      "step": 42
+    },
+    {
+      "entropy": 0.8189643621444702,
+      "epoch": 0.524390243902439,
+      "grad_norm": 0.16293630003929138,
+      "learning_rate": 8.722327359995064e-05,
+      "loss": 0.8089,
+      "mean_token_accuracy": 0.7360092997550964,
+      "num_tokens": 704512.0,
+      "step": 43
+    },
+    {
+      "entropy": 0.8015111684799194,
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.5772698521614075,
+      "learning_rate": 8.655645374285637e-05,
+      "loss": 0.8118,
+      "mean_token_accuracy": 0.7514051795005798,
+      "num_tokens": 720896.0,
+      "step": 44
+    },
+    {
+      "entropy": 0.819705605506897,
+      "epoch": 0.5487804878048781,
+      "grad_norm": 0.17325186729431152,
+      "learning_rate": 8.587536285221656e-05,
+      "loss": 0.82,
+      "mean_token_accuracy": 0.7424853444099426,
+      "num_tokens": 737280.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.8362059593200684,
+      "epoch": 0.5609756097560976,
+      "grad_norm": 0.19030238687992096,
+      "learning_rate": 8.518026681462448e-05,
+      "loss": 0.8567,
+      "mean_token_accuracy": 0.74590665102005,
+      "num_tokens": 753664.0,
+      "step": 46
+    },
+    {
+      "entropy": 0.781765878200531,
+      "epoch": 0.573170731707317,
+      "grad_norm": 0.16227546334266663,
+      "learning_rate": 8.44714369840506e-05,
+      "loss": 0.7698,
+      "mean_token_accuracy": 0.7480449676513672,
+      "num_tokens": 770048.0,
+      "step": 47
+    },
+    {
+      "entropy": 0.7942266464233398,
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.1633511185646057,
+      "learning_rate": 8.374915007591053e-05,
+      "loss": 0.7937,
+      "mean_token_accuracy": 0.7441959977149963,
+      "num_tokens": 786432.0,
+      "step": 48
+    },
+    {
+      "entropy": 0.7600513696670532,
+      "epoch": 0.5975609756097561,
+      "grad_norm": 0.42064133286476135,
+      "learning_rate": 8.301368805903988e-05,
+      "loss": 0.7503,
+      "mean_token_accuracy": 0.7543988227844238,
+      "num_tokens": 802816.0,
+      "step": 49
+    },
+    {
+      "entropy": 0.7933059930801392,
+      "epoch": 0.6097560975609756,
+      "grad_norm": 0.14397192001342773,
+      "learning_rate": 8.226533804561827e-05,
+      "loss": 0.7778,
+      "mean_token_accuracy": 0.7393695116043091,
+      "num_tokens": 819200.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7796611189842224,
+      "epoch": 0.6219512195121951,
+      "grad_norm": 0.16651125252246857,
+      "learning_rate": 8.150439217908556e-05,
+      "loss": 0.7829,
+      "mean_token_accuracy": 0.7496334314346313,
+      "num_tokens": 835584.0,
+      "step": 51
+    },
+    {
+      "entropy": 0.7477437257766724,
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.1598869115114212,
+      "learning_rate": 8.073114752009387e-05,
+      "loss": 0.7318,
+      "mean_token_accuracy": 0.7541544437408447,
+      "num_tokens": 851968.0,
+      "step": 52
+    },
+    {
+      "entropy": 0.7574367523193359,
+      "epoch": 0.6463414634146342,
+      "grad_norm": 0.16568222641944885,
+      "learning_rate": 7.994590593054001e-05,
+      "loss": 0.7553,
+      "mean_token_accuracy": 0.7600806355476379,
+      "num_tokens": 868352.0,
+      "step": 53
+    },
+    {
+      "entropy": 0.7108243107795715,
+      "epoch": 0.6585365853658537,
+      "grad_norm": 0.14883026480674744,
+      "learning_rate": 7.91489739557236e-05,
+      "loss": 0.7076,
+      "mean_token_accuracy": 0.7589198350906372,
+      "num_tokens": 884736.0,
+      "step": 54
+    },
+    {
+      "entropy": 0.8336981534957886,
+      "epoch": 0.6707317073170732,
+      "grad_norm": 0.17898979783058167,
+      "learning_rate": 7.83406627046769e-05,
+      "loss": 0.8401,
+      "mean_token_accuracy": 0.7349706888198853,
+      "num_tokens": 901120.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.8287414312362671,
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.18134883046150208,
+      "learning_rate": 7.752128772871292e-05,
+      "loss": 0.8288,
+      "mean_token_accuracy": 0.7431573867797852,
+      "num_tokens": 917504.0,
+      "step": 56
+    },
+    {
+      "entropy": 0.7957069873809814,
+      "epoch": 0.6951219512195121,
+      "grad_norm": 0.1710679531097412,
+      "learning_rate": 7.669116889823955e-05,
+      "loss": 0.7917,
+      "mean_token_accuracy": 0.748106062412262,
+      "num_tokens": 933888.0,
+      "step": 57
+    },
+    {
+      "entropy": 0.8114748597145081,
+      "epoch": 0.7073170731707317,
+      "grad_norm": 0.1788218915462494,
+      "learning_rate": 7.585063027788731e-05,
+      "loss": 0.807,
+      "mean_token_accuracy": 0.7442570924758911,
+      "num_tokens": 950272.0,
+      "step": 58
+    },
+    {
+      "entropy": 0.812384307384491,
+      "epoch": 0.7195121951219512,
+      "grad_norm": 0.2021624743938446,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8117,
+      "mean_token_accuracy": 0.7293499708175659,
+      "num_tokens": 966656.0,
+      "step": 59
+    },
+    {
+      "entropy": 0.7589200735092163,
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.17116786539554596,
+      "learning_rate": 7.413961013653726e-05,
+      "loss": 0.7535,
+      "mean_token_accuracy": 0.7605693936347961,
+      "num_tokens": 983040.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7704336047172546,
+      "epoch": 0.7439024390243902,
+      "grad_norm": 0.16941235959529877,
+      "learning_rate": 7.326979656943906e-05,
+      "loss": 0.7656,
+      "mean_token_accuracy": 0.7536045908927917,
+      "num_tokens": 999424.0,
+      "step": 61
+    },
+    {
+      "entropy": 0.7519150972366333,
+      "epoch": 0.7560975609756098,
+      "grad_norm": 0.16954171657562256,
+      "learning_rate": 7.239089885950316e-05,
+      "loss": 0.749,
+      "mean_token_accuracy": 0.7558650970458984,
+      "num_tokens": 1015808.0,
+      "step": 62
+    },
+    {
+      "entropy": 0.7944316267967224,
+      "epoch": 0.7682926829268293,
+      "grad_norm": 0.27296677231788635,
+      "learning_rate": 7.150326011382604e-05,
+      "loss": 0.8155,
+      "mean_token_accuracy": 0.7515273690223694,
+      "num_tokens": 1032192.0,
+      "step": 63
+    },
+    {
+      "entropy": 0.7714963555335999,
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.18488256633281708,
+      "learning_rate": 7.060722685185961e-05,
+      "loss": 0.781,
+      "mean_token_accuracy": 0.7584921717643738,
+      "num_tokens": 1048576.0,
+      "step": 64
+    },
+    {
+      "entropy": 0.7712550163269043,
+      "epoch": 0.7926829268292683,
+      "grad_norm": 0.17567600309848785,
+      "learning_rate": 6.970314887013584e-05,
+      "loss": 0.7699,
+      "mean_token_accuracy": 0.7406525015830994,
+      "num_tokens": 1064960.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.8233213424682617,
+      "epoch": 0.8048780487804879,
+      "grad_norm": 0.183174267411232,
+      "learning_rate": 6.879137910571191e-05,
+      "loss": 0.8284,
+      "mean_token_accuracy": 0.7317326664924622,
+      "num_tokens": 1081344.0,
+      "step": 66
+    },
+    {
+      "entropy": 0.7999821305274963,
+      "epoch": 0.8170731707317073,
+      "grad_norm": 0.17293156683444977,
+      "learning_rate": 6.787227349838947e-05,
+      "loss": 0.8077,
+      "mean_token_accuracy": 0.7396138906478882,
+      "num_tokens": 1097728.0,
+      "step": 67
+    },
+    {
+      "entropy": 0.7888548970222473,
+      "epoch": 0.8292682926829268,
+      "grad_norm": 0.1647597849369049,
+      "learning_rate": 6.694619085176159e-05,
+      "loss": 0.7789,
+      "mean_token_accuracy": 0.7311217188835144,
+      "num_tokens": 1114112.0,
+      "step": 68
+    },
+    {
+      "entropy": 0.8527079224586487,
+      "epoch": 0.8414634146341463,
+      "grad_norm": 0.1922655999660492,
+      "learning_rate": 6.601349269314188e-05,
+      "loss": 0.853,
+      "mean_token_accuracy": 0.7415078282356262,
+      "num_tokens": 1130496.0,
+      "step": 69
+    },
+    {
+      "entropy": 0.7573457360267639,
+      "epoch": 0.8536585365853658,
+      "grad_norm": 0.1761794090270996,
+      "learning_rate": 6.507454313243015e-05,
+      "loss": 0.7672,
+      "mean_token_accuracy": 0.7571480870246887,
+      "num_tokens": 1146880.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8084772825241089,
+      "epoch": 0.8658536585365854,
+      "grad_norm": 0.18144868314266205,
+      "learning_rate": 6.412970871996995e-05,
+      "loss": 0.8162,
+      "mean_token_accuracy": 0.738575279712677,
+      "num_tokens": 1163264.0,
+      "step": 71
+    },
+    {
+      "entropy": 0.7593176364898682,
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.17066611349582672,
+      "learning_rate": 6.317935830345338e-05,
+      "loss": 0.7526,
+      "mean_token_accuracy": 0.7476783990859985,
+      "num_tokens": 1179648.0,
+      "step": 72
+    },
+    {
+      "entropy": 0.7786603569984436,
+      "epoch": 0.8902439024390244,
+      "grad_norm": 0.17519912123680115,
+      "learning_rate": 6.222386288392913e-05,
+      "loss": 0.7735,
+      "mean_token_accuracy": 0.7468841671943665,
+      "num_tokens": 1196032.0,
+      "step": 73
+    },
+    {
+      "entropy": 0.7674257755279541,
+      "epoch": 0.9024390243902439,
+      "grad_norm": 0.16099241375923157,
+      "learning_rate": 6.126359547096975e-05,
+      "loss": 0.7703,
+      "mean_token_accuracy": 0.7444403767585754,
+      "num_tokens": 1212416.0,
+      "step": 74
+    },
+    {
+      "entropy": 0.7131564021110535,
+      "epoch": 0.9146341463414634,
+      "grad_norm": 0.1600881665945053,
+      "learning_rate": 6.029893093705492e-05,
+      "loss": 0.7189,
+      "mean_token_accuracy": 0.7669843435287476,
+      "num_tokens": 1228800.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8336191177368164,
+      "epoch": 0.926829268292683,
+      "grad_norm": 0.16658978164196014,
+      "learning_rate": 5.9330245871227454e-05,
+      "loss": 0.8347,
+      "mean_token_accuracy": 0.7218964099884033,
+      "num_tokens": 1245184.0,
+      "step": 76
+    },
+    {
+      "entropy": 0.7960056066513062,
+      "epoch": 0.9390243902439024,
+      "grad_norm": 0.17010802030563354,
+      "learning_rate": 5.835791843207916e-05,
+      "loss": 0.7861,
+      "mean_token_accuracy": 0.7481671571731567,
+      "num_tokens": 1261568.0,
+      "step": 77
+    },
+    {
+      "entropy": 0.7583601474761963,
+      "epoch": 0.9512195121951219,
+      "grad_norm": 0.16307863593101501,
+      "learning_rate": 5.738232820012407e-05,
+      "loss": 0.7559,
+      "mean_token_accuracy": 0.7466397881507874,
+      "num_tokens": 1277952.0,
+      "step": 78
+    },
+    {
+      "entropy": 0.7828479409217834,
+      "epoch": 0.9634146341463414,
+      "grad_norm": 0.17573870718479156,
+      "learning_rate": 5.640385602961634e-05,
+      "loss": 0.7633,
+      "mean_token_accuracy": 0.74590665102005,
+      "num_tokens": 1294336.0,
+      "step": 79
+    },
+    {
+      "entropy": 0.802649736404419,
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.18503673374652863,
+      "learning_rate": 5.5422883899871284e-05,
+      "loss": 0.8117,
+      "mean_token_accuracy": 0.7491446733474731,
+      "num_tokens": 1310720.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7632466554641724,
+      "epoch": 0.9878048780487805,
+      "grad_norm": 0.16268981993198395,
+      "learning_rate": 5.4439794766146746e-05,
+      "loss": 0.7595,
+      "mean_token_accuracy": 0.7531769275665283,
+      "num_tokens": 1327104.0,
+      "step": 81
+    },
+    {
+      "entropy": 0.8030194044113159,
+      "epoch": 1.0,
+      "grad_norm": 0.18873123824596405,
+      "learning_rate": 5.34549724101439e-05,
+      "loss": 0.7987,
+      "mean_token_accuracy": 0.7489736080169678,
+      "num_tokens": 1342464.0,
+      "step": 82
+    },
+    {
+      "entropy": 0.7906725406646729,
+      "epoch": 1.0121951219512195,
+      "grad_norm": 0.17143751680850983,
+      "learning_rate": 5.246880129018516e-05,
+      "loss": 0.7728,
+      "mean_token_accuracy": 0.7521994113922119,
+      "num_tokens": 1358848.0,
+      "step": 83
+    },
+    {
+      "entropy": 0.8525359630584717,
+      "epoch": 1.024390243902439,
+      "grad_norm": 0.17712131142616272,
+      "learning_rate": 5.148166639112799e-05,
+      "loss": 0.842,
+      "mean_token_accuracy": 0.7234237790107727,
+      "num_tokens": 1375232.0,
+      "step": 84
+    },
+    {
+      "entropy": 0.8285623788833618,
+      "epoch": 1.0365853658536586,
+      "grad_norm": 0.17242752015590668,
+      "learning_rate": 5.049395307407329e-05,
+      "loss": 0.8382,
+      "mean_token_accuracy": 0.7247678637504578,
+      "num_tokens": 1391616.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.787007749080658,
+      "epoch": 1.048780487804878,
+      "grad_norm": 0.1731046736240387,
+      "learning_rate": 4.950604692592672e-05,
+      "loss": 0.7812,
+      "mean_token_accuracy": 0.7462732195854187,
+      "num_tokens": 1408000.0,
+      "step": 86
+    },
+    {
+      "entropy": 0.7308117747306824,
+      "epoch": 1.0609756097560976,
+      "grad_norm": 0.1695345640182495,
+      "learning_rate": 4.851833360887201e-05,
+      "loss": 0.7343,
+      "mean_token_accuracy": 0.7636241316795349,
+      "num_tokens": 1424384.0,
+      "step": 87
+    },
+    {
+      "entropy": 0.7794758081436157,
+      "epoch": 1.0731707317073171,
+      "grad_norm": 0.17829656600952148,
+      "learning_rate": 4.7531198709814854e-05,
+      "loss": 0.7748,
+      "mean_token_accuracy": 0.7504276633262634,
+      "num_tokens": 1440768.0,
+      "step": 88
+    },
+    {
+      "entropy": 0.7062034606933594,
+      "epoch": 1.0853658536585367,
+      "grad_norm": 0.1711563915014267,
+      "learning_rate": 4.654502758985611e-05,
+      "loss": 0.7046,
+      "mean_token_accuracy": 0.7575757503509521,
+      "num_tokens": 1457152.0,
+      "step": 89
+    },
+    {
+      "entropy": 0.7635787725448608,
+      "epoch": 1.0975609756097562,
+      "grad_norm": 0.21904154121875763,
+      "learning_rate": 4.5560205233853266e-05,
+      "loss": 0.7718,
+      "mean_token_accuracy": 0.7604472041130066,
+      "num_tokens": 1473536.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.7882238626480103,
+      "epoch": 1.1097560975609757,
+      "grad_norm": 0.18260985612869263,
+      "learning_rate": 4.4577116100128735e-05,
+      "loss": 0.7848,
+      "mean_token_accuracy": 0.7522605061531067,
+      "num_tokens": 1489920.0,
+      "step": 91
+    },
+    {
+      "entropy": 0.7998174428939819,
+      "epoch": 1.1219512195121952,
+      "grad_norm": 0.17797434329986572,
+      "learning_rate": 4.3596143970383664e-05,
+      "loss": 0.7947,
+      "mean_token_accuracy": 0.7371701002120972,
+      "num_tokens": 1506304.0,
+      "step": 92
+    },
+    {
+      "entropy": 0.7851001024246216,
+      "epoch": 1.1341463414634148,
+      "grad_norm": 0.1763421893119812,
+      "learning_rate": 4.2617671799875944e-05,
+      "loss": 0.7854,
+      "mean_token_accuracy": 0.7437683343887329,
+      "num_tokens": 1522688.0,
+      "step": 93
+    },
+    {
+      "entropy": 0.7861537933349609,
+      "epoch": 1.146341463414634,
+      "grad_norm": 0.17330797016620636,
+      "learning_rate": 4.1642081567920846e-05,
+      "loss": 0.7753,
+      "mean_token_accuracy": 0.7458455562591553,
+      "num_tokens": 1539072.0,
+      "step": 94
+    },
+    {
+      "entropy": 0.7692281007766724,
+      "epoch": 1.1585365853658536,
+      "grad_norm": 0.17808745801448822,
+      "learning_rate": 4.066975412877255e-05,
+      "loss": 0.7588,
+      "mean_token_accuracy": 0.7517717480659485,
+      "num_tokens": 1555456.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.7761783599853516,
+      "epoch": 1.170731707317073,
+      "grad_norm": 0.17079956829547882,
+      "learning_rate": 3.970106906294509e-05,
+      "loss": 0.7637,
+      "mean_token_accuracy": 0.7463954091072083,
+      "num_tokens": 1571840.0,
+      "step": 96
+    },
+    {
+      "entropy": 0.8007237911224365,
+      "epoch": 1.1829268292682926,
+      "grad_norm": 0.20593133568763733,
+      "learning_rate": 3.873640452903026e-05,
+      "loss": 0.8,
+      "mean_token_accuracy": 0.7382698059082031,
+      "num_tokens": 1588224.0,
+      "step": 97
+    },
+    {
+      "entropy": 0.7703608870506287,
+      "epoch": 1.1951219512195121,
+      "grad_norm": 0.18243902921676636,
+      "learning_rate": 3.777613711607087e-05,
+      "loss": 0.7671,
+      "mean_token_accuracy": 0.760325014591217,
+      "num_tokens": 1604608.0,
+      "step": 98
+    },
+    {
+      "entropy": 0.7756364941596985,
+      "epoch": 1.2073170731707317,
+      "grad_norm": 0.21990089118480682,
+      "learning_rate": 3.682064169654663e-05,
+      "loss": 0.7624,
+      "mean_token_accuracy": 0.7485337257385254,
+      "num_tokens": 1620992.0,
+      "step": 99
+    },
+    {
+      "entropy": 0.7036648988723755,
+      "epoch": 1.2195121951219512,
+      "grad_norm": 0.17058764398097992,
+      "learning_rate": 3.587029128003006e-05,
+      "loss": 0.7028,
+      "mean_token_accuracy": 0.7634408473968506,
+      "num_tokens": 1637376.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7436861991882324,
+      "epoch": 1.2317073170731707,
+      "grad_norm": 0.17860503494739532,
+      "learning_rate": 3.492545686756986e-05,
+      "loss": 0.7432,
+      "mean_token_accuracy": 0.7567815184593201,
+      "num_tokens": 1653760.0,
+      "step": 101
+    },
+    {
+      "entropy": 0.7702594995498657,
+      "epoch": 1.2439024390243902,
+      "grad_norm": 0.2548927068710327,
+      "learning_rate": 3.3986507306858125e-05,
+      "loss": 0.7747,
+      "mean_token_accuracy": 0.7558650970458984,
+      "num_tokens": 1670144.0,
+      "step": 102
+    },
+    {
+      "entropy": 0.7179501056671143,
+      "epoch": 1.2560975609756098,
+      "grad_norm": 0.1786641776561737,
+      "learning_rate": 3.3053809148238426e-05,
+      "loss": 0.7198,
+      "mean_token_accuracy": 0.7651515007019043,
+      "num_tokens": 1686528.0,
+      "step": 103
+    },
+    {
+      "entropy": 0.7515727281570435,
+      "epoch": 1.2682926829268293,
+      "grad_norm": 0.2297879457473755,
+      "learning_rate": 3.212772650161056e-05,
+      "loss": 0.761,
+      "mean_token_accuracy": 0.7465175986289978,
+      "num_tokens": 1702912.0,
+      "step": 104
+    },
+    {
+      "entropy": 0.7515345215797424,
+      "epoch": 1.2804878048780488,
+      "grad_norm": 0.1867917776107788,
+      "learning_rate": 3.12086208942881e-05,
+      "loss": 0.7452,
+      "mean_token_accuracy": 0.7583088874816895,
+      "num_tokens": 1719296.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.7378115653991699,
+      "epoch": 1.2926829268292683,
+      "grad_norm": 0.18390269577503204,
+      "learning_rate": 3.0296851129864168e-05,
+      "loss": 0.7441,
+      "mean_token_accuracy": 0.754337728023529,
+      "num_tokens": 1735680.0,
+      "step": 106
+    },
+    {
+      "entropy": 0.74615877866745,
+      "epoch": 1.3048780487804879,
+      "grad_norm": 0.1807168424129486,
+      "learning_rate": 2.9392773148140408e-05,
+      "loss": 0.7393,
+      "mean_token_accuracy": 0.763318657875061,
+      "num_tokens": 1752064.0,
+      "step": 107
+    },
+    {
+      "entropy": 0.71029132604599,
+      "epoch": 1.3170731707317074,
+      "grad_norm": 0.17613796889781952,
+      "learning_rate": 2.8496739886173995e-05,
+      "loss": 0.7108,
+      "mean_token_accuracy": 0.7665566802024841,
+      "num_tokens": 1768448.0,
+      "step": 108
+    },
+    {
+      "entropy": 0.7654154300689697,
+      "epoch": 1.329268292682927,
+      "grad_norm": 0.1899922788143158,
+      "learning_rate": 2.7609101140496863e-05,
+      "loss": 0.7681,
+      "mean_token_accuracy": 0.7438294291496277,
+      "num_tokens": 1784832.0,
+      "step": 109
+    },
+    {
+      "entropy": 0.7549581527709961,
+      "epoch": 1.3414634146341464,
+      "grad_norm": 0.17567048966884613,
+      "learning_rate": 2.6730203430560947e-05,
+      "loss": 0.7499,
+      "mean_token_accuracy": 0.7536656856536865,
+      "num_tokens": 1801216.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.7551348209381104,
+      "epoch": 1.3536585365853657,
+      "grad_norm": 0.20108765363693237,
+      "learning_rate": 2.5860389863462765e-05,
+      "loss": 0.7614,
+      "mean_token_accuracy": 0.7620356678962708,
+      "num_tokens": 1817600.0,
+      "step": 111
+    },
+    {
+      "entropy": 0.7832897901535034,
+      "epoch": 1.3658536585365852,
+      "grad_norm": 0.17348282039165497,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7691,
+      "mean_token_accuracy": 0.7339931726455688,
+      "num_tokens": 1833984.0,
+      "step": 112
+    },
+    {
+      "entropy": 0.7925589084625244,
+      "epoch": 1.3780487804878048,
+      "grad_norm": 0.17639540135860443,
+      "learning_rate": 2.414936972211272e-05,
+      "loss": 0.7963,
+      "mean_token_accuracy": 0.7360092997550964,
+      "num_tokens": 1850368.0,
+      "step": 113
+    },
+    {
+      "entropy": 0.7057021260261536,
+      "epoch": 1.3902439024390243,
+      "grad_norm": 0.20399320125579834,
+      "learning_rate": 2.3308831101760486e-05,
+      "loss": 0.7058,
+      "mean_token_accuracy": 0.7655791640281677,
+      "num_tokens": 1866752.0,
+      "step": 114
+    },
+    {
+      "entropy": 0.7151185870170593,
+      "epoch": 1.4024390243902438,
+      "grad_norm": 0.20741577446460724,
+      "learning_rate": 2.247871227128709e-05,
+      "loss": 0.7257,
+      "mean_token_accuracy": 0.7732771039009094,
+      "num_tokens": 1883136.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.7585464715957642,
+      "epoch": 1.4146341463414633,
+      "grad_norm": 0.19852596521377563,
+      "learning_rate": 2.1659337295323118e-05,
+      "loss": 0.7607,
+      "mean_token_accuracy": 0.7528103590011597,
+      "num_tokens": 1899520.0,
+      "step": 116
+    },
+    {
+      "entropy": 0.7574771642684937,
+      "epoch": 1.4268292682926829,
+      "grad_norm": 0.1943759322166443,
+      "learning_rate": 2.0851026044276406e-05,
+      "loss": 0.7517,
+      "mean_token_accuracy": 0.758431077003479,
+      "num_tokens": 1915904.0,
+      "step": 117
+    },
+    {
+      "entropy": 0.7468112707138062,
+      "epoch": 1.4390243902439024,
+      "grad_norm": 0.18073536455631256,
+      "learning_rate": 2.005409406946e-05,
+      "loss": 0.7321,
+      "mean_token_accuracy": 0.7594085931777954,
+      "num_tokens": 1932288.0,
+      "step": 118
+    },
+    {
+      "entropy": 0.7520448565483093,
+      "epoch": 1.451219512195122,
+      "grad_norm": 0.19408191740512848,
+      "learning_rate": 1.9268852479906147e-05,
+      "loss": 0.749,
+      "mean_token_accuracy": 0.7603861093521118,
+      "num_tokens": 1948672.0,
+      "step": 119
+    },
+    {
+      "entropy": 0.7359144687652588,
+      "epoch": 1.4634146341463414,
+      "grad_norm": 0.17132484912872314,
+      "learning_rate": 1.849560782091445e-05,
+      "loss": 0.7331,
+      "mean_token_accuracy": 0.7672287225723267,
+      "num_tokens": 1965056.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.755273699760437,
+      "epoch": 1.475609756097561,
+      "grad_norm": 0.17852893471717834,
+      "learning_rate": 1.7734661954381754e-05,
+      "loss": 0.7459,
+      "mean_token_accuracy": 0.748900294303894,
+      "num_tokens": 1981440.0,
+      "step": 121
+    },
+    {
+      "entropy": 0.8156319856643677,
+      "epoch": 1.4878048780487805,
+      "grad_norm": 0.18380452692508698,
+      "learning_rate": 1.6986311940960147e-05,
+      "loss": 0.8108,
+      "mean_token_accuracy": 0.7369868159294128,
+      "num_tokens": 1997824.0,
+      "step": 122
+    },
+    {
+      "entropy": 0.7805770635604858,
+      "epoch": 1.5,
+      "grad_norm": 0.21706874668598175,
+      "learning_rate": 1.6250849924089484e-05,
+      "loss": 0.7883,
+      "mean_token_accuracy": 0.7556207180023193,
+      "num_tokens": 2014208.0,
+      "step": 123
+    },
+    {
+      "entropy": 0.7428463697433472,
+      "epoch": 1.5121951219512195,
+      "grad_norm": 0.18408456444740295,
+      "learning_rate": 1.552856301594942e-05,
+      "loss": 0.7535,
+      "mean_token_accuracy": 0.7553763389587402,
+      "num_tokens": 2030592.0,
+      "step": 124
+    },
+    {
+      "entropy": 0.6866140365600586,
+      "epoch": 1.524390243902439,
+      "grad_norm": 0.1875113993883133,
+      "learning_rate": 1.4819733185375534e-05,
+      "loss": 0.6852,
+      "mean_token_accuracy": 0.7776148319244385,
+      "num_tokens": 2046976.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.8088199496269226,
+      "epoch": 1.5365853658536586,
+      "grad_norm": 0.20887334644794464,
+      "learning_rate": 1.4124637147783432e-05,
+      "loss": 0.8099,
+      "mean_token_accuracy": 0.7490835785865784,
+      "num_tokens": 2063360.0,
+      "step": 126
+    },
+    {
+      "entropy": 0.7666107416152954,
+      "epoch": 1.548780487804878,
+      "grad_norm": 0.1800202578306198,
+      "learning_rate": 1.3443546257143624e-05,
+      "loss": 0.7785,
+      "mean_token_accuracy": 0.7430351972579956,
+      "num_tokens": 2079744.0,
+      "step": 127
+    },
+    {
+      "entropy": 0.7422869205474854,
+      "epoch": 1.5609756097560976,
+      "grad_norm": 0.19632630050182343,
+      "learning_rate": 1.277672640004936e-05,
+      "loss": 0.7295,
+      "mean_token_accuracy": 0.7572702765464783,
+      "num_tokens": 2096128.0,
+      "step": 128
+    },
+    {
+      "entropy": 0.7855641841888428,
+      "epoch": 1.5731707317073171,
+      "grad_norm": 0.17270389199256897,
+      "learning_rate": 1.2124437891918993e-05,
+      "loss": 0.7849,
+      "mean_token_accuracy": 0.7297776341438293,
+      "num_tokens": 2112512.0,
+      "step": 129
+    },
+    {
+      "entropy": 0.7153923511505127,
+      "epoch": 1.5853658536585367,
+      "grad_norm": 0.19369615614414215,
+      "learning_rate": 1.1486935375373126e-05,
+      "loss": 0.7137,
+      "mean_token_accuracy": 0.7647238373756409,
+      "num_tokens": 2128896.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.7304160594940186,
+      "epoch": 1.5975609756097562,
+      "grad_norm": 0.19279897212982178,
+      "learning_rate": 1.0864467720826343e-05,
+      "loss": 0.7283,
+      "mean_token_accuracy": 0.7572091817855835,
+      "num_tokens": 2145280.0,
+      "step": 131
+    },
+    {
+      "entropy": 0.770353376865387,
+      "epoch": 1.6097560975609757,
+      "grad_norm": 0.1961926519870758,
+      "learning_rate": 1.0257277929332332e-05,
+      "loss": 0.7793,
+      "mean_token_accuracy": 0.7517717480659485,
+      "num_tokens": 2161664.0,
+      "step": 132
+    },
+    {
+      "entropy": 0.7784348726272583,
+      "epoch": 1.6219512195121952,
+      "grad_norm": 0.1828148365020752,
+      "learning_rate": 9.66560303772035e-06,
+      "loss": 0.7804,
+      "mean_token_accuracy": 0.752443790435791,
+      "num_tokens": 2178048.0,
+      "step": 133
+    },
+    {
+      "entropy": 0.7361186742782593,
+      "epoch": 1.6341463414634148,
+      "grad_norm": 0.17069466412067413,
+      "learning_rate": 9.08967402605988e-06,
+      "loss": 0.7324,
+      "mean_token_accuracy": 0.7592864036560059,
+      "num_tokens": 2194432.0,
+      "step": 134
+    },
+    {
+      "entropy": 0.7611117959022522,
+      "epoch": 1.6463414634146343,
+      "grad_norm": 0.19935698807239532,
+      "learning_rate": 8.529715727489912e-06,
+      "loss": 0.7531,
+      "mean_token_accuracy": 0.7578201293945312,
+      "num_tokens": 2210816.0,
+      "step": 135
+    },
+    {
+      "entropy": 0.7541853785514832,
+      "epoch": 1.6585365853658538,
+      "grad_norm": 0.19178248941898346,
+      "learning_rate": 7.985946740447791e-06,
+      "loss": 0.7604,
+      "mean_token_accuracy": 0.7495723366737366,
+      "num_tokens": 2227200.0,
+      "step": 136
+    },
+    {
+      "entropy": 0.8022253513336182,
+      "epoch": 1.6707317073170733,
+      "grad_norm": 0.6668134927749634,
+      "learning_rate": 7.458579343331995e-06,
+      "loss": 0.795,
+      "mean_token_accuracy": 0.7453567981719971,
+      "num_tokens": 2243584.0,
+      "step": 137
+    },
+    {
+      "entropy": 0.7816216945648193,
+      "epoch": 1.6829268292682928,
+      "grad_norm": 0.1943075805902481,
+      "learning_rate": 6.947819411632223e-06,
+      "loss": 0.7777,
+      "mean_token_accuracy": 0.7460899353027344,
+      "num_tokens": 2259968.0,
+      "step": 138
+    },
+    {
+      "entropy": 0.7363425493240356,
+      "epoch": 1.6951219512195121,
+      "grad_norm": 0.17833693325519562,
+      "learning_rate": 6.45386633755894e-06,
+      "loss": 0.7375,
+      "mean_token_accuracy": 0.7467619776725769,
+      "num_tokens": 2276352.0,
+      "step": 139
+    },
+    {
+      "entropy": 0.69004887342453,
+      "epoch": 1.7073170731707317,
+      "grad_norm": 0.17878267168998718,
+      "learning_rate": 5.976912952204017e-06,
+      "loss": 0.6914,
+      "mean_token_accuracy": 0.7705889344215393,
+      "num_tokens": 2292736.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.7620655298233032,
+      "epoch": 1.7195121951219512,
+      "grad_norm": 0.18083210289478302,
+      "learning_rate": 5.51714545026264e-06,
+      "loss": 0.7633,
+      "mean_token_accuracy": 0.7528714537620544,
+      "num_tokens": 2309120.0,
+      "step": 141
+    },
+    {
+      "entropy": 0.7518504858016968,
+      "epoch": 1.7317073170731707,
+      "grad_norm": 0.17854557931423187,
+      "learning_rate": 5.074743317346009e-06,
+      "loss": 0.7422,
+      "mean_token_accuracy": 0.7525048851966858,
+      "num_tokens": 2325504.0,
+      "step": 142
+    },
+    {
+      "entropy": 0.7787827253341675,
+      "epoch": 1.7439024390243902,
+      "grad_norm": 0.18496236205101013,
+      "learning_rate": 4.649879259913137e-06,
+      "loss": 0.772,
+      "mean_token_accuracy": 0.7474951148033142,
+      "num_tokens": 2341888.0,
+      "step": 143
+    },
+    {
+      "entropy": 0.737861156463623,
+      "epoch": 1.7560975609756098,
+      "grad_norm": 0.21382860839366913,
+      "learning_rate": 4.242719137849077e-06,
+      "loss": 0.7329,
+      "mean_token_accuracy": 0.7592253088951111,
+      "num_tokens": 2358272.0,
+      "step": 144
+    },
+    {
+      "entropy": 0.7575418949127197,
+      "epoch": 1.7682926829268293,
+      "grad_norm": 0.18979310989379883,
+      "learning_rate": 3.853421899715992e-06,
+      "loss": 0.7546,
+      "mean_token_accuracy": 0.751099705696106,
+      "num_tokens": 2374656.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.745157778263092,
+      "epoch": 1.7804878048780488,
+      "grad_norm": 0.20623856782913208,
+      "learning_rate": 3.4821395207022766e-06,
+      "loss": 0.7424,
+      "mean_token_accuracy": 0.7672898173332214,
+      "num_tokens": 2391040.0,
+      "step": 146
+    },
+    {
+      "entropy": 0.7937027215957642,
+      "epoch": 1.7926829268292683,
+      "grad_norm": 0.1823415607213974,
+      "learning_rate": 3.1290169432939553e-06,
+      "loss": 0.788,
+      "mean_token_accuracy": 0.7462121248245239,
+      "num_tokens": 2407424.0,
+      "step": 147
+    },
+    {
+      "entropy": 0.7136151790618896,
+      "epoch": 1.8048780487804879,
+      "grad_norm": 0.19226711988449097,
+      "learning_rate": 2.794192020691544e-06,
+      "loss": 0.7127,
+      "mean_token_accuracy": 0.770405650138855,
+      "num_tokens": 2423808.0,
+      "step": 148
+    },
+    {
+      "entropy": 0.7484407424926758,
+      "epoch": 1.8170731707317072,
+      "grad_norm": 0.1926872283220291,
+      "learning_rate": 2.4777954629944477e-06,
+      "loss": 0.7495,
+      "mean_token_accuracy": 0.7630131840705872,
+      "num_tokens": 2440192.0,
+      "step": 149
+    },
+    {
+      "entropy": 0.7251145839691162,
+      "epoch": 1.8292682926829267,
+      "grad_norm": 0.18197566270828247,
+      "learning_rate": 2.179950786173879e-06,
+      "loss": 0.724,
+      "mean_token_accuracy": 0.7534213066101074,
+      "num_tokens": 2456576.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7693850994110107,
+      "epoch": 1.8414634146341462,
+      "grad_norm": 0.17157919704914093,
+      "learning_rate": 1.9007742638543102e-06,
+      "loss": 0.7586,
+      "mean_token_accuracy": 0.7457233667373657,
+      "num_tokens": 2472960.0,
+      "step": 151
+    },
+    {
+      "entropy": 0.767916738986969,
+      "epoch": 1.8536585365853657,
+      "grad_norm": 0.1874380260705948,
+      "learning_rate": 1.6403748819221466e-06,
+      "loss": 0.7599,
+      "mean_token_accuracy": 0.7484726309776306,
+      "num_tokens": 2489344.0,
+      "step": 152
+    },
+    {
+      "entropy": 0.7599184513092041,
+      "epoch": 1.8658536585365852,
+      "grad_norm": 0.18579497933387756,
+      "learning_rate": 1.3988542959794627e-06,
+      "loss": 0.7563,
+      "mean_token_accuracy": 0.7541544437408447,
+      "num_tokens": 2505728.0,
+      "step": 153
+    },
+    {
+      "entropy": 0.767235279083252,
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.176035076379776,
+      "learning_rate": 1.1763067916593262e-06,
+      "loss": 0.76,
+      "mean_token_accuracy": 0.7493279576301575,
+      "num_tokens": 2522112.0,
+      "step": 154
+    },
+    {
+      "entropy": 0.7524126768112183,
+      "epoch": 1.8902439024390243,
+      "grad_norm": 0.18819116055965424,
+      "learning_rate": 9.728192478182574e-07,
+      "loss": 0.7595,
+      "mean_token_accuracy": 0.7498778104782104,
+      "num_tokens": 2538496.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.7433879971504211,
+      "epoch": 1.9024390243902438,
+      "grad_norm": 0.18667981028556824,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 0.7379,
+      "mean_token_accuracy": 0.7423020601272583,
+      "num_tokens": 2554880.0,
+      "step": 156
+    },
+    {
+      "entropy": 0.759426474571228,
+      "epoch": 1.9146341463414633,
+      "grad_norm": 0.19489333033561707,
+      "learning_rate": 6.233343225249933e-07,
+      "loss": 0.7736,
+      "mean_token_accuracy": 0.7575146555900574,
+      "num_tokens": 2571264.0,
+      "step": 157
+    },
+    {
+      "entropy": 0.7506579756736755,
+      "epoch": 1.9268292682926829,
+      "grad_norm": 0.1899450123310089,
+      "learning_rate": 4.774733741942206e-07,
+      "loss": 0.7432,
+      "mean_token_accuracy": 0.7515884637832642,
+      "num_tokens": 2587648.0,
+      "step": 158
+    },
+    {
+      "entropy": 0.7318516969680786,
+      "epoch": 1.9390243902439024,
+      "grad_norm": 0.18016324937343597,
+      "learning_rate": 3.5094519932415417e-07,
+      "loss": 0.7217,
+      "mean_token_accuracy": 0.7611192464828491,
+      "num_tokens": 2604032.0,
+      "step": 159
+    },
+    {
+      "entropy": 0.7873852252960205,
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.18666067719459534,
+      "learning_rate": 2.437991924167937e-07,
+      "loss": 0.7779,
+      "mean_token_accuracy": 0.7483504414558411,
+      "num_tokens": 2620416.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.732664167881012,
+      "epoch": 1.9634146341463414,
+      "grad_norm": 0.1867821365594864,
+      "learning_rate": 1.560771814970885e-07,
+      "loss": 0.7278,
+      "mean_token_accuracy": 0.7568426132202148,
+      "num_tokens": 2636800.0,
+      "step": 161
+    },
+    {
+      "entropy": 0.7545714974403381,
+      "epoch": 1.975609756097561,
+      "grad_norm": 0.20846645534038544,
+      "learning_rate": 8.781341178393244e-08,
+      "loss": 0.7489,
+      "mean_token_accuracy": 0.7635630369186401,
+      "num_tokens": 2653184.0,
+      "step": 162
+    },
+    {
+      "entropy": 0.7096419334411621,
+      "epoch": 1.9878048780487805,
+      "grad_norm": 0.30432114005088806,
+      "learning_rate": 3.9034532321408076e-08,
+      "loss": 0.712,
+      "mean_token_accuracy": 0.7624022364616394,
+      "num_tokens": 2669568.0,
+      "step": 163
+    },
+    {
+      "entropy": 0.7195896506309509,
+      "epoch": 2.0,
+      "grad_norm": 0.19605056941509247,
+      "learning_rate": 9.75958557545842e-09,
+      "loss": 0.7196,
+      "mean_token_accuracy": 0.7672206163406372,
+      "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": 5.959851031343923e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

r32_checkpoint-164/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85c0f6db433d3f1f2fbd7661a576ccda7de2a46bb284701f094aa6132a715db
+size 6225