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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen--Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/cache/models/Qwen--Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c39be7d6b51045c4252d2347a09b3cff0326159fa140090629c686434cc349
+size 1291899160

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

loss.txt

@@ -0,0 +1 @@
+1000,no_eval

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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
+}

trainer_state.json

@@ -0,0 +1,1834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7640878701050621,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0038204393505253103,
+      "grad_norm": 15.201638221740723,
+      "learning_rate": 4.917142857142858e-06,
+      "loss": 0.9785,
+      "mean_token_accuracy": 0.8454411208629609,
+      "num_tokens": 190362.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.007640878701050621,
+      "grad_norm": 3.6675734519958496,
+      "learning_rate": 1.106357142857143e-05,
+      "loss": 0.4654,
+      "mean_token_accuracy": 0.8957700878381729,
+      "num_tokens": 379171.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "grad_norm": 2.4532852172851562,
+      "learning_rate": 1.7210000000000003e-05,
+      "loss": 0.2014,
+      "mean_token_accuracy": 0.9451590657234192,
+      "num_tokens": 573150.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.015281757402101241,
+      "grad_norm": 1.0862683057785034,
+      "learning_rate": 2.3356428571428574e-05,
+      "loss": 0.0905,
+      "mean_token_accuracy": 0.9684270918369293,
+      "num_tokens": 770760.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.019102196752626553,
+      "grad_norm": 1.4964179992675781,
+      "learning_rate": 2.950285714285715e-05,
+      "loss": 0.0957,
+      "mean_token_accuracy": 0.9640194743871688,
+      "num_tokens": 960649.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.022922636103151862,
+      "grad_norm": 0.7489196062088013,
+      "learning_rate": 3.5649285714285724e-05,
+      "loss": 0.0957,
+      "mean_token_accuracy": 0.9661861270666122,
+      "num_tokens": 1149643.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.026743075453677174,
+      "grad_norm": 0.4919213354587555,
+      "learning_rate": 4.179571428571429e-05,
+      "loss": 0.0811,
+      "mean_token_accuracy": 0.968377611041069,
+      "num_tokens": 1341445.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.030563514804202482,
+      "grad_norm": 0.8133232593536377,
+      "learning_rate": 4.3024809062069924e-05,
+      "loss": 0.0638,
+      "mean_token_accuracy": 0.9746772289276123,
+      "num_tokens": 1533608.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.034383954154727794,
+      "grad_norm": 0.5709226131439209,
+      "learning_rate": 4.302403338447426e-05,
+      "loss": 0.0732,
+      "mean_token_accuracy": 0.9714215457439422,
+      "num_tokens": 1726410.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.038204393505253106,
+      "grad_norm": 0.6107519268989563,
+      "learning_rate": 4.3022661062256383e-05,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9731226474046707,
+      "num_tokens": 1915533.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.04202483285577841,
+      "grad_norm": 0.6385495066642761,
+      "learning_rate": 4.3020692146167425e-05,
+      "loss": 0.1017,
+      "mean_token_accuracy": 0.9618591457605362,
+      "num_tokens": 2101018.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.045845272206303724,
+      "grad_norm": 0.4049123525619507,
+      "learning_rate": 4.30181267090217e-05,
+      "loss": 0.0956,
+      "mean_token_accuracy": 0.9634065091609955,
+      "num_tokens": 2293929.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.049665711556829036,
+      "grad_norm": 0.4711824953556061,
+      "learning_rate": 4.301496484569403e-05,
+      "loss": 0.0911,
+      "mean_token_accuracy": 0.9642636924982071,
+      "num_tokens": 2483903.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.05348615090735435,
+      "grad_norm": 0.2694167494773865,
+      "learning_rate": 4.3011206673116235e-05,
+      "loss": 0.0763,
+      "mean_token_accuracy": 0.9684840172529221,
+      "num_tokens": 2676082.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "grad_norm": 0.21997177600860596,
+      "learning_rate": 4.300685233027281e-05,
+      "loss": 0.0692,
+      "mean_token_accuracy": 0.9735830575227737,
+      "num_tokens": 2865817.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.061127029608404965,
+      "grad_norm": 0.48388707637786865,
+      "learning_rate": 4.300190197819575e-05,
+      "loss": 0.0666,
+      "mean_token_accuracy": 0.9729795724153518,
+      "num_tokens": 3059731.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.06494746895893028,
+      "grad_norm": 0.3043380379676819,
+      "learning_rate": 4.299635579995865e-05,
+      "loss": 0.0896,
+      "mean_token_accuracy": 0.9654609531164169,
+      "num_tokens": 3248547.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.06876790830945559,
+      "grad_norm": 0.34322434663772583,
+      "learning_rate": 4.299021400066991e-05,
+      "loss": 0.0671,
+      "mean_token_accuracy": 0.9724334269762039,
+      "num_tokens": 3442361.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.0725883476599809,
+      "grad_norm": 0.21328647434711456,
+      "learning_rate": 4.2983476807465125e-05,
+      "loss": 0.0684,
+      "mean_token_accuracy": 0.9704120546579361,
+      "num_tokens": 3632136.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.07640878701050621,
+      "grad_norm": 0.21835950016975403,
+      "learning_rate": 4.2976144469498725e-05,
+      "loss": 0.066,
+      "mean_token_accuracy": 0.9741405993700027,
+      "num_tokens": 3830824.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.08022922636103152,
+      "grad_norm": 0.28788259625434875,
+      "learning_rate": 4.296821725793474e-05,
+      "loss": 0.0665,
+      "mean_token_accuracy": 0.9729400396347045,
+      "num_tokens": 4021165.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.08404966571155682,
+      "grad_norm": 0.20847582817077637,
+      "learning_rate": 4.295969546593677e-05,
+      "loss": 0.048,
+      "mean_token_accuracy": 0.9813327103853225,
+      "num_tokens": 4217037.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.08787010506208214,
+      "grad_norm": 0.5263293981552124,
+      "learning_rate": 4.2950579408657155e-05,
+      "loss": 0.0515,
+      "mean_token_accuracy": 0.9777360051870346,
+      "num_tokens": 4416323.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 0.3691597878932953,
+      "learning_rate": 4.2940869423225314e-05,
+      "loss": 0.0702,
+      "mean_token_accuracy": 0.9730219930410385,
+      "num_tokens": 4608848.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "grad_norm": 0.418745756149292,
+      "learning_rate": 4.293056586873527e-05,
+      "loss": 0.0795,
+      "mean_token_accuracy": 0.9684157103300095,
+      "num_tokens": 4799085.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.09933142311365807,
+      "grad_norm": 0.1828339397907257,
+      "learning_rate": 4.291966912623238e-05,
+      "loss": 0.0813,
+      "mean_token_accuracy": 0.9673069924116134,
+      "num_tokens": 4989425.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 0.1943412721157074,
+      "learning_rate": 4.290817959869925e-05,
+      "loss": 0.0486,
+      "mean_token_accuracy": 0.9804543942213059,
+      "num_tokens": 5181996.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.1069723018147087,
+      "grad_norm": 0.27603718638420105,
+      "learning_rate": 4.289609771104081e-05,
+      "loss": 0.0694,
+      "mean_token_accuracy": 0.9706949889659882,
+      "num_tokens": 5373158.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.11079274116523401,
+      "grad_norm": 0.2905213534832001,
+      "learning_rate": 4.2883423910068604e-05,
+      "loss": 0.0633,
+      "mean_token_accuracy": 0.9741755068302155,
+      "num_tokens": 5566234.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.19648431241512299,
+      "learning_rate": 4.2870158664484296e-05,
+      "loss": 0.0718,
+      "mean_token_accuracy": 0.9699918508529664,
+      "num_tokens": 5754918.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.11843361986628462,
+      "grad_norm": 0.34930410981178284,
+      "learning_rate": 4.285630246486231e-05,
+      "loss": 0.0704,
+      "mean_token_accuracy": 0.9721553355455399,
+      "num_tokens": 5944190.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.12225405921680993,
+      "grad_norm": 0.3542683720588684,
+      "learning_rate": 4.284185582363168e-05,
+      "loss": 0.0576,
+      "mean_token_accuracy": 0.9750690400600434,
+      "num_tokens": 6139109.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.12607449856733524,
+      "grad_norm": 0.27087774872779846,
+      "learning_rate": 4.282681927505712e-05,
+      "loss": 0.0486,
+      "mean_token_accuracy": 0.9792540937662124,
+      "num_tokens": 6330632.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.12989493791786055,
+      "grad_norm": 0.15475647151470184,
+      "learning_rate": 4.281119337521925e-05,
+      "loss": 0.0694,
+      "mean_token_accuracy": 0.9716268599033355,
+      "num_tokens": 6519770.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.13371537726838587,
+      "grad_norm": 0.19823479652404785,
+      "learning_rate": 4.279497870199406e-05,
+      "loss": 0.0555,
+      "mean_token_accuracy": 0.9756160885095596,
+      "num_tokens": 6711264.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.13753581661891118,
+      "grad_norm": 0.2758966088294983,
+      "learning_rate": 4.277817585503149e-05,
+      "loss": 0.0438,
+      "mean_token_accuracy": 0.9821220278739929,
+      "num_tokens": 6907145.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.1413562559694365,
+      "grad_norm": 0.3245423138141632,
+      "learning_rate": 4.27607854557333e-05,
+      "loss": 0.05,
+      "mean_token_accuracy": 0.9807667016983033,
+      "num_tokens": 7104423.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.1451766953199618,
+      "grad_norm": 0.22670352458953857,
+      "learning_rate": 4.2742808147230056e-05,
+      "loss": 0.0586,
+      "mean_token_accuracy": 0.9768105119466781,
+      "num_tokens": 7294454.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.1489971346704871,
+      "grad_norm": 0.3042696714401245,
+      "learning_rate": 4.2724244594357395e-05,
+      "loss": 0.0658,
+      "mean_token_accuracy": 0.9748756378889084,
+      "num_tokens": 7482853.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.15281757402101243,
+      "grad_norm": 0.2198762446641922,
+      "learning_rate": 4.270509548363136e-05,
+      "loss": 0.0502,
+      "mean_token_accuracy": 0.9786651730537415,
+      "num_tokens": 7679690.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.15663801337153774,
+      "grad_norm": 0.24992121756076813,
+      "learning_rate": 4.268536152322307e-05,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9685411423444747,
+      "num_tokens": 7869078.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.16045845272206305,
+      "grad_norm": 0.2517041265964508,
+      "learning_rate": 4.266504344293253e-05,
+      "loss": 0.0523,
+      "mean_token_accuracy": 0.9794965207576751,
+      "num_tokens": 8062246.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.16427889207258833,
+      "grad_norm": 0.42241668701171875,
+      "learning_rate": 4.264414199416162e-05,
+      "loss": 0.0641,
+      "mean_token_accuracy": 0.9746231615543366,
+      "num_tokens": 8255102.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.16809933142311365,
+      "grad_norm": 0.3903146982192993,
+      "learning_rate": 4.26226579498863e-05,
+      "loss": 0.0676,
+      "mean_token_accuracy": 0.9708555549383163,
+      "num_tokens": 8448152.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.17191977077363896,
+      "grad_norm": 0.18771636486053467,
+      "learning_rate": 4.260059210462805e-05,
+      "loss": 0.0467,
+      "mean_token_accuracy": 0.9809397220611572,
+      "num_tokens": 8641044.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.17574021012416427,
+      "grad_norm": 0.24989716708660126,
+      "learning_rate": 4.257794527442448e-05,
+      "loss": 0.0574,
+      "mean_token_accuracy": 0.9770851105451583,
+      "num_tokens": 8838921.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.17956064947468958,
+      "grad_norm": 0.0954967513680458,
+      "learning_rate": 4.2554718296799135e-05,
+      "loss": 0.0505,
+      "mean_token_accuracy": 0.979452383518219,
+      "num_tokens": 9031067.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.1833810888252149,
+      "grad_norm": 0.23748601973056793,
+      "learning_rate": 4.2530912030730534e-05,
+      "loss": 0.0615,
+      "mean_token_accuracy": 0.9752046942710877,
+      "num_tokens": 9217893.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.1872015281757402,
+      "grad_norm": 0.23530811071395874,
+      "learning_rate": 4.2506527356620404e-05,
+      "loss": 0.0706,
+      "mean_token_accuracy": 0.9701990783214569,
+      "num_tokens": 9412173.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.19102196752626552,
+      "grad_norm": 0.2745545506477356,
+      "learning_rate": 4.248156517626113e-05,
+      "loss": 0.0451,
+      "mean_token_accuracy": 0.9807097434997558,
+      "num_tokens": 9608252.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.19484240687679083,
+      "grad_norm": 0.41043621301651,
+      "learning_rate": 4.245602641280239e-05,
+      "loss": 0.0497,
+      "mean_token_accuracy": 0.9810603886842728,
+      "num_tokens": 9803865.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.19866284622731614,
+      "grad_norm": 0.2759955823421478,
+      "learning_rate": 4.2429912010716984e-05,
+      "loss": 0.0582,
+      "mean_token_accuracy": 0.9766894429922104,
+      "num_tokens": 9995013.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.20248328557784145,
+      "grad_norm": 0.3307853043079376,
+      "learning_rate": 4.2403222935766006e-05,
+      "loss": 0.059,
+      "mean_token_accuracy": 0.9772057175636292,
+      "num_tokens": 10188340.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.20630372492836677,
+      "grad_norm": 0.20665952563285828,
+      "learning_rate": 4.237596017496301e-05,
+      "loss": 0.0608,
+      "mean_token_accuracy": 0.9768591314554215,
+      "num_tokens": 10381615.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.21012416427889208,
+      "grad_norm": 0.1744696944952011,
+      "learning_rate": 4.2348124736537575e-05,
+      "loss": 0.0506,
+      "mean_token_accuracy": 0.9770352751016617,
+      "num_tokens": 10575970.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.2139446036294174,
+      "grad_norm": 0.33633992075920105,
+      "learning_rate": 4.231971764989802e-05,
+      "loss": 0.0608,
+      "mean_token_accuracy": 0.9772638320922852,
+      "num_tokens": 10768443.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.2177650429799427,
+      "grad_norm": 0.2037603110074997,
+      "learning_rate": 4.229073996559331e-05,
+      "loss": 0.053,
+      "mean_token_accuracy": 0.9792750954627991,
+      "num_tokens": 10963013.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.22158548233046801,
+      "grad_norm": 0.2864745855331421,
+      "learning_rate": 4.226119275527421e-05,
+      "loss": 0.0621,
+      "mean_token_accuracy": 0.9746448636054993,
+      "num_tokens": 11151539.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.22540592168099333,
+      "grad_norm": 0.3466282784938812,
+      "learning_rate": 4.2231077111653674e-05,
+      "loss": 0.0572,
+      "mean_token_accuracy": 0.9750597178936005,
+      "num_tokens": 11345874.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.22922636103151864,
+      "grad_norm": 0.20305858552455902,
+      "learning_rate": 4.220039414846639e-05,
+      "loss": 0.0489,
+      "mean_token_accuracy": 0.9798380732536316,
+      "num_tokens": 11540262.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.23304680038204392,
+      "grad_norm": 0.30013033747673035,
+      "learning_rate": 4.2169145000427635e-05,
+      "loss": 0.0643,
+      "mean_token_accuracy": 0.9761583149433136,
+      "num_tokens": 11727141.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.23686723973256923,
+      "grad_norm": 0.2139650285243988,
+      "learning_rate": 4.2137330823191304e-05,
+      "loss": 0.0469,
+      "mean_token_accuracy": 0.9818692028522491,
+      "num_tokens": 11923804.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.24068767908309455,
+      "grad_norm": 0.21393324434757233,
+      "learning_rate": 4.210495279330716e-05,
+      "loss": 0.0794,
+      "mean_token_accuracy": 0.9690388560295105,
+      "num_tokens": 12114269.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.24450811843361986,
+      "grad_norm": 0.27864113450050354,
+      "learning_rate": 4.2072012108177314e-05,
+      "loss": 0.077,
+      "mean_token_accuracy": 0.9711580067873001,
+      "num_tokens": 12301613.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.24832855778414517,
+      "grad_norm": 0.26272112131118774,
+      "learning_rate": 4.2038509986011984e-05,
+      "loss": 0.0624,
+      "mean_token_accuracy": 0.9762404501438141,
+      "num_tokens": 12496573.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.2521489971346705,
+      "grad_norm": 0.15598540008068085,
+      "learning_rate": 4.200444766578437e-05,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9755767703056335,
+      "num_tokens": 12690313.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.2559694364851958,
+      "grad_norm": 0.42017388343811035,
+      "learning_rate": 4.1969826407184916e-05,
+      "loss": 0.0728,
+      "mean_token_accuracy": 0.9695112437009812,
+      "num_tokens": 12878504.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.2597898758357211,
+      "grad_norm": 0.23844686150550842,
+      "learning_rate": 4.1934647490574675e-05,
+      "loss": 0.0556,
+      "mean_token_accuracy": 0.9785339087247849,
+      "num_tokens": 13071352.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.2636103151862464,
+      "grad_norm": 0.22254465520381927,
+      "learning_rate": 4.189891221693798e-05,
+      "loss": 0.063,
+      "mean_token_accuracy": 0.9737227350473404,
+      "num_tokens": 13264834.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.26743075453677173,
+      "grad_norm": 0.15139898657798767,
+      "learning_rate": 4.18626219078343e-05,
+      "loss": 0.0461,
+      "mean_token_accuracy": 0.9813186198472976,
+      "num_tokens": 13455272.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.271251193887297,
+      "grad_norm": 0.40693023800849915,
+      "learning_rate": 4.182577790534941e-05,
+      "loss": 0.0602,
+      "mean_token_accuracy": 0.976009014248848,
+      "num_tokens": 13647607.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.27507163323782235,
+      "grad_norm": 0.2027602195739746,
+      "learning_rate": 4.178838157204572e-05,
+      "loss": 0.0461,
+      "mean_token_accuracy": 0.9815563976764679,
+      "num_tokens": 13837724.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.27889207258834764,
+      "grad_norm": 0.14095771312713623,
+      "learning_rate": 4.1750434290911926e-05,
+      "loss": 0.0657,
+      "mean_token_accuracy": 0.9724122434854507,
+      "num_tokens": 14028092.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.282712511938873,
+      "grad_norm": 0.27064386010169983,
+      "learning_rate": 4.171193746531181e-05,
+      "loss": 0.0514,
+      "mean_token_accuracy": 0.9779324233531952,
+      "num_tokens": 14226064.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "grad_norm": 0.1595909297466278,
+      "learning_rate": 4.167289251893238e-05,
+      "loss": 0.068,
+      "mean_token_accuracy": 0.9747934162616729,
+      "num_tokens": 14410718.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.2903533906399236,
+      "grad_norm": 0.1524188369512558,
+      "learning_rate": 4.163330089573122e-05,
+      "loss": 0.0576,
+      "mean_token_accuracy": 0.97566257417202,
+      "num_tokens": 14599342.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.2941738299904489,
+      "grad_norm": 0.14495456218719482,
+      "learning_rate": 4.159316405988308e-05,
+      "loss": 0.0527,
+      "mean_token_accuracy": 0.979561498761177,
+      "num_tokens": 14793575.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.2979942693409742,
+      "grad_norm": 0.5709442496299744,
+      "learning_rate": 4.15524834957257e-05,
+      "loss": 0.083,
+      "mean_token_accuracy": 0.9667803287506104,
+      "num_tokens": 14984217.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.3018147086914995,
+      "grad_norm": 0.18003742396831512,
+      "learning_rate": 4.1511260707704986e-05,
+      "loss": 0.0663,
+      "mean_token_accuracy": 0.9747018158435822,
+      "num_tokens": 15179803.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.30563514804202485,
+      "grad_norm": 0.21097174286842346,
+      "learning_rate": 4.146949722031929e-05,
+      "loss": 0.0507,
+      "mean_token_accuracy": 0.9834589123725891,
+      "num_tokens": 15378939.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.30945558739255014,
+      "grad_norm": 0.2961026728153229,
+      "learning_rate": 4.14271945780631e-05,
+      "loss": 0.0557,
+      "mean_token_accuracy": 0.9774508029222488,
+      "num_tokens": 15572668.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.3132760267430755,
+      "grad_norm": 0.27165207266807556,
+      "learning_rate": 4.138435434536988e-05,
+      "loss": 0.0715,
+      "mean_token_accuracy": 0.9714416980743408,
+      "num_tokens": 15766237.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.31709646609360076,
+      "grad_norm": 0.13058046996593475,
+      "learning_rate": 4.1340978106554227e-05,
+      "loss": 0.0475,
+      "mean_token_accuracy": 0.9799029618501663,
+      "num_tokens": 15964239.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.3209169054441261,
+      "grad_norm": 0.15920332074165344,
+      "learning_rate": 4.129706746575329e-05,
+      "loss": 0.0493,
+      "mean_token_accuracy": 0.9792453438043595,
+      "num_tokens": 16160992.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.3247373447946514,
+      "grad_norm": 0.19430503249168396,
+      "learning_rate": 4.125262404686742e-05,
+      "loss": 0.0625,
+      "mean_token_accuracy": 0.9731769442558289,
+      "num_tokens": 16352371.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.32855778414517667,
+      "grad_norm": 0.11031383275985718,
+      "learning_rate": 4.1207649493500154e-05,
+      "loss": 0.0509,
+      "mean_token_accuracy": 0.9789532154798508,
+      "num_tokens": 16547451.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.332378223495702,
+      "grad_norm": 0.21514596045017242,
+      "learning_rate": 4.116214546889738e-05,
+      "loss": 0.0547,
+      "mean_token_accuracy": 0.9742819428443908,
+      "num_tokens": 16739926.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.3361986628462273,
+      "grad_norm": 0.2110457569360733,
+      "learning_rate": 4.111611365588588e-05,
+      "loss": 0.0577,
+      "mean_token_accuracy": 0.9753052473068238,
+      "num_tokens": 16931998.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.34001910219675263,
+      "grad_norm": 0.5559974312782288,
+      "learning_rate": 4.106955575681106e-05,
+      "loss": 0.059,
+      "mean_token_accuracy": 0.9771996021270752,
+      "num_tokens": 17125263.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.3438395415472779,
+      "grad_norm": 0.15509715676307678,
+      "learning_rate": 4.102247349347401e-05,
+      "loss": 0.0352,
+      "mean_token_accuracy": 0.9866044849157334,
+      "num_tokens": 17323951.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.34765998089780326,
+      "grad_norm": 0.220753014087677,
+      "learning_rate": 4.097486860706782e-05,
+      "loss": 0.0497,
+      "mean_token_accuracy": 0.9807918220758438,
+      "num_tokens": 17515406.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.35148042024832854,
+      "grad_norm": 0.3094851076602936,
+      "learning_rate": 4.092674285811319e-05,
+      "loss": 0.0494,
+      "mean_token_accuracy": 0.9795226901769638,
+      "num_tokens": 17708032.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.3553008595988539,
+      "grad_norm": 0.26296278834342957,
+      "learning_rate": 4.087809802639333e-05,
+      "loss": 0.0642,
+      "mean_token_accuracy": 0.9748444706201553,
+      "num_tokens": 17896416.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.35912129894937916,
+      "grad_norm": 0.2660556137561798,
+      "learning_rate": 4.082893591088813e-05,
+      "loss": 0.0763,
+      "mean_token_accuracy": 0.9685628533363342,
+      "num_tokens": 18084617.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.3629417382999045,
+      "grad_norm": 0.11729703098535538,
+      "learning_rate": 4.077925832970764e-05,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9762477964162827,
+      "num_tokens": 18273414.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.3667621776504298,
+      "grad_norm": 0.8921375274658203,
+      "learning_rate": 4.0729067120024805e-05,
+      "loss": 0.0422,
+      "mean_token_accuracy": 0.9814232975244522,
+      "num_tokens": 18471101.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.37058261700095513,
+      "grad_norm": 0.14002133905887604,
+      "learning_rate": 4.0678364138007574e-05,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.980798265337944,
+      "num_tokens": 18665070.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.3744030563514804,
+      "grad_norm": 0.164137601852417,
+      "learning_rate": 4.062715125875021e-05,
+      "loss": 0.0532,
+      "mean_token_accuracy": 0.978941360116005,
+      "num_tokens": 18856032.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.37822349570200575,
+      "grad_norm": 0.3199448585510254,
+      "learning_rate": 4.0575430376203964e-05,
+      "loss": 0.0546,
+      "mean_token_accuracy": 0.9780995190143585,
+      "num_tokens": 19055791.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.38204393505253104,
+      "grad_norm": 0.21233463287353516,
+      "learning_rate": 4.0523203403107025e-05,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9815221428871155,
+      "num_tokens": 19253892.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.3858643744030564,
+      "grad_norm": 0.28013288974761963,
+      "learning_rate": 4.0470472270913807e-05,
+      "loss": 0.0532,
+      "mean_token_accuracy": 0.9790537118911743,
+      "num_tokens": 19449346.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.38968481375358166,
+      "grad_norm": 0.29040253162384033,
+      "learning_rate": 4.041723892972348e-05,
+      "loss": 0.0572,
+      "mean_token_accuracy": 0.9756559371948242,
+      "num_tokens": 19640989.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.39350525310410694,
+      "grad_norm": 0.13456866145133972,
+      "learning_rate": 4.036350534820788e-05,
+      "loss": 0.0447,
+      "mean_token_accuracy": 0.9812914997339248,
+      "num_tokens": 19834960.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.3973256924546323,
+      "grad_norm": 0.15088418126106262,
+      "learning_rate": 4.0309273513538705e-05,
+      "loss": 0.0543,
+      "mean_token_accuracy": 0.97936552464962,
+      "num_tokens": 20025923.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.40114613180515757,
+      "grad_norm": 0.1476389616727829,
+      "learning_rate": 4.025454543131401e-05,
+      "loss": 0.0567,
+      "mean_token_accuracy": 0.9769350290298462,
+      "num_tokens": 20215104.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.4049665711556829,
+      "grad_norm": 0.24653594195842743,
+      "learning_rate": 4.019932312548405e-05,
+      "loss": 0.0609,
+      "mean_token_accuracy": 0.9765990972518921,
+      "num_tokens": 20402833.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.4087870105062082,
+      "grad_norm": 0.17821958661079407,
+      "learning_rate": 4.0143608638276414e-05,
+      "loss": 0.0483,
+      "mean_token_accuracy": 0.9801214545965194,
+      "num_tokens": 20599454.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.41260744985673353,
+      "grad_norm": 0.08458976447582245,
+      "learning_rate": 4.008740403012052e-05,
+      "loss": 0.0445,
+      "mean_token_accuracy": 0.9814120203256607,
+      "num_tokens": 20793274.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.4164278892072588,
+      "grad_norm": 0.16333456337451935,
+      "learning_rate": 4.0030711379571394e-05,
+      "loss": 0.0558,
+      "mean_token_accuracy": 0.9752419918775559,
+      "num_tokens": 20983430.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.42024832855778416,
+      "grad_norm": 0.32965436577796936,
+      "learning_rate": 3.997353278323283e-05,
+      "loss": 0.0543,
+      "mean_token_accuracy": 0.9790427118539811,
+      "num_tokens": 21174872.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.42406876790830944,
+      "grad_norm": 0.23592133820056915,
+      "learning_rate": 3.9915870355679814e-05,
+      "loss": 0.0518,
+      "mean_token_accuracy": 0.9799334049224854,
+      "num_tokens": 21363955.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.4278892072588348,
+      "grad_norm": 0.2007017284631729,
+      "learning_rate": 3.985772622938037e-05,
+      "loss": 0.0693,
+      "mean_token_accuracy": 0.971209266781807,
+      "num_tokens": 21554937.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.43170964660936006,
+      "grad_norm": 0.22252358496189117,
+      "learning_rate": 3.979910255461665e-05,
+      "loss": 0.0497,
+      "mean_token_accuracy": 0.9803436905145645,
+      "num_tokens": 21742640.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.4355300859598854,
+      "grad_norm": 0.28110989928245544,
+      "learning_rate": 3.9740001499405454e-05,
+      "loss": 0.043,
+      "mean_token_accuracy": 0.983144435286522,
+      "num_tokens": 21936022.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.4393505253104107,
+      "grad_norm": 0.5248743295669556,
+      "learning_rate": 3.968042524941802e-05,
+      "loss": 0.0556,
+      "mean_token_accuracy": 0.976366838812828,
+      "num_tokens": 22131602.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.44317096466093603,
+      "grad_norm": 0.15875911712646484,
+      "learning_rate": 3.9620376007899225e-05,
+      "loss": 0.054,
+      "mean_token_accuracy": 0.9768787533044815,
+      "num_tokens": 22325559.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.4469914040114613,
+      "grad_norm": 0.1441507190465927,
+      "learning_rate": 3.955985599558606e-05,
+      "loss": 0.0498,
+      "mean_token_accuracy": 0.9814888626337052,
+      "num_tokens": 22517905.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.45081184336198665,
+      "grad_norm": 0.1760101318359375,
+      "learning_rate": 3.949886745062554e-05,
+      "loss": 0.0576,
+      "mean_token_accuracy": 0.9776659190654755,
+      "num_tokens": 22708766.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.45463228271251194,
+      "grad_norm": 0.297606498003006,
+      "learning_rate": 3.943741262849194e-05,
+      "loss": 0.0609,
+      "mean_token_accuracy": 0.975119811296463,
+      "num_tokens": 22897064.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.4584527220630373,
+      "grad_norm": 0.26312318444252014,
+      "learning_rate": 3.937549380190334e-05,
+      "loss": 0.0578,
+      "mean_token_accuracy": 0.9778578579425812,
+      "num_tokens": 23088878.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.46227316141356256,
+      "grad_norm": 0.2967909276485443,
+      "learning_rate": 3.931311326073763e-05,
+      "loss": 0.0557,
+      "mean_token_accuracy": 0.9773400127887726,
+      "num_tokens": 23288227.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.46609360076408785,
+      "grad_norm": 0.15036430954933167,
+      "learning_rate": 3.9250273311947766e-05,
+      "loss": 0.0516,
+      "mean_token_accuracy": 0.9784754246473313,
+      "num_tokens": 23483144.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.4699140401146132,
+      "grad_norm": 0.27099692821502686,
+      "learning_rate": 3.918697627947652e-05,
+      "loss": 0.0385,
+      "mean_token_accuracy": 0.9838829040527344,
+      "num_tokens": 23678857.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.47373447946513847,
+      "grad_norm": 0.15760372579097748,
+      "learning_rate": 3.912322450417046e-05,
+      "loss": 0.0525,
+      "mean_token_accuracy": 0.9788579672574997,
+      "num_tokens": 23870926.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.4775549188156638,
+      "grad_norm": 0.12999805808067322,
+      "learning_rate": 3.905902034369347e-05,
+      "loss": 0.0508,
+      "mean_token_accuracy": 0.9793928295373917,
+      "num_tokens": 24064759.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.4813753581661891,
+      "grad_norm": 0.16970236599445343,
+      "learning_rate": 3.899436617243947e-05,
+      "loss": 0.0536,
+      "mean_token_accuracy": 0.977686858177185,
+      "num_tokens": 24255210.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.48519579751671443,
+      "grad_norm": 0.1461954116821289,
+      "learning_rate": 3.892926438144468e-05,
+      "loss": 0.052,
+      "mean_token_accuracy": 0.9788082480430603,
+      "num_tokens": 24450330.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.4890162368672397,
+      "grad_norm": 0.0894608348608017,
+      "learning_rate": 3.886371737829914e-05,
+      "loss": 0.0493,
+      "mean_token_accuracy": 0.9786105424165725,
+      "num_tokens": 24644117.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.49283667621776506,
+      "grad_norm": 0.11515697836875916,
+      "learning_rate": 3.8797727587057716e-05,
+      "loss": 0.0508,
+      "mean_token_accuracy": 0.9799627989530564,
+      "num_tokens": 24836722.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.49665711556829034,
+      "grad_norm": 0.1395769864320755,
+      "learning_rate": 3.8731297448150406e-05,
+      "loss": 0.0514,
+      "mean_token_accuracy": 0.9781762450933457,
+      "num_tokens": 25028141.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.5004775549188156,
+      "grad_norm": 0.12115350365638733,
+      "learning_rate": 3.8664429418292145e-05,
+      "loss": 0.0509,
+      "mean_token_accuracy": 0.979265108704567,
+      "num_tokens": 25221128.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.504297994269341,
+      "grad_norm": 0.13618040084838867,
+      "learning_rate": 3.859712597039192e-05,
+      "loss": 0.0465,
+      "mean_token_accuracy": 0.982085543870926,
+      "num_tokens": 25414361.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.5081184336198663,
+      "grad_norm": 0.18155395984649658,
+      "learning_rate": 3.852938959346128e-05,
+      "loss": 0.0567,
+      "mean_token_accuracy": 0.9777590453624725,
+      "num_tokens": 25605235.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.5119388729703916,
+      "grad_norm": 0.15678228437900543,
+      "learning_rate": 3.846122279252237e-05,
+      "loss": 0.0389,
+      "mean_token_accuracy": 0.9848253726959229,
+      "num_tokens": 25801181.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.5157593123209169,
+      "grad_norm": 0.26756489276885986,
+      "learning_rate": 3.839262808851524e-05,
+      "loss": 0.0676,
+      "mean_token_accuracy": 0.9738009810447693,
+      "num_tokens": 25988331.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.5195797516714422,
+      "grad_norm": 0.1596137434244156,
+      "learning_rate": 3.832360801820459e-05,
+      "loss": 0.0402,
+      "mean_token_accuracy": 0.9835259169340134,
+      "num_tokens": 26183909.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.5234001910219676,
+      "grad_norm": 0.2432740032672882,
+      "learning_rate": 3.825416513408604e-05,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9817402601242066,
+      "num_tokens": 26378511.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.5272206303724928,
+      "grad_norm": 0.11702600121498108,
+      "learning_rate": 3.818430200429163e-05,
+      "loss": 0.0697,
+      "mean_token_accuracy": 0.9732681095600129,
+      "num_tokens": 26569560.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.5310410697230181,
+      "grad_norm": 0.2008005529642105,
+      "learning_rate": 3.811402121249493e-05,
+      "loss": 0.0513,
+      "mean_token_accuracy": 0.9787397295236587,
+      "num_tokens": 26762807.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.5348615090735435,
+      "grad_norm": 0.1823837012052536,
+      "learning_rate": 3.8043325357815445e-05,
+      "loss": 0.0391,
+      "mean_token_accuracy": 0.9833790808916092,
+      "num_tokens": 26959446.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.5386819484240688,
+      "grad_norm": 0.19221177697181702,
+      "learning_rate": 3.797221705472252e-05,
+      "loss": 0.039,
+      "mean_token_accuracy": 0.9832836896181106,
+      "num_tokens": 27156708.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.542502387774594,
+      "grad_norm": 0.1583368480205536,
+      "learning_rate": 3.790069893293862e-05,
+      "loss": 0.0438,
+      "mean_token_accuracy": 0.9821615636348724,
+      "num_tokens": 27348513.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.5463228271251194,
+      "grad_norm": 0.14715953171253204,
+      "learning_rate": 3.7828773637342113e-05,
+      "loss": 0.0519,
+      "mean_token_accuracy": 0.9778920650482178,
+      "num_tokens": 27540580.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.5501432664756447,
+      "grad_norm": 0.20188972353935242,
+      "learning_rate": 3.775644382786943e-05,
+      "loss": 0.0371,
+      "mean_token_accuracy": 0.9840046137571334,
+      "num_tokens": 27738101.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.55396370582617,
+      "grad_norm": 0.15126635134220123,
+      "learning_rate": 3.768371217941672e-05,
+      "loss": 0.0506,
+      "mean_token_accuracy": 0.9788207143545151,
+      "num_tokens": 27931754.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.5577841451766953,
+      "grad_norm": 0.09126510471105576,
+      "learning_rate": 3.761058138174091e-05,
+      "loss": 0.0387,
+      "mean_token_accuracy": 0.9840620666742325,
+      "num_tokens": 28122701.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.5616045845272206,
+      "grad_norm": 0.41348138451576233,
+      "learning_rate": 3.753705413936023e-05,
+      "loss": 0.0563,
+      "mean_token_accuracy": 0.9763787448406219,
+      "num_tokens": 28312019.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.565425023877746,
+      "grad_norm": 0.10064998269081116,
+      "learning_rate": 3.746313317145419e-05,
+      "loss": 0.0644,
+      "mean_token_accuracy": 0.9752407640218734,
+      "num_tokens": 28497924.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.5692454632282713,
+      "grad_norm": 0.210185706615448,
+      "learning_rate": 3.7388821211763076e-05,
+      "loss": 0.0528,
+      "mean_token_accuracy": 0.9797067105770111,
+      "num_tokens": 28689547.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.5730659025787965,
+      "grad_norm": 0.39739805459976196,
+      "learning_rate": 3.7314121008486755e-05,
+      "loss": 0.0461,
+      "mean_token_accuracy": 0.9805936962366104,
+      "num_tokens": 28883672.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.5768863419293219,
+      "grad_norm": 0.14409542083740234,
+      "learning_rate": 3.723903532418312e-05,
+      "loss": 0.0679,
+      "mean_token_accuracy": 0.9712859630584717,
+      "num_tokens": 29068286.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.5807067812798472,
+      "grad_norm": 0.2085961103439331,
+      "learning_rate": 3.716356693566589e-05,
+      "loss": 0.0637,
+      "mean_token_accuracy": 0.9745287299156189,
+      "num_tokens": 29257579.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.5845272206303725,
+      "grad_norm": 0.15800058841705322,
+      "learning_rate": 3.708771863390193e-05,
+      "loss": 0.0476,
+      "mean_token_accuracy": 0.9808867007493973,
+      "num_tokens": 29454887.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.5883476599808978,
+      "grad_norm": 0.35635408759117126,
+      "learning_rate": 3.701149322390802e-05,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.9803213357925415,
+      "num_tokens": 29651591.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.5921680993314231,
+      "grad_norm": 0.15421795845031738,
+      "learning_rate": 3.693489352464713e-05,
+      "loss": 0.0417,
+      "mean_token_accuracy": 0.9807868421077728,
+      "num_tokens": 29845157.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.5959885386819485,
+      "grad_norm": 0.22060208022594452,
+      "learning_rate": 3.68579223689242e-05,
+      "loss": 0.0644,
+      "mean_token_accuracy": 0.9709617555141449,
+      "num_tokens": 30034025.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.5998089780324737,
+      "grad_norm": 0.23613664507865906,
+      "learning_rate": 3.678058260328131e-05,
+      "loss": 0.0477,
+      "mean_token_accuracy": 0.9798530042171478,
+      "num_tokens": 30229035.0,
+      "step": 785
+    },
+    {
+      "epoch": 0.603629417382999,
+      "grad_norm": 0.12523150444030762,
+      "learning_rate": 3.670287708789248e-05,
+      "loss": 0.0524,
+      "mean_token_accuracy": 0.9785983085632324,
+      "num_tokens": 30418474.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.6074498567335244,
+      "grad_norm": 0.18749313056468964,
+      "learning_rate": 3.6624808696457835e-05,
+      "loss": 0.0763,
+      "mean_token_accuracy": 0.9689610749483109,
+      "num_tokens": 30607423.0,
+      "step": 795
+    },
+    {
+      "epoch": 0.6112702960840497,
+      "grad_norm": 0.14081282913684845,
+      "learning_rate": 3.6546380316097366e-05,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9808779299259186,
+      "num_tokens": 30803864.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.6150907354345749,
+      "grad_norm": 0.13193558156490326,
+      "learning_rate": 3.646759484724415e-05,
+      "loss": 0.0523,
+      "mean_token_accuracy": 0.9788305640220643,
+      "num_tokens": 30995233.0,
+      "step": 805
+    },
+    {
+      "epoch": 0.6189111747851003,
+      "grad_norm": 0.2833406329154968,
+      "learning_rate": 3.638845520353711e-05,
+      "loss": 0.0419,
+      "mean_token_accuracy": 0.981367215514183,
+      "num_tokens": 31187454.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.6227316141356256,
+      "grad_norm": 0.11428867280483246,
+      "learning_rate": 3.6308964311713196e-05,
+      "loss": 0.0408,
+      "mean_token_accuracy": 0.9843004494905472,
+      "num_tokens": 31388786.0,
+      "step": 815
+    },
+    {
+      "epoch": 0.626552053486151,
+      "grad_norm": 0.15500947833061218,
+      "learning_rate": 3.6229125111499226e-05,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9808977574110032,
+      "num_tokens": 31585859.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.6303724928366762,
+      "grad_norm": 0.18459661304950714,
+      "learning_rate": 3.6148940555503124e-05,
+      "loss": 0.0612,
+      "mean_token_accuracy": 0.973130851984024,
+      "num_tokens": 31781245.0,
+      "step": 825
+    },
+    {
+      "epoch": 0.6341929321872015,
+      "grad_norm": 0.23240184783935547,
+      "learning_rate": 3.6068413609104744e-05,
+      "loss": 0.0596,
+      "mean_token_accuracy": 0.9753832727670669,
+      "num_tokens": 31968375.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.6380133715377269,
+      "grad_norm": 0.3594913184642792,
+      "learning_rate": 3.598754725034619e-05,
+      "loss": 0.0394,
+      "mean_token_accuracy": 0.9833639293909073,
+      "num_tokens": 32152583.0,
+      "step": 835
+    },
+    {
+      "epoch": 0.6418338108882522,
+      "grad_norm": 0.23351864516735077,
+      "learning_rate": 3.5906344469821684e-05,
+      "loss": 0.0599,
+      "mean_token_accuracy": 0.9735638827085495,
+      "num_tokens": 32339634.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.6456542502387774,
+      "grad_norm": 0.15344874560832977,
+      "learning_rate": 3.5824808270567e-05,
+      "loss": 0.0588,
+      "mean_token_accuracy": 0.977136743068695,
+      "num_tokens": 32534153.0,
+      "step": 845
+    },
+    {
+      "epoch": 0.6494746895893028,
+      "grad_norm": 0.24362897872924805,
+      "learning_rate": 3.574294166794837e-05,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9823481678962708,
+      "num_tokens": 32725350.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.6532951289398281,
+      "grad_norm": 0.1514531672000885,
+      "learning_rate": 3.566074768955096e-05,
+      "loss": 0.0567,
+      "mean_token_accuracy": 0.9780875772237778,
+      "num_tokens": 32917041.0,
+      "step": 855
+    },
+    {
+      "epoch": 0.6571155682903533,
+      "grad_norm": 0.15000875294208527,
+      "learning_rate": 3.557822937506696e-05,
+      "loss": 0.073,
+      "mean_token_accuracy": 0.9712677448987961,
+      "num_tokens": 33110434.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.6609360076408787,
+      "grad_norm": 0.2099716067314148,
+      "learning_rate": 3.549538977618311e-05,
+      "loss": 0.0682,
+      "mean_token_accuracy": 0.969989937543869,
+      "num_tokens": 33301486.0,
+      "step": 865
+    },
+    {
+      "epoch": 0.664756446991404,
+      "grad_norm": 1.0591760873794556,
+      "learning_rate": 3.5412231956467874e-05,
+      "loss": 0.0622,
+      "mean_token_accuracy": 0.9767576843500138,
+      "num_tokens": 33494914.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.6685768863419294,
+      "grad_norm": 0.18039724230766296,
+      "learning_rate": 3.5328758991258146e-05,
+      "loss": 0.0636,
+      "mean_token_accuracy": 0.9752348959445953,
+      "num_tokens": 33687748.0,
+      "step": 875
+    },
+    {
+      "epoch": 0.6723973256924546,
+      "grad_norm": 0.37878313660621643,
+      "learning_rate": 3.524497396754551e-05,
+      "loss": 0.0586,
+      "mean_token_accuracy": 0.9764747142791748,
+      "num_tokens": 33880399.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.6762177650429799,
+      "grad_norm": 0.1831691712141037,
+      "learning_rate": 3.5160879983862046e-05,
+      "loss": 0.0447,
+      "mean_token_accuracy": 0.9823864996433258,
+      "num_tokens": 34075282.0,
+      "step": 885
+    },
+    {
+      "epoch": 0.6800382043935053,
+      "grad_norm": 0.10887472331523895,
+      "learning_rate": 3.5076480150165817e-05,
+      "loss": 0.0339,
+      "mean_token_accuracy": 0.9854964166879654,
+      "num_tokens": 34273329.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.6838586437440306,
+      "grad_norm": 0.18240153789520264,
+      "learning_rate": 3.4991777587725774e-05,
+      "loss": 0.0556,
+      "mean_token_accuracy": 0.9771496653556824,
+      "num_tokens": 34462663.0,
+      "step": 895
+    },
+    {
+      "epoch": 0.6876790830945558,
+      "grad_norm": 0.10713613778352737,
+      "learning_rate": 3.4906775429006386e-05,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9816964775323868,
+      "num_tokens": 34658745.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.6914995224450812,
+      "grad_norm": 0.39516904950141907,
+      "learning_rate": 3.4821476817551755e-05,
+      "loss": 0.0602,
+      "mean_token_accuracy": 0.9714990973472595,
+      "num_tokens": 34849108.0,
+      "step": 905
+    },
+    {
+      "epoch": 0.6953199617956065,
+      "grad_norm": 0.17023275792598724,
+      "learning_rate": 3.473588490786939e-05,
+      "loss": 0.0444,
+      "mean_token_accuracy": 0.9812820851802826,
+      "num_tokens": 35045821.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.6991404011461319,
+      "grad_norm": 0.14729702472686768,
+      "learning_rate": 3.465000286531353e-05,
+      "loss": 0.0429,
+      "mean_token_accuracy": 0.980825787782669,
+      "num_tokens": 35242509.0,
+      "step": 915
+    },
+    {
+      "epoch": 0.7029608404966571,
+      "grad_norm": 0.1457536220550537,
+      "learning_rate": 3.456383386596808e-05,
+      "loss": 0.0414,
+      "mean_token_accuracy": 0.9837114304304123,
+      "num_tokens": 35435255.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.7067812798471824,
+      "grad_norm": 0.18686139583587646,
+      "learning_rate": 3.447738109652918e-05,
+      "loss": 0.0538,
+      "mean_token_accuracy": 0.9776090174913407,
+      "num_tokens": 35630886.0,
+      "step": 925
+    },
+    {
+      "epoch": 0.7106017191977078,
+      "grad_norm": 0.20606687664985657,
+      "learning_rate": 3.439064775418731e-05,
+      "loss": 0.0603,
+      "mean_token_accuracy": 0.9773728638887406,
+      "num_tokens": 35826949.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.7144221585482331,
+      "grad_norm": 0.12486971914768219,
+      "learning_rate": 3.430363704650912e-05,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9752701312303543,
+      "num_tokens": 36020207.0,
+      "step": 935
+    },
+    {
+      "epoch": 0.7182425978987583,
+      "grad_norm": 0.15200285613536835,
+      "learning_rate": 3.421635219131872e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.9842792868614196,
+      "num_tokens": 36214070.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.7220630372492837,
+      "grad_norm": 0.09536109864711761,
+      "learning_rate": 3.412879641657875e-05,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9808387368917465,
+      "num_tokens": 36404816.0,
+      "step": 945
+    },
+    {
+      "epoch": 0.725883476599809,
+      "grad_norm": 0.22405336797237396,
+      "learning_rate": 3.404097296027098e-05,
+      "loss": 0.047,
+      "mean_token_accuracy": 0.9801785320043563,
+      "num_tokens": 36600303.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.7297039159503342,
+      "grad_norm": 0.1923264116048813,
+      "learning_rate": 3.395288507027655e-05,
+      "loss": 0.0482,
+      "mean_token_accuracy": 0.9776667267084121,
+      "num_tokens": 36794087.0,
+      "step": 955
+    },
+    {
+      "epoch": 0.7335243553008596,
+      "grad_norm": 0.24032950401306152,
+      "learning_rate": 3.386453600425588e-05,
+      "loss": 0.0582,
+      "mean_token_accuracy": 0.9770094871520996,
+      "num_tokens": 36990475.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.7373447946513849,
+      "grad_norm": 0.23802198469638824,
+      "learning_rate": 3.3775929029528174e-05,
+      "loss": 0.044,
+      "mean_token_accuracy": 0.9814777672290802,
+      "num_tokens": 37184588.0,
+      "step": 965
+    },
+    {
+      "epoch": 0.7411652340019103,
+      "grad_norm": 0.2588277757167816,
+      "learning_rate": 3.368706742295061e-05,
+      "loss": 0.0413,
+      "mean_token_accuracy": 0.9830630749464035,
+      "num_tokens": 37372001.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.7449856733524355,
+      "grad_norm": 0.14313346147537231,
+      "learning_rate": 3.359795447079712e-05,
+      "loss": 0.0679,
+      "mean_token_accuracy": 0.9724821150302887,
+      "num_tokens": 37559141.0,
+      "step": 975
+    },
+    {
+      "epoch": 0.7488061127029608,
+      "grad_norm": 0.06837604939937592,
+      "learning_rate": 3.3508593468636916e-05,
+      "loss": 0.0465,
+      "mean_token_accuracy": 0.9818051338195801,
+      "num_tokens": 37756838.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.7526265520534862,
+      "grad_norm": 0.16657404601573944,
+      "learning_rate": 3.341898772121256e-05,
+      "loss": 0.0409,
+      "mean_token_accuracy": 0.9842217713594437,
+      "num_tokens": 37947357.0,
+      "step": 985
+    },
+    {
+      "epoch": 0.7564469914040115,
+      "grad_norm": 0.1696610301733017,
+      "learning_rate": 3.3329140542317766e-05,
+      "loss": 0.0435,
+      "mean_token_accuracy": 0.9822180181741714,
+      "num_tokens": 38141883.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.7602674307545367,
+      "grad_norm": 0.11435242742300034,
+      "learning_rate": 3.3239055254674843e-05,
+      "loss": 0.0466,
+      "mean_token_accuracy": 0.9786978244781495,
+      "num_tokens": 38332542.0,
+      "step": 995
+    },
+    {
+      "epoch": 0.7640878701050621,
+      "grad_norm": 0.13120298087596893,
+      "learning_rate": 3.314873518981184e-05,
+      "loss": 0.0518,
+      "mean_token_accuracy": 0.979632043838501,
+      "num_tokens": 38524994.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2618,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1319279777888727e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad5483d5a687e0a7734da0f1c111638eb80e122087d8bfc03eeb3362c36ddb8
+size 6481