memory-write winner-recipe R2 adapter (517 steps)

.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: Gege24/clobber-ic-9770-mcts-merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Gege24--clobber-ic-9770-mcts-merged
+- 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": "Gege24/clobber-ic-9770-mcts-merged",
+  "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": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_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 sha256:7ebb3cf0e6df159ca1e6827a217d626b15e2df9ee1edf21e56501d9a2deeec35
+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 @@
+517,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 +1,961 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25455440669620877,
+  "eval_steps": 500,
+  "global_step": 517,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002461841457410143,
+      "grad_norm": 4.969754695892334,
+      "learning_rate": 4.302e-06,
+      "loss": 1.1189,
+      "mean_token_accuracy": 0.8113007307052612,
+      "num_tokens": 320493.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.004923682914820286,
+      "grad_norm": 1.6874388456344604,
+      "learning_rate": 9.6795e-06,
+      "loss": 0.86,
+      "mean_token_accuracy": 0.8318304777145386,
+      "num_tokens": 641636.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.007385524372230428,
+      "grad_norm": 1.024154782295227,
+      "learning_rate": 1.5056999999999998e-05,
+      "loss": 0.5203,
+      "mean_token_accuracy": 0.8795766830444336,
+      "num_tokens": 964317.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.009847365829640572,
+      "grad_norm": 0.7188010811805725,
+      "learning_rate": 2.04345e-05,
+      "loss": 0.2224,
+      "mean_token_accuracy": 0.9444798469543457,
+      "num_tokens": 1284810.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.012309207287050714,
+      "grad_norm": 0.44151246547698975,
+      "learning_rate": 2.1509842516210667e-05,
+      "loss": 0.085,
+      "mean_token_accuracy": 0.9784384965896606,
+      "num_tokens": 1605399.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.014771048744460856,
+      "grad_norm": 0.5774744749069214,
+      "learning_rate": 2.1509202748855685e-05,
+      "loss": 0.0344,
+      "mean_token_accuracy": 0.9897613763809204,
+      "num_tokens": 1926494.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.017232890201871,
+      "grad_norm": 0.18032197654247284,
+      "learning_rate": 2.1508070894201505e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9919694185256958,
+      "num_tokens": 2247464.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.019694731659281144,
+      "grad_norm": 0.13021060824394226,
+      "learning_rate": 2.1506447021304556e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9920557975769043,
+      "num_tokens": 2569609.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.022156573116691284,
+      "grad_norm": 0.09289778023958206,
+      "learning_rate": 2.150433122924014e-05,
+      "loss": 0.0284,
+      "mean_token_accuracy": 0.9913681268692016,
+      "num_tokens": 2890136.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.024618414574101428,
+      "grad_norm": 0.11910147964954376,
+      "learning_rate": 2.1501723647096418e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9929254293441773,
+      "num_tokens": 3212967.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.02708025603151157,
+      "grad_norm": 0.06892787665128708,
+      "learning_rate": 2.149862443396651e-05,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9933408498764038,
+      "num_tokens": 3535443.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.029542097488921712,
+      "grad_norm": 0.06759732216596603,
+      "learning_rate": 2.1495033778938793e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9929208397865296,
+      "num_tokens": 3856507.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.032003938946331856,
+      "grad_norm": 0.07114335149526596,
+      "learning_rate": 2.149095190108538e-05,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9924069523811341,
+      "num_tokens": 4176799.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.034465780403742,
+      "grad_norm": 0.06943695992231369,
+      "learning_rate": 2.1486379049448737e-05,
+      "loss": 0.0169,
+      "mean_token_accuracy": 0.993648087978363,
+      "num_tokens": 4499735.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.03692762186115214,
+      "grad_norm": 0.0616086907684803,
+      "learning_rate": 2.1481315503026496e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9931790113449097,
+      "num_tokens": 4820981.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.03938946331856229,
+      "grad_norm": 0.0513451024889946,
+      "learning_rate": 2.1475761570754427e-05,
+      "loss": 0.0207,
+      "mean_token_accuracy": 0.9926488041877747,
+      "num_tokens": 5141030.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.041851304775972424,
+      "grad_norm": 0.056912314146757126,
+      "learning_rate": 2.1469717591487602e-05,
+      "loss": 0.0207,
+      "mean_token_accuracy": 0.9930928468704223,
+      "num_tokens": 5463284.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.04431314623338257,
+      "grad_norm": 0.07296790182590485,
+      "learning_rate": 2.1463183933979705e-05,
+      "loss": 0.015,
+      "mean_token_accuracy": 0.9941470623016357,
+      "num_tokens": 5785382.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.04677498769079271,
+      "grad_norm": 0.06787711381912231,
+      "learning_rate": 2.1456160996860543e-05,
+      "loss": 0.0179,
+      "mean_token_accuracy": 0.9935230731964111,
+      "num_tokens": 6106054.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.049236829148202856,
+      "grad_norm": 0.06585029512643814,
+      "learning_rate": 2.144864920861172e-05,
+      "loss": 0.0186,
+      "mean_token_accuracy": 0.9933484435081482,
+      "num_tokens": 6428795.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.051698670605613,
+      "grad_norm": 0.06587713956832886,
+      "learning_rate": 2.144064902754051e-05,
+      "loss": 0.0185,
+      "mean_token_accuracy": 0.9930931210517884,
+      "num_tokens": 6750701.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.05416051206302314,
+      "grad_norm": 0.07679057866334915,
+      "learning_rate": 2.1432160941751866e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9929586410522461,
+      "num_tokens": 7071691.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.05662235352043329,
+      "grad_norm": 0.04670145362615585,
+      "learning_rate": 2.142318546911867e-05,
+      "loss": 0.0189,
+      "mean_token_accuracy": 0.9934035181999207,
+      "num_tokens": 7393074.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.059084194977843424,
+      "grad_norm": 0.06476707011461258,
+      "learning_rate": 2.1413723157250112e-05,
+      "loss": 0.0164,
+      "mean_token_accuracy": 0.993677806854248,
+      "num_tokens": 7715147.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.06154603643525357,
+      "grad_norm": 0.051915861666202545,
+      "learning_rate": 2.1403774583458295e-05,
+      "loss": 0.0157,
+      "mean_token_accuracy": 0.9937990188598633,
+      "num_tokens": 8036756.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.06400787789266371,
+      "grad_norm": 0.06622428447008133,
+      "learning_rate": 2.1393340354723012e-05,
+      "loss": 0.0172,
+      "mean_token_accuracy": 0.9937798023223877,
+      "num_tokens": 8357904.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.06646971935007386,
+      "grad_norm": 0.048398587852716446,
+      "learning_rate": 2.13824211076547e-05,
+      "loss": 0.0169,
+      "mean_token_accuracy": 0.9936380386352539,
+      "num_tokens": 8679562.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.068931560807484,
+      "grad_norm": 0.0736224353313446,
+      "learning_rate": 2.1371017508455625e-05,
+      "loss": 0.0188,
+      "mean_token_accuracy": 0.9932926297187805,
+      "num_tokens": 9001387.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.07139340226489414,
+      "grad_norm": 0.047113846987485886,
+      "learning_rate": 2.1359130252879188e-05,
+      "loss": 0.0157,
+      "mean_token_accuracy": 0.9938287138938904,
+      "num_tokens": 9323154.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.07385524372230429,
+      "grad_norm": 0.06331256777048111,
+      "learning_rate": 2.1346760066187538e-05,
+      "loss": 0.0189,
+      "mean_token_accuracy": 0.9930492639541626,
+      "num_tokens": 9644568.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.07631708517971443,
+      "grad_norm": 0.06080303713679314,
+      "learning_rate": 2.1333907703107276e-05,
+      "loss": 0.0225,
+      "mean_token_accuracy": 0.9922333717346191,
+      "num_tokens": 9964653.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.07877892663712457,
+      "grad_norm": 0.07311772555112839,
+      "learning_rate": 2.1320573947783423e-05,
+      "loss": 0.0184,
+      "mean_token_accuracy": 0.9932848572731018,
+      "num_tokens": 10285925.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.08124076809453472,
+      "grad_norm": 0.1281968057155609,
+      "learning_rate": 2.1306759613731585e-05,
+      "loss": 0.0178,
+      "mean_token_accuracy": 0.9935338497161865,
+      "num_tokens": 10606433.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.08370260955194485,
+      "grad_norm": 0.03950123116374016,
+      "learning_rate": 2.1292465543788306e-05,
+      "loss": 0.0165,
+      "mean_token_accuracy": 0.9936023473739624,
+      "num_tokens": 10926653.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.08616445100935499,
+      "grad_norm": 0.074995256960392,
+      "learning_rate": 2.127769261005965e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.993098521232605,
+      "num_tokens": 11247504.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.08862629246676514,
+      "grad_norm": 0.054995279759168625,
+      "learning_rate": 2.1262441713867998e-05,
+      "loss": 0.0169,
+      "mean_token_accuracy": 0.993760859966278,
+      "num_tokens": 11568063.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.09108813392417528,
+      "grad_norm": 0.053398437798023224,
+      "learning_rate": 2.1246713785697052e-05,
+      "loss": 0.0169,
+      "mean_token_accuracy": 0.9934692978858948,
+      "num_tokens": 11888599.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.09354997538158542,
+      "grad_norm": 0.07271428406238556,
+      "learning_rate": 2.1230509785135057e-05,
+      "loss": 0.0181,
+      "mean_token_accuracy": 0.9933955669403076,
+      "num_tokens": 12211086.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.09601181683899557,
+      "grad_norm": 0.07579043507575989,
+      "learning_rate": 2.1213830700816276e-05,
+      "loss": 0.0196,
+      "mean_token_accuracy": 0.9933238983154297,
+      "num_tokens": 12532840.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.09847365829640571,
+      "grad_norm": 0.05194873362779617,
+      "learning_rate": 2.1196677550360644e-05,
+      "loss": 0.0172,
+      "mean_token_accuracy": 0.993663489818573,
+      "num_tokens": 12854971.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.10093549975381585,
+      "grad_norm": 0.04237228259444237,
+      "learning_rate": 2.1179051380311706e-05,
+      "loss": 0.0185,
+      "mean_token_accuracy": 0.9933023810386657,
+      "num_tokens": 13176310.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.103397341211226,
+      "grad_norm": 0.05479801818728447,
+      "learning_rate": 2.116095326607275e-05,
+      "loss": 0.019,
+      "mean_token_accuracy": 0.9933096051216126,
+      "num_tokens": 13497271.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.10585918266863614,
+      "grad_norm": 0.050505638122558594,
+      "learning_rate": 2.11423843118412e-05,
+      "loss": 0.0193,
+      "mean_token_accuracy": 0.9930040121078492,
+      "num_tokens": 13818732.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.10832102412604629,
+      "grad_norm": 0.04875461012125015,
+      "learning_rate": 2.1123345650541254e-05,
+      "loss": 0.015,
+      "mean_token_accuracy": 0.9943194031715393,
+      "num_tokens": 14140155.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.11078286558345643,
+      "grad_norm": 0.04343048110604286,
+      "learning_rate": 2.110383844375474e-05,
+      "loss": 0.0173,
+      "mean_token_accuracy": 0.9935325264930726,
+      "num_tokens": 14461326.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.11324470704086657,
+      "grad_norm": 0.05743631348013878,
+      "learning_rate": 2.1083863881650274e-05,
+      "loss": 0.017,
+      "mean_token_accuracy": 0.9938044786453247,
+      "num_tokens": 14781958.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.11570654849827672,
+      "grad_norm": 0.06002819910645485,
+      "learning_rate": 2.1063423182910628e-05,
+      "loss": 0.0179,
+      "mean_token_accuracy": 0.9935547947883606,
+      "num_tokens": 15103260.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.11816838995568685,
+      "grad_norm": 0.04813234880566597,
+      "learning_rate": 2.1042517594658383e-05,
+      "loss": 0.0178,
+      "mean_token_accuracy": 0.9934481143951416,
+      "num_tokens": 15424845.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.12063023141309699,
+      "grad_norm": 0.04317139834165573,
+      "learning_rate": 2.1021148392379833e-05,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9936479210853577,
+      "num_tokens": 15745873.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.12309207287050714,
+      "grad_norm": 0.04026172310113907,
+      "learning_rate": 2.0999316879847178e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.9941782236099244,
+      "num_tokens": 16068592.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.1255539143279173,
+      "grad_norm": 0.03913912549614906,
+      "learning_rate": 2.097702438903896e-05,
+      "loss": 0.0165,
+      "mean_token_accuracy": 0.9937353253364563,
+      "num_tokens": 16389359.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.12801575578532742,
+      "grad_norm": 0.04398415982723236,
+      "learning_rate": 2.095427228005882e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9943455338478089,
+      "num_tokens": 16712502.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.13047759724273758,
+      "grad_norm": 0.03654300794005394,
+      "learning_rate": 2.093106194105249e-05,
+      "loss": 0.0155,
+      "mean_token_accuracy": 0.9941610932350159,
+      "num_tokens": 17032993.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.1329394387001477,
+      "grad_norm": 0.04314443841576576,
+      "learning_rate": 2.090739478812312e-05,
+      "loss": 0.0209,
+      "mean_token_accuracy": 0.9925150752067566,
+      "num_tokens": 17354397.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.13540128015755784,
+      "grad_norm": 0.039179477840662,
+      "learning_rate": 2.0883272265244868e-05,
+      "loss": 0.0158,
+      "mean_token_accuracy": 0.993960165977478,
+      "num_tokens": 17676053.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.137863121614968,
+      "grad_norm": 0.05969119071960449,
+      "learning_rate": 2.0858695844174815e-05,
+      "loss": 0.0156,
+      "mean_token_accuracy": 0.9940330982208252,
+      "num_tokens": 17997892.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.14032496307237813,
+      "grad_norm": 0.034701548516750336,
+      "learning_rate": 2.083366702436315e-05,
+      "loss": 0.0162,
+      "mean_token_accuracy": 0.99384845495224,
+      "num_tokens": 18320416.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.14278680452978829,
+      "grad_norm": 0.03629715368151665,
+      "learning_rate": 2.080818733286169e-05,
+      "loss": 0.0136,
+      "mean_token_accuracy": 0.9944872379302978,
+      "num_tokens": 18641774.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.14524864598719842,
+      "grad_norm": 0.03510307893157005,
+      "learning_rate": 2.078225832423074e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9944174408912658,
+      "num_tokens": 18963943.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.14771048744460857,
+      "grad_norm": 0.05658989027142525,
+      "learning_rate": 2.07558815804442e-05,
+      "loss": 0.0156,
+      "mean_token_accuracy": 0.9939489245414734,
+      "num_tokens": 19284670.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.1501723289020187,
+      "grad_norm": 0.052170414477586746,
+      "learning_rate": 2.072905871079309e-05,
+      "loss": 0.0146,
+      "mean_token_accuracy": 0.9942007660865784,
+      "num_tokens": 19605830.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.15263417035942886,
+      "grad_norm": 0.04669521376490593,
+      "learning_rate": 2.0701791351787333e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9942674160003662,
+      "num_tokens": 19927683.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.155096011816839,
+      "grad_norm": 0.045594099909067154,
+      "learning_rate": 2.0674081167055918e-05,
+      "loss": 0.022,
+      "mean_token_accuracy": 0.9924212217330932,
+      "num_tokens": 20249155.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.15755785327424915,
+      "grad_norm": 0.042525216937065125,
+      "learning_rate": 2.064592984724541e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9942982792854309,
+      "num_tokens": 20570187.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.16001969473165928,
+      "grad_norm": 0.04177013039588928,
+      "learning_rate": 2.0617339109916796e-05,
+      "loss": 0.0158,
+      "mean_token_accuracy": 0.9939341902732849,
+      "num_tokens": 20890900.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.16248153618906944,
+      "grad_norm": 0.043914180248975754,
+      "learning_rate": 2.058831069944068e-05,
+      "loss": 0.0159,
+      "mean_token_accuracy": 0.994042980670929,
+      "num_tokens": 21211005.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.16494337764647957,
+      "grad_norm": 0.038002047687768936,
+      "learning_rate": 2.0558846386890867e-05,
+      "loss": 0.0146,
+      "mean_token_accuracy": 0.9943417191505433,
+      "num_tokens": 21532493.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.1674052191038897,
+      "grad_norm": 0.03630073741078377,
+      "learning_rate": 2.0528947969936308e-05,
+      "loss": 0.0141,
+      "mean_token_accuracy": 0.9944631576538085,
+      "num_tokens": 21854914.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.16986706056129985,
+      "grad_norm": 0.051170364022254944,
+      "learning_rate": 2.0498617272731426e-05,
+      "loss": 0.0168,
+      "mean_token_accuracy": 0.9939067363739014,
+      "num_tokens": 22176913.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.17232890201870998,
+      "grad_norm": 0.05258825421333313,
+      "learning_rate": 2.0467856145804803e-05,
+      "loss": 0.0173,
+      "mean_token_accuracy": 0.9933236837387085,
+      "num_tokens": 22497434.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.17479074347612014,
+      "grad_norm": 0.06009254977107048,
+      "learning_rate": 2.0436666465946293e-05,
+      "loss": 0.0159,
+      "mean_token_accuracy": 0.9938840627670288,
+      "num_tokens": 22817721.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.17725258493353027,
+      "grad_norm": 0.04241907596588135,
+      "learning_rate": 2.0405050136092498e-05,
+      "loss": 0.0143,
+      "mean_token_accuracy": 0.9944479584693908,
+      "num_tokens": 23139931.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.17971442639094043,
+      "grad_norm": 0.05310116335749626,
+      "learning_rate": 2.03730090852107e-05,
+      "loss": 0.0165,
+      "mean_token_accuracy": 0.9938408613204956,
+      "num_tokens": 23462350.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.18217626784835056,
+      "grad_norm": 0.05389350652694702,
+      "learning_rate": 2.034054526818113e-05,
+      "loss": 0.0175,
+      "mean_token_accuracy": 0.9935489892959595,
+      "num_tokens": 23783401.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.18463810930576072,
+      "grad_norm": 0.054103367030620575,
+      "learning_rate": 2.0307660665677727e-05,
+      "loss": 0.0158,
+      "mean_token_accuracy": 0.9939422011375427,
+      "num_tokens": 24104565.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.18709995076317085,
+      "grad_norm": 0.04009604454040527,
+      "learning_rate": 2.027435728404728e-05,
+      "loss": 0.0156,
+      "mean_token_accuracy": 0.9941097736358643,
+      "num_tokens": 24425664.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.189561792220581,
+      "grad_norm": 0.04380296170711517,
+      "learning_rate": 2.0240637155187022e-05,
+      "loss": 0.0152,
+      "mean_token_accuracy": 0.9941174745559692,
+      "num_tokens": 24748557.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.19202363367799113,
+      "grad_norm": 0.032586026936769485,
+      "learning_rate": 2.0206502336420666e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9946724891662597,
+      "num_tokens": 25069808.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.1944854751354013,
+      "grad_norm": 0.06130707263946533,
+      "learning_rate": 2.0171954910372855e-05,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9931009531021118,
+      "num_tokens": 25390913.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.19694731659281142,
+      "grad_norm": 0.044839657843112946,
+      "learning_rate": 2.0136996984842144e-05,
+      "loss": 0.0156,
+      "mean_token_accuracy": 0.9942690134048462,
+      "num_tokens": 25711590.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.19940915805022155,
+      "grad_norm": 0.03433138132095337,
+      "learning_rate": 2.0101630692672366e-05,
+      "loss": 0.0134,
+      "mean_token_accuracy": 0.9945015668869018,
+      "num_tokens": 26033049.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.2018709995076317,
+      "grad_norm": 0.06145159527659416,
+      "learning_rate": 2.006585819162251e-05,
+      "loss": 0.0161,
+      "mean_token_accuracy": 0.9938944458961487,
+      "num_tokens": 26355422.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.20433284096504184,
+      "grad_norm": 0.046625472605228424,
+      "learning_rate": 2.002968166423509e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9942839503288269,
+      "num_tokens": 26676082.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.206794682422452,
+      "grad_norm": 0.03417025879025459,
+      "learning_rate": 1.999310331770294e-05,
+      "loss": 0.0138,
+      "mean_token_accuracy": 0.9944490194320679,
+      "num_tokens": 26997020.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.20925652387986213,
+      "grad_norm": 0.04904766008257866,
+      "learning_rate": 1.9956125383734614e-05,
+      "loss": 0.017,
+      "mean_token_accuracy": 0.9935599088668823,
+      "num_tokens": 27317984.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.21171836533727229,
+      "grad_norm": 0.03379844129085541,
+      "learning_rate": 1.9918750118418164e-05,
+      "loss": 0.0149,
+      "mean_token_accuracy": 0.9941614151000977,
+      "num_tokens": 27638796.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.21418020679468242,
+      "grad_norm": 0.03055359609425068,
+      "learning_rate": 1.988097980208353e-05,
+      "loss": 0.0147,
+      "mean_token_accuracy": 0.9942783713340759,
+      "num_tokens": 27960939.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.21664204825209257,
+      "grad_norm": 0.03959130495786667,
+      "learning_rate": 1.98428167391634e-05,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9945441961288453,
+      "num_tokens": 28281371.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.2191038897095027,
+      "grad_norm": 0.034778300672769547,
+      "learning_rate": 1.980426325805261e-05,
+      "loss": 0.0173,
+      "mean_token_accuracy": 0.9936829090118409,
+      "num_tokens": 28602755.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.22156573116691286,
+      "grad_norm": 0.054818179458379745,
+      "learning_rate": 1.97653217109661e-05,
+      "loss": 0.0158,
+      "mean_token_accuracy": 0.9938953042030334,
+      "num_tokens": 28924168.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.224027572624323,
+      "grad_norm": 0.030057087540626526,
+      "learning_rate": 1.9725994473795378e-05,
+      "loss": 0.0148,
+      "mean_token_accuracy": 0.9941797971725463,
+      "num_tokens": 29246171.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.22648941408173315,
+      "grad_norm": 0.05861424282193184,
+      "learning_rate": 1.968628394596358e-05,
+      "loss": 0.0144,
+      "mean_token_accuracy": 0.9942707657814026,
+      "num_tokens": 29569027.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.22895125553914328,
+      "grad_norm": 0.03463579714298248,
+      "learning_rate": 1.9646192550279074e-05,
+      "loss": 0.0148,
+      "mean_token_accuracy": 0.9943474292755127,
+      "num_tokens": 29890638.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.23141309699655344,
+      "grad_norm": 0.03462537005543709,
+      "learning_rate": 1.9605722732787628e-05,
+      "loss": 0.014,
+      "mean_token_accuracy": 0.9945291399955749,
+      "num_tokens": 30212106.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.23387493845396357,
+      "grad_norm": 0.03469887748360634,
+      "learning_rate": 1.9564876962623197e-05,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9939306259155274,
+      "num_tokens": 30534173.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.2363367799113737,
+      "grad_norm": 0.03356148675084114,
+      "learning_rate": 1.952365773185726e-05,
+      "loss": 0.0179,
+      "mean_token_accuracy": 0.9932782292366028,
+      "num_tokens": 30855988.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.23879862136878385,
+      "grad_norm": 0.05688195675611496,
+      "learning_rate": 1.9482067555346758e-05,
+      "loss": 0.0164,
+      "mean_token_accuracy": 0.9938588380813599,
+      "num_tokens": 31176045.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.24126046282619398,
+      "grad_norm": 0.03223969042301178,
+      "learning_rate": 1.94401089705807e-05,
+      "loss": 0.0172,
+      "mean_token_accuracy": 0.9935418725013733,
+      "num_tokens": 31497673.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.24372230428360414,
+      "grad_norm": 0.027766678482294083,
+      "learning_rate": 1.9397784537525315e-05,
+      "loss": 0.0153,
+      "mean_token_accuracy": 0.9940999031066895,
+      "num_tokens": 31818418.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.24618414574101427,
+      "grad_norm": 0.03331609442830086,
+      "learning_rate": 1.935509683846787e-05,
+      "loss": 0.0143,
+      "mean_token_accuracy": 0.9943779587745667,
+      "num_tokens": 32140371.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.24864598719842443,
+      "grad_norm": 0.052040133625268936,
+      "learning_rate": 1.9312048477859128e-05,
+      "loss": 0.0159,
+      "mean_token_accuracy": 0.9938185095787049,
+      "num_tokens": 32462318.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.2511078286558346,
+      "grad_norm": 0.029004910960793495,
+      "learning_rate": 1.9268642082154432e-05,
+      "loss": 0.0145,
+      "mean_token_accuracy": 0.9943286895751953,
+      "num_tokens": 32783640.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.2535696701132447,
+      "grad_norm": 0.03675747662782669,
+      "learning_rate": 1.9224880299653475e-05,
+      "loss": 0.0161,
+      "mean_token_accuracy": 0.9940426826477051,
+      "num_tokens": 33104542.0,
+      "step": 515
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2031,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4742460103760282e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b656f14e8ef686a1b60adc4e8dfe10523fb124598535fbcba18f0e39082203a
+size 6609