Upload task output 1

.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/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen2.5-3B-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": "Qwen/Qwen2.5-3B-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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "q_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 sha256:0733808bfab15a29a5c62c13ab54987b147477454f64539eee96c0573076c642
+size 957942768

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 @@
+337,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 +1,637 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.35362014690451204,
+  "eval_steps": 500,
+  "global_step": 337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005246589716684155,
+      "grad_norm": 8.869540214538574,
+      "learning_rate": 8.401166180758017e-06,
+      "loss": 0.9257,
+      "mean_token_accuracy": 0.8380203127861023,
+      "num_tokens": 289686.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.01049317943336831,
+      "grad_norm": 1.9420901536941528,
+      "learning_rate": 1.8902623906705538e-05,
+      "loss": 0.5266,
+      "mean_token_accuracy": 0.8593480110168457,
+      "num_tokens": 584447.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.015739769150052464,
+      "grad_norm": 1.2173879146575928,
+      "learning_rate": 2.9404081632653062e-05,
+      "loss": 0.3377,
+      "mean_token_accuracy": 0.894003939628601,
+      "num_tokens": 865283.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.02098635886673662,
+      "grad_norm": 0.9192031621932983,
+      "learning_rate": 3.990553935860058e-05,
+      "loss": 0.3091,
+      "mean_token_accuracy": 0.9075875878334045,
+      "num_tokens": 1150898.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.026232948583420776,
+      "grad_norm": 0.8734805583953857,
+      "learning_rate": 5.0406997084548104e-05,
+      "loss": 0.2471,
+      "mean_token_accuracy": 0.9180729031562805,
+      "num_tokens": 1456620.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.03147953830010493,
+      "grad_norm": 0.7508789300918579,
+      "learning_rate": 6.090845481049563e-05,
+      "loss": 0.2155,
+      "mean_token_accuracy": 0.9300779223442077,
+      "num_tokens": 1751457.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03672612801678909,
+      "grad_norm": 0.8536575436592102,
+      "learning_rate": 7.140991253644314e-05,
+      "loss": 0.2623,
+      "mean_token_accuracy": 0.9183142781257629,
+      "num_tokens": 2039245.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04197271773347324,
+      "grad_norm": 0.868010938167572,
+      "learning_rate": 7.350762136663497e-05,
+      "loss": 0.2239,
+      "mean_token_accuracy": 0.9314786314964294,
+      "num_tokens": 2330149.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0472193074501574,
+      "grad_norm": 0.7415319681167603,
+      "learning_rate": 7.349712991638426e-05,
+      "loss": 0.2124,
+      "mean_token_accuracy": 0.935946810245514,
+      "num_tokens": 2627934.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05246589716684155,
+      "grad_norm": 0.6589397192001343,
+      "learning_rate": 7.347857138053374e-05,
+      "loss": 0.2258,
+      "mean_token_accuracy": 0.9339556813240051,
+      "num_tokens": 2909298.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05771248688352571,
+      "grad_norm": 0.8945339322090149,
+      "learning_rate": 7.345195119268144e-05,
+      "loss": 0.2135,
+      "mean_token_accuracy": 0.9362031579017639,
+      "num_tokens": 3215160.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.06295907660020986,
+      "grad_norm": 0.6015563607215881,
+      "learning_rate": 7.341727714672879e-05,
+      "loss": 0.223,
+      "mean_token_accuracy": 0.9350167393684388,
+      "num_tokens": 3512700.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06820566631689402,
+      "grad_norm": 0.9376577138900757,
+      "learning_rate": 7.337455939459886e-05,
+      "loss": 0.1949,
+      "mean_token_accuracy": 0.9446848630905151,
+      "num_tokens": 3798243.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07345225603357818,
+      "grad_norm": 0.8647239804267883,
+      "learning_rate": 7.332381044326387e-05,
+      "loss": 0.192,
+      "mean_token_accuracy": 0.9473262071609497,
+      "num_tokens": 4088918.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07869884575026233,
+      "grad_norm": 0.6758660078048706,
+      "learning_rate": 7.326504515108353e-05,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9533717513084412,
+      "num_tokens": 4373400.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.08394543546694648,
+      "grad_norm": 0.6870194673538208,
+      "learning_rate": 7.319828072345472e-05,
+      "loss": 0.1719,
+      "mean_token_accuracy": 0.947171425819397,
+      "num_tokens": 4658256.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08919202518363065,
+      "grad_norm": 0.677169680595398,
+      "learning_rate": 7.312353670777409e-05,
+      "loss": 0.2406,
+      "mean_token_accuracy": 0.9317703485488892,
+      "num_tokens": 4942712.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.0944386149003148,
+      "grad_norm": 0.7355192303657532,
+      "learning_rate": 7.304083498771491e-05,
+      "loss": 0.1559,
+      "mean_token_accuracy": 0.9547448277473449,
+      "num_tokens": 5236965.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.09968520461699895,
+      "grad_norm": 0.8258501291275024,
+      "learning_rate": 7.295019977681995e-05,
+      "loss": 0.1484,
+      "mean_token_accuracy": 0.9531127452850342,
+      "num_tokens": 5531311.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.1049317943336831,
+      "grad_norm": 0.6302676200866699,
+      "learning_rate": 7.285165761141225e-05,
+      "loss": 0.1302,
+      "mean_token_accuracy": 0.9609502911567688,
+      "num_tokens": 5824530.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.11017838405036726,
+      "grad_norm": 0.7048377990722656,
+      "learning_rate": 7.274523734282567e-05,
+      "loss": 0.1655,
+      "mean_token_accuracy": 0.9510802745819091,
+      "num_tokens": 6126073.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.11542497376705142,
+      "grad_norm": 0.708620011806488,
+      "learning_rate": 7.263097012895783e-05,
+      "loss": 0.1919,
+      "mean_token_accuracy": 0.9440585255622864,
+      "num_tokens": 6428088.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.12067156348373557,
+      "grad_norm": 0.7772646546363831,
+      "learning_rate": 7.250888942514763e-05,
+      "loss": 0.1791,
+      "mean_token_accuracy": 0.9519138216972352,
+      "num_tokens": 6709759.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.1259181532004197,
+      "grad_norm": 0.728533148765564,
+      "learning_rate": 7.237903097438013e-05,
+      "loss": 0.1794,
+      "mean_token_accuracy": 0.9493731379508972,
+      "num_tokens": 7009928.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1311647429171039,
+      "grad_norm": 0.5031924843788147,
+      "learning_rate": 7.224143279682167e-05,
+      "loss": 0.1966,
+      "mean_token_accuracy": 0.9432877659797668,
+      "num_tokens": 7299912.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.13641133263378805,
+      "grad_norm": 0.7311460375785828,
+      "learning_rate": 7.209613517868828e-05,
+      "loss": 0.1623,
+      "mean_token_accuracy": 0.9553608179092408,
+      "num_tokens": 7587766.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.1416579223504722,
+      "grad_norm": 0.4527396261692047,
+      "learning_rate": 7.194318066045057e-05,
+      "loss": 0.1552,
+      "mean_token_accuracy": 0.9542324781417847,
+      "num_tokens": 7883332.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.14690451206715635,
+      "grad_norm": 0.5695252418518066,
+      "learning_rate": 7.178261402437872e-05,
+      "loss": 0.1409,
+      "mean_token_accuracy": 0.9568296670913696,
+      "num_tokens": 8184963.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.1521511017838405,
+      "grad_norm": 0.47259852290153503,
+      "learning_rate": 7.161448228143099e-05,
+      "loss": 0.1465,
+      "mean_token_accuracy": 0.9609991312026978,
+      "num_tokens": 8481153.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.15739769150052466,
+      "grad_norm": 0.5303276181221008,
+      "learning_rate": 7.143883465748988e-05,
+      "loss": 0.183,
+      "mean_token_accuracy": 0.9521325826644897,
+      "num_tokens": 8775155.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.1626442812172088,
+      "grad_norm": 0.46558475494384766,
+      "learning_rate": 7.125572257894959e-05,
+      "loss": 0.205,
+      "mean_token_accuracy": 0.9444481015205384,
+      "num_tokens": 9071761.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.16789087093389296,
+      "grad_norm": 0.6111699342727661,
+      "learning_rate": 7.106519965765934e-05,
+      "loss": 0.1717,
+      "mean_token_accuracy": 0.9499832153320312,
+      "num_tokens": 9363710.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1731374606505771,
+      "grad_norm": 0.7169287204742432,
+      "learning_rate": 7.086732167522687e-05,
+      "loss": 0.2031,
+      "mean_token_accuracy": 0.9435471892356873,
+      "num_tokens": 9650095.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.1783840503672613,
+      "grad_norm": 0.41854023933410645,
+      "learning_rate": 7.066214656668653e-05,
+      "loss": 0.128,
+      "mean_token_accuracy": 0.9642794132232666,
+      "num_tokens": 9943925.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.18363064008394545,
+      "grad_norm": 0.5462023019790649,
+      "learning_rate": 7.044973440353702e-05,
+      "loss": 0.1692,
+      "mean_token_accuracy": 0.9510787844657898,
+      "num_tokens": 10239935.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1888772298006296,
+      "grad_norm": 0.682062566280365,
+      "learning_rate": 7.023014737615354e-05,
+      "loss": 0.0925,
+      "mean_token_accuracy": 0.9718472838401795,
+      "num_tokens": 10542283.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.19412381951731375,
+      "grad_norm": 0.4446072578430176,
+      "learning_rate": 7.000344977557959e-05,
+      "loss": 0.1831,
+      "mean_token_accuracy": 0.9482220768928528,
+      "num_tokens": 10833066.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.1993704092339979,
+      "grad_norm": 0.35908645391464233,
+      "learning_rate": 6.976970797470374e-05,
+      "loss": 0.1553,
+      "mean_token_accuracy": 0.9547260999679565,
+      "num_tokens": 11138524.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.20461699895068206,
+      "grad_norm": 0.5753610134124756,
+      "learning_rate": 6.95289904088269e-05,
+      "loss": 0.1783,
+      "mean_token_accuracy": 0.9493900299072265,
+      "num_tokens": 11434453.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.2098635886673662,
+      "grad_norm": 0.5665861964225769,
+      "learning_rate": 6.928136755562561e-05,
+      "loss": 0.1653,
+      "mean_token_accuracy": 0.9550609827041626,
+      "num_tokens": 11730328.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.21511017838405036,
+      "grad_norm": 0.5666924118995667,
+      "learning_rate": 6.902691191451765e-05,
+      "loss": 0.1927,
+      "mean_token_accuracy": 0.9518372297286988,
+      "num_tokens": 12015188.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.2203567681007345,
+      "grad_norm": 0.41499361395835876,
+      "learning_rate": 6.876569798543542e-05,
+      "loss": 0.1149,
+      "mean_token_accuracy": 0.9646952271461486,
+      "num_tokens": 12310232.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.22560335781741866,
+      "grad_norm": 0.44563302397727966,
+      "learning_rate": 6.84978022470137e-05,
+      "loss": 0.1195,
+      "mean_token_accuracy": 0.9647434711456299,
+      "num_tokens": 12591060.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.23084994753410285,
+      "grad_norm": 0.9801908731460571,
+      "learning_rate": 6.822330313419822e-05,
+      "loss": 0.1501,
+      "mean_token_accuracy": 0.9570110678672791,
+      "num_tokens": 12879679.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.236096537250787,
+      "grad_norm": 0.590543806552887,
+      "learning_rate": 6.79422810152813e-05,
+      "loss": 0.1879,
+      "mean_token_accuracy": 0.949954628944397,
+      "num_tokens": 13169419.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.24134312696747115,
+      "grad_norm": 0.5752514004707336,
+      "learning_rate": 6.765481816837146e-05,
+      "loss": 0.1507,
+      "mean_token_accuracy": 0.9556933283805847,
+      "num_tokens": 13471416.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.2465897166841553,
+      "grad_norm": 0.47486424446105957,
+      "learning_rate": 6.736099875730397e-05,
+      "loss": 0.1675,
+      "mean_token_accuracy": 0.956990647315979,
+      "num_tokens": 13767085.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.2518363064008394,
+      "grad_norm": 0.7542303800582886,
+      "learning_rate": 6.706090880699916e-05,
+      "loss": 0.1798,
+      "mean_token_accuracy": 0.9498309254646301,
+      "num_tokens": 14071045.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2570828961175236,
+      "grad_norm": 0.5474414825439453,
+      "learning_rate": 6.675463617827598e-05,
+      "loss": 0.1698,
+      "mean_token_accuracy": 0.9535765051841736,
+      "num_tokens": 14362641.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.2623294858342078,
+      "grad_norm": 0.5496485829353333,
+      "learning_rate": 6.644227054212787e-05,
+      "loss": 0.1457,
+      "mean_token_accuracy": 0.9581978678703308,
+      "num_tokens": 14664981.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.2675760755508919,
+      "grad_norm": 0.49473029375076294,
+      "learning_rate": 6.612390335346883e-05,
+      "loss": 0.155,
+      "mean_token_accuracy": 0.9565532088279725,
+      "num_tokens": 14959011.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.2728226652675761,
+      "grad_norm": 0.303487628698349,
+      "learning_rate": 6.579962782435706e-05,
+      "loss": 0.1509,
+      "mean_token_accuracy": 0.9600463390350342,
+      "num_tokens": 15245374.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2780692549842602,
+      "grad_norm": 0.5282312631607056,
+      "learning_rate": 6.546953889670418e-05,
+      "loss": 0.1702,
+      "mean_token_accuracy": 0.9531951785087586,
+      "num_tokens": 15525453.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.2833158447009444,
+      "grad_norm": 0.28557926416397095,
+      "learning_rate": 6.513373321447803e-05,
+      "loss": 0.1937,
+      "mean_token_accuracy": 0.9494660019874572,
+      "num_tokens": 15809199.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.2885624344176285,
+      "grad_norm": 0.4175744652748108,
+      "learning_rate": 6.479230909540701e-05,
+      "loss": 0.125,
+      "mean_token_accuracy": 0.9632657885551452,
+      "num_tokens": 16101826.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.2938090241343127,
+      "grad_norm": 0.46477630734443665,
+      "learning_rate": 6.444536650219457e-05,
+      "loss": 0.1477,
+      "mean_token_accuracy": 0.9573351144790649,
+      "num_tokens": 16390495.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.2990556138509968,
+      "grad_norm": 0.40762028098106384,
+      "learning_rate": 6.409300701325186e-05,
+      "loss": 0.1447,
+      "mean_token_accuracy": 0.9613166928291321,
+      "num_tokens": 16685503.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.304302203567681,
+      "grad_norm": 0.24077750742435455,
+      "learning_rate": 6.37353337929575e-05,
+      "loss": 0.172,
+      "mean_token_accuracy": 0.9532236933708191,
+      "num_tokens": 16964030.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.3095487932843652,
+      "grad_norm": 0.826016366481781,
+      "learning_rate": 6.337245156145292e-05,
+      "loss": 0.1803,
+      "mean_token_accuracy": 0.955608320236206,
+      "num_tokens": 17262831.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.3147953830010493,
+      "grad_norm": 0.4392148554325104,
+      "learning_rate": 6.300446656398228e-05,
+      "loss": 0.1769,
+      "mean_token_accuracy": 0.950160825252533,
+      "num_tokens": 17542500.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.3200419727177335,
+      "grad_norm": 0.5865193009376526,
+      "learning_rate": 6.263148653978572e-05,
+      "loss": 0.1245,
+      "mean_token_accuracy": 0.9670758128166199,
+      "num_tokens": 17833796.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.3252885624344176,
+      "grad_norm": 0.5191839337348938,
+      "learning_rate": 6.225362069055539e-05,
+      "loss": 0.192,
+      "mean_token_accuracy": 0.947128975391388,
+      "num_tokens": 18131801.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.3305351521511018,
+      "grad_norm": 0.41704511642456055,
+      "learning_rate": 6.187097964846317e-05,
+      "loss": 0.1353,
+      "mean_token_accuracy": 0.9619265556335449,
+      "num_tokens": 18429696.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.3357817418677859,
+      "grad_norm": 0.5766462087631226,
+      "learning_rate": 6.148367544376953e-05,
+      "loss": 0.1647,
+      "mean_token_accuracy": 0.9554041147232055,
+      "num_tokens": 18726485.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.3410283315844701,
+      "grad_norm": 0.4433589577674866,
+      "learning_rate": 6.109182147202329e-05,
+      "loss": 0.1643,
+      "mean_token_accuracy": 0.9574645280838012,
+      "num_tokens": 19017396.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.3462749213011542,
+      "grad_norm": 0.4165564179420471,
+      "learning_rate": 6.069553246086131e-05,
+      "loss": 0.1669,
+      "mean_token_accuracy": 0.9528910636901855,
+      "num_tokens": 19320603.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3515215110178384,
+      "grad_norm": 0.6303921341896057,
+      "learning_rate": 6.0294924436418496e-05,
+      "loss": 0.1796,
+      "mean_token_accuracy": 0.9498880624771118,
+      "num_tokens": 19599038.0,
+      "step": 335
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 953,
+  "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": 4.871895722016768e+17,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefabb0bc9c05c832856033880586c68ce019b321f1d535072277cd830a3cf96
+size 6417