Upload task output c15480fd-48d7-4667-8f6e-7e4d60211a32

.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/86e2e02ad6141127
+- 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": 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": [
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_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 sha256:3f1ce927e26f6eacfc950c5b8dad9b8b215a8eadced9b1551ab88b62910908a0
+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 @@
+460,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 +1,862 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.44145873320537427,
+  "eval_steps": 500,
+  "global_step": 460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0047984644913627635,
+      "grad_norm": 32.591251373291016,
+      "learning_rate": 8.401166180758017e-06,
+      "loss": 1.152,
+      "mean_token_accuracy": 0.730931556224823,
+      "num_tokens": 799294.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.009596928982725527,
+      "grad_norm": 3.1753504276275635,
+      "learning_rate": 1.8902623906705538e-05,
+      "loss": 0.5765,
+      "mean_token_accuracy": 0.8255371809005737,
+      "num_tokens": 1589820.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.014395393474088292,
+      "grad_norm": 2.811250686645508,
+      "learning_rate": 2.9404081632653062e-05,
+      "loss": 0.4173,
+      "mean_token_accuracy": 0.8512514710426331,
+      "num_tokens": 2378183.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.019193857965451054,
+      "grad_norm": 2.1911630630493164,
+      "learning_rate": 3.990553935860058e-05,
+      "loss": 0.3916,
+      "mean_token_accuracy": 0.8533002972602844,
+      "num_tokens": 3183115.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02399232245681382,
+      "grad_norm": 3.374872922897339,
+      "learning_rate": 5.0406997084548104e-05,
+      "loss": 0.3496,
+      "mean_token_accuracy": 0.8802085399627686,
+      "num_tokens": 3991639.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.028790786948176585,
+      "grad_norm": 2.2735555171966553,
+      "learning_rate": 6.090845481049563e-05,
+      "loss": 0.3253,
+      "mean_token_accuracy": 0.8847130298614502,
+      "num_tokens": 4786386.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03358925143953935,
+      "grad_norm": 1.5320895910263062,
+      "learning_rate": 7.140991253644314e-05,
+      "loss": 0.2999,
+      "mean_token_accuracy": 0.8903302311897278,
+      "num_tokens": 5575841.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03838771593090211,
+      "grad_norm": 2.4821479320526123,
+      "learning_rate": 7.350805771429152e-05,
+      "loss": 0.3198,
+      "mean_token_accuracy": 0.8918884038925171,
+      "num_tokens": 6351291.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04318618042226487,
+      "grad_norm": 1.3984349966049194,
+      "learning_rate": 7.349933866980902e-05,
+      "loss": 0.2805,
+      "mean_token_accuracy": 0.8992334485054017,
+      "num_tokens": 7127815.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04798464491362764,
+      "grad_norm": 0.9826128482818604,
+      "learning_rate": 7.348391492008383e-05,
+      "loss": 0.2894,
+      "mean_token_accuracy": 0.8915998458862304,
+      "num_tokens": 7928844.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.052783109404990404,
+      "grad_norm": 1.3426622152328491,
+      "learning_rate": 7.34617902179726e-05,
+      "loss": 0.2652,
+      "mean_token_accuracy": 0.9018174767494201,
+      "num_tokens": 8725094.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.05758157389635317,
+      "grad_norm": 0.9711771607398987,
+      "learning_rate": 7.343296994678593e-05,
+      "loss": 0.2739,
+      "mean_token_accuracy": 0.8992493629455567,
+      "num_tokens": 9521312.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06238003838771593,
+      "grad_norm": 0.986544132232666,
+      "learning_rate": 7.339746111897856e-05,
+      "loss": 0.2652,
+      "mean_token_accuracy": 0.8993094563484192,
+      "num_tokens": 10328920.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.0671785028790787,
+      "grad_norm": 1.0141630172729492,
+      "learning_rate": 7.335527237444306e-05,
+      "loss": 0.2582,
+      "mean_token_accuracy": 0.9018368721008301,
+      "num_tokens": 11129367.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07197696737044146,
+      "grad_norm": 1.9091362953186035,
+      "learning_rate": 7.330641397840763e-05,
+      "loss": 0.2532,
+      "mean_token_accuracy": 0.9050414323806762,
+      "num_tokens": 11925943.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.07677543186180422,
+      "grad_norm": 0.6851639747619629,
+      "learning_rate": 7.32508978189384e-05,
+      "loss": 0.2463,
+      "mean_token_accuracy": 0.9032415986061096,
+      "num_tokens": 12715832.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08157389635316699,
+      "grad_norm": 0.9245691299438477,
+      "learning_rate": 7.318873740404686e-05,
+      "loss": 0.2409,
+      "mean_token_accuracy": 0.9095496535301208,
+      "num_tokens": 13512930.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.08637236084452975,
+      "grad_norm": 1.114152431488037,
+      "learning_rate": 7.311994785840315e-05,
+      "loss": 0.236,
+      "mean_token_accuracy": 0.9103517293930053,
+      "num_tokens": 14310763.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.09117082533589252,
+      "grad_norm": 0.6443946361541748,
+      "learning_rate": 7.304454591965593e-05,
+      "loss": 0.2337,
+      "mean_token_accuracy": 0.9106445193290711,
+      "num_tokens": 15077828.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.09596928982725528,
+      "grad_norm": 0.8331279158592224,
+      "learning_rate": 7.296254993435989e-05,
+      "loss": 0.2407,
+      "mean_token_accuracy": 0.9029403924942017,
+      "num_tokens": 15876828.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.10076775431861804,
+      "grad_norm": 1.4841084480285645,
+      "learning_rate": 7.287397985351168e-05,
+      "loss": 0.245,
+      "mean_token_accuracy": 0.9005821108818054,
+      "num_tokens": 16684191.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.10556621880998081,
+      "grad_norm": 0.5702885985374451,
+      "learning_rate": 7.27788572276955e-05,
+      "loss": 0.2268,
+      "mean_token_accuracy": 0.905585777759552,
+      "num_tokens": 17499344.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.11036468330134357,
+      "grad_norm": 0.6955417990684509,
+      "learning_rate": 7.267720520183951e-05,
+      "loss": 0.228,
+      "mean_token_accuracy": 0.9089990615844726,
+      "num_tokens": 18311988.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.11516314779270634,
+      "grad_norm": 0.8562710881233215,
+      "learning_rate": 7.256904850958429e-05,
+      "loss": 0.2313,
+      "mean_token_accuracy": 0.9063257932662964,
+      "num_tokens": 19117619.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1199616122840691,
+      "grad_norm": 0.5443550944328308,
+      "learning_rate": 7.245441346726467e-05,
+      "loss": 0.2237,
+      "mean_token_accuracy": 0.9092974305152893,
+      "num_tokens": 19905936.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.12476007677543186,
+      "grad_norm": 0.6315863728523254,
+      "learning_rate": 7.233332796750656e-05,
+      "loss": 0.2152,
+      "mean_token_accuracy": 0.9135099887847901,
+      "num_tokens": 20687613.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.1295585412667946,
+      "grad_norm": 0.9352563619613647,
+      "learning_rate": 7.220582147244025e-05,
+      "loss": 0.217,
+      "mean_token_accuracy": 0.9076200485229492,
+      "num_tokens": 21492115.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.1343570057581574,
+      "grad_norm": 0.8867104649543762,
+      "learning_rate": 7.207192500653172e-05,
+      "loss": 0.2312,
+      "mean_token_accuracy": 0.9056767225265503,
+      "num_tokens": 22272734.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.13915547024952016,
+      "grad_norm": 0.6146453022956848,
+      "learning_rate": 7.193167114903386e-05,
+      "loss": 0.2261,
+      "mean_token_accuracy": 0.905716347694397,
+      "num_tokens": 23051480.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.14395393474088292,
+      "grad_norm": 1.0299674272537231,
+      "learning_rate": 7.178509402605946e-05,
+      "loss": 0.2346,
+      "mean_token_accuracy": 0.9057998061180115,
+      "num_tokens": 23843143.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14875239923224567,
+      "grad_norm": 0.810525119304657,
+      "learning_rate": 7.16322293022777e-05,
+      "loss": 0.2307,
+      "mean_token_accuracy": 0.9111165881156922,
+      "num_tokens": 24637524.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.15355086372360843,
+      "grad_norm": 0.4699096977710724,
+      "learning_rate": 7.147311417223636e-05,
+      "loss": 0.2297,
+      "mean_token_accuracy": 0.9072130799293519,
+      "num_tokens": 25434785.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.15834932821497122,
+      "grad_norm": 0.8143472671508789,
+      "learning_rate": 7.130778735131171e-05,
+      "loss": 0.2186,
+      "mean_token_accuracy": 0.9113067984580994,
+      "num_tokens": 26236980.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.16314779270633398,
+      "grad_norm": 0.5336032509803772,
+      "learning_rate": 7.113628906628854e-05,
+      "loss": 0.2186,
+      "mean_token_accuracy": 0.9100312232971192,
+      "num_tokens": 27022193.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.16794625719769674,
+      "grad_norm": 0.5377821922302246,
+      "learning_rate": 7.095866104557217e-05,
+      "loss": 0.2136,
+      "mean_token_accuracy": 0.9070743322372437,
+      "num_tokens": 27814657.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.1727447216890595,
+      "grad_norm": 0.4592677354812622,
+      "learning_rate": 7.077494650903529e-05,
+      "loss": 0.2115,
+      "mean_token_accuracy": 0.909694254398346,
+      "num_tokens": 28609492.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.17754318618042225,
+      "grad_norm": 0.9938281178474426,
+      "learning_rate": 7.058519015750186e-05,
+      "loss": 0.2187,
+      "mean_token_accuracy": 0.9073381423950195,
+      "num_tokens": 29402462.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.18234165067178504,
+      "grad_norm": 0.5051109194755554,
+      "learning_rate": 7.038943816187062e-05,
+      "loss": 0.2174,
+      "mean_token_accuracy": 0.9115898251533509,
+      "num_tokens": 30207426.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.1871401151631478,
+      "grad_norm": 0.6154143214225769,
+      "learning_rate": 7.018773815188091e-05,
+      "loss": 0.2008,
+      "mean_token_accuracy": 0.9124987602233887,
+      "num_tokens": 30985559.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.19193857965451055,
+      "grad_norm": 0.6422397494316101,
+      "learning_rate": 6.998013920452367e-05,
+      "loss": 0.2071,
+      "mean_token_accuracy": 0.9167937636375427,
+      "num_tokens": 31763312.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.1967370441458733,
+      "grad_norm": 0.5240011215209961,
+      "learning_rate": 6.976669183210004e-05,
+      "loss": 0.2196,
+      "mean_token_accuracy": 0.9105538129806519,
+      "num_tokens": 32546702.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.20153550863723607,
+      "grad_norm": 0.48978161811828613,
+      "learning_rate": 6.954744796993096e-05,
+      "loss": 0.2165,
+      "mean_token_accuracy": 0.9121721982955933,
+      "num_tokens": 33362696.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.20633397312859886,
+      "grad_norm": 0.6336808204650879,
+      "learning_rate": 6.932246096372041e-05,
+      "loss": 0.2257,
+      "mean_token_accuracy": 0.9081306457519531,
+      "num_tokens": 34162694.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.21113243761996162,
+      "grad_norm": 0.47279420495033264,
+      "learning_rate": 6.909178555657557e-05,
+      "loss": 0.2116,
+      "mean_token_accuracy": 0.9091696262359619,
+      "num_tokens": 34949786.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.21593090211132437,
+      "grad_norm": 0.5637255907058716,
+      "learning_rate": 6.885547787568674e-05,
+      "loss": 0.209,
+      "mean_token_accuracy": 0.9129250407218933,
+      "num_tokens": 35750169.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.22072936660268713,
+      "grad_norm": 1.205546498298645,
+      "learning_rate": 6.861359541867084e-05,
+      "loss": 0.2012,
+      "mean_token_accuracy": 0.9175987482070923,
+      "num_tokens": 36542344.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.2255278310940499,
+      "grad_norm": 0.8636100888252258,
+      "learning_rate": 6.836619703958119e-05,
+      "loss": 0.2041,
+      "mean_token_accuracy": 0.9169086694717408,
+      "num_tokens": 37351148.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.23032629558541268,
+      "grad_norm": 0.6066936254501343,
+      "learning_rate": 6.811334293458733e-05,
+      "loss": 0.1971,
+      "mean_token_accuracy": 0.9161781072616577,
+      "num_tokens": 38114955.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.23512476007677544,
+      "grad_norm": 0.5045466423034668,
+      "learning_rate": 6.78550946273283e-05,
+      "loss": 0.1991,
+      "mean_token_accuracy": 0.9162214040756226,
+      "num_tokens": 38908489.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.2399232245681382,
+      "grad_norm": 0.4524458646774292,
+      "learning_rate": 6.759151495394289e-05,
+      "loss": 0.2079,
+      "mean_token_accuracy": 0.9115633845329285,
+      "num_tokens": 39711511.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.24472168905950095,
+      "grad_norm": 0.3954505920410156,
+      "learning_rate": 6.732266804778059e-05,
+      "loss": 0.2071,
+      "mean_token_accuracy": 0.9117343664169312,
+      "num_tokens": 40499386.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.2495201535508637,
+      "grad_norm": 0.8436290621757507,
+      "learning_rate": 6.704861932379685e-05,
+      "loss": 0.2021,
+      "mean_token_accuracy": 0.9147255301475525,
+      "num_tokens": 41305685.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.2543186180422265,
+      "grad_norm": 0.47678083181381226,
+      "learning_rate": 6.676943546263647e-05,
+      "loss": 0.2084,
+      "mean_token_accuracy": 0.9162402510643005,
+      "num_tokens": 42099299.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.2591170825335892,
+      "grad_norm": 0.6068950295448303,
+      "learning_rate": 6.648518439440924e-05,
+      "loss": 0.2101,
+      "mean_token_accuracy": 0.9077034235000611,
+      "num_tokens": 42916607.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.263915547024952,
+      "grad_norm": 0.49654993414878845,
+      "learning_rate": 6.619593528216123e-05,
+      "loss": 0.2048,
+      "mean_token_accuracy": 0.9157393455505372,
+      "num_tokens": 43714272.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.2687140115163148,
+      "grad_norm": 0.7558993697166443,
+      "learning_rate": 6.590175850504635e-05,
+      "loss": 0.2071,
+      "mean_token_accuracy": 0.9156303167343139,
+      "num_tokens": 44506596.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.27351247600767753,
+      "grad_norm": 0.4323616623878479,
+      "learning_rate": 6.560272564120192e-05,
+      "loss": 0.1981,
+      "mean_token_accuracy": 0.9156986951828003,
+      "num_tokens": 45282564.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.2783109404990403,
+      "grad_norm": 0.3599900007247925,
+      "learning_rate": 6.52989094503325e-05,
+      "loss": 0.2077,
+      "mean_token_accuracy": 0.9143546223640442,
+      "num_tokens": 46098513.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.28310940499040305,
+      "grad_norm": 0.33340930938720703,
+      "learning_rate": 6.499038385600624e-05,
+      "loss": 0.1938,
+      "mean_token_accuracy": 0.9212781906127929,
+      "num_tokens": 46887829.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "grad_norm": 0.306796133518219,
+      "learning_rate": 6.467722392766801e-05,
+      "loss": 0.1959,
+      "mean_token_accuracy": 0.9193766951560974,
+      "num_tokens": 47691699.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2927063339731286,
+      "grad_norm": 0.3488706648349762,
+      "learning_rate": 6.435950586237382e-05,
+      "loss": 0.2066,
+      "mean_token_accuracy": 0.9102665543556213,
+      "num_tokens": 48486193.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.29750479846449135,
+      "grad_norm": 0.5964604020118713,
+      "learning_rate": 6.403730696625067e-05,
+      "loss": 0.1893,
+      "mean_token_accuracy": 0.9162996411323547,
+      "num_tokens": 49288543.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.30230326295585414,
+      "grad_norm": 0.3607555627822876,
+      "learning_rate": 6.371070563568684e-05,
+      "loss": 0.1923,
+      "mean_token_accuracy": 0.9159826397895813,
+      "num_tokens": 50087277.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.30710172744721687,
+      "grad_norm": 0.5310798287391663,
+      "learning_rate": 6.337978133825659e-05,
+      "loss": 0.1871,
+      "mean_token_accuracy": 0.9196419477462768,
+      "num_tokens": 50868001.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.31190019193857965,
+      "grad_norm": 0.5248069167137146,
+      "learning_rate": 6.304461459338445e-05,
+      "loss": 0.2029,
+      "mean_token_accuracy": 0.9152723550796509,
+      "num_tokens": 51662419.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.31669865642994244,
+      "grad_norm": 0.3722710907459259,
+      "learning_rate": 6.270528695275349e-05,
+      "loss": 0.201,
+      "mean_token_accuracy": 0.91062912940979,
+      "num_tokens": 52446100.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.32149712092130517,
+      "grad_norm": 0.36808404326438904,
+      "learning_rate": 6.236188098046236e-05,
+      "loss": 0.2001,
+      "mean_token_accuracy": 0.9152203679084778,
+      "num_tokens": 53244169.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.32629558541266795,
+      "grad_norm": 0.25250986218452454,
+      "learning_rate": 6.201448023293617e-05,
+      "loss": 0.2013,
+      "mean_token_accuracy": 0.911141550540924,
+      "num_tokens": 54040490.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.3310940499040307,
+      "grad_norm": 0.31841546297073364,
+      "learning_rate": 6.166316923859576e-05,
+      "loss": 0.2054,
+      "mean_token_accuracy": 0.9115605592727661,
+      "num_tokens": 54866178.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.33589251439539347,
+      "grad_norm": 26.990447998046875,
+      "learning_rate": 6.130803347729047e-05,
+      "loss": 0.1908,
+      "mean_token_accuracy": 0.9202599406242371,
+      "num_tokens": 55653730.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.34069097888675626,
+      "grad_norm": 0.30666667222976685,
+      "learning_rate": 6.094915935949953e-05,
+      "loss": 0.1885,
+      "mean_token_accuracy": 0.9189923286437989,
+      "num_tokens": 56444777.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.345489443378119,
+      "grad_norm": 0.4795357882976532,
+      "learning_rate": 6.0586634205306915e-05,
+      "loss": 0.1956,
+      "mean_token_accuracy": 0.9183237552642822,
+      "num_tokens": 57253377.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3502879078694818,
+      "grad_norm": 0.23285166919231415,
+      "learning_rate": 6.022054622315494e-05,
+      "loss": 0.1871,
+      "mean_token_accuracy": 0.9199147820472717,
+      "num_tokens": 58042662.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.3550863723608445,
+      "grad_norm": 0.4314901530742645,
+      "learning_rate": 5.9850984488381596e-05,
+      "loss": 0.1962,
+      "mean_token_accuracy": 0.9169607877731323,
+      "num_tokens": 58831799.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3598848368522073,
+      "grad_norm": 0.3640917241573334,
+      "learning_rate": 5.94780389215471e-05,
+      "loss": 0.1933,
+      "mean_token_accuracy": 0.9174081683158875,
+      "num_tokens": 59645117.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.3646833013435701,
+      "grad_norm": 0.2740689516067505,
+      "learning_rate": 5.910180026655467e-05,
+      "loss": 0.1907,
+      "mean_token_accuracy": 0.9203463912010192,
+      "num_tokens": 60430338.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.3694817658349328,
+      "grad_norm": 0.2786269783973694,
+      "learning_rate": 5.872236006857106e-05,
+      "loss": 0.185,
+      "mean_token_accuracy": 0.9187370657920837,
+      "num_tokens": 61209084.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.3742802303262956,
+      "grad_norm": 0.24551868438720703,
+      "learning_rate": 5.833981065175203e-05,
+      "loss": 0.1857,
+      "mean_token_accuracy": 0.9178588390350342,
+      "num_tokens": 62007757.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.3790786948176583,
+      "grad_norm": 0.6173501014709473,
+      "learning_rate": 5.7954245096778384e-05,
+      "loss": 0.189,
+      "mean_token_accuracy": 0.9154422998428344,
+      "num_tokens": 62797095.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.3838771593090211,
+      "grad_norm": 0.22034378349781036,
+      "learning_rate": 5.756575721820784e-05,
+      "loss": 0.2012,
+      "mean_token_accuracy": 0.909715449810028,
+      "num_tokens": 63594142.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.3886756238003839,
+      "grad_norm": 0.39530545473098755,
+      "learning_rate": 5.717444154164841e-05,
+      "loss": 0.1912,
+      "mean_token_accuracy": 0.9185901284217834,
+      "num_tokens": 64395013.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.3934740882917466,
+      "grad_norm": 0.5130671262741089,
+      "learning_rate": 5.678039328075872e-05,
+      "loss": 0.2055,
+      "mean_token_accuracy": 0.9089265704154968,
+      "num_tokens": 65183834.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.3982725527831094,
+      "grad_norm": 0.25764885544776917,
+      "learning_rate": 5.638370831408094e-05,
+      "loss": 0.201,
+      "mean_token_accuracy": 0.9145246505737304,
+      "num_tokens": 65971151.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.40307101727447214,
+      "grad_norm": 1.2055509090423584,
+      "learning_rate": 5.5984483161711884e-05,
+      "loss": 0.2015,
+      "mean_token_accuracy": 0.9111255884170533,
+      "num_tokens": 66785774.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.40786948176583493,
+      "grad_norm": 0.25073662400245667,
+      "learning_rate": 5.5582814961818154e-05,
+      "loss": 0.1953,
+      "mean_token_accuracy": 0.9116534113883972,
+      "num_tokens": 67574032.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.4126679462571977,
+      "grad_norm": 0.46643003821372986,
+      "learning_rate": 5.5178801447000696e-05,
+      "loss": 0.2133,
+      "mean_token_accuracy": 0.9100813388824462,
+      "num_tokens": 68372777.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.41746641074856045,
+      "grad_norm": 0.20133262872695923,
+      "learning_rate": 5.4772540920514845e-05,
+      "loss": 0.1939,
+      "mean_token_accuracy": 0.916495680809021,
+      "num_tokens": 69170895.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.42226487523992323,
+      "grad_norm": 0.23032309114933014,
+      "learning_rate": 5.4364132232351584e-05,
+      "loss": 0.2009,
+      "mean_token_accuracy": 0.9147676229476929,
+      "num_tokens": 69973680.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.42706333973128596,
+      "grad_norm": 0.33535414934158325,
+      "learning_rate": 5.395367475518553e-05,
+      "loss": 0.1898,
+      "mean_token_accuracy": 0.9177168607711792,
+      "num_tokens": 70753938.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.43186180422264875,
+      "grad_norm": 0.41969069838523865,
+      "learning_rate": 5.3541268360196046e-05,
+      "loss": 0.1918,
+      "mean_token_accuracy": 0.91667799949646,
+      "num_tokens": 71546158.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.43666026871401153,
+      "grad_norm": 0.20039504766464233,
+      "learning_rate": 5.3127013392766776e-05,
+      "loss": 0.1955,
+      "mean_token_accuracy": 0.9168407678604126,
+      "num_tokens": 72367912.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.44145873320537427,
+      "grad_norm": 0.2675475776195526,
+      "learning_rate": 5.271101064807009e-05,
+      "loss": 0.1944,
+      "mean_token_accuracy": 0.9160084128379822,
+      "num_tokens": 73158030.0,
+      "step": 460
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1042,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2135909642812785e+18,
+  "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 sha256:936a56b0843e28a6df9bd35bdbe564dc8d384c050bcdcc2978320afb7824a279
+size 6545