Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-945/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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-Coder-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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_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 sha256:1dfd7fd939deef499d38be9c540585f139549a88e891e2a576a8742f49dd64d7
+size 119801528

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 %}

checkpoint-800/README.md

@@ -0,0 +1,209 @@
+---
+base_model: /home/abubnov/models/qwen2.5-coder-3b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/abubnov/models/qwen2.5-coder-3b
+- 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

checkpoint-800/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/abubnov/models/qwen2.5-coder-3b",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad2fd6ef13205de8bd934dbab414e4704b03a69c359b27da93b4aafe55033c2
+size 119801528

checkpoint-800/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 %}

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d481e3ed49b541a4fee952f11606819c7092cd936d5e1d12461901145b225a8f
+size 239892858

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78d6e2dcd9575c3d0177be9f586b5c353b276ac90c1f2cdabbb177fc2781a1f
+size 14244

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8804bb16a95c6215e163e5607c21273c5f5e8569936763fccf81c35efa28a2
+size 1064

checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-800/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5396825396825395,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7227754831314086,
+      "epoch": 0.031746031746031744,
+      "grad_norm": 1.1366468667984009,
+      "learning_rate": 9e-05,
+      "loss": 2.8658143997192385,
+      "mean_token_accuracy": 0.5204534128308296,
+      "num_tokens": 5666.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1383487015962601,
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.24305662512779236,
+      "learning_rate": 0.00019,
+      "loss": 1.157881259918213,
+      "mean_token_accuracy": 0.747118815779686,
+      "num_tokens": 11228.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.6970422968268395,
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.16163931787014008,
+      "learning_rate": 0.00019995328702916715,
+      "loss": 0.7050998210906982,
+      "mean_token_accuracy": 0.8266415625810624,
+      "num_tokens": 16938.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.5631089679896831,
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.1934506595134735,
+      "learning_rate": 0.00019979186612193827,
+      "loss": 0.518431282043457,
+      "mean_token_accuracy": 0.8579314455389977,
+      "num_tokens": 22355.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.4461665920913219,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.19076411426067352,
+      "learning_rate": 0.00019951534671117278,
+      "loss": 0.4521681785583496,
+      "mean_token_accuracy": 0.8751249805092811,
+      "num_tokens": 28033.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.4643573462963104,
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.15169695019721985,
+      "learning_rate": 0.0001991240477303831,
+      "loss": 0.4400327682495117,
+      "mean_token_accuracy": 0.8792907446622849,
+      "num_tokens": 33491.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.365592984110117,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.19082750380039215,
+      "learning_rate": 0.00019861842049818747,
+      "loss": 0.3689171075820923,
+      "mean_token_accuracy": 0.8955714568495751,
+      "num_tokens": 39334.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.3994899570941925,
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.22246494889259338,
+      "learning_rate": 0.0001979990481977654,
+      "loss": 0.38646960258483887,
+      "mean_token_accuracy": 0.8857234820723534,
+      "num_tokens": 44818.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.366699343547225,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.10320783406496048,
+      "learning_rate": 0.00019726664520422255,
+      "loss": 0.3445246458053589,
+      "mean_token_accuracy": 0.8934612423181534,
+      "num_tokens": 50677.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.3574436727911234,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.11693304032087326,
+      "learning_rate": 0.00019642205626064092,
+      "loss": 0.35196170806884763,
+      "mean_token_accuracy": 0.8924582287669182,
+      "num_tokens": 56210.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.3415878858417273,
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.1074284091591835,
+      "learning_rate": 0.00019546625550376416,
+      "loss": 0.33331873416900637,
+      "mean_token_accuracy": 0.8991662472486496,
+      "num_tokens": 62063.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.32437219470739365,
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.11062154173851013,
+      "learning_rate": 0.00019440034534044237,
+      "loss": 0.30573971271514894,
+      "mean_token_accuracy": 0.9001727238297462,
+      "num_tokens": 67992.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.3190695196390152,
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.11065158247947693,
+      "learning_rate": 0.00019322555517613187,
+      "loss": 0.31588168144226075,
+      "mean_token_accuracy": 0.9023894265294075,
+      "num_tokens": 73587.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.32216995768249035,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.14468607306480408,
+      "learning_rate": 0.0001919432399969165,
+      "loss": 0.3158241271972656,
+      "mean_token_accuracy": 0.9021097734570503,
+      "num_tokens": 79119.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.31658302918076514,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.09196920692920685,
+      "learning_rate": 0.00019055487880668634,
+      "loss": 0.30810258388519285,
+      "mean_token_accuracy": 0.9032961145043373,
+      "num_tokens": 84949.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.3345262251794338,
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.0972098857164383,
+      "learning_rate": 0.00018906207292127578,
+      "loss": 0.3160905122756958,
+      "mean_token_accuracy": 0.9008760690689087,
+      "num_tokens": 90418.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.276963048055768,
+      "epoch": 0.5396825396825397,
+      "grad_norm": 0.0893082544207573,
+      "learning_rate": 0.00018746654412152888,
+      "loss": 0.28638601303100586,
+      "mean_token_accuracy": 0.9065180748701096,
+      "num_tokens": 96436.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.324129705876112,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07999411970376968,
+      "learning_rate": 0.00018577013266742206,
+      "loss": 0.305109429359436,
+      "mean_token_accuracy": 0.9052717864513398,
+      "num_tokens": 102223.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.3255684822797775,
+      "epoch": 0.6031746031746031,
+      "grad_norm": 0.09610118716955185,
+      "learning_rate": 0.00018397479517553484,
+      "loss": 0.3202303647994995,
+      "mean_token_accuracy": 0.8935918360948563,
+      "num_tokens": 107629.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.31572582088410855,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.12048293650150299,
+      "learning_rate": 0.00018208260236231622,
+      "loss": 0.30115087032318116,
+      "mean_token_accuracy": 0.9004874512553215,
+      "num_tokens": 113055.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.30431781969964505,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.10186965018510818,
+      "learning_rate": 0.00018009573665575025,
+      "loss": 0.30716614723205565,
+      "mean_token_accuracy": 0.8994262963533401,
+      "num_tokens": 118543.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.2934673883020878,
+      "epoch": 0.6984126984126984,
+      "grad_norm": 0.06708242744207382,
+      "learning_rate": 0.00017801648967817496,
+      "loss": 0.28838367462158204,
+      "mean_token_accuracy": 0.9054950103163719,
+      "num_tokens": 124352.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.33580498173832896,
+      "epoch": 0.7301587301587301,
+      "grad_norm": 0.08463180810213089,
+      "learning_rate": 0.00017584725960315798,
+      "loss": 0.31860477924346925,
+      "mean_token_accuracy": 0.8984977260231972,
+      "num_tokens": 129580.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.28108432702720165,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.08562931418418884,
+      "learning_rate": 0.00017359054838947776,
+      "loss": 0.28187878131866456,
+      "mean_token_accuracy": 0.9082333862781524,
+      "num_tokens": 135436.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.2990231603384018,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.09380577504634857,
+      "learning_rate": 0.0001712489588954002,
+      "loss": 0.28119051456451416,
+      "mean_token_accuracy": 0.9102276802062989,
+      "num_tokens": 141182.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.30382733382284643,
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.07645034790039062,
+      "learning_rate": 0.00016882519187657948,
+      "loss": 0.29003133773803713,
+      "mean_token_accuracy": 0.9052957415580749,
+      "num_tokens": 146683.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.27974450327455996,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.07793932408094406,
+      "learning_rate": 0.00016632204287104517,
+      "loss": 0.28378610610961913,
+      "mean_token_accuracy": 0.9071699053049087,
+      "num_tokens": 152464.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.27756214514374733,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.08467274904251099,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.27063760757446287,
+      "mean_token_accuracy": 0.9070401296019555,
+      "num_tokens": 158366.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.2848128478974104,
+      "epoch": 0.9206349206349206,
+      "grad_norm": 0.08799296617507935,
+      "learning_rate": 0.00016108923551222954,
+      "loss": 0.2736989974975586,
+      "mean_token_accuracy": 0.9117912963032723,
+      "num_tokens": 164354.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.2887926273047924,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.08142666518688202,
+      "learning_rate": 0.00015836561260371642,
+      "loss": 0.2762760639190674,
+      "mean_token_accuracy": 0.9110032752156257,
+      "num_tokens": 170194.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.2911578442901373,
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.07968642562627792,
+      "learning_rate": 0.00015557467163683093,
+      "loss": 0.28809950351715086,
+      "mean_token_accuracy": 0.9043565198779107,
+      "num_tokens": 175853.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.2943920481950045,
+      "epoch": 1.0158730158730158,
+      "grad_norm": 0.08365320414304733,
+      "learning_rate": 0.00015271963164275495,
+      "loss": 0.27865099906921387,
+      "mean_token_accuracy": 0.9042463362216949,
+      "num_tokens": 181430.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.2911732569336891,
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.08910917490720749,
+      "learning_rate": 0.00014980378558356668,
+      "loss": 0.28408806324005126,
+      "mean_token_accuracy": 0.9075512051582336,
+      "num_tokens": 186823.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.27633472084999083,
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.054748956114053726,
+      "learning_rate": 0.00014683049655418566,
+      "loss": 0.27398593425750734,
+      "mean_token_accuracy": 0.9088717252016068,
+      "num_tokens": 192618.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.29899220876395705,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.1026228591799736,
+      "learning_rate": 0.00014380319390342713,
+      "loss": 0.27963986396789553,
+      "mean_token_accuracy": 0.9076534271240234,
+      "num_tokens": 198264.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.27999303340911863,
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.07460694015026093,
+      "learning_rate": 0.00014072536927864067,
+      "loss": 0.27371869087219236,
+      "mean_token_accuracy": 0.9113201141357422,
+      "num_tokens": 203999.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.2836035009473562,
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.05994534492492676,
+      "learning_rate": 0.0001376005725984943,
+      "loss": 0.2734062671661377,
+      "mean_token_accuracy": 0.9102857768535614,
+      "num_tokens": 209875.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.27055577710270884,
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.15462082624435425,
+      "learning_rate": 0.00013443240795854932,
+      "loss": 0.26778972148895264,
+      "mean_token_accuracy": 0.9114238187670708,
+      "num_tokens": 215695.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.28204834908246995,
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.08471743762493134,
+      "learning_rate": 0.00013122452947434828,
+      "loss": 0.2707425594329834,
+      "mean_token_accuracy": 0.9076912581920624,
+      "num_tokens": 221300.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.2921843770891428,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.06258587539196014,
+      "learning_rate": 0.00012798063706681058,
+      "loss": 0.2830580949783325,
+      "mean_token_accuracy": 0.9059961527585983,
+      "num_tokens": 226770.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.27955467700958253,
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.11677869409322739,
+      "learning_rate": 0.00012470447219479713,
+      "loss": 0.2767421960830688,
+      "mean_token_accuracy": 0.9056397631764412,
+      "num_tokens": 232493.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.2816464897245169,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.20853769779205322,
+      "learning_rate": 0.00012139981353976524,
+      "loss": 0.2793292760848999,
+      "mean_token_accuracy": 0.9049514532089233,
+      "num_tokens": 238158.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.2885897036641836,
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.07681034505367279,
+      "learning_rate": 0.00011807047264749189,
+      "loss": 0.2701925039291382,
+      "mean_token_accuracy": 0.9056044742465019,
+      "num_tokens": 243766.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.28189543783664706,
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.06424044817686081,
+      "learning_rate": 0.0001147202895318916,
+      "loss": 0.2593745470046997,
+      "mean_token_accuracy": 0.9096330463886261,
+      "num_tokens": 249691.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.28342911675572396,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.1278621256351471,
+      "learning_rate": 0.0001113531282459996,
+      "loss": 0.28381073474884033,
+      "mean_token_accuracy": 0.9061736151576042,
+      "num_tokens": 255233.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.28202038891613485,
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.06751440465450287,
+      "learning_rate": 0.00010797287242522858,
+      "loss": 0.27419445514678953,
+      "mean_token_accuracy": 0.9094104260206223,
+      "num_tokens": 260859.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.27363024093210697,
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.06995254009962082,
+      "learning_rate": 0.00010458342080803956,
+      "loss": 0.2693720817565918,
+      "mean_token_accuracy": 0.9083198413252831,
+      "num_tokens": 266554.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.2726555660367012,
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.09802178293466568,
+      "learning_rate": 0.00010118868273919284,
+      "loss": 0.2669402837753296,
+      "mean_token_accuracy": 0.9095989406108856,
+      "num_tokens": 272262.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.2873748764395714,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.059039562940597534,
+      "learning_rate": 9.779257366076608e-05,
+      "loss": 0.27708461284637453,
+      "mean_token_accuracy": 0.907341231405735,
+      "num_tokens": 277809.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.28209226317703723,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.07545655220746994,
+      "learning_rate": 9.439901059613973e-05,
+      "loss": 0.2581690549850464,
+      "mean_token_accuracy": 0.9121931448578835,
+      "num_tokens": 283664.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.272804581746459,
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.07380068302154541,
+      "learning_rate": 9.101190763215848e-05,
+      "loss": 0.26886236667633057,
+      "mean_token_accuracy": 0.9086462184786797,
+      "num_tokens": 289371.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.28114392757415774,
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.078324094414711,
+      "learning_rate": 8.763517140467981e-05,
+      "loss": 0.27371978759765625,
+      "mean_token_accuracy": 0.9067111536860466,
+      "num_tokens": 294986.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.28820689432322977,
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.10492384433746338,
+      "learning_rate": 8.42726965927164e-05,
+      "loss": 0.2796510696411133,
+      "mean_token_accuracy": 0.9053183734416962,
+      "num_tokens": 300487.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.26856297068297863,
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.0673430785536766,
+      "learning_rate": 8.092836142636932e-05,
+      "loss": 0.2611644506454468,
+      "mean_token_accuracy": 0.9129276722669601,
+      "num_tokens": 306372.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.29797249287366867,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.06676393002271652,
+      "learning_rate": 7.760602321373322e-05,
+      "loss": 0.28323547840118407,
+      "mean_token_accuracy": 0.9016937434673309,
+      "num_tokens": 311775.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.2688152402639389,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.08283069729804993,
+      "learning_rate": 7.43095138919326e-05,
+      "loss": 0.2640655517578125,
+      "mean_token_accuracy": 0.902265977859497,
+      "num_tokens": 317591.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.29286824017763136,
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.05436806008219719,
+      "learning_rate": 7.104263560742067e-05,
+      "loss": 0.27632272243499756,
+      "mean_token_accuracy": 0.9019043281674385,
+      "num_tokens": 323077.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.2781177669763565,
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.05500198155641556,
+      "learning_rate": 6.780915633063827e-05,
+      "loss": 0.27087790966033937,
+      "mean_token_accuracy": 0.9046190366148948,
+      "num_tokens": 328692.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.27223661690950396,
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.07625019550323486,
+      "learning_rate": 6.461280551009096e-05,
+      "loss": 0.26836280822753905,
+      "mean_token_accuracy": 0.9067093715071678,
+      "num_tokens": 334381.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.27323946319520476,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.072757288813591,
+      "learning_rate": 6.145726977085669e-05,
+      "loss": 0.2648139953613281,
+      "mean_token_accuracy": 0.90970708578825,
+      "num_tokens": 340111.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.2718470089137554,
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.06298787891864777,
+      "learning_rate": 5.8346188662485536e-05,
+      "loss": 0.2643317461013794,
+      "mean_token_accuracy": 0.904901784658432,
+      "num_tokens": 345896.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.28305209055542946,
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.0733041912317276,
+      "learning_rate": 5.528315046119544e-05,
+      "loss": 0.2636791944503784,
+      "mean_token_accuracy": 0.9123735308647156,
+      "num_tokens": 351673.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.2617435783147812,
+      "epoch": 2.0,
+      "grad_norm": 0.07501133531332016,
+      "learning_rate": 5.227168803120619e-05,
+      "loss": 0.26242828369140625,
+      "mean_token_accuracy": 0.9104171916842461,
+      "num_tokens": 357322.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.26802175454795363,
+      "epoch": 2.0317460317460316,
+      "grad_norm": 0.04739142954349518,
+      "learning_rate": 4.931527474998444e-05,
+      "loss": 0.25396668910980225,
+      "mean_token_accuracy": 0.9118479937314987,
+      "num_tokens": 363159.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.27135957442224024,
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.07097524404525757,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.25786685943603516,
+      "mean_token_accuracy": 0.9111087501049042,
+      "num_tokens": 368909.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.2646398801356554,
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.05924823880195618,
+      "learning_rate": 4.35811677463153e-05,
+      "loss": 0.2504109382629395,
+      "mean_token_accuracy": 0.9110997319221497,
+      "num_tokens": 374682.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.27993031218647957,
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.058568164706230164,
+      "learning_rate": 4.081008766043856e-05,
+      "loss": 0.2658329963684082,
+      "mean_token_accuracy": 0.906340380012989,
+      "num_tokens": 380133.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.270343242585659,
+      "epoch": 2.1587301587301586,
+      "grad_norm": 0.07652401179075241,
+      "learning_rate": 3.810727636839739e-05,
+      "loss": 0.26411163806915283,
+      "mean_token_accuracy": 0.9062801778316498,
+      "num_tokens": 385694.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.26379697881639,
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.06572549045085907,
+      "learning_rate": 3.547585125387394e-05,
+      "loss": 0.26352672576904296,
+      "mean_token_accuracy": 0.9080587550997734,
+      "num_tokens": 391353.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.2779304336756468,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.0634949803352356,
+      "learning_rate": 3.2918847364759556e-05,
+      "loss": 0.26194489002227783,
+      "mean_token_accuracy": 0.9062734320759773,
+      "num_tokens": 396876.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.2617481011897326,
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.05917736515402794,
+      "learning_rate": 3.0439213912574304e-05,
+      "loss": 0.26019647121429446,
+      "mean_token_accuracy": 0.9100751489400863,
+      "num_tokens": 402577.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.2559076685458422,
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.07124771922826767,
+      "learning_rate": 2.8039810870888762e-05,
+      "loss": 0.25075175762176516,
+      "mean_token_accuracy": 0.9124972775578499,
+      "num_tokens": 408405.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.2648021761327982,
+      "epoch": 2.317460317460317,
+      "grad_norm": 0.06209827587008476,
+      "learning_rate": 2.5723405676671584e-05,
+      "loss": 0.24744985103607178,
+      "mean_token_accuracy": 0.915162692964077,
+      "num_tokens": 414204.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.2807385498657823,
+      "epoch": 2.3492063492063493,
+      "grad_norm": 0.0612325593829155,
+      "learning_rate": 2.349267003836757e-05,
+      "loss": 0.26713953018188474,
+      "mean_token_accuracy": 0.9052686139941215,
+      "num_tokens": 419721.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.2669257506728172,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.06792369484901428,
+      "learning_rate": 2.1350176854387492e-05,
+      "loss": 0.26758475303649903,
+      "mean_token_accuracy": 0.9066236048936844,
+      "num_tokens": 425297.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.2817291833460331,
+      "epoch": 2.4126984126984126,
+      "grad_norm": 0.07440292090177536,
+      "learning_rate": 1.9298397245564125e-05,
+      "loss": 0.26947109699249266,
+      "mean_token_accuracy": 0.9070651844143868,
+      "num_tokens": 430708.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.2823494378477335,
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.08691683411598206,
+      "learning_rate": 1.733969770499697e-05,
+      "loss": 0.2715198040008545,
+      "mean_token_accuracy": 0.9081029698252678,
+      "num_tokens": 436157.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.2502023309469223,
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.057402949780225754,
+      "learning_rate": 1.547633736857308e-05,
+      "loss": 0.24733474254608154,
+      "mean_token_accuracy": 0.9128626599907875,
+      "num_tokens": 442078.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.2789640363305807,
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.08202935755252838,
+      "learning_rate": 1.3710465409312356e-05,
+      "loss": 0.2598316431045532,
+      "mean_token_accuracy": 0.9110502526164055,
+      "num_tokens": 447709.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.2569702621549368,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.0657891258597374,
+      "learning_rate": 1.2044118558542183e-05,
+      "loss": 0.2518922805786133,
+      "mean_token_accuracy": 0.913571135699749,
+      "num_tokens": 453518.0,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0863910427885568e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb601ecd2bf594898b1129204a988d020e0fdb23c6d6e6733f079e88458dd3d
+size 5176

checkpoint-945/README.md

@@ -0,0 +1,209 @@
+---
+base_model: /home/abubnov/models/qwen2.5-coder-3b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/abubnov/models/qwen2.5-coder-3b
+- 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

checkpoint-945/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/abubnov/models/qwen2.5-coder-3b",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-945/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfd7fd939deef499d38be9c540585f139549a88e891e2a576a8742f49dd64d7
+size 119801528

checkpoint-945/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 %}

checkpoint-945/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4787e9094d70de781a5845174717cb1fbe26fa26a42314c799d4620da962c6
+size 239892858

checkpoint-945/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577dffedea14e4943031f7fa8384abd7e5877404899ede90492d0de9eac57fa4
+size 14244

checkpoint-945/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aeea9621b1c05fb9d17060ccfa15672bc0b0a478b1c25e2ee28cbf69f61cccd
+size 1064

checkpoint-945/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-945/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-945/trainer_state.json

@@ -0,0 +1,974 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 945,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7227754831314086,
+      "epoch": 0.031746031746031744,
+      "grad_norm": 1.1366468667984009,
+      "learning_rate": 9e-05,
+      "loss": 2.8658143997192385,
+      "mean_token_accuracy": 0.5204534128308296,
+      "num_tokens": 5666.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1383487015962601,
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.24305662512779236,
+      "learning_rate": 0.00019,
+      "loss": 1.157881259918213,
+      "mean_token_accuracy": 0.747118815779686,
+      "num_tokens": 11228.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.6970422968268395,
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.16163931787014008,
+      "learning_rate": 0.00019995328702916715,
+      "loss": 0.7050998210906982,
+      "mean_token_accuracy": 0.8266415625810624,
+      "num_tokens": 16938.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.5631089679896831,
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.1934506595134735,
+      "learning_rate": 0.00019979186612193827,
+      "loss": 0.518431282043457,
+      "mean_token_accuracy": 0.8579314455389977,
+      "num_tokens": 22355.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.4461665920913219,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.19076411426067352,
+      "learning_rate": 0.00019951534671117278,
+      "loss": 0.4521681785583496,
+      "mean_token_accuracy": 0.8751249805092811,
+      "num_tokens": 28033.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.4643573462963104,
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.15169695019721985,
+      "learning_rate": 0.0001991240477303831,
+      "loss": 0.4400327682495117,
+      "mean_token_accuracy": 0.8792907446622849,
+      "num_tokens": 33491.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.365592984110117,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.19082750380039215,
+      "learning_rate": 0.00019861842049818747,
+      "loss": 0.3689171075820923,
+      "mean_token_accuracy": 0.8955714568495751,
+      "num_tokens": 39334.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.3994899570941925,
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.22246494889259338,
+      "learning_rate": 0.0001979990481977654,
+      "loss": 0.38646960258483887,
+      "mean_token_accuracy": 0.8857234820723534,
+      "num_tokens": 44818.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.366699343547225,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.10320783406496048,
+      "learning_rate": 0.00019726664520422255,
+      "loss": 0.3445246458053589,
+      "mean_token_accuracy": 0.8934612423181534,
+      "num_tokens": 50677.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.3574436727911234,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.11693304032087326,
+      "learning_rate": 0.00019642205626064092,
+      "loss": 0.35196170806884763,
+      "mean_token_accuracy": 0.8924582287669182,
+      "num_tokens": 56210.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.3415878858417273,
+      "epoch": 0.3492063492063492,
+      "grad_norm": 0.1074284091591835,
+      "learning_rate": 0.00019546625550376416,
+      "loss": 0.33331873416900637,
+      "mean_token_accuracy": 0.8991662472486496,
+      "num_tokens": 62063.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.32437219470739365,
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.11062154173851013,
+      "learning_rate": 0.00019440034534044237,
+      "loss": 0.30573971271514894,
+      "mean_token_accuracy": 0.9001727238297462,
+      "num_tokens": 67992.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.3190695196390152,
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.11065158247947693,
+      "learning_rate": 0.00019322555517613187,
+      "loss": 0.31588168144226075,
+      "mean_token_accuracy": 0.9023894265294075,
+      "num_tokens": 73587.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.32216995768249035,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.14468607306480408,
+      "learning_rate": 0.0001919432399969165,
+      "loss": 0.3158241271972656,
+      "mean_token_accuracy": 0.9021097734570503,
+      "num_tokens": 79119.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.31658302918076514,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.09196920692920685,
+      "learning_rate": 0.00019055487880668634,
+      "loss": 0.30810258388519285,
+      "mean_token_accuracy": 0.9032961145043373,
+      "num_tokens": 84949.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.3345262251794338,
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.0972098857164383,
+      "learning_rate": 0.00018906207292127578,
+      "loss": 0.3160905122756958,
+      "mean_token_accuracy": 0.9008760690689087,
+      "num_tokens": 90418.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.276963048055768,
+      "epoch": 0.5396825396825397,
+      "grad_norm": 0.0893082544207573,
+      "learning_rate": 0.00018746654412152888,
+      "loss": 0.28638601303100586,
+      "mean_token_accuracy": 0.9065180748701096,
+      "num_tokens": 96436.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.324129705876112,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07999411970376968,
+      "learning_rate": 0.00018577013266742206,
+      "loss": 0.305109429359436,
+      "mean_token_accuracy": 0.9052717864513398,
+      "num_tokens": 102223.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.3255684822797775,
+      "epoch": 0.6031746031746031,
+      "grad_norm": 0.09610118716955185,
+      "learning_rate": 0.00018397479517553484,
+      "loss": 0.3202303647994995,
+      "mean_token_accuracy": 0.8935918360948563,
+      "num_tokens": 107629.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.31572582088410855,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.12048293650150299,
+      "learning_rate": 0.00018208260236231622,
+      "loss": 0.30115087032318116,
+      "mean_token_accuracy": 0.9004874512553215,
+      "num_tokens": 113055.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.30431781969964505,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.10186965018510818,
+      "learning_rate": 0.00018009573665575025,
+      "loss": 0.30716614723205565,
+      "mean_token_accuracy": 0.8994262963533401,
+      "num_tokens": 118543.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.2934673883020878,
+      "epoch": 0.6984126984126984,
+      "grad_norm": 0.06708242744207382,
+      "learning_rate": 0.00017801648967817496,
+      "loss": 0.28838367462158204,
+      "mean_token_accuracy": 0.9054950103163719,
+      "num_tokens": 124352.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.33580498173832896,
+      "epoch": 0.7301587301587301,
+      "grad_norm": 0.08463180810213089,
+      "learning_rate": 0.00017584725960315798,
+      "loss": 0.31860477924346925,
+      "mean_token_accuracy": 0.8984977260231972,
+      "num_tokens": 129580.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.28108432702720165,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.08562931418418884,
+      "learning_rate": 0.00017359054838947776,
+      "loss": 0.28187878131866456,
+      "mean_token_accuracy": 0.9082333862781524,
+      "num_tokens": 135436.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.2990231603384018,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.09380577504634857,
+      "learning_rate": 0.0001712489588954002,
+      "loss": 0.28119051456451416,
+      "mean_token_accuracy": 0.9102276802062989,
+      "num_tokens": 141182.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.30382733382284643,
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.07645034790039062,
+      "learning_rate": 0.00016882519187657948,
+      "loss": 0.29003133773803713,
+      "mean_token_accuracy": 0.9052957415580749,
+      "num_tokens": 146683.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.27974450327455996,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.07793932408094406,
+      "learning_rate": 0.00016632204287104517,
+      "loss": 0.28378610610961913,
+      "mean_token_accuracy": 0.9071699053049087,
+      "num_tokens": 152464.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.27756214514374733,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.08467274904251099,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.27063760757446287,
+      "mean_token_accuracy": 0.9070401296019555,
+      "num_tokens": 158366.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.2848128478974104,
+      "epoch": 0.9206349206349206,
+      "grad_norm": 0.08799296617507935,
+      "learning_rate": 0.00016108923551222954,
+      "loss": 0.2736989974975586,
+      "mean_token_accuracy": 0.9117912963032723,
+      "num_tokens": 164354.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.2887926273047924,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.08142666518688202,
+      "learning_rate": 0.00015836561260371642,
+      "loss": 0.2762760639190674,
+      "mean_token_accuracy": 0.9110032752156257,
+      "num_tokens": 170194.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.2911578442901373,
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.07968642562627792,
+      "learning_rate": 0.00015557467163683093,
+      "loss": 0.28809950351715086,
+      "mean_token_accuracy": 0.9043565198779107,
+      "num_tokens": 175853.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.2943920481950045,
+      "epoch": 1.0158730158730158,
+      "grad_norm": 0.08365320414304733,
+      "learning_rate": 0.00015271963164275495,
+      "loss": 0.27865099906921387,
+      "mean_token_accuracy": 0.9042463362216949,
+      "num_tokens": 181430.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.2911732569336891,
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.08910917490720749,
+      "learning_rate": 0.00014980378558356668,
+      "loss": 0.28408806324005126,
+      "mean_token_accuracy": 0.9075512051582336,
+      "num_tokens": 186823.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.27633472084999083,
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.054748956114053726,
+      "learning_rate": 0.00014683049655418566,
+      "loss": 0.27398593425750734,
+      "mean_token_accuracy": 0.9088717252016068,
+      "num_tokens": 192618.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.29899220876395705,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.1026228591799736,
+      "learning_rate": 0.00014380319390342713,
+      "loss": 0.27963986396789553,
+      "mean_token_accuracy": 0.9076534271240234,
+      "num_tokens": 198264.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.27999303340911863,
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.07460694015026093,
+      "learning_rate": 0.00014072536927864067,
+      "loss": 0.27371869087219236,
+      "mean_token_accuracy": 0.9113201141357422,
+      "num_tokens": 203999.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.2836035009473562,
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.05994534492492676,
+      "learning_rate": 0.0001376005725984943,
+      "loss": 0.2734062671661377,
+      "mean_token_accuracy": 0.9102857768535614,
+      "num_tokens": 209875.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.27055577710270884,
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.15462082624435425,
+      "learning_rate": 0.00013443240795854932,
+      "loss": 0.26778972148895264,
+      "mean_token_accuracy": 0.9114238187670708,
+      "num_tokens": 215695.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.28204834908246995,
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.08471743762493134,
+      "learning_rate": 0.00013122452947434828,
+      "loss": 0.2707425594329834,
+      "mean_token_accuracy": 0.9076912581920624,
+      "num_tokens": 221300.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.2921843770891428,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.06258587539196014,
+      "learning_rate": 0.00012798063706681058,
+      "loss": 0.2830580949783325,
+      "mean_token_accuracy": 0.9059961527585983,
+      "num_tokens": 226770.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.27955467700958253,
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.11677869409322739,
+      "learning_rate": 0.00012470447219479713,
+      "loss": 0.2767421960830688,
+      "mean_token_accuracy": 0.9056397631764412,
+      "num_tokens": 232493.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.2816464897245169,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.20853769779205322,
+      "learning_rate": 0.00012139981353976524,
+      "loss": 0.2793292760848999,
+      "mean_token_accuracy": 0.9049514532089233,
+      "num_tokens": 238158.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.2885897036641836,
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.07681034505367279,
+      "learning_rate": 0.00011807047264749189,
+      "loss": 0.2701925039291382,
+      "mean_token_accuracy": 0.9056044742465019,
+      "num_tokens": 243766.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.28189543783664706,
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.06424044817686081,
+      "learning_rate": 0.0001147202895318916,
+      "loss": 0.2593745470046997,
+      "mean_token_accuracy": 0.9096330463886261,
+      "num_tokens": 249691.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.28342911675572396,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.1278621256351471,
+      "learning_rate": 0.0001113531282459996,
+      "loss": 0.28381073474884033,
+      "mean_token_accuracy": 0.9061736151576042,
+      "num_tokens": 255233.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.28202038891613485,
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.06751440465450287,
+      "learning_rate": 0.00010797287242522858,
+      "loss": 0.27419445514678953,
+      "mean_token_accuracy": 0.9094104260206223,
+      "num_tokens": 260859.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.27363024093210697,
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.06995254009962082,
+      "learning_rate": 0.00010458342080803956,
+      "loss": 0.2693720817565918,
+      "mean_token_accuracy": 0.9083198413252831,
+      "num_tokens": 266554.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.2726555660367012,
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.09802178293466568,
+      "learning_rate": 0.00010118868273919284,
+      "loss": 0.2669402837753296,
+      "mean_token_accuracy": 0.9095989406108856,
+      "num_tokens": 272262.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.2873748764395714,
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.059039562940597534,
+      "learning_rate": 9.779257366076608e-05,
+      "loss": 0.27708461284637453,
+      "mean_token_accuracy": 0.907341231405735,
+      "num_tokens": 277809.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.28209226317703723,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.07545655220746994,
+      "learning_rate": 9.439901059613973e-05,
+      "loss": 0.2581690549850464,
+      "mean_token_accuracy": 0.9121931448578835,
+      "num_tokens": 283664.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.272804581746459,
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.07380068302154541,
+      "learning_rate": 9.101190763215848e-05,
+      "loss": 0.26886236667633057,
+      "mean_token_accuracy": 0.9086462184786797,
+      "num_tokens": 289371.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.28114392757415774,
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.078324094414711,
+      "learning_rate": 8.763517140467981e-05,
+      "loss": 0.27371978759765625,
+      "mean_token_accuracy": 0.9067111536860466,
+      "num_tokens": 294986.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.28820689432322977,
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.10492384433746338,
+      "learning_rate": 8.42726965927164e-05,
+      "loss": 0.2796510696411133,
+      "mean_token_accuracy": 0.9053183734416962,
+      "num_tokens": 300487.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.26856297068297863,
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.0673430785536766,
+      "learning_rate": 8.092836142636932e-05,
+      "loss": 0.2611644506454468,
+      "mean_token_accuracy": 0.9129276722669601,
+      "num_tokens": 306372.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.29797249287366867,
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.06676393002271652,
+      "learning_rate": 7.760602321373322e-05,
+      "loss": 0.28323547840118407,
+      "mean_token_accuracy": 0.9016937434673309,
+      "num_tokens": 311775.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.2688152402639389,
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.08283069729804993,
+      "learning_rate": 7.43095138919326e-05,
+      "loss": 0.2640655517578125,
+      "mean_token_accuracy": 0.902265977859497,
+      "num_tokens": 317591.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.29286824017763136,
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.05436806008219719,
+      "learning_rate": 7.104263560742067e-05,
+      "loss": 0.27632272243499756,
+      "mean_token_accuracy": 0.9019043281674385,
+      "num_tokens": 323077.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.2781177669763565,
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.05500198155641556,
+      "learning_rate": 6.780915633063827e-05,
+      "loss": 0.27087790966033937,
+      "mean_token_accuracy": 0.9046190366148948,
+      "num_tokens": 328692.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.27223661690950396,
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.07625019550323486,
+      "learning_rate": 6.461280551009096e-05,
+      "loss": 0.26836280822753905,
+      "mean_token_accuracy": 0.9067093715071678,
+      "num_tokens": 334381.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.27323946319520476,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.072757288813591,
+      "learning_rate": 6.145726977085669e-05,
+      "loss": 0.2648139953613281,
+      "mean_token_accuracy": 0.90970708578825,
+      "num_tokens": 340111.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.2718470089137554,
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.06298787891864777,
+      "learning_rate": 5.8346188662485536e-05,
+      "loss": 0.2643317461013794,
+      "mean_token_accuracy": 0.904901784658432,
+      "num_tokens": 345896.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.28305209055542946,
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.0733041912317276,
+      "learning_rate": 5.528315046119544e-05,
+      "loss": 0.2636791944503784,
+      "mean_token_accuracy": 0.9123735308647156,
+      "num_tokens": 351673.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.2617435783147812,
+      "epoch": 2.0,
+      "grad_norm": 0.07501133531332016,
+      "learning_rate": 5.227168803120619e-05,
+      "loss": 0.26242828369140625,
+      "mean_token_accuracy": 0.9104171916842461,
+      "num_tokens": 357322.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.26802175454795363,
+      "epoch": 2.0317460317460316,
+      "grad_norm": 0.04739142954349518,
+      "learning_rate": 4.931527474998444e-05,
+      "loss": 0.25396668910980225,
+      "mean_token_accuracy": 0.9118479937314987,
+      "num_tokens": 363159.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.27135957442224024,
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.07097524404525757,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.25786685943603516,
+      "mean_token_accuracy": 0.9111087501049042,
+      "num_tokens": 368909.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.2646398801356554,
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.05924823880195618,
+      "learning_rate": 4.35811677463153e-05,
+      "loss": 0.2504109382629395,
+      "mean_token_accuracy": 0.9110997319221497,
+      "num_tokens": 374682.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.27993031218647957,
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.058568164706230164,
+      "learning_rate": 4.081008766043856e-05,
+      "loss": 0.2658329963684082,
+      "mean_token_accuracy": 0.906340380012989,
+      "num_tokens": 380133.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.270343242585659,
+      "epoch": 2.1587301587301586,
+      "grad_norm": 0.07652401179075241,
+      "learning_rate": 3.810727636839739e-05,
+      "loss": 0.26411163806915283,
+      "mean_token_accuracy": 0.9062801778316498,
+      "num_tokens": 385694.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.26379697881639,
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.06572549045085907,
+      "learning_rate": 3.547585125387394e-05,
+      "loss": 0.26352672576904296,
+      "mean_token_accuracy": 0.9080587550997734,
+      "num_tokens": 391353.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.2779304336756468,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.0634949803352356,
+      "learning_rate": 3.2918847364759556e-05,
+      "loss": 0.26194489002227783,
+      "mean_token_accuracy": 0.9062734320759773,
+      "num_tokens": 396876.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.2617481011897326,
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.05917736515402794,
+      "learning_rate": 3.0439213912574304e-05,
+      "loss": 0.26019647121429446,
+      "mean_token_accuracy": 0.9100751489400863,
+      "num_tokens": 402577.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.2559076685458422,
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.07124771922826767,
+      "learning_rate": 2.8039810870888762e-05,
+      "loss": 0.25075175762176516,
+      "mean_token_accuracy": 0.9124972775578499,
+      "num_tokens": 408405.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.2648021761327982,
+      "epoch": 2.317460317460317,
+      "grad_norm": 0.06209827587008476,
+      "learning_rate": 2.5723405676671584e-05,
+      "loss": 0.24744985103607178,
+      "mean_token_accuracy": 0.915162692964077,
+      "num_tokens": 414204.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.2807385498657823,
+      "epoch": 2.3492063492063493,
+      "grad_norm": 0.0612325593829155,
+      "learning_rate": 2.349267003836757e-05,
+      "loss": 0.26713953018188474,
+      "mean_token_accuracy": 0.9052686139941215,
+      "num_tokens": 419721.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.2669257506728172,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.06792369484901428,
+      "learning_rate": 2.1350176854387492e-05,
+      "loss": 0.26758475303649903,
+      "mean_token_accuracy": 0.9066236048936844,
+      "num_tokens": 425297.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.2817291833460331,
+      "epoch": 2.4126984126984126,
+      "grad_norm": 0.07440292090177536,
+      "learning_rate": 1.9298397245564125e-05,
+      "loss": 0.26947109699249266,
+      "mean_token_accuracy": 0.9070651844143868,
+      "num_tokens": 430708.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.2823494378477335,
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.08691683411598206,
+      "learning_rate": 1.733969770499697e-05,
+      "loss": 0.2715198040008545,
+      "mean_token_accuracy": 0.9081029698252678,
+      "num_tokens": 436157.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.2502023309469223,
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.057402949780225754,
+      "learning_rate": 1.547633736857308e-05,
+      "loss": 0.24733474254608154,
+      "mean_token_accuracy": 0.9128626599907875,
+      "num_tokens": 442078.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.2789640363305807,
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.08202935755252838,
+      "learning_rate": 1.3710465409312356e-05,
+      "loss": 0.2598316431045532,
+      "mean_token_accuracy": 0.9110502526164055,
+      "num_tokens": 447709.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.2569702621549368,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.0657891258597374,
+      "learning_rate": 1.2044118558542183e-05,
+      "loss": 0.2518922805786133,
+      "mean_token_accuracy": 0.913571135699749,
+      "num_tokens": 453518.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.30509118661284446,
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.06226721778512001,
+      "learning_rate": 1.0479218756760801e-05,
+      "loss": 0.28301548957824707,
+      "mean_token_accuracy": 0.9006569445133209,
+      "num_tokens": 458660.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.26878854297101495,
+      "epoch": 2.6031746031746033,
+      "grad_norm": 0.08471657335758209,
+      "learning_rate": 9.017570936898834e-06,
+      "loss": 0.25441818237304686,
+      "mean_token_accuracy": 0.913353081047535,
+      "num_tokens": 464425.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.26796630285680295,
+      "epoch": 2.634920634920635,
+      "grad_norm": 0.08099494874477386,
+      "learning_rate": 7.660860942535531e-06,
+      "loss": 0.2650477170944214,
+      "mean_token_accuracy": 0.9064913064241409,
+      "num_tokens": 469951.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.2573456011712551,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.06200960651040077,
+      "learning_rate": 6.410653583471049e-06,
+      "loss": 0.24512960910797119,
+      "mean_token_accuracy": 0.9124153345823288,
+      "num_tokens": 475855.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.2702272081747651,
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.05739385262131691,
+      "learning_rate": 5.268390830897352e-06,
+      "loss": 0.2525698900222778,
+      "mean_token_accuracy": 0.9123304262757301,
+      "num_tokens": 481587.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.25637628957629205,
+      "epoch": 2.7301587301587302,
+      "grad_norm": 0.06797543913125992,
+      "learning_rate": 4.235390154249319e-06,
+      "loss": 0.24502739906311036,
+      "mean_token_accuracy": 0.9152422398328781,
+      "num_tokens": 487517.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.26860512383282187,
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.0768144428730011,
+      "learning_rate": 3.3128430016545086e-06,
+      "loss": 0.26233835220336915,
+      "mean_token_accuracy": 0.9065091878175735,
+      "num_tokens": 493162.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.27704833559691905,
+      "epoch": 2.7936507936507935,
+      "grad_norm": 0.058013975620269775,
+      "learning_rate": 2.5018134257339454e-06,
+      "loss": 0.2659024477005005,
+      "mean_token_accuracy": 0.9072319209575653,
+      "num_tokens": 498734.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.26322649177163837,
+      "epoch": 2.825396825396825,
+      "grad_norm": 0.06313176453113556,
+      "learning_rate": 1.8032368563391745e-06,
+      "loss": 0.24617037773132325,
+      "mean_token_accuracy": 0.9113279536366463,
+      "num_tokens": 504706.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.26887267380952834,
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.057793453335762024,
+      "learning_rate": 1.2179190216409343e-06,
+      "loss": 0.25469746589660647,
+      "mean_token_accuracy": 0.9091615468263626,
+      "num_tokens": 510504.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.2738068286329508,
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.06475513428449631,
+      "learning_rate": 7.465350188138209e-07,
+      "loss": 0.2575427770614624,
+      "mean_token_accuracy": 0.9124535873532296,
+      "num_tokens": 516159.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.2642780113965273,
+      "epoch": 2.9206349206349205,
+      "grad_norm": 0.08064750581979752,
+      "learning_rate": 3.896285353889417e-07,
+      "loss": 0.25164711475372314,
+      "mean_token_accuracy": 0.9099403232336044,
+      "num_tokens": 521956.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.2682258732616901,
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.06471122801303864,
+      "learning_rate": 1.4761122217252787e-07,
+      "loss": 0.2547882556915283,
+      "mean_token_accuracy": 0.9095430165529251,
+      "num_tokens": 527699.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.2765565741807222,
+      "epoch": 2.984126984126984,
+      "grad_norm": 0.07435508817434311,
+      "learning_rate": 2.0762218453818096e-08,
+      "loss": 0.26333184242248536,
+      "mean_token_accuracy": 0.9075064033269882,
+      "num_tokens": 533220.0,
+      "step": 940
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2821237140291584e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-945/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb601ecd2bf594898b1129204a988d020e0fdb23c6d6e6733f079e88458dd3d
+size 5176

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}