Upload folder using huggingface_hub

.gitattributes

@@ -45,3 +45,8 @@ checkpoint-416/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-624/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-728/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1144/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-936/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
-    "o_proj",
-    "gate_proj"
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5711c28d3d33aa09d94c62c9a136b8bf0f0cdbd49f90528dd206ab969f2ec3e
+oid sha256:95c4b7c94260f78eb6b4165cbcfe2ddb885354992826a11e83ca4b9e7c8bd821
 size 645975704

checkpoint-104/adapter_config.json

@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "k_proj",
     "o_proj",
-    "q_proj",
+    "k_proj",
     "v_proj",
+    "gate_proj",
     "up_proj",
-    "gate_proj"
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-104/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc6cd409c955d35b5a6a620baedd9530a4c5f73f68bbe3082ddb660de6919d8
+oid sha256:9d6430332b35903fbe27ffd3a1197f5b7fbd52bcc875764fb1e821a2e7a5b20c
 size 645975704

checkpoint-104/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5478a87659e3fd833f6e0be022f6cade6754457ac9844e658a304f95edb93418
+oid sha256:f5bcd586d240329adeb61a0d88dfdc39a7929160f2a1981cc02598c906b3f725
 size 1292087115

checkpoint-104/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b46d4a17bc33ca1534ecbb381b92bb917feb262b6cd6ea1e0aeef66ab3378a5
+oid sha256:817d9fbbff18256e8cef65db78ce19214fbe3654af0f1b141d490e62b9af0250
 size 15429

checkpoint-104/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ea02c0f84cb7b79a7d01dc1ad12d59feb06a7206324175c7723c9e9e70ef38
+oid sha256:60551e7ecc6d5a8b013d3bc76091044e8844ac84770cf81eed580746fb6ba572
 size 15429

checkpoint-104/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0510c2eb154e655092dfd2b66e653579331ca3559570cdc26dff724493936f08
+oid sha256:040370e091f12fe65f69ba400a634fd1339b37b81f13988f1a38d5c6186a703c
 size 15429

checkpoint-104/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ef7e6fbd41972ea743427f306fa0e581982d06dd2fd9a83bc6f1f6e4371346
+oid sha256:dfeb92000c97b0e9acd896f2bd294a72b5b71931102c1288570a6085a7b77932
 size 15429

checkpoint-104/trainer_state.json

@@ -11,55 +11,55 @@
   "log_history": [
     {
       "epoch": 0.24096385542168675,
-      "grad_norm": 0.2236759215593338,
+      "grad_norm": 0.17040389776229858,
       "learning_rate": 0.000511,
-      "loss": 0.4204,
-      "mean_token_accuracy": 0.900120057463646,
-      "num_tokens": 567991.0,
+      "loss": 0.4303,
+      "mean_token_accuracy": 0.8983636182546616,
+      "num_tokens": 569446.0,
       "step": 25
     },
     {
       "epoch": 0.4819277108433735,
-      "grad_norm": 0.1322442889213562,
+      "grad_norm": 0.19750550389289856,
       "learning_rate": 0.000511,
-      "loss": 0.2913,
-      "mean_token_accuracy": 0.9270081639289856,
-      "num_tokens": 1135343.0,
+      "loss": 0.2953,
+      "mean_token_accuracy": 0.9258013522624969,
+      "num_tokens": 1138403.0,
       "step": 50
     },
     {
       "epoch": 0.7228915662650602,
-      "grad_norm": 0.19739408791065216,
+      "grad_norm": 0.2441304326057434,
       "learning_rate": 0.000511,
-      "loss": 0.2186,
-      "mean_token_accuracy": 0.9418566429615021,
-      "num_tokens": 1703784.0,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.9427212655544281,
+      "num_tokens": 1705606.0,
       "step": 75
     },
     {
       "epoch": 0.963855421686747,
-      "grad_norm": 0.17215745151042938,
+      "grad_norm": 0.19773538410663605,
       "learning_rate": 0.000511,
-      "loss": 0.1963,
-      "mean_token_accuracy": 0.9479192215204238,
-      "num_tokens": 2269891.0,
+      "loss": 0.194,
+      "mean_token_accuracy": 0.9479873812198639,
+      "num_tokens": 2271060.0,
       "step": 100
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.19681453704833984,
-      "eval_mean_token_accuracy": 0.9478744319144715,
-      "eval_num_tokens": 2345494.0,
-      "eval_runtime": 4.3187,
-      "eval_samples_per_second": 85.442,
-      "eval_steps_per_second": 10.883,
+      "eval_loss": 0.1995953470468521,
+      "eval_mean_token_accuracy": 0.9460804703387808,
+      "eval_num_tokens": 2345411.0,
+      "eval_runtime": 4.3258,
+      "eval_samples_per_second": 85.303,
+      "eval_steps_per_second": 10.865,
       "step": 104
     }
   ],
   "logging_steps": 25,
-  "max_steps": 728,
+  "max_steps": 1248,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 12,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -73,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0256509033879962e+17,
+  "total_flos": 1.0256292003813786e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-104/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92f33d5ca39ba292c6b171cffeb00f4d1c361214bebb8604f8ce3482d3b7c8c
+oid sha256:9abd2e560826c250d1fd3df1ec10e14fef0b5ef3b175f43df982f2fc9f2f11d9
 size 6097

checkpoint-1040/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-1040/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1040/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66061757a3f9c7e694bd0869920435ba5cd7a0117a26a35caaceea1882296a8
+size 645975704

checkpoint-1040/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
+}

checkpoint-1040/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-1040/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46dc0b6cd60733e44769de8e8e0858d07c1b25a992eae50a74b529c3e4db236
+size 1292087499

checkpoint-1040/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7192a40ca4014f502efc59dacc942dad83ac6b1e5dbffc44a7e2368a17abffd4
+size 15429

checkpoint-1040/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f988a134540f1261cc919cb029bec83fd4a129faeedd432eda41941d88caca
+size 15429

checkpoint-1040/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a00527b6663b32e26bbe8bf4772fd7934576df924e6fc0a26b27e451253945f
+size 15429

checkpoint-1040/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d158f929065935ff5e42e00f4c943d51cb4a72cc008d4cc7441b13796917f2b6
+size 15429

checkpoint-1040/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452277350ad8f5efad158760275ed80bf2a10a74384da69a532b63915629f8f6
+size 1465

checkpoint-1040/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
+  }
+}

checkpoint-1040/tokenizer.json

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

checkpoint-1040/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
+}

checkpoint-1040/trainer_state.json

@@ -0,0 +1,503 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.17040389776229858,
+      "learning_rate": 0.000511,
+      "loss": 0.4303,
+      "mean_token_accuracy": 0.8983636182546616,
+      "num_tokens": 569446.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.19750550389289856,
+      "learning_rate": 0.000511,
+      "loss": 0.2953,
+      "mean_token_accuracy": 0.9258013522624969,
+      "num_tokens": 1138403.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.2441304326057434,
+      "learning_rate": 0.000511,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.9427212655544281,
+      "num_tokens": 1705606.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.19773538410663605,
+      "learning_rate": 0.000511,
+      "loss": 0.194,
+      "mean_token_accuracy": 0.9479873812198639,
+      "num_tokens": 2271060.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1995953470468521,
+      "eval_mean_token_accuracy": 0.9460804703387808,
+      "eval_num_tokens": 2345411.0,
+      "eval_runtime": 4.3258,
+      "eval_samples_per_second": 85.303,
+      "eval_steps_per_second": 10.865,
+      "step": 104
+    },
+    {
+      "epoch": 1.202409638554217,
+      "grad_norm": 0.0789426863193512,
+      "learning_rate": 0.000511,
+      "loss": 0.16,
+      "mean_token_accuracy": 0.9584937607399141,
+      "num_tokens": 2836512.0,
+      "step": 125
+    },
+    {
+      "epoch": 1.4433734939759035,
+      "grad_norm": 0.10643763095140457,
+      "learning_rate": 0.000511,
+      "loss": 0.1408,
+      "mean_token_accuracy": 0.9620217531919479,
+      "num_tokens": 3403395.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6843373493975904,
+      "grad_norm": 0.08403506129980087,
+      "learning_rate": 0.000511,
+      "loss": 0.1314,
+      "mean_token_accuracy": 0.9630346685647965,
+      "num_tokens": 3970344.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.9253012048192772,
+      "grad_norm": 0.10631190985441208,
+      "learning_rate": 0.000511,
+      "loss": 0.1272,
+      "mean_token_accuracy": 0.9646087974309921,
+      "num_tokens": 4538034.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.14445580542087555,
+      "eval_mean_token_accuracy": 0.9612192435467497,
+      "eval_num_tokens": 4690349.0,
+      "eval_runtime": 4.2683,
+      "eval_samples_per_second": 86.451,
+      "eval_steps_per_second": 11.011,
+      "step": 208
+    },
+    {
+      "epoch": 2.163855421686747,
+      "grad_norm": 0.08164115995168686,
+      "learning_rate": 0.000511,
+      "loss": 0.1067,
+      "mean_token_accuracy": 0.9689010110768405,
+      "num_tokens": 5091219.0,
+      "step": 225
+    },
+    {
+      "epoch": 2.404819277108434,
+      "grad_norm": 0.08637778460979462,
+      "learning_rate": 0.000511,
+      "loss": 0.0968,
+      "mean_token_accuracy": 0.9721185141801834,
+      "num_tokens": 5658328.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.6457831325301204,
+      "grad_norm": 0.0902683362364769,
+      "learning_rate": 0.000511,
+      "loss": 0.091,
+      "mean_token_accuracy": 0.9744718617200852,
+      "num_tokens": 6225744.0,
+      "step": 275
+    },
+    {
+      "epoch": 2.886746987951807,
+      "grad_norm": 0.09357521682977676,
+      "learning_rate": 0.000511,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.9727102434635162,
+      "num_tokens": 6794402.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.14705069363117218,
+      "eval_mean_token_accuracy": 0.9624257531571896,
+      "eval_num_tokens": 7035273.0,
+      "eval_runtime": 4.2634,
+      "eval_samples_per_second": 86.55,
+      "eval_steps_per_second": 11.024,
+      "step": 312
+    },
+    {
+      "epoch": 3.125301204819277,
+      "grad_norm": 0.14760874211788177,
+      "learning_rate": 0.000511,
+      "loss": 0.0842,
+      "mean_token_accuracy": 0.9764150320881545,
+      "num_tokens": 7334495.0,
+      "step": 325
+    },
+    {
+      "epoch": 3.3662650602409636,
+      "grad_norm": 0.09895172715187073,
+      "learning_rate": 0.000511,
+      "loss": 0.0777,
+      "mean_token_accuracy": 0.9774631917476654,
+      "num_tokens": 7903478.0,
+      "step": 350
+    },
+    {
+      "epoch": 3.6072289156626507,
+      "grad_norm": 0.10538128763437271,
+      "learning_rate": 0.000511,
+      "loss": 0.0742,
+      "mean_token_accuracy": 0.9783486902713776,
+      "num_tokens": 8469479.0,
+      "step": 375
+    },
+    {
+      "epoch": 3.8481927710843373,
+      "grad_norm": 0.09741026163101196,
+      "learning_rate": 0.000511,
+      "loss": 0.0679,
+      "mean_token_accuracy": 0.9803410685062408,
+      "num_tokens": 9036138.0,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.14550796151161194,
+      "eval_mean_token_accuracy": 0.9638357936067784,
+      "eval_num_tokens": 9380804.0,
+      "eval_runtime": 4.2387,
+      "eval_samples_per_second": 87.055,
+      "eval_steps_per_second": 11.088,
+      "step": 416
+    },
+    {
+      "epoch": 4.086746987951807,
+      "grad_norm": 0.10616449266672134,
+      "learning_rate": 0.000511,
+      "loss": 0.0625,
+      "mean_token_accuracy": 0.9811063475079007,
+      "num_tokens": 9598059.0,
+      "step": 425
+    },
+    {
+      "epoch": 4.327710843373494,
+      "grad_norm": 0.09445353597402573,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.9833864039182663,
+      "num_tokens": 10165089.0,
+      "step": 450
+    },
+    {
+      "epoch": 4.5686746987951805,
+      "grad_norm": 0.07407805323600769,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.984256454706192,
+      "num_tokens": 10732931.0,
+      "step": 475
+    },
+    {
+      "epoch": 4.809638554216868,
+      "grad_norm": 0.07322381436824799,
+      "learning_rate": 0.000511,
+      "loss": 0.0462,
+      "mean_token_accuracy": 0.9861221539974213,
+      "num_tokens": 11301466.0,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14242176711559296,
+      "eval_mean_token_accuracy": 0.9691625554510888,
+      "eval_num_tokens": 11726407.0,
+      "eval_runtime": 4.2397,
+      "eval_samples_per_second": 87.035,
+      "eval_steps_per_second": 11.086,
+      "step": 520
+    },
+    {
+      "epoch": 5.048192771084337,
+      "grad_norm": 0.06890378147363663,
+      "learning_rate": 0.000511,
+      "loss": 0.0538,
+      "mean_token_accuracy": 0.9846178467827614,
+      "num_tokens": 11856936.0,
+      "step": 525
+    },
+    {
+      "epoch": 5.289156626506024,
+      "grad_norm": 0.05453705042600632,
+      "learning_rate": 0.000511,
+      "loss": 0.0485,
+      "mean_token_accuracy": 0.9858993107080459,
+      "num_tokens": 12423275.0,
+      "step": 550
+    },
+    {
+      "epoch": 5.530120481927711,
+      "grad_norm": 0.0743594691157341,
+      "learning_rate": 0.000511,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9857969325780869,
+      "num_tokens": 12992045.0,
+      "step": 575
+    },
+    {
+      "epoch": 5.771084337349397,
+      "grad_norm": 0.06587184965610504,
+      "learning_rate": 0.000511,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9862634456157684,
+      "num_tokens": 13560037.0,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.1241711750626564,
+      "eval_mean_token_accuracy": 0.9710005204728309,
+      "eval_num_tokens": 14071932.0,
+      "eval_runtime": 4.2228,
+      "eval_samples_per_second": 87.383,
+      "eval_steps_per_second": 11.13,
+      "step": 624
+    },
+    {
+      "epoch": 6.009638554216868,
+      "grad_norm": 0.06124307960271835,
+      "learning_rate": 0.000511,
+      "loss": 0.0368,
+      "mean_token_accuracy": 0.9886124525407348,
+      "num_tokens": 14102915.0,
+      "step": 625
+    },
+    {
+      "epoch": 6.250602409638554,
+      "grad_norm": 0.10462699830532074,
+      "learning_rate": 0.000511,
+      "loss": 0.0378,
+      "mean_token_accuracy": 0.9887062352895737,
+      "num_tokens": 14669309.0,
+      "step": 650
+    },
+    {
+      "epoch": 6.491566265060241,
+      "grad_norm": 0.09343062341213226,
+      "learning_rate": 0.000511,
+      "loss": 0.0353,
+      "mean_token_accuracy": 0.9892213380336762,
+      "num_tokens": 15237353.0,
+      "step": 675
+    },
+    {
+      "epoch": 6.732530120481927,
+      "grad_norm": 0.08443740010261536,
+      "learning_rate": 0.000511,
+      "loss": 0.0364,
+      "mean_token_accuracy": 0.9892494148015976,
+      "num_tokens": 15804441.0,
+      "step": 700
+    },
+    {
+      "epoch": 6.973493975903614,
+      "grad_norm": 0.07635796070098877,
+      "learning_rate": 0.000511,
+      "loss": 0.0397,
+      "mean_token_accuracy": 0.9886371964216232,
+      "num_tokens": 16368577.0,
+      "step": 725
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.17054519057273865,
+      "eval_mean_token_accuracy": 0.9649876089806252,
+      "eval_num_tokens": 16416958.0,
+      "eval_runtime": 4.2384,
+      "eval_samples_per_second": 87.061,
+      "eval_steps_per_second": 11.089,
+      "step": 728
+    },
+    {
+      "epoch": 7.212048192771085,
+      "grad_norm": 0.0668734461069107,
+      "learning_rate": 0.000511,
+      "loss": 0.0333,
+      "mean_token_accuracy": 0.9895464802029157,
+      "num_tokens": 16927490.0,
+      "step": 750
+    },
+    {
+      "epoch": 7.453012048192771,
+      "grad_norm": 0.06639474630355835,
+      "learning_rate": 0.000511,
+      "loss": 0.0325,
+      "mean_token_accuracy": 0.9908391135931015,
+      "num_tokens": 17494143.0,
+      "step": 775
+    },
+    {
+      "epoch": 7.693975903614458,
+      "grad_norm": 0.10801058262586594,
+      "learning_rate": 0.000511,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.9909009468555451,
+      "num_tokens": 18063423.0,
+      "step": 800
+    },
+    {
+      "epoch": 7.934939759036144,
+      "grad_norm": 0.048982683569192886,
+      "learning_rate": 0.000511,
+      "loss": 0.0313,
+      "mean_token_accuracy": 0.9908118671178818,
+      "num_tokens": 18630905.0,
+      "step": 825
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.1113305315375328,
+      "eval_mean_token_accuracy": 0.9737493814306056,
+      "eval_num_tokens": 18762023.0,
+      "eval_runtime": 4.2275,
+      "eval_samples_per_second": 87.285,
+      "eval_steps_per_second": 11.118,
+      "step": 832
+    },
+    {
+      "epoch": 8.173493975903614,
+      "grad_norm": 0.05220003426074982,
+      "learning_rate": 0.000511,
+      "loss": 0.0277,
+      "mean_token_accuracy": 0.9916808304160533,
+      "num_tokens": 19184427.0,
+      "step": 850
+    },
+    {
+      "epoch": 8.4144578313253,
+      "grad_norm": 0.08605129271745682,
+      "learning_rate": 0.000511,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9915985196828843,
+      "num_tokens": 19754417.0,
+      "step": 875
+    },
+    {
+      "epoch": 8.655421686746989,
+      "grad_norm": 0.0517394132912159,
+      "learning_rate": 0.000511,
+      "loss": 0.0258,
+      "mean_token_accuracy": 0.9922689855098724,
+      "num_tokens": 20322925.0,
+      "step": 900
+    },
+    {
+      "epoch": 8.896385542168675,
+      "grad_norm": 0.059128183871507645,
+      "learning_rate": 0.000511,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9923817366361618,
+      "num_tokens": 20889889.0,
+      "step": 925
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.1412837952375412,
+      "eval_mean_token_accuracy": 0.97177672893443,
+      "eval_num_tokens": 21107006.0,
+      "eval_runtime": 4.2426,
+      "eval_samples_per_second": 86.974,
+      "eval_steps_per_second": 11.078,
+      "step": 936
+    },
+    {
+      "epoch": 9.134939759036145,
+      "grad_norm": 0.08735097944736481,
+      "learning_rate": 0.000511,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9934688914905895,
+      "num_tokens": 21433768.0,
+      "step": 950
+    },
+    {
+      "epoch": 9.375903614457831,
+      "grad_norm": 0.07706229388713837,
+      "learning_rate": 0.000511,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.9933523815870285,
+      "num_tokens": 22001855.0,
+      "step": 975
+    },
+    {
+      "epoch": 9.616867469879518,
+      "grad_norm": 0.0835743248462677,
+      "learning_rate": 0.000511,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9938382267951965,
+      "num_tokens": 22568226.0,
+      "step": 1000
+    },
+    {
+      "epoch": 9.857831325301206,
+      "grad_norm": 0.10814040899276733,
+      "learning_rate": 0.000511,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.99358702480793,
+      "num_tokens": 23136558.0,
+      "step": 1025
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.1364360749721527,
+      "eval_mean_token_accuracy": 0.9739730041077796,
+      "eval_num_tokens": 23451914.0,
+      "eval_runtime": 4.2514,
+      "eval_samples_per_second": 86.796,
+      "eval_steps_per_second": 11.055,
+      "step": 1040
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0255354758734807e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1040/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abd2e560826c250d1fd3df1ec10e14fef0b5ef3b175f43df982f2fc9f2f11d9
+size 6097

checkpoint-1144/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-1144/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1144/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e882018e13dfbe4351e85492b79837e849f80b25965af3cb6e6e05476ad74984
+size 645975704

checkpoint-1144/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
+}

checkpoint-1144/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-1144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611a5a6306be133e8189d3c2d2effee32520c6b86af695386fd9ca093fb3ef00
+size 1292087499

checkpoint-1144/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921c3558b350428dd8a94da8a439c82d6425668f0aecb552d6302e557f051149
+size 15429

checkpoint-1144/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9629a3e0c533752ff4f92042146dfe38d88e56eddc93e3a0a2eda7ec8fee66ab
+size 15429

checkpoint-1144/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96e07b2f576bce4903e5d4366edbe298a6e23ba5bfce11d027d0dc7eb3badd1
+size 15429

checkpoint-1144/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bff42b9972acb3629b58fb5f8bb917288ba84c0c058d3a78d9afb4362ce22d
+size 15429

checkpoint-1144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c496ce956a9f4d9e6a27aafa9069963fbee98d3a4307671375068a8769a91d5
+size 1465

checkpoint-1144/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
+  }
+}

checkpoint-1144/tokenizer.json

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

checkpoint-1144/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
+}

checkpoint-1144/trainer_state.json

@@ -0,0 +1,549 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 1144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.17040389776229858,
+      "learning_rate": 0.000511,
+      "loss": 0.4303,
+      "mean_token_accuracy": 0.8983636182546616,
+      "num_tokens": 569446.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.19750550389289856,
+      "learning_rate": 0.000511,
+      "loss": 0.2953,
+      "mean_token_accuracy": 0.9258013522624969,
+      "num_tokens": 1138403.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.2441304326057434,
+      "learning_rate": 0.000511,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.9427212655544281,
+      "num_tokens": 1705606.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.19773538410663605,
+      "learning_rate": 0.000511,
+      "loss": 0.194,
+      "mean_token_accuracy": 0.9479873812198639,
+      "num_tokens": 2271060.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1995953470468521,
+      "eval_mean_token_accuracy": 0.9460804703387808,
+      "eval_num_tokens": 2345411.0,
+      "eval_runtime": 4.3258,
+      "eval_samples_per_second": 85.303,
+      "eval_steps_per_second": 10.865,
+      "step": 104
+    },
+    {
+      "epoch": 1.202409638554217,
+      "grad_norm": 0.0789426863193512,
+      "learning_rate": 0.000511,
+      "loss": 0.16,
+      "mean_token_accuracy": 0.9584937607399141,
+      "num_tokens": 2836512.0,
+      "step": 125
+    },
+    {
+      "epoch": 1.4433734939759035,
+      "grad_norm": 0.10643763095140457,
+      "learning_rate": 0.000511,
+      "loss": 0.1408,
+      "mean_token_accuracy": 0.9620217531919479,
+      "num_tokens": 3403395.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6843373493975904,
+      "grad_norm": 0.08403506129980087,
+      "learning_rate": 0.000511,
+      "loss": 0.1314,
+      "mean_token_accuracy": 0.9630346685647965,
+      "num_tokens": 3970344.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.9253012048192772,
+      "grad_norm": 0.10631190985441208,
+      "learning_rate": 0.000511,
+      "loss": 0.1272,
+      "mean_token_accuracy": 0.9646087974309921,
+      "num_tokens": 4538034.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.14445580542087555,
+      "eval_mean_token_accuracy": 0.9612192435467497,
+      "eval_num_tokens": 4690349.0,
+      "eval_runtime": 4.2683,
+      "eval_samples_per_second": 86.451,
+      "eval_steps_per_second": 11.011,
+      "step": 208
+    },
+    {
+      "epoch": 2.163855421686747,
+      "grad_norm": 0.08164115995168686,
+      "learning_rate": 0.000511,
+      "loss": 0.1067,
+      "mean_token_accuracy": 0.9689010110768405,
+      "num_tokens": 5091219.0,
+      "step": 225
+    },
+    {
+      "epoch": 2.404819277108434,
+      "grad_norm": 0.08637778460979462,
+      "learning_rate": 0.000511,
+      "loss": 0.0968,
+      "mean_token_accuracy": 0.9721185141801834,
+      "num_tokens": 5658328.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.6457831325301204,
+      "grad_norm": 0.0902683362364769,
+      "learning_rate": 0.000511,
+      "loss": 0.091,
+      "mean_token_accuracy": 0.9744718617200852,
+      "num_tokens": 6225744.0,
+      "step": 275
+    },
+    {
+      "epoch": 2.886746987951807,
+      "grad_norm": 0.09357521682977676,
+      "learning_rate": 0.000511,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.9727102434635162,
+      "num_tokens": 6794402.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.14705069363117218,
+      "eval_mean_token_accuracy": 0.9624257531571896,
+      "eval_num_tokens": 7035273.0,
+      "eval_runtime": 4.2634,
+      "eval_samples_per_second": 86.55,
+      "eval_steps_per_second": 11.024,
+      "step": 312
+    },
+    {
+      "epoch": 3.125301204819277,
+      "grad_norm": 0.14760874211788177,
+      "learning_rate": 0.000511,
+      "loss": 0.0842,
+      "mean_token_accuracy": 0.9764150320881545,
+      "num_tokens": 7334495.0,
+      "step": 325
+    },
+    {
+      "epoch": 3.3662650602409636,
+      "grad_norm": 0.09895172715187073,
+      "learning_rate": 0.000511,
+      "loss": 0.0777,
+      "mean_token_accuracy": 0.9774631917476654,
+      "num_tokens": 7903478.0,
+      "step": 350
+    },
+    {
+      "epoch": 3.6072289156626507,
+      "grad_norm": 0.10538128763437271,
+      "learning_rate": 0.000511,
+      "loss": 0.0742,
+      "mean_token_accuracy": 0.9783486902713776,
+      "num_tokens": 8469479.0,
+      "step": 375
+    },
+    {
+      "epoch": 3.8481927710843373,
+      "grad_norm": 0.09741026163101196,
+      "learning_rate": 0.000511,
+      "loss": 0.0679,
+      "mean_token_accuracy": 0.9803410685062408,
+      "num_tokens": 9036138.0,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.14550796151161194,
+      "eval_mean_token_accuracy": 0.9638357936067784,
+      "eval_num_tokens": 9380804.0,
+      "eval_runtime": 4.2387,
+      "eval_samples_per_second": 87.055,
+      "eval_steps_per_second": 11.088,
+      "step": 416
+    },
+    {
+      "epoch": 4.086746987951807,
+      "grad_norm": 0.10616449266672134,
+      "learning_rate": 0.000511,
+      "loss": 0.0625,
+      "mean_token_accuracy": 0.9811063475079007,
+      "num_tokens": 9598059.0,
+      "step": 425
+    },
+    {
+      "epoch": 4.327710843373494,
+      "grad_norm": 0.09445353597402573,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.9833864039182663,
+      "num_tokens": 10165089.0,
+      "step": 450
+    },
+    {
+      "epoch": 4.5686746987951805,
+      "grad_norm": 0.07407805323600769,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.984256454706192,
+      "num_tokens": 10732931.0,
+      "step": 475
+    },
+    {
+      "epoch": 4.809638554216868,
+      "grad_norm": 0.07322381436824799,
+      "learning_rate": 0.000511,
+      "loss": 0.0462,
+      "mean_token_accuracy": 0.9861221539974213,
+      "num_tokens": 11301466.0,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14242176711559296,
+      "eval_mean_token_accuracy": 0.9691625554510888,
+      "eval_num_tokens": 11726407.0,
+      "eval_runtime": 4.2397,
+      "eval_samples_per_second": 87.035,
+      "eval_steps_per_second": 11.086,
+      "step": 520
+    },
+    {
+      "epoch": 5.048192771084337,
+      "grad_norm": 0.06890378147363663,
+      "learning_rate": 0.000511,
+      "loss": 0.0538,
+      "mean_token_accuracy": 0.9846178467827614,
+      "num_tokens": 11856936.0,
+      "step": 525
+    },
+    {
+      "epoch": 5.289156626506024,
+      "grad_norm": 0.05453705042600632,
+      "learning_rate": 0.000511,
+      "loss": 0.0485,
+      "mean_token_accuracy": 0.9858993107080459,
+      "num_tokens": 12423275.0,
+      "step": 550
+    },
+    {
+      "epoch": 5.530120481927711,
+      "grad_norm": 0.0743594691157341,
+      "learning_rate": 0.000511,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9857969325780869,
+      "num_tokens": 12992045.0,
+      "step": 575
+    },
+    {
+      "epoch": 5.771084337349397,
+      "grad_norm": 0.06587184965610504,
+      "learning_rate": 0.000511,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9862634456157684,
+      "num_tokens": 13560037.0,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.1241711750626564,
+      "eval_mean_token_accuracy": 0.9710005204728309,
+      "eval_num_tokens": 14071932.0,
+      "eval_runtime": 4.2228,
+      "eval_samples_per_second": 87.383,
+      "eval_steps_per_second": 11.13,
+      "step": 624
+    },
+    {
+      "epoch": 6.009638554216868,
+      "grad_norm": 0.06124307960271835,
+      "learning_rate": 0.000511,
+      "loss": 0.0368,
+      "mean_token_accuracy": 0.9886124525407348,
+      "num_tokens": 14102915.0,
+      "step": 625
+    },
+    {
+      "epoch": 6.250602409638554,
+      "grad_norm": 0.10462699830532074,
+      "learning_rate": 0.000511,
+      "loss": 0.0378,
+      "mean_token_accuracy": 0.9887062352895737,
+      "num_tokens": 14669309.0,
+      "step": 650
+    },
+    {
+      "epoch": 6.491566265060241,
+      "grad_norm": 0.09343062341213226,
+      "learning_rate": 0.000511,
+      "loss": 0.0353,
+      "mean_token_accuracy": 0.9892213380336762,
+      "num_tokens": 15237353.0,
+      "step": 675
+    },
+    {
+      "epoch": 6.732530120481927,
+      "grad_norm": 0.08443740010261536,
+      "learning_rate": 0.000511,
+      "loss": 0.0364,
+      "mean_token_accuracy": 0.9892494148015976,
+      "num_tokens": 15804441.0,
+      "step": 700
+    },
+    {
+      "epoch": 6.973493975903614,
+      "grad_norm": 0.07635796070098877,
+      "learning_rate": 0.000511,
+      "loss": 0.0397,
+      "mean_token_accuracy": 0.9886371964216232,
+      "num_tokens": 16368577.0,
+      "step": 725
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.17054519057273865,
+      "eval_mean_token_accuracy": 0.9649876089806252,
+      "eval_num_tokens": 16416958.0,
+      "eval_runtime": 4.2384,
+      "eval_samples_per_second": 87.061,
+      "eval_steps_per_second": 11.089,
+      "step": 728
+    },
+    {
+      "epoch": 7.212048192771085,
+      "grad_norm": 0.0668734461069107,
+      "learning_rate": 0.000511,
+      "loss": 0.0333,
+      "mean_token_accuracy": 0.9895464802029157,
+      "num_tokens": 16927490.0,
+      "step": 750
+    },
+    {
+      "epoch": 7.453012048192771,
+      "grad_norm": 0.06639474630355835,
+      "learning_rate": 0.000511,
+      "loss": 0.0325,
+      "mean_token_accuracy": 0.9908391135931015,
+      "num_tokens": 17494143.0,
+      "step": 775
+    },
+    {
+      "epoch": 7.693975903614458,
+      "grad_norm": 0.10801058262586594,
+      "learning_rate": 0.000511,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.9909009468555451,
+      "num_tokens": 18063423.0,
+      "step": 800
+    },
+    {
+      "epoch": 7.934939759036144,
+      "grad_norm": 0.048982683569192886,
+      "learning_rate": 0.000511,
+      "loss": 0.0313,
+      "mean_token_accuracy": 0.9908118671178818,
+      "num_tokens": 18630905.0,
+      "step": 825
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.1113305315375328,
+      "eval_mean_token_accuracy": 0.9737493814306056,
+      "eval_num_tokens": 18762023.0,
+      "eval_runtime": 4.2275,
+      "eval_samples_per_second": 87.285,
+      "eval_steps_per_second": 11.118,
+      "step": 832
+    },
+    {
+      "epoch": 8.173493975903614,
+      "grad_norm": 0.05220003426074982,
+      "learning_rate": 0.000511,
+      "loss": 0.0277,
+      "mean_token_accuracy": 0.9916808304160533,
+      "num_tokens": 19184427.0,
+      "step": 850
+    },
+    {
+      "epoch": 8.4144578313253,
+      "grad_norm": 0.08605129271745682,
+      "learning_rate": 0.000511,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9915985196828843,
+      "num_tokens": 19754417.0,
+      "step": 875
+    },
+    {
+      "epoch": 8.655421686746989,
+      "grad_norm": 0.0517394132912159,
+      "learning_rate": 0.000511,
+      "loss": 0.0258,
+      "mean_token_accuracy": 0.9922689855098724,
+      "num_tokens": 20322925.0,
+      "step": 900
+    },
+    {
+      "epoch": 8.896385542168675,
+      "grad_norm": 0.059128183871507645,
+      "learning_rate": 0.000511,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9923817366361618,
+      "num_tokens": 20889889.0,
+      "step": 925
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.1412837952375412,
+      "eval_mean_token_accuracy": 0.97177672893443,
+      "eval_num_tokens": 21107006.0,
+      "eval_runtime": 4.2426,
+      "eval_samples_per_second": 86.974,
+      "eval_steps_per_second": 11.078,
+      "step": 936
+    },
+    {
+      "epoch": 9.134939759036145,
+      "grad_norm": 0.08735097944736481,
+      "learning_rate": 0.000511,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9934688914905895,
+      "num_tokens": 21433768.0,
+      "step": 950
+    },
+    {
+      "epoch": 9.375903614457831,
+      "grad_norm": 0.07706229388713837,
+      "learning_rate": 0.000511,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.9933523815870285,
+      "num_tokens": 22001855.0,
+      "step": 975
+    },
+    {
+      "epoch": 9.616867469879518,
+      "grad_norm": 0.0835743248462677,
+      "learning_rate": 0.000511,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9938382267951965,
+      "num_tokens": 22568226.0,
+      "step": 1000
+    },
+    {
+      "epoch": 9.857831325301206,
+      "grad_norm": 0.10814040899276733,
+      "learning_rate": 0.000511,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.99358702480793,
+      "num_tokens": 23136558.0,
+      "step": 1025
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.1364360749721527,
+      "eval_mean_token_accuracy": 0.9739730041077796,
+      "eval_num_tokens": 23451914.0,
+      "eval_runtime": 4.2514,
+      "eval_samples_per_second": 86.796,
+      "eval_steps_per_second": 11.055,
+      "step": 1040
+    },
+    {
+      "epoch": 10.096385542168674,
+      "grad_norm": 0.07988773286342621,
+      "learning_rate": 0.000511,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9941012221153336,
+      "num_tokens": 23687880.0,
+      "step": 1050
+    },
+    {
+      "epoch": 10.337349397590362,
+      "grad_norm": 0.069613017141819,
+      "learning_rate": 0.000511,
+      "loss": 0.0196,
+      "mean_token_accuracy": 0.9939718806743622,
+      "num_tokens": 24256496.0,
+      "step": 1075
+    },
+    {
+      "epoch": 10.578313253012048,
+      "grad_norm": 0.04984867945313454,
+      "learning_rate": 0.000511,
+      "loss": 0.0175,
+      "mean_token_accuracy": 0.9947837656736374,
+      "num_tokens": 24825055.0,
+      "step": 1100
+    },
+    {
+      "epoch": 10.819277108433734,
+      "grad_norm": 0.05473554879426956,
+      "learning_rate": 0.000511,
+      "loss": 0.0168,
+      "mean_token_accuracy": 0.9948917692899704,
+      "num_tokens": 25390292.0,
+      "step": 1125
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.14471808075904846,
+      "eval_mean_token_accuracy": 0.9728963070727409,
+      "eval_num_tokens": 25797341.0,
+      "eval_runtime": 4.2294,
+      "eval_samples_per_second": 87.246,
+      "eval_steps_per_second": 11.113,
+      "step": 1144
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1280899812653793e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abd2e560826c250d1fd3df1ec10e14fef0b5ef3b175f43df982f2fc9f2f11d9
+size 6097

checkpoint-1248/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-1248/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}