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-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-852/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: DongfuJiang/Qwen2.5-0.5B-Instruct
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: qwen2_chunking_mlp_freeze_uniform_with_shared_start_sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2_chunking_mlp_freeze_uniform_with_shared_start_sft
+
+This model is a fine-tuned version of [DongfuJiang/Qwen2.5-0.5B-Instruct](https://huggingface.co/DongfuJiang/Qwen2.5-0.5B-Instruct) on the wikitext-103-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.9502
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.107         | 0.5867 | 500  | 4.0980          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 2.18.0
+- Tokenizers 0.20.3

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
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.9997066588442358,
+    "eval_loss": 3.9502358436584473,
+    "eval_runtime": 120.5085,
+    "eval_samples_per_second": 50.295,
+    "eval_steps_per_second": 6.29,
+    "perplexity": 51.94761690624261,
+    "total_flos": 2.4088250058539008e+17,
+    "train_loss": 4.953971872866993,
+    "train_runtime": 3149.0681,
+    "train_samples_per_second": 17.32,
+    "train_steps_per_second": 0.271
+}

checkpoint-500/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-500/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "DongfuJiang/Qwen2.5-0.5B-Instruct",
+  "adapter_hidden_size": null,
+  "aggregation_mode": "mlp",
+  "architectures": [
+    "Qwen2ChunkingForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "chunking_mode": "uniform_with_shared_start",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layers_to_prune": null,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2_chunking",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "num_layers_per_chunk": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_adapters": false,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98dc386f6b8dd3f1de88e5be9d7764ba1751e24f3275cc7c07aca9811fa608e7
+size 1471720384

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbcdb32451db221a8dc7da41f77b1c0e95bcbe04334ff6d9cee245107103fbf
+size 1921800122

checkpoint-500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

checkpoint-500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

checkpoint-500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

checkpoint-500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

checkpoint-500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

checkpoint-500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

checkpoint-500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b8e87305e4845ce7851de7641acda9c70ee03aba232b8f8c8019dc55a199e9
+size 1064

checkpoint-500/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-500/tokenizer.json

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,391 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5866823115283074,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011733646230566148,
+      "grad_norm": 158.19329833984375,
+      "learning_rate": 1.1627906976744188e-06,
+      "loss": 16.8855,
+      "step": 10
+    },
+    {
+      "epoch": 0.023467292461132296,
+      "grad_norm": 56.40153884887695,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 15.0868,
+      "step": 20
+    },
+    {
+      "epoch": 0.03520093869169844,
+      "grad_norm": 65.71855163574219,
+      "learning_rate": 3.4883720930232564e-06,
+      "loss": 12.3109,
+      "step": 30
+    },
+    {
+      "epoch": 0.04693458492226459,
+      "grad_norm": 47.712074279785156,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 10.5382,
+      "step": 40
+    },
+    {
+      "epoch": 0.05866823115283074,
+      "grad_norm": 18.6832332611084,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 9.1851,
+      "step": 50
+    },
+    {
+      "epoch": 0.07040187738339689,
+      "grad_norm": 23.909244537353516,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 8.1563,
+      "step": 60
+    },
+    {
+      "epoch": 0.08213552361396304,
+      "grad_norm": 15.935365676879883,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 7.2683,
+      "step": 70
+    },
+    {
+      "epoch": 0.09386916984452918,
+      "grad_norm": 18.156291961669922,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 6.6225,
+      "step": 80
+    },
+    {
+      "epoch": 0.10560281607509533,
+      "grad_norm": 14.451725959777832,
+      "learning_rate": 9.999327189969768e-06,
+      "loss": 6.2144,
+      "step": 90
+    },
+    {
+      "epoch": 0.11733646230566148,
+      "grad_norm": 20.55025863647461,
+      "learning_rate": 9.991760156443892e-06,
+      "loss": 5.9333,
+      "step": 100
+    },
+    {
+      "epoch": 0.12907010853622763,
+      "grad_norm": 9.335273742675781,
+      "learning_rate": 9.975797845734699e-06,
+      "loss": 5.7416,
+      "step": 110
+    },
+    {
+      "epoch": 0.14080375476679377,
+      "grad_norm": 12.944341659545898,
+      "learning_rate": 9.951467103687879e-06,
+      "loss": 5.5528,
+      "step": 120
+    },
+    {
+      "epoch": 0.15253740099735993,
+      "grad_norm": 13.229466438293457,
+      "learning_rate": 9.918808850403192e-06,
+      "loss": 5.4369,
+      "step": 130
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 10.06254768371582,
+      "learning_rate": 9.877878011413924e-06,
+      "loss": 5.2938,
+      "step": 140
+    },
+    {
+      "epoch": 0.17600469345849223,
+      "grad_norm": 11.859220504760742,
+      "learning_rate": 9.828743425311654e-06,
+      "loss": 5.2013,
+      "step": 150
+    },
+    {
+      "epoch": 0.18773833968905837,
+      "grad_norm": 11.55561637878418,
+      "learning_rate": 9.771487727971642e-06,
+      "loss": 5.1234,
+      "step": 160
+    },
+    {
+      "epoch": 0.19947198591962453,
+      "grad_norm": 9.468324661254883,
+      "learning_rate": 9.70620721357358e-06,
+      "loss": 5.0474,
+      "step": 170
+    },
+    {
+      "epoch": 0.21120563215019067,
+      "grad_norm": 10.732479095458984,
+      "learning_rate": 9.633011672651443e-06,
+      "loss": 4.9805,
+      "step": 180
+    },
+    {
+      "epoch": 0.22293927838075683,
+      "grad_norm": 10.652563095092773,
+      "learning_rate": 9.552024207444794e-06,
+      "loss": 4.9355,
+      "step": 190
+    },
+    {
+      "epoch": 0.23467292461132297,
+      "grad_norm": 6.873952865600586,
+      "learning_rate": 9.463381024862116e-06,
+      "loss": 4.8471,
+      "step": 200
+    },
+    {
+      "epoch": 0.2464065708418891,
+      "grad_norm": 9.639769554138184,
+      "learning_rate": 9.36723120740434e-06,
+      "loss": 4.8064,
+      "step": 210
+    },
+    {
+      "epoch": 0.25814021707245527,
+      "grad_norm": 9.389469146728516,
+      "learning_rate": 9.26373646243388e-06,
+      "loss": 4.7518,
+      "step": 220
+    },
+    {
+      "epoch": 0.26987386330302143,
+      "grad_norm": 6.799657344818115,
+      "learning_rate": 9.153070850210803e-06,
+      "loss": 4.6989,
+      "step": 230
+    },
+    {
+      "epoch": 0.28160750953358754,
+      "grad_norm": 9.919508934020996,
+      "learning_rate": 9.035420491153596e-06,
+      "loss": 4.6511,
+      "step": 240
+    },
+    {
+      "epoch": 0.2933411557641537,
+      "grad_norm": 8.014354705810547,
+      "learning_rate": 8.910983252816794e-06,
+      "loss": 4.6346,
+      "step": 250
+    },
+    {
+      "epoch": 0.30507480199471987,
+      "grad_norm": 7.689748287200928,
+      "learning_rate": 8.779968417111991e-06,
+      "loss": 4.6151,
+      "step": 260
+    },
+    {
+      "epoch": 0.31680844822528603,
+      "grad_norm": 6.760936737060547,
+      "learning_rate": 8.642596328331864e-06,
+      "loss": 4.5728,
+      "step": 270
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 7.691278457641602,
+      "learning_rate": 8.499098022569177e-06,
+      "loss": 4.5157,
+      "step": 280
+    },
+    {
+      "epoch": 0.3402757406864183,
+      "grad_norm": 6.514494895935059,
+      "learning_rate": 8.349714839154035e-06,
+      "loss": 4.4863,
+      "step": 290
+    },
+    {
+      "epoch": 0.35200938691698447,
+      "grad_norm": 7.121197700500488,
+      "learning_rate": 8.19469801476288e-06,
+      "loss": 4.4432,
+      "step": 300
+    },
+    {
+      "epoch": 0.3637430331475506,
+      "grad_norm": 6.118000030517578,
+      "learning_rate": 8.034308260881854e-06,
+      "loss": 4.4499,
+      "step": 310
+    },
+    {
+      "epoch": 0.37547667937811674,
+      "grad_norm": 6.461143493652344,
+      "learning_rate": 7.868815325335168e-06,
+      "loss": 4.4294,
+      "step": 320
+    },
+    {
+      "epoch": 0.3872103256086829,
+      "grad_norm": 5.675752639770508,
+      "learning_rate": 7.698497538615928e-06,
+      "loss": 4.4118,
+      "step": 330
+    },
+    {
+      "epoch": 0.39894397183924907,
+      "grad_norm": 5.432925701141357,
+      "learning_rate": 7.5236413457823745e-06,
+      "loss": 4.3359,
+      "step": 340
+    },
+    {
+      "epoch": 0.4106776180698152,
+      "grad_norm": 4.405528545379639,
+      "learning_rate": 7.344540824706855e-06,
+      "loss": 4.3412,
+      "step": 350
+    },
+    {
+      "epoch": 0.42241126430038134,
+      "grad_norm": 5.6253886222839355,
+      "learning_rate": 7.161497191487693e-06,
+      "loss": 4.3042,
+      "step": 360
+    },
+    {
+      "epoch": 0.4341449105309475,
+      "grad_norm": 4.410622596740723,
+      "learning_rate": 6.9748182938558225e-06,
+      "loss": 4.3081,
+      "step": 370
+    },
+    {
+      "epoch": 0.44587855676151367,
+      "grad_norm": 5.902497291564941,
+      "learning_rate": 6.784818093428144e-06,
+      "loss": 4.2947,
+      "step": 380
+    },
+    {
+      "epoch": 0.4576122029920798,
+      "grad_norm": 4.575879096984863,
+      "learning_rate": 6.591816137678388e-06,
+      "loss": 4.2322,
+      "step": 390
+    },
+    {
+      "epoch": 0.46934584922264594,
+      "grad_norm": 4.4911956787109375,
+      "learning_rate": 6.396137022513545e-06,
+      "loss": 4.2262,
+      "step": 400
+    },
+    {
+      "epoch": 0.4810794954532121,
+      "grad_norm": 5.822395324707031,
+      "learning_rate": 6.198109846359682e-06,
+      "loss": 4.2415,
+      "step": 410
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 5.228771209716797,
+      "learning_rate": 5.998067656675318e-06,
+      "loss": 4.1806,
+      "step": 420
+    },
+    {
+      "epoch": 0.5045467879143444,
+      "grad_norm": 4.534237861633301,
+      "learning_rate": 5.7963468898232026e-06,
+      "loss": 4.2051,
+      "step": 430
+    },
+    {
+      "epoch": 0.5162804341449105,
+      "grad_norm": 4.696606636047363,
+      "learning_rate": 5.593286805242549e-06,
+      "loss": 4.1919,
+      "step": 440
+    },
+    {
+      "epoch": 0.5280140803754767,
+      "grad_norm": 4.736946105957031,
+      "learning_rate": 5.389228914873334e-06,
+      "loss": 4.184,
+      "step": 450
+    },
+    {
+      "epoch": 0.5397477266060429,
+      "grad_norm": 3.714312791824341,
+      "learning_rate": 5.18451640879228e-06,
+      "loss": 4.164,
+      "step": 460
+    },
+    {
+      "epoch": 0.551481372836609,
+      "grad_norm": 4.020701885223389,
+      "learning_rate": 4.979493578026523e-06,
+      "loss": 4.1435,
+      "step": 470
+    },
+    {
+      "epoch": 0.5632150190671751,
+      "grad_norm": 3.9667632579803467,
+      "learning_rate": 4.774505235515628e-06,
+      "loss": 4.1239,
+      "step": 480
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 3.7402360439300537,
+      "learning_rate": 4.5698961361958955e-06,
+      "loss": 4.1297,
+      "step": 490
+    },
+    {
+      "epoch": 0.5866823115283074,
+      "grad_norm": 3.3449549674987793,
+      "learning_rate": 4.3660103971821635e-06,
+      "loss": 4.107,
+      "step": 500
+    },
+    {
+      "epoch": 0.5866823115283074,
+      "eval_loss": 4.097958087921143,
+      "eval_runtime": 120.8684,
+      "eval_samples_per_second": 50.145,
+      "eval_steps_per_second": 6.271,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 852,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.413629698113536e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2930fe4ac62a09f64dab3c7a5475ee28cb161e625cedcb525f5c5328c26be104
+size 5496

checkpoint-852/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-852/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "DongfuJiang/Qwen2.5-0.5B-Instruct",
+  "adapter_hidden_size": null,
+  "aggregation_mode": "mlp",
+  "architectures": [
+    "Qwen2ChunkingForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "chunking_mode": "uniform_with_shared_start",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layers_to_prune": null,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2_chunking",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "num_layers_per_chunk": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_adapters": false,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-852/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

checkpoint-852/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91362e21fb85c5a7fadc0c45ebeb3893ec0c5cfd72b353556d1442ec76491cc
+size 1471720384

checkpoint-852/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0256790de0f0ea67bc55d0fd8382f09eb78cd8b93c9a5519d62a1513f87bb20b
+size 1921800122

checkpoint-852/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

checkpoint-852/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

checkpoint-852/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

checkpoint-852/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

checkpoint-852/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

checkpoint-852/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

checkpoint-852/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

checkpoint-852/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

checkpoint-852/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cea3ad9d75460ada93ba40415f1a62f00e895914f396644e273ed6512e901a
+size 1064

checkpoint-852/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-852/tokenizer.json

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

checkpoint-852/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-852/trainer_state.json

@@ -0,0 +1,636 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997066588442358,
+  "eval_steps": 500,
+  "global_step": 852,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011733646230566148,
+      "grad_norm": 158.19329833984375,
+      "learning_rate": 1.1627906976744188e-06,
+      "loss": 16.8855,
+      "step": 10
+    },
+    {
+      "epoch": 0.023467292461132296,
+      "grad_norm": 56.40153884887695,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 15.0868,
+      "step": 20
+    },
+    {
+      "epoch": 0.03520093869169844,
+      "grad_norm": 65.71855163574219,
+      "learning_rate": 3.4883720930232564e-06,
+      "loss": 12.3109,
+      "step": 30
+    },
+    {
+      "epoch": 0.04693458492226459,
+      "grad_norm": 47.712074279785156,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 10.5382,
+      "step": 40
+    },
+    {
+      "epoch": 0.05866823115283074,
+      "grad_norm": 18.6832332611084,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 9.1851,
+      "step": 50
+    },
+    {
+      "epoch": 0.07040187738339689,
+      "grad_norm": 23.909244537353516,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 8.1563,
+      "step": 60
+    },
+    {
+      "epoch": 0.08213552361396304,
+      "grad_norm": 15.935365676879883,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 7.2683,
+      "step": 70
+    },
+    {
+      "epoch": 0.09386916984452918,
+      "grad_norm": 18.156291961669922,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 6.6225,
+      "step": 80
+    },
+    {
+      "epoch": 0.10560281607509533,
+      "grad_norm": 14.451725959777832,
+      "learning_rate": 9.999327189969768e-06,
+      "loss": 6.2144,
+      "step": 90
+    },
+    {
+      "epoch": 0.11733646230566148,
+      "grad_norm": 20.55025863647461,
+      "learning_rate": 9.991760156443892e-06,
+      "loss": 5.9333,
+      "step": 100
+    },
+    {
+      "epoch": 0.12907010853622763,
+      "grad_norm": 9.335273742675781,
+      "learning_rate": 9.975797845734699e-06,
+      "loss": 5.7416,
+      "step": 110
+    },
+    {
+      "epoch": 0.14080375476679377,
+      "grad_norm": 12.944341659545898,
+      "learning_rate": 9.951467103687879e-06,
+      "loss": 5.5528,
+      "step": 120
+    },
+    {
+      "epoch": 0.15253740099735993,
+      "grad_norm": 13.229466438293457,
+      "learning_rate": 9.918808850403192e-06,
+      "loss": 5.4369,
+      "step": 130
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 10.06254768371582,
+      "learning_rate": 9.877878011413924e-06,
+      "loss": 5.2938,
+      "step": 140
+    },
+    {
+      "epoch": 0.17600469345849223,
+      "grad_norm": 11.859220504760742,
+      "learning_rate": 9.828743425311654e-06,
+      "loss": 5.2013,
+      "step": 150
+    },
+    {
+      "epoch": 0.18773833968905837,
+      "grad_norm": 11.55561637878418,
+      "learning_rate": 9.771487727971642e-06,
+      "loss": 5.1234,
+      "step": 160
+    },
+    {
+      "epoch": 0.19947198591962453,
+      "grad_norm": 9.468324661254883,
+      "learning_rate": 9.70620721357358e-06,
+      "loss": 5.0474,
+      "step": 170
+    },
+    {
+      "epoch": 0.21120563215019067,
+      "grad_norm": 10.732479095458984,
+      "learning_rate": 9.633011672651443e-06,
+      "loss": 4.9805,
+      "step": 180
+    },
+    {
+      "epoch": 0.22293927838075683,
+      "grad_norm": 10.652563095092773,
+      "learning_rate": 9.552024207444794e-06,
+      "loss": 4.9355,
+      "step": 190
+    },
+    {
+      "epoch": 0.23467292461132297,
+      "grad_norm": 6.873952865600586,
+      "learning_rate": 9.463381024862116e-06,
+      "loss": 4.8471,
+      "step": 200
+    },
+    {
+      "epoch": 0.2464065708418891,
+      "grad_norm": 9.639769554138184,
+      "learning_rate": 9.36723120740434e-06,
+      "loss": 4.8064,
+      "step": 210
+    },
+    {
+      "epoch": 0.25814021707245527,
+      "grad_norm": 9.389469146728516,
+      "learning_rate": 9.26373646243388e-06,
+      "loss": 4.7518,
+      "step": 220
+    },
+    {
+      "epoch": 0.26987386330302143,
+      "grad_norm": 6.799657344818115,
+      "learning_rate": 9.153070850210803e-06,
+      "loss": 4.6989,
+      "step": 230
+    },
+    {
+      "epoch": 0.28160750953358754,
+      "grad_norm": 9.919508934020996,
+      "learning_rate": 9.035420491153596e-06,
+      "loss": 4.6511,
+      "step": 240
+    },
+    {
+      "epoch": 0.2933411557641537,
+      "grad_norm": 8.014354705810547,
+      "learning_rate": 8.910983252816794e-06,
+      "loss": 4.6346,
+      "step": 250
+    },
+    {
+      "epoch": 0.30507480199471987,
+      "grad_norm": 7.689748287200928,
+      "learning_rate": 8.779968417111991e-06,
+      "loss": 4.6151,
+      "step": 260
+    },
+    {
+      "epoch": 0.31680844822528603,
+      "grad_norm": 6.760936737060547,
+      "learning_rate": 8.642596328331864e-06,
+      "loss": 4.5728,
+      "step": 270
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 7.691278457641602,
+      "learning_rate": 8.499098022569177e-06,
+      "loss": 4.5157,
+      "step": 280
+    },
+    {
+      "epoch": 0.3402757406864183,
+      "grad_norm": 6.514494895935059,
+      "learning_rate": 8.349714839154035e-06,
+      "loss": 4.4863,
+      "step": 290
+    },
+    {
+      "epoch": 0.35200938691698447,
+      "grad_norm": 7.121197700500488,
+      "learning_rate": 8.19469801476288e-06,
+      "loss": 4.4432,
+      "step": 300
+    },
+    {
+      "epoch": 0.3637430331475506,
+      "grad_norm": 6.118000030517578,
+      "learning_rate": 8.034308260881854e-06,
+      "loss": 4.4499,
+      "step": 310
+    },
+    {
+      "epoch": 0.37547667937811674,
+      "grad_norm": 6.461143493652344,
+      "learning_rate": 7.868815325335168e-06,
+      "loss": 4.4294,
+      "step": 320
+    },
+    {
+      "epoch": 0.3872103256086829,
+      "grad_norm": 5.675752639770508,
+      "learning_rate": 7.698497538615928e-06,
+      "loss": 4.4118,
+      "step": 330
+    },
+    {
+      "epoch": 0.39894397183924907,
+      "grad_norm": 5.432925701141357,
+      "learning_rate": 7.5236413457823745e-06,
+      "loss": 4.3359,
+      "step": 340
+    },
+    {
+      "epoch": 0.4106776180698152,
+      "grad_norm": 4.405528545379639,
+      "learning_rate": 7.344540824706855e-06,
+      "loss": 4.3412,
+      "step": 350
+    },
+    {
+      "epoch": 0.42241126430038134,
+      "grad_norm": 5.6253886222839355,
+      "learning_rate": 7.161497191487693e-06,
+      "loss": 4.3042,
+      "step": 360
+    },
+    {
+      "epoch": 0.4341449105309475,
+      "grad_norm": 4.410622596740723,
+      "learning_rate": 6.9748182938558225e-06,
+      "loss": 4.3081,
+      "step": 370
+    },
+    {
+      "epoch": 0.44587855676151367,
+      "grad_norm": 5.902497291564941,
+      "learning_rate": 6.784818093428144e-06,
+      "loss": 4.2947,
+      "step": 380
+    },
+    {
+      "epoch": 0.4576122029920798,
+      "grad_norm": 4.575879096984863,
+      "learning_rate": 6.591816137678388e-06,
+      "loss": 4.2322,
+      "step": 390
+    },
+    {
+      "epoch": 0.46934584922264594,
+      "grad_norm": 4.4911956787109375,
+      "learning_rate": 6.396137022513545e-06,
+      "loss": 4.2262,
+      "step": 400
+    },
+    {
+      "epoch": 0.4810794954532121,
+      "grad_norm": 5.822395324707031,
+      "learning_rate": 6.198109846359682e-06,
+      "loss": 4.2415,
+      "step": 410
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 5.228771209716797,
+      "learning_rate": 5.998067656675318e-06,
+      "loss": 4.1806,
+      "step": 420
+    },
+    {
+      "epoch": 0.5045467879143444,
+      "grad_norm": 4.534237861633301,
+      "learning_rate": 5.7963468898232026e-06,
+      "loss": 4.2051,
+      "step": 430
+    },
+    {
+      "epoch": 0.5162804341449105,
+      "grad_norm": 4.696606636047363,
+      "learning_rate": 5.593286805242549e-06,
+      "loss": 4.1919,
+      "step": 440
+    },
+    {
+      "epoch": 0.5280140803754767,
+      "grad_norm": 4.736946105957031,
+      "learning_rate": 5.389228914873334e-06,
+      "loss": 4.184,
+      "step": 450
+    },
+    {
+      "epoch": 0.5397477266060429,
+      "grad_norm": 3.714312791824341,
+      "learning_rate": 5.18451640879228e-06,
+      "loss": 4.164,
+      "step": 460
+    },
+    {
+      "epoch": 0.551481372836609,
+      "grad_norm": 4.020701885223389,
+      "learning_rate": 4.979493578026523e-06,
+      "loss": 4.1435,
+      "step": 470
+    },
+    {
+      "epoch": 0.5632150190671751,
+      "grad_norm": 3.9667632579803467,
+      "learning_rate": 4.774505235515628e-06,
+      "loss": 4.1239,
+      "step": 480
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 3.7402360439300537,
+      "learning_rate": 4.5698961361958955e-06,
+      "loss": 4.1297,
+      "step": 490
+    },
+    {
+      "epoch": 0.5866823115283074,
+      "grad_norm": 3.3449549674987793,
+      "learning_rate": 4.3660103971821635e-06,
+      "loss": 4.107,
+      "step": 500
+    },
+    {
+      "epoch": 0.5866823115283074,
+      "eval_loss": 4.097958087921143,
+      "eval_runtime": 120.8684,
+      "eval_samples_per_second": 50.145,
+      "eval_steps_per_second": 6.271,
+      "step": 500
+    },
+    {
+      "epoch": 0.5984159577588736,
+      "grad_norm": 3.9140114784240723,
+      "learning_rate": 4.163190919022357e-06,
+      "loss": 4.0708,
+      "step": 510
+    },
+    {
+      "epoch": 0.6101496039894397,
+      "grad_norm": 2.8521409034729004,
+      "learning_rate": 3.961778808998066e-06,
+      "loss": 4.0891,
+      "step": 520
+    },
+    {
+      "epoch": 0.6218832502200059,
+      "grad_norm": 3.21331524848938,
+      "learning_rate": 3.762112807441108e-06,
+      "loss": 4.0593,
+      "step": 530
+    },
+    {
+      "epoch": 0.6336168964505721,
+      "grad_norm": 2.4329190254211426,
+      "learning_rate": 3.56452871803087e-06,
+      "loss": 4.0827,
+      "step": 540
+    },
+    {
+      "epoch": 0.6453505426811381,
+      "grad_norm": 2.4796149730682373,
+      "learning_rate": 3.3693588430306035e-06,
+      "loss": 4.0539,
+      "step": 550
+    },
+    {
+      "epoch": 0.6570841889117043,
+      "grad_norm": 2.6811649799346924,
+      "learning_rate": 3.1769314244125056e-06,
+      "loss": 4.0513,
+      "step": 560
+    },
+    {
+      "epoch": 0.6688178351422704,
+      "grad_norm": 2.397920846939087,
+      "learning_rate": 2.987570091811479e-06,
+      "loss": 4.0313,
+      "step": 570
+    },
+    {
+      "epoch": 0.6805514813728366,
+      "grad_norm": 2.68379807472229,
+      "learning_rate": 2.801593318236078e-06,
+      "loss": 4.0205,
+      "step": 580
+    },
+    {
+      "epoch": 0.6922851276034028,
+      "grad_norm": 2.4063057899475098,
+      "learning_rate": 2.6193138844519785e-06,
+      "loss": 4.0359,
+      "step": 590
+    },
+    {
+      "epoch": 0.7040187738339689,
+      "grad_norm": 2.6436047554016113,
+      "learning_rate": 2.4410383529388448e-06,
+      "loss": 4.0142,
+      "step": 600
+    },
+    {
+      "epoch": 0.7157524200645351,
+      "grad_norm": 2.204946756362915,
+      "learning_rate": 2.2670665523052534e-06,
+      "loss": 3.9906,
+      "step": 610
+    },
+    {
+      "epoch": 0.7274860662951012,
+      "grad_norm": 2.283926010131836,
+      "learning_rate": 2.097691073028836e-06,
+      "loss": 4.0181,
+      "step": 620
+    },
+    {
+      "epoch": 0.7392197125256673,
+      "grad_norm": 2.106992483139038,
+      "learning_rate": 1.9331967753697077e-06,
+      "loss": 4.0127,
+      "step": 630
+    },
+    {
+      "epoch": 0.7509533587562335,
+      "grad_norm": 2.0476365089416504,
+      "learning_rate": 1.7738603102847696e-06,
+      "loss": 4.0151,
+      "step": 640
+    },
+    {
+      "epoch": 0.7626870049867996,
+      "grad_norm": 2.019026517868042,
+      "learning_rate": 1.6199496541486647e-06,
+      "loss": 3.9824,
+      "step": 650
+    },
+    {
+      "epoch": 0.7744206512173658,
+      "grad_norm": 2.1455600261688232,
+      "learning_rate": 1.471723658063856e-06,
+      "loss": 3.9689,
+      "step": 660
+    },
+    {
+      "epoch": 0.786154297447932,
+      "grad_norm": 2.0698354244232178,
+      "learning_rate": 1.3294316125178474e-06,
+      "loss": 3.9877,
+      "step": 670
+    },
+    {
+      "epoch": 0.7978879436784981,
+      "grad_norm": 2.0827808380126953,
+      "learning_rate": 1.1933128281197042e-06,
+      "loss": 3.9864,
+      "step": 680
+    },
+    {
+      "epoch": 0.8096215899090642,
+      "grad_norm": 2.235387086868286,
+      "learning_rate": 1.063596233120997e-06,
+      "loss": 3.9962,
+      "step": 690
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "grad_norm": 2.029141902923584,
+      "learning_rate": 9.40499988398082e-07,
+      "loss": 3.9658,
+      "step": 700
+    },
+    {
+      "epoch": 0.8330888823701965,
+      "grad_norm": 1.9971383810043335,
+      "learning_rate": 8.242311205432418e-07,
+      "loss": 3.9552,
+      "step": 710
+    },
+    {
+      "epoch": 0.8448225286007627,
+      "grad_norm": 2.0364105701446533,
+      "learning_rate": 7.149851736817609e-07,
+      "loss": 3.9712,
+      "step": 720
+    },
+    {
+      "epoch": 0.8565561748313288,
+      "grad_norm": 1.8077551126480103,
+      "learning_rate": 6.12945880600535e-07,
+      "loss": 3.9483,
+      "step": 730
+    },
+    {
+      "epoch": 0.868289821061895,
+      "grad_norm": 1.9532560110092163,
+      "learning_rate": 5.18284853741301e-07,
+      "loss": 3.9692,
+      "step": 740
+    },
+    {
+      "epoch": 0.8800234672924612,
+      "grad_norm": 2.1647019386291504,
+      "learning_rate": 4.311612965781903e-07,
+      "loss": 3.9518,
+      "step": 750
+    },
+    {
+      "epoch": 0.8917571135230273,
+      "grad_norm": 1.997475504875183,
+      "learning_rate": 3.5172173586502543e-07,
+      "loss": 3.9206,
+      "step": 760
+    },
+    {
+      "epoch": 0.9034907597535934,
+      "grad_norm": 1.925897240638733,
+      "learning_rate": 2.800997752026596e-07,
+      "loss": 3.9863,
+      "step": 770
+    },
+    {
+      "epoch": 0.9152244059841596,
+      "grad_norm": 1.7154505252838135,
+      "learning_rate": 2.1641587034083756e-07,
+      "loss": 3.9431,
+      "step": 780
+    },
+    {
+      "epoch": 0.9269580522147257,
+      "grad_norm": 1.8487329483032227,
+      "learning_rate": 1.6077712659244792e-07,
+      "loss": 3.9338,
+      "step": 790
+    },
+    {
+      "epoch": 0.9386916984452919,
+      "grad_norm": 1.8064842224121094,
+      "learning_rate": 1.1327711870091963e-07,
+      "loss": 3.9529,
+      "step": 800
+    },
+    {
+      "epoch": 0.950425344675858,
+      "grad_norm": 1.842482328414917,
+      "learning_rate": 7.399573346368871e-08,
+      "loss": 3.9651,
+      "step": 810
+    },
+    {
+      "epoch": 0.9621589909064242,
+      "grad_norm": 1.6884958744049072,
+      "learning_rate": 4.299903537641703e-08,
+      "loss": 3.9445,
+      "step": 820
+    },
+    {
+      "epoch": 0.9738926371369904,
+      "grad_norm": 1.7613016366958618,
+      "learning_rate": 2.0339155523945164e-08,
+      "loss": 3.9624,
+      "step": 830
+    },
+    {
+      "epoch": 0.9856262833675564,
+      "grad_norm": 1.8088396787643433,
+      "learning_rate": 6.054203904817812e-09,
+      "loss": 3.9723,
+      "step": 840
+    },
+    {
+      "epoch": 0.9973599295981226,
+      "grad_norm": 1.7286911010742188,
+      "learning_rate": 1.6820533686179308e-10,
+      "loss": 3.9213,
+      "step": 850
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 852,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4088250058539008e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-852/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2930fe4ac62a09f64dab3c7a5475ee28cb161e625cedcb525f5c5328c26be104
+size 5496

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "DongfuJiang/Qwen2.5-0.5B-Instruct",
+  "adapter_hidden_size": null,
+  "aggregation_mode": "mlp",
+  "architectures": [
+    "Qwen2ChunkingForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "chunking_mode": "uniform_with_shared_start",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layers_to_prune": null,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2_chunking",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "num_layers_per_chunk": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_adapters": false,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9997066588442358,
+    "eval_loss": 3.9502358436584473,
+    "eval_runtime": 120.5085,
+    "eval_samples_per_second": 50.295,
+    "eval_steps_per_second": 6.29,
+    "perplexity": 51.94761690624261
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}