Hugging Face's logo

bluuluu
/
Qwen2-VL-2B-Instruct-SFT

Image-Text-to-Text
Transformers
Safetensors
qwen2_vl
Generated from Trainer
R1-V
trl
sft
conversational
text-generation-inference
Model card Files Community
bluuluu commited on
Commit
709da1f
·
verified ·
1 Parent(s): 439935c

Model save

Browse files
Files changed (9) hide show
  1. README.md +2 -4
  2. all_results.json +6 -6
  3. config.json +1 -1
  4. model.safetensors +1 -1
  5. tokenizer.json +2 -2
  6. tokenizer_config.json +0 -1
  7. train_results.json +6 -6
  8. trainer_state.json +0 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -1,11 +1,9 @@
1
  ---
2
  base_model: Qwen/Qwen2-VL-2B-Instruct
3
- datasets: MMInstruction/Clevr_CoGenT_TrainA_R1
4
  library_name: transformers
5
  model_name: Qwen2-VL-2B-Instruct-SFT
6
  tags:
7
  - generated_from_trainer
8
- - R1-V
9
  - trl
10
  - sft
11
  licence: license
@@ -13,7 +11,7 @@ licence: license
13
 
14
  # Model Card for Qwen2-VL-2B-Instruct-SFT
15
 
16
- This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the [MMInstruction/Clevr_CoGenT_TrainA_R1](https://huggingface.co/datasets/MMInstruction/Clevr_CoGenT_TrainA_R1) dataset.
17
  It has been trained using [TRL](https://github.com/huggingface/trl).
18
 
19
  ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
29
 
30
  ## Training procedure
31
 
32
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/hxbtcd5t)
33
 
34
 
35
  This model was trained with SFT.
 
1
  ---
2
  base_model: Qwen/Qwen2-VL-2B-Instruct
 
3
  library_name: transformers
4
  model_name: Qwen2-VL-2B-Instruct-SFT
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
  licence: license
 
11
 
12
  # Model Card for Qwen2-VL-2B-Instruct-SFT
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/kd2rv0e6)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.9990182603573532,
3
- "total_flos": 3801667199303680.0,
4
- "train_loss": 0.13866351419509207,
5
- "train_runtime": 19174.2073,
6
  "train_samples": 40742,
7
- "train_samples_per_second": 2.125,
8
- "train_steps_per_second": 0.033
9
  }
 
1
  {
2
+ "epoch": 0.9998919736415686,
3
+ "total_flos": 2.0789981999005696e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 2.6266,
6
  "train_samples": 40742,
7
+ "train_samples_per_second": 15511.09,
8
+ "train_steps_per_second": 242.135
9
  }
config.json CHANGED
@@ -31,7 +31,7 @@
31
  "tie_word_embeddings": true,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.51.1",
34
- "use_cache": true,
35
  "use_sliding_window": false,
36
  "video_token_id": 151656,
37
  "vision_config": {
 
31
  "tie_word_embeddings": true,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.51.1",
34
+ "use_cache": false,
35
  "use_sliding_window": false,
36
  "video_token_id": 151656,
37
  "vision_config": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b273740cd5cd9da749e890d55f3aa7359dab6251a6b6efc9401e1679cac1fe73
3
  size 4418050848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93d511a98455c9d5009dcd7ea903d76fcb4303705b60a2d3a9362d1f716da4d
3
  size 4418050848
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
3
- size 11420538
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json CHANGED
@@ -138,7 +138,6 @@
138
  "model_max_length": 32768,
139
  "pad_token": "<|endoftext|>",
140
  "padding_side": "left",
141
- "processor_class": "Qwen2VLProcessor",
142
  "split_special_tokens": false,
143
  "tokenizer_class": "Qwen2Tokenizer",
144
  "unk_token": null
 
138
  "model_max_length": 32768,
139
  "pad_token": "<|endoftext|>",
140
  "padding_side": "left",
 
141
  "split_special_tokens": false,
142
  "tokenizer_class": "Qwen2Tokenizer",
143
  "unk_token": null
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.9990182603573532,
3
- "total_flos": 3801667199303680.0,
4
- "train_loss": 0.13866351419509207,
5
- "train_runtime": 19174.2073,
6
  "train_samples": 40742,
7
- "train_samples_per_second": 2.125,
8
- "train_steps_per_second": 0.033
9
  }
 
1
  {
2
+ "epoch": 0.9998919736415686,
3
+ "total_flos": 2.0789981999005696e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 2.6266,
6
  "train_samples": 40742,
7
+ "train_samples_per_second": 15511.09,
8
+ "train_steps_per_second": 242.135
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0ad5fbd3e0469121f3468c0072223705b7b01e3a9485a29ea073465504a8a2e
3
  size 7096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5400234002a39681ded90e6b855bb91540f369831054877899b9164742860350
3
  size 7096