Raullen commited on
Commit
4fc4792
·
verified ·
1 Parent(s): 178635f

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. README.md +81 -93
  3. adapter_config.json +4 -4
  4. adapter_model.safetensors +1 -1
  5. all_results.json +10 -6
  6. checkpoint-150/README.md +208 -0
  7. checkpoint-150/adapter_config.json +42 -0
  8. checkpoint-150/adapter_model.safetensors +3 -0
  9. checkpoint-150/added_tokens.json +16 -0
  10. checkpoint-150/chat_template.jinja +7 -0
  11. checkpoint-150/merges.txt +0 -0
  12. checkpoint-150/optimizer.pt +3 -0
  13. checkpoint-150/preprocessor_config.json +39 -0
  14. checkpoint-150/rng_state.pth +3 -0
  15. checkpoint-150/scheduler.pt +3 -0
  16. checkpoint-150/special_tokens_map.json +31 -0
  17. checkpoint-150/tokenizer.json +3 -0
  18. checkpoint-150/tokenizer_config.json +144 -0
  19. checkpoint-150/trainer_state.json +292 -0
  20. checkpoint-150/training_args.bin +3 -0
  21. checkpoint-150/video_preprocessor_config.json +43 -0
  22. checkpoint-150/vocab.json +0 -0
  23. checkpoint-550/README.md +208 -0
  24. checkpoint-550/adapter_config.json +42 -0
  25. checkpoint-550/adapter_model.safetensors +3 -0
  26. checkpoint-550/added_tokens.json +16 -0
  27. checkpoint-550/chat_template.jinja +7 -0
  28. checkpoint-550/merges.txt +0 -0
  29. checkpoint-550/optimizer.pt +3 -0
  30. checkpoint-550/preprocessor_config.json +39 -0
  31. checkpoint-550/rng_state.pth +3 -0
  32. checkpoint-550/scheduler.pt +3 -0
  33. checkpoint-550/special_tokens_map.json +31 -0
  34. checkpoint-550/tokenizer.json +3 -0
  35. checkpoint-550/tokenizer_config.json +144 -0
  36. checkpoint-550/trainer_state.json +980 -0
  37. checkpoint-550/training_args.bin +3 -0
  38. checkpoint-550/video_preprocessor_config.json +43 -0
  39. checkpoint-550/vocab.json +0 -0
  40. checkpoint-600/README.md +208 -0
  41. checkpoint-600/adapter_config.json +42 -0
  42. checkpoint-600/adapter_model.safetensors +3 -0
  43. checkpoint-600/added_tokens.json +16 -0
  44. checkpoint-600/chat_template.jinja +7 -0
  45. checkpoint-600/merges.txt +0 -0
  46. checkpoint-600/optimizer.pt +3 -0
  47. checkpoint-600/preprocessor_config.json +39 -0
  48. checkpoint-600/rng_state.pth +3 -0
  49. checkpoint-600/scheduler.pt +3 -0
  50. checkpoint-600/special_tokens_map.json +31 -0
.gitattributes CHANGED
@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,106 +1,94 @@
1
  ---
 
2
  license: mit
3
  base_model: Qwen/Qwen2-VL-2B-Instruct
4
- library_name: peft
5
  tags:
6
- - video-language-model
7
- - pet-detection
8
- - lora
9
- - qwen2-vl
10
- datasets:
11
- - Raullen/petvlm-data
12
  pipeline_tag: video-text-to-text
 
 
 
13
  ---
14
 
15
- # PetVLM - Sherlock Pet
16
-
17
- A LoRA adapter for Qwen2-VL-2B-Instruct, fine-tuned to detect naughty vs nice pet behavior with a sarcastic pet detective persona.
18
 
19
- ## Model Description
20
 
21
- - **Base Model**: [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct)
22
- - **Fine-tuning**: LoRA (rank=16, alpha=32, dropout=0.05)
23
- - **Training Data**: [Raullen/petvlm-data](https://huggingface.co/datasets/Raullen/petvlm-data) (40 labeled pet videos)
24
 
25
- ## Output Format
26
 
27
- - **ALERT!** - Naughty behavior detected (climbing, scratching furniture, stealing food, etc.)
 
28
  - **All Clear** - Good behavior (sleeping, eating properly, playing nicely)
29
 
30
- ## Usage
31
-
32
- ```python
33
- import torch
34
- from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
35
- from peft import PeftModel
36
- from qwen_vl_utils import process_vision_info
37
-
38
- # Load base model
39
- base_model = Qwen2VLForConditionalGeneration.from_pretrained(
40
- "Qwen/Qwen2-VL-2B-Instruct",
41
- torch_dtype=torch.bfloat16,
42
- device_map="auto"
43
- )
44
-
45
- # Load LoRA adapter
46
- model = PeftModel.from_pretrained(base_model, "Raullen/petvlm")
47
- model.eval()
48
-
49
- processor = AutoProcessor.from_pretrained("Raullen/petvlm")
50
-
51
- # Analyze a video
52
- messages = [
53
- {
54
- "role": "user",
55
- "content": [
56
- {"type": "video", "video": "path/to/video.mp4", "nframes": 8},
57
- {"type": "text", "text": "What is the pet doing?"}
58
- ]
59
- }
60
- ]
61
-
62
- text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
63
- image_inputs, video_inputs = process_vision_info(messages)
64
-
65
- inputs = processor(
66
- text=[text],
67
- images=image_inputs,
68
- videos=video_inputs,
69
- padding=True,
70
- return_tensors="pt"
71
- ).to(model.device)
72
-
73
- with torch.no_grad():
74
- output = model.generate(**inputs, max_new_tokens=256)
75
-
76
- response = processor.batch_decode(output[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0]
77
- print(response)
78
- ```
79
-
80
- ## Training Parameters
81
-
82
- | Parameter | Value |
83
- |-----------|-------|
84
- | LoRA rank | 16 |
85
- | LoRA alpha | 32 |
86
- | LoRA dropout | 0.05 |
87
- | Learning rate | 2e-4 |
88
- | Epochs | 30 |
89
- | Batch size | 1 |
90
-
91
- ## Sample Outputs
92
-
93
- **Naughty:**
94
- > "ALERT! The acrobatic menace has achieved full Spider-Cat mode, scaling kitchen cabinets like it's an Olympic sport. Recommend securing all elevated surfaces immediately."
95
-
96
- **Nice:**
97
- > "All Clear. The suspect is peacefully napping by the fireplace like a perfect little angel. Don't be fooled though - this is just the calm before the zoomies."
98
-
99
- ## Links
100
-
101
- - **Code**: [github.com/raullenchai/petvlm](https://github.com/raullenchai/petvlm)
102
- - **Dataset**: [Raullen/petvlm-data](https://huggingface.co/datasets/Raullen/petvlm-data)
103
-
104
- ## License
105
-
106
- MIT
 
1
  ---
2
+ library_name: peft
3
  license: mit
4
  base_model: Qwen/Qwen2-VL-2B-Instruct
 
5
  tags:
6
+ - llama-factory
7
+ - lora
8
+ - transformers
9
+ - video-language-model
10
+ - pet-detection
 
11
  pipeline_tag: video-text-to-text
12
+ model-index:
13
+ - name: petvlm-v1.1
14
+ results: []
15
  ---
16
 
17
+ # PetVLM v1.1 - Sherlock Pet
 
 
18
 
19
+ A video-language model fine-tuned to detect naughty vs nice pet behavior with a sarcastic pet detective persona.
20
 
21
+ **Accuracy: 87.5%** on held-out test set (7/8 correct)
 
 
22
 
23
+ ## Model Description
24
 
25
+ PetVLM analyzes pet videos and classifies behavior:
26
+ - **ALERT!** - Naughty behavior (climbing furniture, scratching, stealing food)
27
  - **All Clear** - Good behavior (sleeping, eating properly, playing nicely)
28
 
29
+ ## Training Data
30
+
31
+ - **Dataset Size**: 175 videos (cleaned and balanced)
32
+ - **Label Balance**: 51% ALERT / 49% All Clear
33
+ - **Best Checkpoint**: epoch 3.6
34
+ - **Training Time**: ~13 minutes on RTX 4090
35
+
36
+ ## Intended Uses
37
+
38
+ - Home pet monitoring
39
+ - Pet behavior analysis
40
+ - Entertainment (sarcastic detective persona)
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-05
48
+ - train_batch_size: 1
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 4
53
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
+ - lr_scheduler_type: cosine
55
+ - lr_scheduler_warmup_ratio: 0.05
56
+ - num_epochs: 15.0
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss |
61
+ |:-------------:|:-------:|:----:|:---------------:|
62
+ | 3.2859 | 0.6369 | 25 | 2.8292 |
63
+ | 2.0143 | 1.2548 | 50 | 1.9940 |
64
+ | 1.6829 | 1.8917 | 75 | 1.7856 |
65
+ | 1.4774 | 2.5096 | 100 | 1.7516 |
66
+ | 1.1908 | 3.1274 | 125 | 1.6817 |
67
+ | 1.2046 | 3.7643 | 150 | 1.6712 |
68
+ | 0.8012 | 4.3822 | 175 | 1.7618 |
69
+ | 0.9595 | 5.0 | 200 | 1.7216 |
70
+ | 0.5115 | 5.6369 | 225 | 1.8212 |
71
+ | 0.4666 | 6.2548 | 250 | 2.1777 |
72
+ | 0.4082 | 6.8917 | 275 | 2.0293 |
73
+ | 0.2262 | 7.5096 | 300 | 2.3396 |
74
+ | 0.1774 | 8.1274 | 325 | 2.3459 |
75
+ | 0.1512 | 8.7643 | 350 | 2.4745 |
76
+ | 0.0719 | 9.3822 | 375 | 2.7719 |
77
+ | 0.0741 | 10.0 | 400 | 2.7706 |
78
+ | 0.0679 | 10.6369 | 425 | 2.8739 |
79
+ | 0.036 | 11.2548 | 450 | 3.0192 |
80
+ | 0.03 | 11.8917 | 475 | 3.0430 |
81
+ | 0.0226 | 12.5096 | 500 | 3.1513 |
82
+ | 0.0155 | 13.1274 | 525 | 3.1610 |
83
+ | 0.015 | 13.7643 | 550 | 3.1778 |
84
+ | 0.0169 | 14.3822 | 575 | 3.2098 |
85
+ | 0.0223 | 15.0 | 600 | 3.2078 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - PEFT 0.17.1
91
+ - Transformers 4.57.1
92
+ - Pytorch 2.10.0+cu128
93
+ - Datasets 4.0.0
94
+ - Tokenizers 0.22.2
 
 
 
 
 
 
 
 
 
 
 
adapter_config.json CHANGED
@@ -27,11 +27,11 @@
27
  "target_modules": [
28
  "q_proj",
29
  "down_proj",
30
- "up_proj",
31
- "o_proj",
32
- "gate_proj",
33
  "k_proj",
34
- "v_proj"
 
 
 
35
  ],
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
 
27
  "target_modules": [
28
  "q_proj",
29
  "down_proj",
 
 
 
30
  "k_proj",
31
+ "gate_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj"
35
  ],
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1dd27a313df49d8699dc96b4aa1f47241b6125d126ab2cc20d4d0da9b451aa7
3
  size 73916992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6ca2140cc4e5fe0e7e52a899e43c4d0408c6a76746753531b402c24b163003
3
  size 73916992
all_results.json CHANGED
@@ -1,8 +1,12 @@
1
  {
2
- "epoch": 30.0,
3
- "total_flos": 5518966123560960.0,
4
- "train_loss": 0.2944723299946054,
5
- "train_runtime": 391.3174,
6
- "train_samples_per_second": 3.067,
7
- "train_steps_per_second": 3.067
 
 
 
 
8
  }
 
1
  {
2
+ "epoch": 15.0,
3
+ "eval_loss": 1.6712156534194946,
4
+ "eval_runtime": 1.0633,
5
+ "eval_samples_per_second": 16.928,
6
+ "eval_steps_per_second": 2.821,
7
+ "total_flos": 9073846488268800.0,
8
+ "train_loss": 0.6906163080533345,
9
+ "train_runtime": 779.0869,
10
+ "train_samples_per_second": 3.023,
11
+ "train_steps_per_second": 0.77
12
  }
checkpoint-150/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ''
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
7
+ - llama-factory
8
+ - lora
9
+ - transformers
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- 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. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ 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).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.17.1
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "down_proj",
30
+ "k_proj",
31
+ "gate_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-150/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6ca2140cc4e5fe0e7e52a899e43c4d0408c6a76746753531b402c24b163003
3
+ size 73916992
checkpoint-150/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-150/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a642d17c1c73fad815087952a478c772878909c210fd4914c986672a0bfa548
3
+ size 148053627
checkpoint-150/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6e6d863e9252d057b8bff34caf1524e75fc35623783624e2dd9cd68bc1abc9
3
+ size 14645
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3efc26ade01a6604f9a215d672abb2ca177306c58c8b2a458d5dfc6e30502e39
3
+ size 1465
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-150/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "clean_up_tokenization_spaces": false,
134
+ "eos_token": "<|im_end|>",
135
+ "errors": "replace",
136
+ "extra_special_tokens": {},
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "right",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 150,
3
+ "best_metric": 1.6712156534194946,
4
+ "best_model_checkpoint": "/root/Sherlock-Pet/output/sherlock_pet_v2/checkpoint-150",
5
+ "epoch": 3.7643312101910826,
6
+ "eval_steps": 25,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.12738853503184713,
14
+ "grad_norm": 2.745800018310547,
15
+ "learning_rate": 6.666666666666667e-06,
16
+ "loss": 3.7984,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.25477707006369427,
21
+ "grad_norm": 2.8450679779052734,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 3.8072,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.3821656050955414,
28
+ "grad_norm": 2.421614408493042,
29
+ "learning_rate": 2.3333333333333336e-05,
30
+ "loss": 3.7454,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.5095541401273885,
35
+ "grad_norm": 2.301647186279297,
36
+ "learning_rate": 3.1666666666666666e-05,
37
+ "loss": 3.3677,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.6369426751592356,
42
+ "grad_norm": 2.822660446166992,
43
+ "learning_rate": 4e-05,
44
+ "loss": 3.2859,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.6369426751592356,
49
+ "eval_loss": 2.8292243480682373,
50
+ "eval_runtime": 1.1711,
51
+ "eval_samples_per_second": 15.371,
52
+ "eval_steps_per_second": 2.562,
53
+ "step": 25
54
+ },
55
+ {
56
+ "epoch": 0.7643312101910829,
57
+ "grad_norm": 3.327336549758911,
58
+ "learning_rate": 4.8333333333333334e-05,
59
+ "loss": 2.8454,
60
+ "step": 30
61
+ },
62
+ {
63
+ "epoch": 0.89171974522293,
64
+ "grad_norm": 2.4171416759490967,
65
+ "learning_rate": 4.999392477398737e-05,
66
+ "loss": 2.5979,
67
+ "step": 35
68
+ },
69
+ {
70
+ "epoch": 1.0,
71
+ "grad_norm": 6.1299028396606445,
72
+ "learning_rate": 4.996924922870762e-05,
73
+ "loss": 2.5103,
74
+ "step": 40
75
+ },
76
+ {
77
+ "epoch": 1.127388535031847,
78
+ "grad_norm": 3.7290937900543213,
79
+ "learning_rate": 4.992561238637912e-05,
80
+ "loss": 2.1311,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 1.2547770700636942,
85
+ "grad_norm": 3.363525152206421,
86
+ "learning_rate": 4.9863047384206835e-05,
87
+ "loss": 2.0143,
88
+ "step": 50
89
+ },
90
+ {
91
+ "epoch": 1.2547770700636942,
92
+ "eval_loss": 1.9939861297607422,
93
+ "eval_runtime": 1.1275,
94
+ "eval_samples_per_second": 15.965,
95
+ "eval_steps_per_second": 2.661,
96
+ "step": 50
97
+ },
98
+ {
99
+ "epoch": 1.3821656050955413,
100
+ "grad_norm": 2.934461832046509,
101
+ "learning_rate": 4.978160173317438e-05,
102
+ "loss": 2.0247,
103
+ "step": 55
104
+ },
105
+ {
106
+ "epoch": 1.5095541401273884,
107
+ "grad_norm": 2.9091031551361084,
108
+ "learning_rate": 4.968133728196486e-05,
109
+ "loss": 1.9287,
110
+ "step": 60
111
+ },
112
+ {
113
+ "epoch": 1.6369426751592355,
114
+ "grad_norm": 2.8760178089141846,
115
+ "learning_rate": 4.956233016999379e-05,
116
+ "loss": 1.7431,
117
+ "step": 65
118
+ },
119
+ {
120
+ "epoch": 1.7643312101910829,
121
+ "grad_norm": 3.208024263381958,
122
+ "learning_rate": 4.9424670769589984e-05,
123
+ "loss": 1.8979,
124
+ "step": 70
125
+ },
126
+ {
127
+ "epoch": 1.89171974522293,
128
+ "grad_norm": 2.7759275436401367,
129
+ "learning_rate": 4.9268463617368e-05,
130
+ "loss": 1.6829,
131
+ "step": 75
132
+ },
133
+ {
134
+ "epoch": 1.89171974522293,
135
+ "eval_loss": 1.7856135368347168,
136
+ "eval_runtime": 1.1733,
137
+ "eval_samples_per_second": 15.342,
138
+ "eval_steps_per_second": 2.557,
139
+ "step": 75
140
+ },
141
+ {
142
+ "epoch": 2.0,
143
+ "grad_norm": 6.358933448791504,
144
+ "learning_rate": 4.9093827334844546e-05,
145
+ "loss": 1.6997,
146
+ "step": 80
147
+ },
148
+ {
149
+ "epoch": 2.127388535031847,
150
+ "grad_norm": 4.402135848999023,
151
+ "learning_rate": 4.8900894538358944e-05,
152
+ "loss": 1.587,
153
+ "step": 85
154
+ },
155
+ {
156
+ "epoch": 2.254777070063694,
157
+ "grad_norm": 3.39581036567688,
158
+ "learning_rate": 4.8689811738366155e-05,
159
+ "loss": 1.5455,
160
+ "step": 90
161
+ },
162
+ {
163
+ "epoch": 2.3821656050955413,
164
+ "grad_norm": 3.3852970600128174,
165
+ "learning_rate": 4.8460739228178806e-05,
166
+ "loss": 1.5951,
167
+ "step": 95
168
+ },
169
+ {
170
+ "epoch": 2.5095541401273884,
171
+ "grad_norm": 4.223837375640869,
172
+ "learning_rate": 4.821385096224268e-05,
173
+ "loss": 1.4774,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 2.5095541401273884,
178
+ "eval_loss": 1.7516053915023804,
179
+ "eval_runtime": 1.1669,
180
+ "eval_samples_per_second": 15.425,
181
+ "eval_steps_per_second": 2.571,
182
+ "step": 100
183
+ },
184
+ {
185
+ "epoch": 2.6369426751592355,
186
+ "grad_norm": 3.7523889541625977,
187
+ "learning_rate": 4.7949334424038176e-05,
188
+ "loss": 1.448,
189
+ "step": 105
190
+ },
191
+ {
192
+ "epoch": 2.7643312101910826,
193
+ "grad_norm": 4.22092866897583,
194
+ "learning_rate": 4.7667390483707986e-05,
195
+ "loss": 1.4961,
196
+ "step": 110
197
+ },
198
+ {
199
+ "epoch": 2.8917197452229297,
200
+ "grad_norm": 3.6937355995178223,
201
+ "learning_rate": 4.736823324551909e-05,
202
+ "loss": 1.4448,
203
+ "step": 115
204
+ },
205
+ {
206
+ "epoch": 3.0,
207
+ "grad_norm": 8.089461326599121,
208
+ "learning_rate": 4.7052089885275055e-05,
209
+ "loss": 1.5377,
210
+ "step": 120
211
+ },
212
+ {
213
+ "epoch": 3.127388535031847,
214
+ "grad_norm": 3.593388557434082,
215
+ "learning_rate": 4.671920047780186e-05,
216
+ "loss": 1.1908,
217
+ "step": 125
218
+ },
219
+ {
220
+ "epoch": 3.127388535031847,
221
+ "eval_loss": 1.6817084550857544,
222
+ "eval_runtime": 1.1628,
223
+ "eval_samples_per_second": 15.48,
224
+ "eval_steps_per_second": 2.58,
225
+ "step": 125
226
+ },
227
+ {
228
+ "epoch": 3.254777070063694,
229
+ "grad_norm": 4.622504234313965,
230
+ "learning_rate": 4.6369817814638475e-05,
231
+ "loss": 1.3108,
232
+ "step": 130
233
+ },
234
+ {
235
+ "epoch": 3.3821656050955413,
236
+ "grad_norm": 5.402882099151611,
237
+ "learning_rate": 4.600420721207053e-05,
238
+ "loss": 1.1886,
239
+ "step": 135
240
+ },
241
+ {
242
+ "epoch": 3.5095541401273884,
243
+ "grad_norm": 4.38949728012085,
244
+ "learning_rate": 4.5622646309652794e-05,
245
+ "loss": 1.1127,
246
+ "step": 140
247
+ },
248
+ {
249
+ "epoch": 3.6369426751592355,
250
+ "grad_norm": 4.939103126525879,
251
+ "learning_rate": 4.522542485937369e-05,
252
+ "loss": 1.1102,
253
+ "step": 145
254
+ },
255
+ {
256
+ "epoch": 3.7643312101910826,
257
+ "grad_norm": 4.718697547912598,
258
+ "learning_rate": 4.481284450562163e-05,
259
+ "loss": 1.2046,
260
+ "step": 150
261
+ },
262
+ {
263
+ "epoch": 3.7643312101910826,
264
+ "eval_loss": 1.6712156534194946,
265
+ "eval_runtime": 1.1162,
266
+ "eval_samples_per_second": 16.126,
267
+ "eval_steps_per_second": 2.688,
268
+ "step": 150
269
+ }
270
+ ],
271
+ "logging_steps": 5,
272
+ "max_steps": 600,
273
+ "num_input_tokens_seen": 0,
274
+ "num_train_epochs": 15,
275
+ "save_steps": 50,
276
+ "stateful_callbacks": {
277
+ "TrainerControl": {
278
+ "args": {
279
+ "should_epoch_stop": false,
280
+ "should_evaluate": false,
281
+ "should_log": false,
282
+ "should_save": true,
283
+ "should_training_stop": false
284
+ },
285
+ "attributes": {}
286
+ }
287
+ },
288
+ "total_flos": 2277554611691520.0,
289
+ "train_batch_size": 1,
290
+ "trial_name": null,
291
+ "trial_params": null
292
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb46dc44937ba4dbf6e54e6b92a8c41ca12d164348e1ad4fd80375a1f258dd54
3
+ size 6225
checkpoint-150/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": null,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_frames": 4,
28
+ "min_pixels": 3136,
29
+ "num_frames": null,
30
+ "pad_size": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 12845056,
38
+ "shortest_edge": 3136
39
+ },
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
checkpoint-150/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-550/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ''
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
7
+ - llama-factory
8
+ - lora
9
+ - transformers
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- 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. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ 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).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.17.1
checkpoint-550/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "down_proj",
30
+ "k_proj",
31
+ "gate_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-550/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ea1d743da91106d7a14ccbe30eafa8e9ff99cf23e9d26be3eb73758fe15dc7
3
+ size 73916992
checkpoint-550/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-550/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-550/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b752d0b4e71cb3d1946e391ac6906eb97c14fc9f677532d2697767f3e9b806c3
3
+ size 148053627
checkpoint-550/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1851973b8c68a6f82b6396255984ce5e83694a12ce1d695a04bb21de22306d
3
+ size 14645
checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d59d99262a0f3f58c0510a59464aaddb984b05dc8dea0c6b004171981d01fcf5
3
+ size 1465
checkpoint-550/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-550/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
checkpoint-550/tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "clean_up_tokenization_spaces": false,
134
+ "eos_token": "<|im_end|>",
135
+ "errors": "replace",
136
+ "extra_special_tokens": {},
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "right",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,980 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 150,
3
+ "best_metric": 1.6712156534194946,
4
+ "best_model_checkpoint": "/root/Sherlock-Pet/output/sherlock_pet_v2/checkpoint-150",
5
+ "epoch": 13.764331210191083,
6
+ "eval_steps": 25,
7
+ "global_step": 550,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.12738853503184713,
14
+ "grad_norm": 2.745800018310547,
15
+ "learning_rate": 6.666666666666667e-06,
16
+ "loss": 3.7984,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.25477707006369427,
21
+ "grad_norm": 2.8450679779052734,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 3.8072,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.3821656050955414,
28
+ "grad_norm": 2.421614408493042,
29
+ "learning_rate": 2.3333333333333336e-05,
30
+ "loss": 3.7454,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.5095541401273885,
35
+ "grad_norm": 2.301647186279297,
36
+ "learning_rate": 3.1666666666666666e-05,
37
+ "loss": 3.3677,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.6369426751592356,
42
+ "grad_norm": 2.822660446166992,
43
+ "learning_rate": 4e-05,
44
+ "loss": 3.2859,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.6369426751592356,
49
+ "eval_loss": 2.8292243480682373,
50
+ "eval_runtime": 1.1711,
51
+ "eval_samples_per_second": 15.371,
52
+ "eval_steps_per_second": 2.562,
53
+ "step": 25
54
+ },
55
+ {
56
+ "epoch": 0.7643312101910829,
57
+ "grad_norm": 3.327336549758911,
58
+ "learning_rate": 4.8333333333333334e-05,
59
+ "loss": 2.8454,
60
+ "step": 30
61
+ },
62
+ {
63
+ "epoch": 0.89171974522293,
64
+ "grad_norm": 2.4171416759490967,
65
+ "learning_rate": 4.999392477398737e-05,
66
+ "loss": 2.5979,
67
+ "step": 35
68
+ },
69
+ {
70
+ "epoch": 1.0,
71
+ "grad_norm": 6.1299028396606445,
72
+ "learning_rate": 4.996924922870762e-05,
73
+ "loss": 2.5103,
74
+ "step": 40
75
+ },
76
+ {
77
+ "epoch": 1.127388535031847,
78
+ "grad_norm": 3.7290937900543213,
79
+ "learning_rate": 4.992561238637912e-05,
80
+ "loss": 2.1311,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 1.2547770700636942,
85
+ "grad_norm": 3.363525152206421,
86
+ "learning_rate": 4.9863047384206835e-05,
87
+ "loss": 2.0143,
88
+ "step": 50
89
+ },
90
+ {
91
+ "epoch": 1.2547770700636942,
92
+ "eval_loss": 1.9939861297607422,
93
+ "eval_runtime": 1.1275,
94
+ "eval_samples_per_second": 15.965,
95
+ "eval_steps_per_second": 2.661,
96
+ "step": 50
97
+ },
98
+ {
99
+ "epoch": 1.3821656050955413,
100
+ "grad_norm": 2.934461832046509,
101
+ "learning_rate": 4.978160173317438e-05,
102
+ "loss": 2.0247,
103
+ "step": 55
104
+ },
105
+ {
106
+ "epoch": 1.5095541401273884,
107
+ "grad_norm": 2.9091031551361084,
108
+ "learning_rate": 4.968133728196486e-05,
109
+ "loss": 1.9287,
110
+ "step": 60
111
+ },
112
+ {
113
+ "epoch": 1.6369426751592355,
114
+ "grad_norm": 2.8760178089141846,
115
+ "learning_rate": 4.956233016999379e-05,
116
+ "loss": 1.7431,
117
+ "step": 65
118
+ },
119
+ {
120
+ "epoch": 1.7643312101910829,
121
+ "grad_norm": 3.208024263381958,
122
+ "learning_rate": 4.9424670769589984e-05,
123
+ "loss": 1.8979,
124
+ "step": 70
125
+ },
126
+ {
127
+ "epoch": 1.89171974522293,
128
+ "grad_norm": 2.7759275436401367,
129
+ "learning_rate": 4.9268463617368e-05,
130
+ "loss": 1.6829,
131
+ "step": 75
132
+ },
133
+ {
134
+ "epoch": 1.89171974522293,
135
+ "eval_loss": 1.7856135368347168,
136
+ "eval_runtime": 1.1733,
137
+ "eval_samples_per_second": 15.342,
138
+ "eval_steps_per_second": 2.557,
139
+ "step": 75
140
+ },
141
+ {
142
+ "epoch": 2.0,
143
+ "grad_norm": 6.358933448791504,
144
+ "learning_rate": 4.9093827334844546e-05,
145
+ "loss": 1.6997,
146
+ "step": 80
147
+ },
148
+ {
149
+ "epoch": 2.127388535031847,
150
+ "grad_norm": 4.402135848999023,
151
+ "learning_rate": 4.8900894538358944e-05,
152
+ "loss": 1.587,
153
+ "step": 85
154
+ },
155
+ {
156
+ "epoch": 2.254777070063694,
157
+ "grad_norm": 3.39581036567688,
158
+ "learning_rate": 4.8689811738366155e-05,
159
+ "loss": 1.5455,
160
+ "step": 90
161
+ },
162
+ {
163
+ "epoch": 2.3821656050955413,
164
+ "grad_norm": 3.3852970600128174,
165
+ "learning_rate": 4.8460739228178806e-05,
166
+ "loss": 1.5951,
167
+ "step": 95
168
+ },
169
+ {
170
+ "epoch": 2.5095541401273884,
171
+ "grad_norm": 4.223837375640869,
172
+ "learning_rate": 4.821385096224268e-05,
173
+ "loss": 1.4774,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 2.5095541401273884,
178
+ "eval_loss": 1.7516053915023804,
179
+ "eval_runtime": 1.1669,
180
+ "eval_samples_per_second": 15.425,
181
+ "eval_steps_per_second": 2.571,
182
+ "step": 100
183
+ },
184
+ {
185
+ "epoch": 2.6369426751592355,
186
+ "grad_norm": 3.7523889541625977,
187
+ "learning_rate": 4.7949334424038176e-05,
188
+ "loss": 1.448,
189
+ "step": 105
190
+ },
191
+ {
192
+ "epoch": 2.7643312101910826,
193
+ "grad_norm": 4.22092866897583,
194
+ "learning_rate": 4.7667390483707986e-05,
195
+ "loss": 1.4961,
196
+ "step": 110
197
+ },
198
+ {
199
+ "epoch": 2.8917197452229297,
200
+ "grad_norm": 3.6937355995178223,
201
+ "learning_rate": 4.736823324551909e-05,
202
+ "loss": 1.4448,
203
+ "step": 115
204
+ },
205
+ {
206
+ "epoch": 3.0,
207
+ "grad_norm": 8.089461326599121,
208
+ "learning_rate": 4.7052089885275055e-05,
209
+ "loss": 1.5377,
210
+ "step": 120
211
+ },
212
+ {
213
+ "epoch": 3.127388535031847,
214
+ "grad_norm": 3.593388557434082,
215
+ "learning_rate": 4.671920047780186e-05,
216
+ "loss": 1.1908,
217
+ "step": 125
218
+ },
219
+ {
220
+ "epoch": 3.127388535031847,
221
+ "eval_loss": 1.6817084550857544,
222
+ "eval_runtime": 1.1628,
223
+ "eval_samples_per_second": 15.48,
224
+ "eval_steps_per_second": 2.58,
225
+ "step": 125
226
+ },
227
+ {
228
+ "epoch": 3.254777070063694,
229
+ "grad_norm": 4.622504234313965,
230
+ "learning_rate": 4.6369817814638475e-05,
231
+ "loss": 1.3108,
232
+ "step": 130
233
+ },
234
+ {
235
+ "epoch": 3.3821656050955413,
236
+ "grad_norm": 5.402882099151611,
237
+ "learning_rate": 4.600420721207053e-05,
238
+ "loss": 1.1886,
239
+ "step": 135
240
+ },
241
+ {
242
+ "epoch": 3.5095541401273884,
243
+ "grad_norm": 4.38949728012085,
244
+ "learning_rate": 4.5622646309652794e-05,
245
+ "loss": 1.1127,
246
+ "step": 140
247
+ },
248
+ {
249
+ "epoch": 3.6369426751592355,
250
+ "grad_norm": 4.939103126525879,
251
+ "learning_rate": 4.522542485937369e-05,
252
+ "loss": 1.1102,
253
+ "step": 145
254
+ },
255
+ {
256
+ "epoch": 3.7643312101910826,
257
+ "grad_norm": 4.718697547912598,
258
+ "learning_rate": 4.481284450562163e-05,
259
+ "loss": 1.2046,
260
+ "step": 150
261
+ },
262
+ {
263
+ "epoch": 3.7643312101910826,
264
+ "eval_loss": 1.6712156534194946,
265
+ "eval_runtime": 1.1162,
266
+ "eval_samples_per_second": 16.126,
267
+ "eval_steps_per_second": 2.688,
268
+ "step": 150
269
+ },
270
+ {
271
+ "epoch": 3.8917197452229297,
272
+ "grad_norm": 5.0807881355285645,
273
+ "learning_rate": 4.438521855612054e-05,
274
+ "loss": 1.0573,
275
+ "step": 155
276
+ },
277
+ {
278
+ "epoch": 4.0,
279
+ "grad_norm": 8.19217300415039,
280
+ "learning_rate": 4.3942871744008374e-05,
281
+ "loss": 1.3037,
282
+ "step": 160
283
+ },
284
+ {
285
+ "epoch": 4.127388535031847,
286
+ "grad_norm": 4.953968524932861,
287
+ "learning_rate": 4.3486139981239304e-05,
288
+ "loss": 0.879,
289
+ "step": 165
290
+ },
291
+ {
292
+ "epoch": 4.254777070063694,
293
+ "grad_norm": 6.172196388244629,
294
+ "learning_rate": 4.301537010349696e-05,
295
+ "loss": 0.9412,
296
+ "step": 170
297
+ },
298
+ {
299
+ "epoch": 4.382165605095541,
300
+ "grad_norm": 5.977532386779785,
301
+ "learning_rate": 4.2530919606812216e-05,
302
+ "loss": 0.8012,
303
+ "step": 175
304
+ },
305
+ {
306
+ "epoch": 4.382165605095541,
307
+ "eval_loss": 1.7618356943130493,
308
+ "eval_runtime": 1.189,
309
+ "eval_samples_per_second": 15.139,
310
+ "eval_steps_per_second": 2.523,
311
+ "step": 175
312
+ },
313
+ {
314
+ "epoch": 4.509554140127388,
315
+ "grad_norm": 4.794788360595703,
316
+ "learning_rate": 4.203315637608578e-05,
317
+ "loss": 0.9443,
318
+ "step": 180
319
+ },
320
+ {
321
+ "epoch": 4.6369426751592355,
322
+ "grad_norm": 5.241445541381836,
323
+ "learning_rate": 4.152245840572153e-05,
324
+ "loss": 0.8479,
325
+ "step": 185
326
+ },
327
+ {
328
+ "epoch": 4.764331210191083,
329
+ "grad_norm": 5.526820182800293,
330
+ "learning_rate": 4.099921351258292e-05,
331
+ "loss": 0.8732,
332
+ "step": 190
333
+ },
334
+ {
335
+ "epoch": 4.89171974522293,
336
+ "grad_norm": 7.235106945037842,
337
+ "learning_rate": 4.046381904149024e-05,
338
+ "loss": 0.8117,
339
+ "step": 195
340
+ },
341
+ {
342
+ "epoch": 5.0,
343
+ "grad_norm": 9.936717987060547,
344
+ "learning_rate": 3.991668156348261e-05,
345
+ "loss": 0.9595,
346
+ "step": 200
347
+ },
348
+ {
349
+ "epoch": 5.0,
350
+ "eval_loss": 1.7216202020645142,
351
+ "eval_runtime": 1.1216,
352
+ "eval_samples_per_second": 16.048,
353
+ "eval_steps_per_second": 2.675,
354
+ "step": 200
355
+ },
356
+ {
357
+ "epoch": 5.127388535031847,
358
+ "grad_norm": 5.190134525299072,
359
+ "learning_rate": 3.935821656707359e-05,
360
+ "loss": 0.6461,
361
+ "step": 205
362
+ },
363
+ {
364
+ "epoch": 5.254777070063694,
365
+ "grad_norm": 6.523595809936523,
366
+ "learning_rate": 3.878884814273509e-05,
367
+ "loss": 0.5982,
368
+ "step": 210
369
+ },
370
+ {
371
+ "epoch": 5.382165605095541,
372
+ "grad_norm": 6.567984580993652,
373
+ "learning_rate": 3.8209008660848974e-05,
374
+ "loss": 0.6205,
375
+ "step": 215
376
+ },
377
+ {
378
+ "epoch": 5.509554140127388,
379
+ "grad_norm": 7.569522380828857,
380
+ "learning_rate": 3.76191384433711e-05,
381
+ "loss": 0.5558,
382
+ "step": 220
383
+ },
384
+ {
385
+ "epoch": 5.6369426751592355,
386
+ "grad_norm": 4.997279644012451,
387
+ "learning_rate": 3.7019685429456986e-05,
388
+ "loss": 0.5115,
389
+ "step": 225
390
+ },
391
+ {
392
+ "epoch": 5.6369426751592355,
393
+ "eval_loss": 1.8211851119995117,
394
+ "eval_runtime": 1.1401,
395
+ "eval_samples_per_second": 15.789,
396
+ "eval_steps_per_second": 2.631,
397
+ "step": 225
398
+ },
399
+ {
400
+ "epoch": 5.764331210191083,
401
+ "grad_norm": 5.285463333129883,
402
+ "learning_rate": 3.6411104835303166e-05,
403
+ "loss": 0.6233,
404
+ "step": 230
405
+ },
406
+ {
407
+ "epoch": 5.89171974522293,
408
+ "grad_norm": 7.245285987854004,
409
+ "learning_rate": 3.579385880846232e-05,
410
+ "loss": 0.5701,
411
+ "step": 235
412
+ },
413
+ {
414
+ "epoch": 6.0,
415
+ "grad_norm": 9.988482475280762,
416
+ "learning_rate": 3.516841607689501e-05,
417
+ "loss": 0.652,
418
+ "step": 240
419
+ },
420
+ {
421
+ "epoch": 6.127388535031847,
422
+ "grad_norm": 5.565608978271484,
423
+ "learning_rate": 3.453525159302415e-05,
424
+ "loss": 0.3898,
425
+ "step": 245
426
+ },
427
+ {
428
+ "epoch": 6.254777070063694,
429
+ "grad_norm": 6.4225287437438965,
430
+ "learning_rate": 3.389484617306292e-05,
431
+ "loss": 0.4666,
432
+ "step": 250
433
+ },
434
+ {
435
+ "epoch": 6.254777070063694,
436
+ "eval_loss": 2.177734136581421,
437
+ "eval_runtime": 1.0978,
438
+ "eval_samples_per_second": 16.396,
439
+ "eval_steps_per_second": 2.733,
440
+ "step": 250
441
+ },
442
+ {
443
+ "epoch": 6.382165605095541,
444
+ "grad_norm": 4.287829399108887,
445
+ "learning_rate": 3.3247686131889574e-05,
446
+ "loss": 0.3194,
447
+ "step": 255
448
+ },
449
+ {
450
+ "epoch": 6.509554140127388,
451
+ "grad_norm": 7.155808448791504,
452
+ "learning_rate": 3.2594262913746865e-05,
453
+ "loss": 0.3603,
454
+ "step": 260
455
+ },
456
+ {
457
+ "epoch": 6.6369426751592355,
458
+ "grad_norm": 7.35886812210083,
459
+ "learning_rate": 3.1935072719046115e-05,
460
+ "loss": 0.4139,
461
+ "step": 265
462
+ },
463
+ {
464
+ "epoch": 6.764331210191083,
465
+ "grad_norm": 6.846656322479248,
466
+ "learning_rate": 3.127061612755961e-05,
467
+ "loss": 0.398,
468
+ "step": 270
469
+ },
470
+ {
471
+ "epoch": 6.89171974522293,
472
+ "grad_norm": 7.843795299530029,
473
+ "learning_rate": 3.06013977182874e-05,
474
+ "loss": 0.4082,
475
+ "step": 275
476
+ },
477
+ {
478
+ "epoch": 6.89171974522293,
479
+ "eval_loss": 2.0292844772338867,
480
+ "eval_runtime": 1.1814,
481
+ "eval_samples_per_second": 15.236,
482
+ "eval_steps_per_second": 2.539,
483
+ "step": 275
484
+ },
485
+ {
486
+ "epoch": 7.0,
487
+ "grad_norm": 7.938873767852783,
488
+ "learning_rate": 2.9927925686287006e-05,
489
+ "loss": 0.3706,
490
+ "step": 280
491
+ },
492
+ {
493
+ "epoch": 7.127388535031847,
494
+ "grad_norm": 4.278555393218994,
495
+ "learning_rate": 2.925071145675733e-05,
496
+ "loss": 0.2333,
497
+ "step": 285
498
+ },
499
+ {
500
+ "epoch": 7.254777070063694,
501
+ "grad_norm": 7.001745700836182,
502
+ "learning_rate": 2.8570269296669466e-05,
503
+ "loss": 0.2746,
504
+ "step": 290
505
+ },
506
+ {
507
+ "epoch": 7.382165605095541,
508
+ "grad_norm": 7.84188985824585,
509
+ "learning_rate": 2.788711592423966e-05,
510
+ "loss": 0.2495,
511
+ "step": 295
512
+ },
513
+ {
514
+ "epoch": 7.509554140127388,
515
+ "grad_norm": 7.395780563354492,
516
+ "learning_rate": 2.720177011654067e-05,
517
+ "loss": 0.2262,
518
+ "step": 300
519
+ },
520
+ {
521
+ "epoch": 7.509554140127388,
522
+ "eval_loss": 2.3396387100219727,
523
+ "eval_runtime": 1.1699,
524
+ "eval_samples_per_second": 15.387,
525
+ "eval_steps_per_second": 2.564,
526
+ "step": 300
527
+ },
528
+ {
529
+ "epoch": 7.6369426751592355,
530
+ "grad_norm": 4.985588073730469,
531
+ "learning_rate": 2.6514752315549847e-05,
532
+ "loss": 0.2665,
533
+ "step": 305
534
+ },
535
+ {
536
+ "epoch": 7.764331210191083,
537
+ "grad_norm": 4.297209739685059,
538
+ "learning_rate": 2.5826584232932706e-05,
539
+ "loss": 0.2769,
540
+ "step": 310
541
+ },
542
+ {
543
+ "epoch": 7.89171974522293,
544
+ "grad_norm": 6.710094928741455,
545
+ "learning_rate": 2.5137788453862515e-05,
546
+ "loss": 0.2252,
547
+ "step": 315
548
+ },
549
+ {
550
+ "epoch": 8.0,
551
+ "grad_norm": 13.744440078735352,
552
+ "learning_rate": 2.4448888040176365e-05,
553
+ "loss": 0.2672,
554
+ "step": 320
555
+ },
556
+ {
557
+ "epoch": 8.127388535031848,
558
+ "grad_norm": 3.4223597049713135,
559
+ "learning_rate": 2.3760406133169443e-05,
560
+ "loss": 0.1774,
561
+ "step": 325
562
+ },
563
+ {
564
+ "epoch": 8.127388535031848,
565
+ "eval_loss": 2.345935821533203,
566
+ "eval_runtime": 1.1092,
567
+ "eval_samples_per_second": 16.228,
568
+ "eval_steps_per_second": 2.705,
569
+ "step": 325
570
+ },
571
+ {
572
+ "epoch": 8.254777070063694,
573
+ "grad_norm": 4.574872016906738,
574
+ "learning_rate": 2.3072865556328822e-05,
575
+ "loss": 0.1316,
576
+ "step": 330
577
+ },
578
+ {
579
+ "epoch": 8.382165605095542,
580
+ "grad_norm": 3.8134524822235107,
581
+ "learning_rate": 2.238678841830867e-05,
582
+ "loss": 0.1199,
583
+ "step": 335
584
+ },
585
+ {
586
+ "epoch": 8.509554140127388,
587
+ "grad_norm": 3.943145751953125,
588
+ "learning_rate": 2.1702695716448278e-05,
589
+ "loss": 0.1955,
590
+ "step": 340
591
+ },
592
+ {
593
+ "epoch": 8.636942675159236,
594
+ "grad_norm": 5.184530258178711,
595
+ "learning_rate": 2.1021106941134012e-05,
596
+ "loss": 0.1369,
597
+ "step": 345
598
+ },
599
+ {
600
+ "epoch": 8.764331210191083,
601
+ "grad_norm": 7.904541492462158,
602
+ "learning_rate": 2.0342539681305602e-05,
603
+ "loss": 0.1512,
604
+ "step": 350
605
+ },
606
+ {
607
+ "epoch": 8.764331210191083,
608
+ "eval_loss": 2.4745495319366455,
609
+ "eval_runtime": 1.105,
610
+ "eval_samples_per_second": 16.29,
611
+ "eval_steps_per_second": 2.715,
612
+ "step": 350
613
+ },
614
+ {
615
+ "epoch": 8.89171974522293,
616
+ "grad_norm": 7.2708740234375,
617
+ "learning_rate": 1.9667509231406334e-05,
618
+ "loss": 0.1519,
619
+ "step": 355
620
+ },
621
+ {
622
+ "epoch": 9.0,
623
+ "grad_norm": 13.182251930236816,
624
+ "learning_rate": 1.899652820007576e-05,
625
+ "loss": 0.1857,
626
+ "step": 360
627
+ },
628
+ {
629
+ "epoch": 9.127388535031848,
630
+ "grad_norm": 2.628040313720703,
631
+ "learning_rate": 1.8330106120881846e-05,
632
+ "loss": 0.0731,
633
+ "step": 365
634
+ },
635
+ {
636
+ "epoch": 9.254777070063694,
637
+ "grad_norm": 2.4514880180358887,
638
+ "learning_rate": 1.7668749065388385e-05,
639
+ "loss": 0.0974,
640
+ "step": 370
641
+ },
642
+ {
643
+ "epoch": 9.382165605095542,
644
+ "grad_norm": 3.9326188564300537,
645
+ "learning_rate": 1.70129592588513e-05,
646
+ "loss": 0.0719,
647
+ "step": 375
648
+ },
649
+ {
650
+ "epoch": 9.382165605095542,
651
+ "eval_loss": 2.771934747695923,
652
+ "eval_runtime": 1.0823,
653
+ "eval_samples_per_second": 16.632,
654
+ "eval_steps_per_second": 2.772,
655
+ "step": 375
656
+ },
657
+ {
658
+ "epoch": 9.509554140127388,
659
+ "grad_norm": 5.222805976867676,
660
+ "learning_rate": 1.6363234698835896e-05,
661
+ "loss": 0.0901,
662
+ "step": 380
663
+ },
664
+ {
665
+ "epoch": 9.636942675159236,
666
+ "grad_norm": 4.620385646820068,
667
+ "learning_rate": 1.5720068777044476e-05,
668
+ "loss": 0.1384,
669
+ "step": 385
670
+ },
671
+ {
672
+ "epoch": 9.764331210191083,
673
+ "grad_norm": 3.4555652141571045,
674
+ "learning_rate": 1.5083949904641654e-05,
675
+ "loss": 0.0785,
676
+ "step": 390
677
+ },
678
+ {
679
+ "epoch": 9.89171974522293,
680
+ "grad_norm": 5.134110927581787,
681
+ "learning_rate": 1.44553611413617e-05,
682
+ "loss": 0.0952,
683
+ "step": 395
684
+ },
685
+ {
686
+ "epoch": 10.0,
687
+ "grad_norm": 2.9739015102386475,
688
+ "learning_rate": 1.383477982867984e-05,
689
+ "loss": 0.0741,
690
+ "step": 400
691
+ },
692
+ {
693
+ "epoch": 10.0,
694
+ "eval_loss": 2.7705841064453125,
695
+ "eval_runtime": 1.0966,
696
+ "eval_samples_per_second": 16.414,
697
+ "eval_steps_per_second": 2.736,
698
+ "step": 400
699
+ },
700
+ {
701
+ "epoch": 10.127388535031848,
702
+ "grad_norm": 2.2853662967681885,
703
+ "learning_rate": 1.322267722732582e-05,
704
+ "loss": 0.0545,
705
+ "step": 405
706
+ },
707
+ {
708
+ "epoch": 10.254777070063694,
709
+ "grad_norm": 8.12447738647461,
710
+ "learning_rate": 1.2619518159415139e-05,
711
+ "loss": 0.0576,
712
+ "step": 410
713
+ },
714
+ {
715
+ "epoch": 10.382165605095542,
716
+ "grad_norm": 1.5649133920669556,
717
+ "learning_rate": 1.202576065546963e-05,
718
+ "loss": 0.0513,
719
+ "step": 415
720
+ },
721
+ {
722
+ "epoch": 10.509554140127388,
723
+ "grad_norm": 6.421708583831787,
724
+ "learning_rate": 1.1441855606595545e-05,
725
+ "loss": 0.061,
726
+ "step": 420
727
+ },
728
+ {
729
+ "epoch": 10.636942675159236,
730
+ "grad_norm": 4.642502784729004,
731
+ "learning_rate": 1.0868246422083204e-05,
732
+ "loss": 0.0679,
733
+ "step": 425
734
+ },
735
+ {
736
+ "epoch": 10.636942675159236,
737
+ "eval_loss": 2.8739261627197266,
738
+ "eval_runtime": 1.1304,
739
+ "eval_samples_per_second": 15.924,
740
+ "eval_steps_per_second": 2.654,
741
+ "step": 425
742
+ },
743
+ {
744
+ "epoch": 10.764331210191083,
745
+ "grad_norm": 4.243600845336914,
746
+ "learning_rate": 1.0305368692688174e-05,
747
+ "loss": 0.0629,
748
+ "step": 430
749
+ },
750
+ {
751
+ "epoch": 10.89171974522293,
752
+ "grad_norm": 2.6516973972320557,
753
+ "learning_rate": 9.753649859849775e-06,
754
+ "loss": 0.0557,
755
+ "step": 435
756
+ },
757
+ {
758
+ "epoch": 11.0,
759
+ "grad_norm": 10.662928581237793,
760
+ "learning_rate": 9.213508891098064e-06,
761
+ "loss": 0.0572,
762
+ "step": 440
763
+ },
764
+ {
765
+ "epoch": 11.127388535031848,
766
+ "grad_norm": 2.290684223175049,
767
+ "learning_rate": 8.685355961895784e-06,
768
+ "loss": 0.0381,
769
+ "step": 445
770
+ },
771
+ {
772
+ "epoch": 11.254777070063694,
773
+ "grad_norm": 3.5246331691741943,
774
+ "learning_rate": 8.169592144156885e-06,
775
+ "loss": 0.036,
776
+ "step": 450
777
+ },
778
+ {
779
+ "epoch": 11.254777070063694,
780
+ "eval_loss": 3.0192348957061768,
781
+ "eval_runtime": 1.1442,
782
+ "eval_samples_per_second": 15.732,
783
+ "eval_steps_per_second": 2.622,
784
+ "step": 450
785
+ },
786
+ {
787
+ "epoch": 11.382165605095542,
788
+ "grad_norm": 1.1039093732833862,
789
+ "learning_rate": 7.666609101678121e-06,
790
+ "loss": 0.0416,
791
+ "step": 455
792
+ },
793
+ {
794
+ "epoch": 11.509554140127388,
795
+ "grad_norm": 1.7566171884536743,
796
+ "learning_rate": 7.176788792715075e-06,
797
+ "loss": 0.0469,
798
+ "step": 460
799
+ },
800
+ {
801
+ "epoch": 11.636942675159236,
802
+ "grad_norm": 5.540022373199463,
803
+ "learning_rate": 6.700503179928458e-06,
804
+ "loss": 0.0593,
805
+ "step": 465
806
+ },
807
+ {
808
+ "epoch": 11.764331210191083,
809
+ "grad_norm": 2.7685348987579346,
810
+ "learning_rate": 6.2381139479208564e-06,
811
+ "loss": 0.0322,
812
+ "step": 470
813
+ },
814
+ {
815
+ "epoch": 11.89171974522293,
816
+ "grad_norm": 1.5013082027435303,
817
+ "learning_rate": 5.78997222857853e-06,
818
+ "loss": 0.03,
819
+ "step": 475
820
+ },
821
+ {
822
+ "epoch": 11.89171974522293,
823
+ "eval_loss": 3.0430448055267334,
824
+ "eval_runtime": 1.142,
825
+ "eval_samples_per_second": 15.762,
826
+ "eval_steps_per_second": 2.627,
827
+ "step": 475
828
+ },
829
+ {
830
+ "epoch": 12.0,
831
+ "grad_norm": 1.6596020460128784,
832
+ "learning_rate": 5.356418334426791e-06,
833
+ "loss": 0.0206,
834
+ "step": 480
835
+ },
836
+ {
837
+ "epoch": 12.127388535031848,
838
+ "grad_norm": 1.6733341217041016,
839
+ "learning_rate": 4.937781500201474e-06,
840
+ "loss": 0.0269,
841
+ "step": 485
842
+ },
843
+ {
844
+ "epoch": 12.254777070063694,
845
+ "grad_norm": 2.3883769512176514,
846
+ "learning_rate": 4.534379632832692e-06,
847
+ "loss": 0.0243,
848
+ "step": 490
849
+ },
850
+ {
851
+ "epoch": 12.382165605095542,
852
+ "grad_norm": 1.5162509679794312,
853
+ "learning_rate": 4.146519070030757e-06,
854
+ "loss": 0.0227,
855
+ "step": 495
856
+ },
857
+ {
858
+ "epoch": 12.509554140127388,
859
+ "grad_norm": 1.2816208600997925,
860
+ "learning_rate": 3.7744943476576562e-06,
861
+ "loss": 0.0226,
862
+ "step": 500
863
+ },
864
+ {
865
+ "epoch": 12.509554140127388,
866
+ "eval_loss": 3.151336908340454,
867
+ "eval_runtime": 1.1322,
868
+ "eval_samples_per_second": 15.898,
869
+ "eval_steps_per_second": 2.65,
870
+ "step": 500
871
+ },
872
+ {
873
+ "epoch": 12.636942675159236,
874
+ "grad_norm": 0.6974829435348511,
875
+ "learning_rate": 3.418587976060653e-06,
876
+ "loss": 0.0206,
877
+ "step": 505
878
+ },
879
+ {
880
+ "epoch": 12.764331210191083,
881
+ "grad_norm": 0.8186230659484863,
882
+ "learning_rate": 3.0790702255378974e-06,
883
+ "loss": 0.0287,
884
+ "step": 510
885
+ },
886
+ {
887
+ "epoch": 12.89171974522293,
888
+ "grad_norm": 0.8705646395683289,
889
+ "learning_rate": 2.7561989210989235e-06,
890
+ "loss": 0.0218,
891
+ "step": 515
892
+ },
893
+ {
894
+ "epoch": 13.0,
895
+ "grad_norm": 3.0652782917022705,
896
+ "learning_rate": 2.4502192466760276e-06,
897
+ "loss": 0.0268,
898
+ "step": 520
899
+ },
900
+ {
901
+ "epoch": 13.127388535031848,
902
+ "grad_norm": 1.0207325220108032,
903
+ "learning_rate": 2.1613635589349756e-06,
904
+ "loss": 0.0155,
905
+ "step": 525
906
+ },
907
+ {
908
+ "epoch": 13.127388535031848,
909
+ "eval_loss": 3.1609668731689453,
910
+ "eval_runtime": 1.1337,
911
+ "eval_samples_per_second": 15.877,
912
+ "eval_steps_per_second": 2.646,
913
+ "step": 525
914
+ },
915
+ {
916
+ "epoch": 13.254777070063694,
917
+ "grad_norm": 1.7514115571975708,
918
+ "learning_rate": 1.8898512108266569e-06,
919
+ "loss": 0.017,
920
+ "step": 530
921
+ },
922
+ {
923
+ "epoch": 13.382165605095542,
924
+ "grad_norm": 1.1046432256698608,
925
+ "learning_rate": 1.6358883850134816e-06,
926
+ "loss": 0.0154,
927
+ "step": 535
928
+ },
929
+ {
930
+ "epoch": 13.509554140127388,
931
+ "grad_norm": 0.9812297821044922,
932
+ "learning_rate": 1.3996679372972304e-06,
933
+ "loss": 0.0205,
934
+ "step": 540
935
+ },
936
+ {
937
+ "epoch": 13.636942675159236,
938
+ "grad_norm": 1.1135008335113525,
939
+ "learning_rate": 1.1813692501670276e-06,
940
+ "loss": 0.0249,
941
+ "step": 545
942
+ },
943
+ {
944
+ "epoch": 13.764331210191083,
945
+ "grad_norm": 1.5334270000457764,
946
+ "learning_rate": 9.811580965787965e-07,
947
+ "loss": 0.015,
948
+ "step": 550
949
+ },
950
+ {
951
+ "epoch": 13.764331210191083,
952
+ "eval_loss": 3.177839517593384,
953
+ "eval_runtime": 1.1297,
954
+ "eval_samples_per_second": 15.934,
955
+ "eval_steps_per_second": 2.656,
956
+ "step": 550
957
+ }
958
+ ],
959
+ "logging_steps": 5,
960
+ "max_steps": 600,
961
+ "num_input_tokens_seen": 0,
962
+ "num_train_epochs": 15,
963
+ "save_steps": 50,
964
+ "stateful_callbacks": {
965
+ "TrainerControl": {
966
+ "args": {
967
+ "should_epoch_stop": false,
968
+ "should_evaluate": false,
969
+ "should_log": false,
970
+ "should_save": true,
971
+ "should_training_stop": false
972
+ },
973
+ "attributes": {}
974
+ }
975
+ },
976
+ "total_flos": 8326402741149696.0,
977
+ "train_batch_size": 1,
978
+ "trial_name": null,
979
+ "trial_params": null
980
+ }
checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb46dc44937ba4dbf6e54e6b92a8c41ca12d164348e1ad4fd80375a1f258dd54
3
+ size 6225
checkpoint-550/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": null,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_frames": 4,
28
+ "min_pixels": 3136,
29
+ "num_frames": null,
30
+ "pad_size": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 12845056,
38
+ "shortest_edge": 3136
39
+ },
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
checkpoint-550/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-600/README.md ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ''
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
7
+ - llama-factory
8
+ - lora
9
+ - transformers
10
+ ---
11
+
12
+ # Model Card for Model ID
13
+
14
+ <!-- Provide a quick summary of what the model is/does. -->
15
+
16
+
17
+
18
+ ## Model Details
19
+
20
+ ### Model Description
21
+
22
+ <!-- Provide a longer summary of what this model is. -->
23
+
24
+
25
+
26
+ - **Developed by:** [More Information Needed]
27
+ - **Funded by [optional]:** [More Information Needed]
28
+ - **Shared by [optional]:** [More Information Needed]
29
+ - **Model type:** [More Information Needed]
30
+ - **Language(s) (NLP):** [More Information Needed]
31
+ - **License:** [More Information Needed]
32
+ - **Finetuned from model [optional]:** [More Information Needed]
33
+
34
+ ### Model Sources [optional]
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** [More Information Needed]
39
+ - **Paper [optional]:** [More Information Needed]
40
+ - **Demo [optional]:** [More Information Needed]
41
+
42
+ ## Uses
43
+
44
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
+
46
+ ### Direct Use
47
+
48
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Downstream Use [optional]
53
+
54
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
+
56
+ [More Information Needed]
57
+
58
+ ### Out-of-Scope Use
59
+
60
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ## Bias, Risks, and Limitations
65
+
66
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
+
68
+ [More Information Needed]
69
+
70
+ ### Recommendations
71
+
72
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
+
74
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
+
76
+ ## How to Get Started with the Model
77
+
78
+ Use the code below to get started with the model.
79
+
80
+ [More Information Needed]
81
+
82
+ ## Training Details
83
+
84
+ ### Training Data
85
+
86
+ <!-- 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. -->
87
+
88
+ [More Information Needed]
89
+
90
+ ### Training Procedure
91
+
92
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
+
94
+ #### Preprocessing [optional]
95
+
96
+ [More Information Needed]
97
+
98
+
99
+ #### Training Hyperparameters
100
+
101
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
+
103
+ #### Speeds, Sizes, Times [optional]
104
+
105
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
+
107
+ [More Information Needed]
108
+
109
+ ## Evaluation
110
+
111
+ <!-- This section describes the evaluation protocols and provides the results. -->
112
+
113
+ ### Testing Data, Factors & Metrics
114
+
115
+ #### Testing Data
116
+
117
+ <!-- This should link to a Dataset Card if possible. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Factors
122
+
123
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
+
125
+ [More Information Needed]
126
+
127
+ #### Metrics
128
+
129
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
+
131
+ [More Information Needed]
132
+
133
+ ### Results
134
+
135
+ [More Information Needed]
136
+
137
+ #### Summary
138
+
139
+
140
+
141
+ ## Model Examination [optional]
142
+
143
+ <!-- Relevant interpretability work for the model goes here -->
144
+
145
+ [More Information Needed]
146
+
147
+ ## Environmental Impact
148
+
149
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
+
151
+ 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).
152
+
153
+ - **Hardware Type:** [More Information Needed]
154
+ - **Hours used:** [More Information Needed]
155
+ - **Cloud Provider:** [More Information Needed]
156
+ - **Compute Region:** [More Information Needed]
157
+ - **Carbon Emitted:** [More Information Needed]
158
+
159
+ ## Technical Specifications [optional]
160
+
161
+ ### Model Architecture and Objective
162
+
163
+ [More Information Needed]
164
+
165
+ ### Compute Infrastructure
166
+
167
+ [More Information Needed]
168
+
169
+ #### Hardware
170
+
171
+ [More Information Needed]
172
+
173
+ #### Software
174
+
175
+ [More Information Needed]
176
+
177
+ ## Citation [optional]
178
+
179
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
+
181
+ **BibTeX:**
182
+
183
+ [More Information Needed]
184
+
185
+ **APA:**
186
+
187
+ [More Information Needed]
188
+
189
+ ## Glossary [optional]
190
+
191
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
+
193
+ [More Information Needed]
194
+
195
+ ## More Information [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Authors [optional]
200
+
201
+ [More Information Needed]
202
+
203
+ ## Model Card Contact
204
+
205
+ [More Information Needed]
206
+ ### Framework versions
207
+
208
+ - PEFT 0.17.1
checkpoint-600/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "down_proj",
30
+ "k_proj",
31
+ "gate_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-600/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f3841e9633ffe5a9bd96a030b2ab2bc6fe6ad8e71e2b2ad644485d70f560ef
3
+ size 73916992
checkpoint-600/added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
checkpoint-600/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
checkpoint-600/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d50570db6472692e90fce409d5b27e147e77b0651a5e37fefd2296832a62439
3
+ size 148053627
checkpoint-600/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5fcf8676def8d8317087706af7bea7f1d82a0c9edc6054cc3b7221c4c6b4b9
3
+ size 14645
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ae3778a43ab33194e3eb557cd3e82c54c63f22364e734be5b5c32d5a5037dd
3
+ size 1465
checkpoint-600/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }