upload
Browse files- 2e_5_r8_2VQAlora2nd/README.md +202 -0
- 2e_5_r8_2VQAlora2nd/adapter_config.json +38 -0
- 2e_5_r8_2VQAlora2nd/adapter_model.safetensors +3 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +202 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +38 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +3 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +3 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +3 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +3 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +533 -0
- 2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin +3 -0
- 2e_5_r8_2VQAlora2nd/training_args.bin +3 -0
- 4e_5_2VQAlora2nd/README.md +202 -0
- 4e_5_2VQAlora2nd/adapter_config.json +38 -0
- 4e_5_2VQAlora2nd/adapter_model.safetensors +3 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +202 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +38 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +3 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +3 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +3 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +3 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +149 -0
- 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin +3 -0
- 4e_5_2VQAlora2nd/training_args.bin +3 -0
- 4e_5_r8_2VQAlora2nd/README.md +202 -0
- 4e_5_r8_2VQAlora2nd/adapter_config.json +38 -0
- 4e_5_r8_2VQAlora2nd/adapter_model.safetensors +3 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +202 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +38 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +3 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +3 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +3 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +3 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +533 -0
- 4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin +3 -0
- 4e_5_r8_2VQAlora2nd/training_args.bin +3 -0
2e_5_r8_2VQAlora2nd/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
2e_5_r8_2VQAlora2nd/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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": 16,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 8,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"up_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"down_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"k_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
2e_5_r8_2VQAlora2nd/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b0232e69491294015ab0a4efd85b1b6e1b7d740369cb5272f16a0c3a0b1dd2e
|
3 |
+
size 82145000
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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": 16,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 8,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"up_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"down_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"k_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ecd06d454a5ef19de39fef869cf97fd790549b09548406d84a8c939662c9951
|
3 |
+
size 82145000
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e58c4171fc1708d1a7c9827f39f2780c58fa8c1147ac2040914171331cbcca38
|
3 |
+
size 159745054
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d
|
3 |
+
size 14244
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf58c2acdbed25fa02315fba4c7735d145c4d933480a8c2806b5a368de6c669
|
3 |
+
size 1000
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json
ADDED
@@ -0,0 +1,533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.623073935508728,
|
3 |
+
"best_model_checkpoint": "/workspace/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80",
|
4 |
+
"epoch": 1.4269788182831662,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 5e-06,
|
14 |
+
"loss": 0.8086,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 1e-05,
|
20 |
+
"loss": 0.6797,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 1.5000000000000002e-05,
|
26 |
+
"loss": 0.4551,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.07,
|
31 |
+
"learning_rate": 2e-05,
|
32 |
+
"loss": 0.543,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.09,
|
37 |
+
"learning_rate": 1.9995769500822007e-05,
|
38 |
+
"loss": 0.3105,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.11,
|
43 |
+
"learning_rate": 1.9983081582712684e-05,
|
44 |
+
"loss": 0.4727,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.12,
|
49 |
+
"learning_rate": 1.9961946980917457e-05,
|
50 |
+
"loss": 0.6914,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.14,
|
55 |
+
"learning_rate": 1.9932383577419432e-05,
|
56 |
+
"loss": 0.5586,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.16,
|
61 |
+
"learning_rate": 1.9894416385809444e-05,
|
62 |
+
"loss": 0.4395,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.18,
|
67 |
+
"learning_rate": 1.9848077530122083e-05,
|
68 |
+
"loss": 0.457,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.2,
|
73 |
+
"learning_rate": 1.9793406217655516e-05,
|
74 |
+
"loss": 0.3574,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.21,
|
79 |
+
"learning_rate": 1.973044870579824e-05,
|
80 |
+
"loss": 0.6641,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.23,
|
85 |
+
"learning_rate": 1.9659258262890683e-05,
|
86 |
+
"loss": 0.5117,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.25,
|
91 |
+
"learning_rate": 1.957989512315489e-05,
|
92 |
+
"loss": 0.5742,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.27,
|
97 |
+
"learning_rate": 1.949242643573034e-05,
|
98 |
+
"loss": 0.4824,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.29,
|
103 |
+
"learning_rate": 1.9396926207859085e-05,
|
104 |
+
"loss": 0.416,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.3,
|
109 |
+
"learning_rate": 1.9293475242268224e-05,
|
110 |
+
"loss": 0.625,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.32,
|
115 |
+
"learning_rate": 1.9182161068802742e-05,
|
116 |
+
"loss": 0.2354,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.34,
|
121 |
+
"learning_rate": 1.9063077870366504e-05,
|
122 |
+
"loss": 0.7891,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.36,
|
127 |
+
"learning_rate": 1.8936326403234125e-05,
|
128 |
+
"loss": 0.668,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.36,
|
133 |
+
"eval_loss": 0.6457709074020386,
|
134 |
+
"eval_runtime": 330.0437,
|
135 |
+
"eval_samples_per_second": 1.366,
|
136 |
+
"eval_steps_per_second": 0.685,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.37,
|
141 |
+
"learning_rate": 1.880201391180111e-05,
|
142 |
+
"loss": 0.5391,
|
143 |
+
"step": 21
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.39,
|
147 |
+
"learning_rate": 1.866025403784439e-05,
|
148 |
+
"loss": 0.3848,
|
149 |
+
"step": 22
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.41,
|
153 |
+
"learning_rate": 1.8511166724369997e-05,
|
154 |
+
"loss": 0.4434,
|
155 |
+
"step": 23
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.43,
|
159 |
+
"learning_rate": 1.8354878114129368e-05,
|
160 |
+
"loss": 0.5977,
|
161 |
+
"step": 24
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.45,
|
165 |
+
"learning_rate": 1.819152044288992e-05,
|
166 |
+
"loss": 0.543,
|
167 |
+
"step": 25
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.46,
|
171 |
+
"learning_rate": 1.802123192755044e-05,
|
172 |
+
"loss": 0.7422,
|
173 |
+
"step": 26
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.48,
|
177 |
+
"learning_rate": 1.784415664919576e-05,
|
178 |
+
"loss": 0.5039,
|
179 |
+
"step": 27
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.5,
|
183 |
+
"learning_rate": 1.766044443118978e-05,
|
184 |
+
"loss": 0.3848,
|
185 |
+
"step": 28
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.52,
|
189 |
+
"learning_rate": 1.7470250712409963e-05,
|
190 |
+
"loss": 0.5195,
|
191 |
+
"step": 29
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.54,
|
195 |
+
"learning_rate": 1.7273736415730488e-05,
|
196 |
+
"loss": 0.3945,
|
197 |
+
"step": 30
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.55,
|
201 |
+
"learning_rate": 1.7071067811865477e-05,
|
202 |
+
"loss": 0.5586,
|
203 |
+
"step": 31
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.57,
|
207 |
+
"learning_rate": 1.686241637868734e-05,
|
208 |
+
"loss": 0.4512,
|
209 |
+
"step": 32
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.59,
|
213 |
+
"learning_rate": 1.6647958656139377e-05,
|
214 |
+
"loss": 0.5273,
|
215 |
+
"step": 33
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.61,
|
219 |
+
"learning_rate": 1.6427876096865394e-05,
|
220 |
+
"loss": 0.5273,
|
221 |
+
"step": 34
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.62,
|
225 |
+
"learning_rate": 1.6202354912682602e-05,
|
226 |
+
"loss": 0.7734,
|
227 |
+
"step": 35
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.64,
|
231 |
+
"learning_rate": 1.5971585917027864e-05,
|
232 |
+
"loss": 0.875,
|
233 |
+
"step": 36
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.66,
|
237 |
+
"learning_rate": 1.573576436351046e-05,
|
238 |
+
"loss": 0.6602,
|
239 |
+
"step": 37
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.68,
|
243 |
+
"learning_rate": 1.5495089780708062e-05,
|
244 |
+
"loss": 0.8047,
|
245 |
+
"step": 38
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.7,
|
249 |
+
"learning_rate": 1.5249765803345602e-05,
|
250 |
+
"loss": 0.793,
|
251 |
+
"step": 39
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.71,
|
255 |
+
"learning_rate": 1.5000000000000002e-05,
|
256 |
+
"loss": 0.6562,
|
257 |
+
"step": 40
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.71,
|
261 |
+
"eval_loss": 0.6437277793884277,
|
262 |
+
"eval_runtime": 322.5002,
|
263 |
+
"eval_samples_per_second": 1.398,
|
264 |
+
"eval_steps_per_second": 0.701,
|
265 |
+
"step": 40
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.73,
|
269 |
+
"learning_rate": 1.4746003697476406e-05,
|
270 |
+
"loss": 0.5859,
|
271 |
+
"step": 41
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.75,
|
275 |
+
"learning_rate": 1.4487991802004625e-05,
|
276 |
+
"loss": 0.6328,
|
277 |
+
"step": 42
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.77,
|
281 |
+
"learning_rate": 1.4226182617406996e-05,
|
282 |
+
"loss": 0.4727,
|
283 |
+
"step": 43
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.78,
|
287 |
+
"learning_rate": 1.396079766039157e-05,
|
288 |
+
"loss": 0.6836,
|
289 |
+
"step": 44
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.8,
|
293 |
+
"learning_rate": 1.3692061473126845e-05,
|
294 |
+
"loss": 0.6875,
|
295 |
+
"step": 45
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.82,
|
299 |
+
"learning_rate": 1.342020143325669e-05,
|
300 |
+
"loss": 0.75,
|
301 |
+
"step": 46
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.84,
|
305 |
+
"learning_rate": 1.3145447561516138e-05,
|
306 |
+
"loss": 0.4512,
|
307 |
+
"step": 47
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.86,
|
311 |
+
"learning_rate": 1.2868032327110904e-05,
|
312 |
+
"loss": 0.6875,
|
313 |
+
"step": 48
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.87,
|
317 |
+
"learning_rate": 1.2588190451025209e-05,
|
318 |
+
"loss": 0.7734,
|
319 |
+
"step": 49
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.89,
|
323 |
+
"learning_rate": 1.2306158707424402e-05,
|
324 |
+
"loss": 0.6328,
|
325 |
+
"step": 50
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.91,
|
329 |
+
"learning_rate": 1.2022175723320382e-05,
|
330 |
+
"loss": 0.6992,
|
331 |
+
"step": 51
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.93,
|
335 |
+
"learning_rate": 1.1736481776669307e-05,
|
336 |
+
"loss": 0.5977,
|
337 |
+
"step": 52
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.95,
|
341 |
+
"learning_rate": 1.1449318593072468e-05,
|
342 |
+
"loss": 0.5742,
|
343 |
+
"step": 53
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 0.96,
|
347 |
+
"learning_rate": 1.1160929141252303e-05,
|
348 |
+
"loss": 0.3633,
|
349 |
+
"step": 54
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.98,
|
353 |
+
"learning_rate": 1.0871557427476585e-05,
|
354 |
+
"loss": 0.6836,
|
355 |
+
"step": 55
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 1.0,
|
359 |
+
"learning_rate": 1.0581448289104759e-05,
|
360 |
+
"loss": 0.8086,
|
361 |
+
"step": 56
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 1.02,
|
365 |
+
"learning_rate": 1.0290847187431115e-05,
|
366 |
+
"loss": 0.3984,
|
367 |
+
"step": 57
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.03,
|
371 |
+
"learning_rate": 1e-05,
|
372 |
+
"loss": 0.4531,
|
373 |
+
"step": 58
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.05,
|
377 |
+
"learning_rate": 9.709152812568886e-06,
|
378 |
+
"loss": 0.5039,
|
379 |
+
"step": 59
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 1.07,
|
383 |
+
"learning_rate": 9.418551710895243e-06,
|
384 |
+
"loss": 0.6211,
|
385 |
+
"step": 60
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 1.07,
|
389 |
+
"eval_loss": 0.6246171593666077,
|
390 |
+
"eval_runtime": 327.5115,
|
391 |
+
"eval_samples_per_second": 1.377,
|
392 |
+
"eval_steps_per_second": 0.69,
|
393 |
+
"step": 60
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.09,
|
397 |
+
"learning_rate": 9.128442572523418e-06,
|
398 |
+
"loss": 0.3184,
|
399 |
+
"step": 61
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.11,
|
403 |
+
"learning_rate": 8.839070858747697e-06,
|
404 |
+
"loss": 0.4434,
|
405 |
+
"step": 62
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.12,
|
409 |
+
"learning_rate": 8.550681406927534e-06,
|
410 |
+
"loss": 0.4141,
|
411 |
+
"step": 63
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.14,
|
415 |
+
"learning_rate": 8.263518223330698e-06,
|
416 |
+
"loss": 0.3477,
|
417 |
+
"step": 64
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 1.16,
|
421 |
+
"learning_rate": 7.977824276679623e-06,
|
422 |
+
"loss": 0.4844,
|
423 |
+
"step": 65
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.18,
|
427 |
+
"learning_rate": 7.6938412925756e-06,
|
428 |
+
"loss": 0.4902,
|
429 |
+
"step": 66
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.2,
|
433 |
+
"learning_rate": 7.411809548974792e-06,
|
434 |
+
"loss": 0.5547,
|
435 |
+
"step": 67
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 1.21,
|
439 |
+
"learning_rate": 7.131967672889101e-06,
|
440 |
+
"loss": 0.3965,
|
441 |
+
"step": 68
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.23,
|
445 |
+
"learning_rate": 6.854552438483866e-06,
|
446 |
+
"loss": 0.6133,
|
447 |
+
"step": 69
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.25,
|
451 |
+
"learning_rate": 6.579798566743314e-06,
|
452 |
+
"loss": 0.5312,
|
453 |
+
"step": 70
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 1.27,
|
457 |
+
"learning_rate": 6.3079385268731575e-06,
|
458 |
+
"loss": 0.4766,
|
459 |
+
"step": 71
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.28,
|
463 |
+
"learning_rate": 6.039202339608432e-06,
|
464 |
+
"loss": 0.8125,
|
465 |
+
"step": 72
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.3,
|
469 |
+
"learning_rate": 5.773817382593008e-06,
|
470 |
+
"loss": 0.4551,
|
471 |
+
"step": 73
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.32,
|
475 |
+
"learning_rate": 5.512008197995379e-06,
|
476 |
+
"loss": 0.4219,
|
477 |
+
"step": 74
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 1.34,
|
481 |
+
"learning_rate": 5.253996302523596e-06,
|
482 |
+
"loss": 0.3867,
|
483 |
+
"step": 75
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.36,
|
487 |
+
"learning_rate": 5.000000000000003e-06,
|
488 |
+
"loss": 0.5156,
|
489 |
+
"step": 76
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.37,
|
493 |
+
"learning_rate": 4.7502341966544e-06,
|
494 |
+
"loss": 0.5469,
|
495 |
+
"step": 77
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 1.39,
|
499 |
+
"learning_rate": 4.504910219291941e-06,
|
500 |
+
"loss": 0.3984,
|
501 |
+
"step": 78
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.41,
|
505 |
+
"learning_rate": 4.264235636489542e-06,
|
506 |
+
"loss": 0.4395,
|
507 |
+
"step": 79
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.43,
|
511 |
+
"learning_rate": 4.028414082972141e-06,
|
512 |
+
"loss": 0.6719,
|
513 |
+
"step": 80
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.43,
|
517 |
+
"eval_loss": 0.623073935508728,
|
518 |
+
"eval_runtime": 322.1595,
|
519 |
+
"eval_samples_per_second": 1.4,
|
520 |
+
"eval_steps_per_second": 0.702,
|
521 |
+
"step": 80
|
522 |
+
}
|
523 |
+
],
|
524 |
+
"logging_steps": 1,
|
525 |
+
"max_steps": 112,
|
526 |
+
"num_input_tokens_seen": 0,
|
527 |
+
"num_train_epochs": 2,
|
528 |
+
"save_steps": 40,
|
529 |
+
"total_flos": 4979777395845120.0,
|
530 |
+
"train_batch_size": 2,
|
531 |
+
"trial_name": null,
|
532 |
+
"trial_params": null
|
533 |
+
}
|
2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3fb2b54d9ce3c79a2533cc4f7113f96de9b3af85fa1d22489c50d5969473c5a
|
3 |
+
size 4792
|
2e_5_r8_2VQAlora2nd/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3fb2b54d9ce3c79a2533cc4f7113f96de9b3af85fa1d22489c50d5969473c5a
|
3 |
+
size 4792
|
4e_5_2VQAlora2nd/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
4e_5_2VQAlora2nd/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 16,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"k_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"down_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
4e_5_2VQAlora2nd/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ec223b0f496bb70eced664b2e732b675e4285577505c475ba9c48886f4fbcd5
|
3 |
+
size 122253960
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 16,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"k_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"down_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ec223b0f496bb70eced664b2e732b675e4285577505c475ba9c48886f4fbcd5
|
3 |
+
size 122253960
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ba45b246b37370bda13027e4d8bd1349db0353bb2b3a540a7892a9d76989300
|
3 |
+
size 235243422
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d
|
3 |
+
size 14244
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91de2e5150296a3888b9d86e8412c0c3aac23a6d23700fef3e75d90a2393e8e1
|
3 |
+
size 1000
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6341778635978699,
|
3 |
+
"best_model_checkpoint": "/workspace/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80",
|
4 |
+
"epoch": 1.4269788182831662,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09,
|
13 |
+
"learning_rate": 3.9991539001644015e-05,
|
14 |
+
"loss": 0.5469,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.18,
|
19 |
+
"learning_rate": 3.9696155060244166e-05,
|
20 |
+
"loss": 0.5094,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.27,
|
25 |
+
"learning_rate": 3.898485287146068e-05,
|
26 |
+
"loss": 0.4844,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.36,
|
31 |
+
"learning_rate": 3.787265280646825e-05,
|
32 |
+
"loss": 0.5625,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.36,
|
37 |
+
"eval_loss": 0.6666426062583923,
|
38 |
+
"eval_runtime": 313.5071,
|
39 |
+
"eval_samples_per_second": 1.439,
|
40 |
+
"eval_steps_per_second": 0.721,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.45,
|
45 |
+
"learning_rate": 3.638304088577984e-05,
|
46 |
+
"loss": 0.4938,
|
47 |
+
"step": 25
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.54,
|
51 |
+
"learning_rate": 3.4547472831460976e-05,
|
52 |
+
"loss": 0.4969,
|
53 |
+
"step": 30
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.62,
|
57 |
+
"learning_rate": 3.2404709825365204e-05,
|
58 |
+
"loss": 0.5219,
|
59 |
+
"step": 35
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.71,
|
63 |
+
"learning_rate": 3.0000000000000004e-05,
|
64 |
+
"loss": 0.7219,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.71,
|
69 |
+
"eval_loss": 0.6467391848564148,
|
70 |
+
"eval_runtime": 318.6731,
|
71 |
+
"eval_samples_per_second": 1.415,
|
72 |
+
"eval_steps_per_second": 0.709,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.8,
|
77 |
+
"learning_rate": 2.738412294625369e-05,
|
78 |
+
"loss": 0.575,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.89,
|
83 |
+
"learning_rate": 2.4612317414848804e-05,
|
84 |
+
"loss": 0.6344,
|
85 |
+
"step": 50
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.98,
|
89 |
+
"learning_rate": 2.174311485495317e-05,
|
90 |
+
"loss": 0.5469,
|
91 |
+
"step": 55
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.07,
|
95 |
+
"learning_rate": 1.8837103421790486e-05,
|
96 |
+
"loss": 0.4469,
|
97 |
+
"step": 60
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.07,
|
101 |
+
"eval_loss": 0.6086602210998535,
|
102 |
+
"eval_runtime": 320.0767,
|
103 |
+
"eval_samples_per_second": 1.409,
|
104 |
+
"eval_steps_per_second": 0.706,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.16,
|
109 |
+
"learning_rate": 1.5955648553359247e-05,
|
110 |
+
"loss": 0.3141,
|
111 |
+
"step": 65
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.25,
|
115 |
+
"learning_rate": 1.3159597133486628e-05,
|
116 |
+
"loss": 0.3953,
|
117 |
+
"step": 70
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.34,
|
121 |
+
"learning_rate": 1.0507992605047193e-05,
|
122 |
+
"loss": 0.3875,
|
123 |
+
"step": 75
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.43,
|
127 |
+
"learning_rate": 8.056828165944282e-06,
|
128 |
+
"loss": 0.3766,
|
129 |
+
"step": 80
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.43,
|
133 |
+
"eval_loss": 0.6341778635978699,
|
134 |
+
"eval_runtime": 315.0947,
|
135 |
+
"eval_samples_per_second": 1.431,
|
136 |
+
"eval_steps_per_second": 0.717,
|
137 |
+
"step": 80
|
138 |
+
}
|
139 |
+
],
|
140 |
+
"logging_steps": 5,
|
141 |
+
"max_steps": 112,
|
142 |
+
"num_input_tokens_seen": 0,
|
143 |
+
"num_train_epochs": 2,
|
144 |
+
"save_steps": 40,
|
145 |
+
"total_flos": 4993136137955328.0,
|
146 |
+
"train_batch_size": 2,
|
147 |
+
"trial_name": null,
|
148 |
+
"trial_params": null
|
149 |
+
}
|
4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a68ac9690d72595e0b21c7496fbf44aa8a0d4c5bd0264468e35b12eddd8e350
|
3 |
+
size 4792
|
4e_5_2VQAlora2nd/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a68ac9690d72595e0b21c7496fbf44aa8a0d4c5bd0264468e35b12eddd8e350
|
3 |
+
size 4792
|
4e_5_r8_2VQAlora2nd/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
4e_5_r8_2VQAlora2nd/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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": 16,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 8,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"q_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
4e_5_r8_2VQAlora2nd/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4251bacf03189ccc18b2f3b80149c2984023e37d29f135866c07d3b3ea7f27d
|
3 |
+
size 82145000
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.1.dev0
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaMistralForCausalLM",
|
5 |
+
"parent_library": "llava.model.language_model.llava_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
|
8 |
+
"bias": "none",
|
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": 16,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"mm_projector"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 8,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"q_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4251bacf03189ccc18b2f3b80149c2984023e37d29f135866c07d3b3ea7f27d
|
3 |
+
size 82145000
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:142e2e403e738467fe0ae0d0cad7e4805d9c808c4ce3bb564c84cab83eae59f8
|
3 |
+
size 159745054
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d
|
3 |
+
size 14244
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91de2e5150296a3888b9d86e8412c0c3aac23a6d23700fef3e75d90a2393e8e1
|
3 |
+
size 1000
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json
ADDED
@@ -0,0 +1,533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6239878535270691,
|
3 |
+
"best_model_checkpoint": "/workspace/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80",
|
4 |
+
"epoch": 1.4269788182831662,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 1e-05,
|
14 |
+
"loss": 0.8086,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 2e-05,
|
20 |
+
"loss": 0.6797,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 3.0000000000000004e-05,
|
26 |
+
"loss": 0.4492,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.07,
|
31 |
+
"learning_rate": 4e-05,
|
32 |
+
"loss": 0.5117,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.09,
|
37 |
+
"learning_rate": 3.9991539001644015e-05,
|
38 |
+
"loss": 0.3027,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.11,
|
43 |
+
"learning_rate": 3.996616316542537e-05,
|
44 |
+
"loss": 0.4629,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.12,
|
49 |
+
"learning_rate": 3.9923893961834914e-05,
|
50 |
+
"loss": 0.6875,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.14,
|
55 |
+
"learning_rate": 3.9864767154838864e-05,
|
56 |
+
"loss": 0.5586,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.16,
|
61 |
+
"learning_rate": 3.978883277161889e-05,
|
62 |
+
"loss": 0.4551,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.18,
|
67 |
+
"learning_rate": 3.9696155060244166e-05,
|
68 |
+
"loss": 0.4297,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.2,
|
73 |
+
"learning_rate": 3.958681243531103e-05,
|
74 |
+
"loss": 0.3301,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.21,
|
79 |
+
"learning_rate": 3.946089741159648e-05,
|
80 |
+
"loss": 0.6367,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.23,
|
85 |
+
"learning_rate": 3.931851652578137e-05,
|
86 |
+
"loss": 0.4883,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.25,
|
91 |
+
"learning_rate": 3.915979024630978e-05,
|
92 |
+
"loss": 0.5625,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.27,
|
97 |
+
"learning_rate": 3.898485287146068e-05,
|
98 |
+
"loss": 0.4492,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.29,
|
103 |
+
"learning_rate": 3.879385241571817e-05,
|
104 |
+
"loss": 0.4395,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.3,
|
109 |
+
"learning_rate": 3.858695048453645e-05,
|
110 |
+
"loss": 0.6016,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.32,
|
115 |
+
"learning_rate": 3.8364322137605484e-05,
|
116 |
+
"loss": 0.2266,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.34,
|
121 |
+
"learning_rate": 3.812615574073301e-05,
|
122 |
+
"loss": 0.8047,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.36,
|
127 |
+
"learning_rate": 3.787265280646825e-05,
|
128 |
+
"loss": 0.6797,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.36,
|
133 |
+
"eval_loss": 0.6560852527618408,
|
134 |
+
"eval_runtime": 313.3213,
|
135 |
+
"eval_samples_per_second": 1.439,
|
136 |
+
"eval_steps_per_second": 0.721,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.37,
|
141 |
+
"learning_rate": 3.760402782360222e-05,
|
142 |
+
"loss": 0.5625,
|
143 |
+
"step": 21
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.39,
|
147 |
+
"learning_rate": 3.732050807568878e-05,
|
148 |
+
"loss": 0.3496,
|
149 |
+
"step": 22
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.41,
|
153 |
+
"learning_rate": 3.702233344873999e-05,
|
154 |
+
"loss": 0.4316,
|
155 |
+
"step": 23
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.43,
|
159 |
+
"learning_rate": 3.6709756228258735e-05,
|
160 |
+
"loss": 0.5938,
|
161 |
+
"step": 24
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.45,
|
165 |
+
"learning_rate": 3.638304088577984e-05,
|
166 |
+
"loss": 0.543,
|
167 |
+
"step": 25
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.46,
|
171 |
+
"learning_rate": 3.604246385510088e-05,
|
172 |
+
"loss": 0.7305,
|
173 |
+
"step": 26
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.48,
|
177 |
+
"learning_rate": 3.568831329839152e-05,
|
178 |
+
"loss": 0.4941,
|
179 |
+
"step": 27
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.5,
|
183 |
+
"learning_rate": 3.532088886237956e-05,
|
184 |
+
"loss": 0.3711,
|
185 |
+
"step": 28
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.52,
|
189 |
+
"learning_rate": 3.4940501424819927e-05,
|
190 |
+
"loss": 0.5,
|
191 |
+
"step": 29
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.54,
|
195 |
+
"learning_rate": 3.4547472831460976e-05,
|
196 |
+
"loss": 0.4004,
|
197 |
+
"step": 30
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.55,
|
201 |
+
"learning_rate": 3.4142135623730954e-05,
|
202 |
+
"loss": 0.5547,
|
203 |
+
"step": 31
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.57,
|
207 |
+
"learning_rate": 3.372483275737468e-05,
|
208 |
+
"loss": 0.4336,
|
209 |
+
"step": 32
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.59,
|
213 |
+
"learning_rate": 3.3295917312278754e-05,
|
214 |
+
"loss": 0.4766,
|
215 |
+
"step": 33
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.61,
|
219 |
+
"learning_rate": 3.285575219373079e-05,
|
220 |
+
"loss": 0.4824,
|
221 |
+
"step": 34
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.62,
|
225 |
+
"learning_rate": 3.2404709825365204e-05,
|
226 |
+
"loss": 0.7305,
|
227 |
+
"step": 35
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.64,
|
231 |
+
"learning_rate": 3.194317183405573e-05,
|
232 |
+
"loss": 0.8555,
|
233 |
+
"step": 36
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.66,
|
237 |
+
"learning_rate": 3.147152872702092e-05,
|
238 |
+
"loss": 0.6484,
|
239 |
+
"step": 37
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.68,
|
243 |
+
"learning_rate": 3.0990179561416124e-05,
|
244 |
+
"loss": 0.8008,
|
245 |
+
"step": 38
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.7,
|
249 |
+
"learning_rate": 3.0499531606691204e-05,
|
250 |
+
"loss": 0.7617,
|
251 |
+
"step": 39
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.71,
|
255 |
+
"learning_rate": 3.0000000000000004e-05,
|
256 |
+
"loss": 0.6445,
|
257 |
+
"step": 40
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.71,
|
261 |
+
"eval_loss": 0.6416881680488586,
|
262 |
+
"eval_runtime": 321.2436,
|
263 |
+
"eval_samples_per_second": 1.404,
|
264 |
+
"eval_steps_per_second": 0.704,
|
265 |
+
"step": 40
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.73,
|
269 |
+
"learning_rate": 2.9492007394952812e-05,
|
270 |
+
"loss": 0.5781,
|
271 |
+
"step": 41
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.75,
|
275 |
+
"learning_rate": 2.897598360400925e-05,
|
276 |
+
"loss": 0.6133,
|
277 |
+
"step": 42
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.77,
|
281 |
+
"learning_rate": 2.8452365234813992e-05,
|
282 |
+
"loss": 0.4551,
|
283 |
+
"step": 43
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.78,
|
287 |
+
"learning_rate": 2.792159532078314e-05,
|
288 |
+
"loss": 0.6562,
|
289 |
+
"step": 44
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.8,
|
293 |
+
"learning_rate": 2.738412294625369e-05,
|
294 |
+
"loss": 0.6484,
|
295 |
+
"step": 45
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.82,
|
299 |
+
"learning_rate": 2.684040286651338e-05,
|
300 |
+
"loss": 0.7695,
|
301 |
+
"step": 46
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.84,
|
305 |
+
"learning_rate": 2.6290895123032277e-05,
|
306 |
+
"loss": 0.4355,
|
307 |
+
"step": 47
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.86,
|
311 |
+
"learning_rate": 2.5736064654221808e-05,
|
312 |
+
"loss": 0.6445,
|
313 |
+
"step": 48
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.87,
|
317 |
+
"learning_rate": 2.5176380902050418e-05,
|
318 |
+
"loss": 0.7656,
|
319 |
+
"step": 49
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.89,
|
323 |
+
"learning_rate": 2.4612317414848804e-05,
|
324 |
+
"loss": 0.6172,
|
325 |
+
"step": 50
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.91,
|
329 |
+
"learning_rate": 2.4044351446640763e-05,
|
330 |
+
"loss": 0.6836,
|
331 |
+
"step": 51
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.93,
|
335 |
+
"learning_rate": 2.3472963553338614e-05,
|
336 |
+
"loss": 0.5859,
|
337 |
+
"step": 52
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.95,
|
341 |
+
"learning_rate": 2.2898637186144935e-05,
|
342 |
+
"loss": 0.5078,
|
343 |
+
"step": 53
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 0.96,
|
347 |
+
"learning_rate": 2.2321858282504606e-05,
|
348 |
+
"loss": 0.332,
|
349 |
+
"step": 54
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.98,
|
353 |
+
"learning_rate": 2.174311485495317e-05,
|
354 |
+
"loss": 0.6758,
|
355 |
+
"step": 55
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 1.0,
|
359 |
+
"learning_rate": 2.1162896578209517e-05,
|
360 |
+
"loss": 0.7812,
|
361 |
+
"step": 56
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 1.02,
|
365 |
+
"learning_rate": 2.058169437486223e-05,
|
366 |
+
"loss": 0.3379,
|
367 |
+
"step": 57
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.03,
|
371 |
+
"learning_rate": 2e-05,
|
372 |
+
"loss": 0.3945,
|
373 |
+
"step": 58
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.05,
|
377 |
+
"learning_rate": 1.9418305625137773e-05,
|
378 |
+
"loss": 0.4141,
|
379 |
+
"step": 59
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 1.07,
|
383 |
+
"learning_rate": 1.8837103421790486e-05,
|
384 |
+
"loss": 0.5352,
|
385 |
+
"step": 60
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 1.07,
|
389 |
+
"eval_loss": 0.6122210621833801,
|
390 |
+
"eval_runtime": 324.6814,
|
391 |
+
"eval_samples_per_second": 1.389,
|
392 |
+
"eval_steps_per_second": 0.696,
|
393 |
+
"step": 60
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.09,
|
397 |
+
"learning_rate": 1.8256885145046837e-05,
|
398 |
+
"loss": 0.293,
|
399 |
+
"step": 61
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.11,
|
403 |
+
"learning_rate": 1.7678141717495394e-05,
|
404 |
+
"loss": 0.3887,
|
405 |
+
"step": 62
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.12,
|
409 |
+
"learning_rate": 1.7101362813855068e-05,
|
410 |
+
"loss": 0.3613,
|
411 |
+
"step": 63
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.14,
|
415 |
+
"learning_rate": 1.6527036446661396e-05,
|
416 |
+
"loss": 0.2754,
|
417 |
+
"step": 64
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 1.16,
|
421 |
+
"learning_rate": 1.5955648553359247e-05,
|
422 |
+
"loss": 0.4277,
|
423 |
+
"step": 65
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.18,
|
427 |
+
"learning_rate": 1.53876825851512e-05,
|
428 |
+
"loss": 0.4199,
|
429 |
+
"step": 66
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.2,
|
433 |
+
"learning_rate": 1.4823619097949584e-05,
|
434 |
+
"loss": 0.5,
|
435 |
+
"step": 67
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 1.21,
|
439 |
+
"learning_rate": 1.4263935345778202e-05,
|
440 |
+
"loss": 0.3555,
|
441 |
+
"step": 68
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.23,
|
445 |
+
"learning_rate": 1.3709104876967732e-05,
|
446 |
+
"loss": 0.5,
|
447 |
+
"step": 69
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.25,
|
451 |
+
"learning_rate": 1.3159597133486628e-05,
|
452 |
+
"loss": 0.4609,
|
453 |
+
"step": 70
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 1.27,
|
457 |
+
"learning_rate": 1.2615877053746315e-05,
|
458 |
+
"loss": 0.3887,
|
459 |
+
"step": 71
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.28,
|
463 |
+
"learning_rate": 1.2078404679216864e-05,
|
464 |
+
"loss": 0.7617,
|
465 |
+
"step": 72
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.3,
|
469 |
+
"learning_rate": 1.1547634765186016e-05,
|
470 |
+
"loss": 0.377,
|
471 |
+
"step": 73
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.32,
|
475 |
+
"learning_rate": 1.1024016395990758e-05,
|
476 |
+
"loss": 0.3477,
|
477 |
+
"step": 74
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 1.34,
|
481 |
+
"learning_rate": 1.0507992605047193e-05,
|
482 |
+
"loss": 0.3223,
|
483 |
+
"step": 75
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.36,
|
487 |
+
"learning_rate": 1.0000000000000006e-05,
|
488 |
+
"loss": 0.457,
|
489 |
+
"step": 76
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.37,
|
493 |
+
"learning_rate": 9.5004683933088e-06,
|
494 |
+
"loss": 0.4785,
|
495 |
+
"step": 77
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 1.39,
|
499 |
+
"learning_rate": 9.009820438583881e-06,
|
500 |
+
"loss": 0.3438,
|
501 |
+
"step": 78
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.41,
|
505 |
+
"learning_rate": 8.528471272979083e-06,
|
506 |
+
"loss": 0.3867,
|
507 |
+
"step": 79
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.43,
|
511 |
+
"learning_rate": 8.056828165944282e-06,
|
512 |
+
"loss": 0.5742,
|
513 |
+
"step": 80
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.43,
|
517 |
+
"eval_loss": 0.6239878535270691,
|
518 |
+
"eval_runtime": 319.0711,
|
519 |
+
"eval_samples_per_second": 1.413,
|
520 |
+
"eval_steps_per_second": 0.708,
|
521 |
+
"step": 80
|
522 |
+
}
|
523 |
+
],
|
524 |
+
"logging_steps": 1,
|
525 |
+
"max_steps": 112,
|
526 |
+
"num_input_tokens_seen": 0,
|
527 |
+
"num_train_epochs": 2,
|
528 |
+
"save_steps": 40,
|
529 |
+
"total_flos": 4979777395845120.0,
|
530 |
+
"train_batch_size": 2,
|
531 |
+
"trial_name": null,
|
532 |
+
"trial_params": null
|
533 |
+
}
|
4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f73ff44b36523bfd37fc79f37cdae3c4041859200e83d922156941e7db0343f
|
3 |
+
size 4792
|
4e_5_r8_2VQAlora2nd/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f73ff44b36523bfd37fc79f37cdae3c4041859200e83d922156941e7db0343f
|
3 |
+
size 4792
|