Hugging Face's logo

Theon1130
/
CombineVS

Safetensors
Model card Files Community
Theon1130 commited on
Commit
88fe5f9
•
1 Parent(s): 5c4a385

a

Browse files
Files changed (12) hide show
  1. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/README.md +202 -0
  2. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/adapter_config.json +38 -0
  3. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/adapter_model.safetensors +3 -0
  4. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/optimizer.pt +3 -0
  5. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/rng_state.pth +3 -0
  6. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/scheduler.pt +3 -0
  7. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/trainer_state.json +1477 -0
  8. checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/training_args.bin +3 -0
  9. coslakevqa/README.md +202 -0
  10. coslakevqa/adapter_config.json +38 -0
  11. coslakevqa/adapter_model.safetensors +3 -0
  12. coslakevqa/training_args.bin +3 -0
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /workspace/PMC_llava-v1.6-mistral
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
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/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/PMC_llava-v1.6-mistral",
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": 64,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": [
21
+ "mm_projector"
22
+ ],
23
+ "peft_type": "LORA",
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "down_proj",
30
+ "gate_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": null,
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f352b1bc2b1578187e48cc8654a2522aaaade50687185b90d6bde160173dce
3
+ size 202470344
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e89a8cf3232bf8efbe2c3ffec987a6e61433bdc9868ba9907633aca0114e31e
3
+ size 386238366
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff258695e660cb5b52380fa47adb047e2c6dc192b1f04047f569e6216697361
3
+ size 14244
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da667ae51f3358f8cb770853045dc2ee75e2b09e61e144721be788c454a3f796
3
+ size 1000
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,1477 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4184834361076355,
3
+ "best_model_checkpoint": "/workspace/checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240",
4
+ "epoch": 0.9114645145976739,
5
+ "eval_steps": 120,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2.5e-06,
14
+ "loss": 0.3594,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 5e-06,
20
+ "loss": 0.3262,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 7.500000000000001e-06,
26
+ "loss": 0.5625,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 1e-05,
32
+ "loss": 0.4434,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 1.25e-05,
38
+ "loss": 0.5078,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 1.5000000000000002e-05,
44
+ "loss": 0.3711,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 1.7500000000000002e-05,
50
+ "loss": 0.3867,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 2e-05,
56
+ "loss": 0.4355,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 2.25e-05,
62
+ "loss": 0.3047,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 2.5e-05,
68
+ "loss": 0.2256,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 2.75e-05,
74
+ "loss": 0.4551,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 3.0000000000000004e-05,
80
+ "loss": 0.5078,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.05,
85
+ "learning_rate": 3.2500000000000004e-05,
86
+ "loss": 0.6133,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "learning_rate": 3.5000000000000004e-05,
92
+ "loss": 0.2734,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 3.7500000000000003e-05,
98
+ "loss": 0.2393,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.06,
103
+ "learning_rate": 4e-05,
104
+ "loss": 0.3652,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.06,
109
+ "learning_rate": 3.999962054697454e-05,
110
+ "loss": 0.3477,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.07,
115
+ "learning_rate": 3.999848220229662e-05,
116
+ "loss": 0.3086,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.07,
121
+ "learning_rate": 3.9996585009161056e-05,
122
+ "loss": 0.4512,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.08,
127
+ "learning_rate": 3.999392903955744e-05,
128
+ "loss": 0.2139,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.08,
133
+ "learning_rate": 3.999051439426732e-05,
134
+ "loss": 0.457,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.08,
139
+ "learning_rate": 3.9986341202860467e-05,
140
+ "loss": 0.3887,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.09,
145
+ "learning_rate": 3.998140962368987e-05,
146
+ "loss": 0.1963,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.09,
151
+ "learning_rate": 3.99757198438858e-05,
152
+ "loss": 0.2695,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.09,
157
+ "learning_rate": 3.9969272079348685e-05,
158
+ "loss": 0.5039,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.1,
163
+ "learning_rate": 3.9962066574740886e-05,
164
+ "loss": 0.3008,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.1,
169
+ "learning_rate": 3.9954103603477465e-05,
170
+ "loss": 0.3848,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "learning_rate": 3.994538346771576e-05,
176
+ "loss": 0.3418,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.11,
181
+ "learning_rate": 3.993590649834398e-05,
182
+ "loss": 0.3301,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.11,
187
+ "learning_rate": 3.992567305496859e-05,
188
+ "loss": 0.5156,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.12,
193
+ "learning_rate": 3.991468352590069e-05,
194
+ "loss": 0.2188,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.12,
199
+ "learning_rate": 3.990293832814129e-05,
200
+ "loss": 0.3477,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.13,
205
+ "learning_rate": 3.989043790736547e-05,
206
+ "loss": 0.1729,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.13,
211
+ "learning_rate": 3.987718273790548e-05,
212
+ "loss": 0.3359,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.13,
217
+ "learning_rate": 3.986317332273273e-05,
218
+ "loss": 0.249,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.14,
223
+ "learning_rate": 3.984841019343872e-05,
224
+ "loss": 0.2051,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.14,
229
+ "learning_rate": 3.983289391021486e-05,
230
+ "loss": 0.3008,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.14,
235
+ "learning_rate": 3.9816625061831206e-05,
236
+ "loss": 0.291,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.15,
241
+ "learning_rate": 3.9799604265614145e-05,
242
+ "loss": 0.2715,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.15,
247
+ "learning_rate": 3.9781832167422926e-05,
248
+ "loss": 0.3613,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.16,
253
+ "learning_rate": 3.976330944162519e-05,
254
+ "loss": 0.249,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.16,
259
+ "learning_rate": 3.974403679107139e-05,
260
+ "loss": 0.4297,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.16,
265
+ "learning_rate": 3.972401494706805e-05,
266
+ "loss": 0.1943,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.17,
271
+ "learning_rate": 3.970324466935013e-05,
272
+ "loss": 0.3672,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.17,
277
+ "learning_rate": 3.968172674605209e-05,
278
+ "loss": 0.3145,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.17,
283
+ "learning_rate": 3.965946199367804e-05,
284
+ "loss": 0.3711,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.18,
289
+ "learning_rate": 3.9636451257070744e-05,
290
+ "loss": 0.3652,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.18,
295
+ "learning_rate": 3.9612695409379555e-05,
296
+ "loss": 0.4219,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.19,
301
+ "learning_rate": 3.958819535202732e-05,
302
+ "loss": 0.6016,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.19,
307
+ "learning_rate": 3.9562952014676116e-05,
308
+ "loss": 0.1904,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.19,
313
+ "learning_rate": 3.9536966355192016e-05,
314
+ "loss": 0.3398,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.2,
319
+ "learning_rate": 3.951023935960874e-05,
320
+ "loss": 0.2246,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.2,
325
+ "learning_rate": 3.948277204209021e-05,
326
+ "loss": 0.2061,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.21,
331
+ "learning_rate": 3.94545654448921e-05,
332
+ "loss": 0.3613,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.21,
337
+ "learning_rate": 3.942562063832228e-05,
338
+ "loss": 0.3438,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.21,
343
+ "learning_rate": 3.9395938720700196e-05,
344
+ "loss": 0.2246,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.22,
349
+ "learning_rate": 3.936552081831518e-05,
350
+ "loss": 0.2451,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.22,
355
+ "learning_rate": 3.933436808538375e-05,
356
+ "loss": 0.3125,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.22,
361
+ "learning_rate": 3.930248170400578e-05,
362
+ "loss": 0.2949,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.23,
367
+ "learning_rate": 3.9269862884119666e-05,
368
+ "loss": 0.5,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.23,
373
+ "learning_rate": 3.923651286345638e-05,
374
+ "loss": 0.4609,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.24,
379
+ "learning_rate": 3.920243290749257e-05,
380
+ "loss": 0.2275,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.24,
385
+ "learning_rate": 3.916762430940245e-05,
386
+ "loss": 0.1118,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.24,
391
+ "learning_rate": 3.913208839000882e-05,
392
+ "loss": 0.4199,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.25,
397
+ "learning_rate": 3.9095826497732894e-05,
398
+ "loss": 0.3281,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.25,
403
+ "learning_rate": 3.9058840008543136e-05,
404
+ "loss": 0.1387,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.25,
409
+ "learning_rate": 3.9021130325903076e-05,
410
+ "loss": 0.3008,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.26,
415
+ "learning_rate": 3.898269888071803e-05,
416
+ "loss": 0.3594,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.26,
421
+ "learning_rate": 3.894354713128081e-05,
422
+ "loss": 0.4023,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.27,
427
+ "learning_rate": 3.89036765632164e-05,
428
+ "loss": 0.4531,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.27,
433
+ "learning_rate": 3.886308868942555e-05,
434
+ "loss": 0.2168,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.27,
439
+ "learning_rate": 3.882178505002743e-05,
440
+ "loss": 0.3965,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.28,
445
+ "learning_rate": 3.877976721230114e-05,
446
+ "loss": 0.2197,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.28,
451
+ "learning_rate": 3.8737036770626215e-05,
452
+ "loss": 0.1758,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.28,
457
+ "learning_rate": 3.8693595346422216e-05,
458
+ "loss": 0.1445,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.29,
463
+ "learning_rate": 3.864944458808712e-05,
464
+ "loss": 0.3203,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.29,
469
+ "learning_rate": 3.860458617093481e-05,
470
+ "loss": 0.3613,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.3,
475
+ "learning_rate": 3.85590217971315e-05,
476
+ "loss": 0.1318,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.3,
481
+ "learning_rate": 3.851275319563113e-05,
482
+ "loss": 0.2129,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.3,
487
+ "learning_rate": 3.846578212210979e-05,
488
+ "loss": 0.3516,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.31,
493
+ "learning_rate": 3.841811035889908e-05,
494
+ "loss": 0.2734,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.31,
499
+ "learning_rate": 3.836973971491847e-05,
500
+ "loss": 0.1108,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.32,
505
+ "learning_rate": 3.832067202560668e-05,
506
+ "loss": 0.3594,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.32,
511
+ "learning_rate": 3.827090915285202e-05,
512
+ "loss": 0.2471,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.32,
517
+ "learning_rate": 3.822045298492177e-05,
518
+ "loss": 0.2539,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.33,
523
+ "learning_rate": 3.8169305436390474e-05,
524
+ "loss": 0.3125,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.33,
529
+ "learning_rate": 3.8117468448067345e-05,
530
+ "loss": 0.1826,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.33,
535
+ "learning_rate": 3.806494398692258e-05,
536
+ "loss": 0.2354,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.34,
541
+ "learning_rate": 3.801173404601275e-05,
542
+ "loss": 0.165,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.34,
547
+ "learning_rate": 3.7957840644405164e-05,
548
+ "loss": 0.2393,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.35,
553
+ "learning_rate": 3.790326582710125e-05,
554
+ "loss": 0.2793,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.35,
559
+ "learning_rate": 3.784801166495896e-05,
560
+ "loss": 0.6172,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.35,
565
+ "learning_rate": 3.77920802546142e-05,
566
+ "loss": 0.2754,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.36,
571
+ "learning_rate": 3.773547371840124e-05,
572
+ "loss": 0.3066,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.36,
577
+ "learning_rate": 3.7678194204272246e-05,
578
+ "loss": 0.3438,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.36,
583
+ "learning_rate": 3.7620243885715695e-05,
584
+ "loss": 0.3477,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.37,
589
+ "learning_rate": 3.756162496167396e-05,
590
+ "loss": 0.1621,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.37,
595
+ "learning_rate": 3.750233965645985e-05,
596
+ "loss": 0.4648,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.38,
601
+ "learning_rate": 3.744239021967222e-05,
602
+ "loss": 0.21,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.38,
607
+ "learning_rate": 3.738177892611057e-05,
608
+ "loss": 0.2715,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.38,
613
+ "learning_rate": 3.732050807568878e-05,
614
+ "loss": 0.4512,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.39,
619
+ "learning_rate": 3.72585799933478e-05,
620
+ "loss": 0.4746,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.39,
625
+ "learning_rate": 3.719599702896745e-05,
626
+ "loss": 0.1826,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.39,
631
+ "learning_rate": 3.713276155727726e-05,
632
+ "loss": 0.1436,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.4,
637
+ "learning_rate": 3.706887597776632e-05,
638
+ "loss": 0.1816,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.4,
643
+ "learning_rate": 3.700434271459229e-05,
644
+ "loss": 0.2891,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.41,
649
+ "learning_rate": 3.6939164216489345e-05,
650
+ "loss": 0.1514,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.41,
655
+ "learning_rate": 3.687334295667533e-05,
656
+ "loss": 0.1787,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.41,
661
+ "learning_rate": 3.680688143275786e-05,
662
+ "loss": 0.3516,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.42,
667
+ "learning_rate": 3.673978216663956e-05,
668
+ "loss": 0.3926,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.42,
673
+ "learning_rate": 3.667204770442239e-05,
674
+ "loss": 0.2793,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.43,
679
+ "learning_rate": 3.6603680616311013e-05,
680
+ "loss": 0.4473,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.43,
685
+ "learning_rate": 3.653468349651527e-05,
686
+ "loss": 0.4355,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.43,
691
+ "learning_rate": 3.646505896315175e-05,
692
+ "loss": 0.1445,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.44,
697
+ "learning_rate": 3.639480965814443e-05,
698
+ "loss": 0.2139,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.44,
703
+ "learning_rate": 3.632393824712444e-05,
704
+ "loss": 0.2031,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.44,
709
+ "learning_rate": 3.625244741932892e-05,
710
+ "loss": 0.208,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.45,
715
+ "learning_rate": 3.6180339887498953e-05,
716
+ "loss": 0.3242,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.45,
721
+ "learning_rate": 3.610761838777665e-05,
722
+ "loss": 0.3613,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.46,
727
+ "learning_rate": 3.6034285679601334e-05,
728
+ "loss": 0.1963,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.46,
733
+ "eval_loss": 0.44719600677490234,
734
+ "eval_runtime": 576.0743,
735
+ "eval_samples_per_second": 1.477,
736
+ "eval_steps_per_second": 0.739,
737
+ "step": 120
738
+ },
739
+ {
740
+ "epoch": 0.46,
741
+ "learning_rate": 3.5960344545604796e-05,
742
+ "loss": 0.1982,
743
+ "step": 121
744
+ },
745
+ {
746
+ "epoch": 0.46,
747
+ "learning_rate": 3.588579779150572e-05,
748
+ "loss": 0.3184,
749
+ "step": 122
750
+ },
751
+ {
752
+ "epoch": 0.47,
753
+ "learning_rate": 3.581064824600327e-05,
754
+ "loss": 0.3203,
755
+ "step": 123
756
+ },
757
+ {
758
+ "epoch": 0.47,
759
+ "learning_rate": 3.573489876066967e-05,
760
+ "loss": 0.4238,
761
+ "step": 124
762
+ },
763
+ {
764
+ "epoch": 0.47,
765
+ "learning_rate": 3.565855220984206e-05,
766
+ "loss": 0.2656,
767
+ "step": 125
768
+ },
769
+ {
770
+ "epoch": 0.48,
771
+ "learning_rate": 3.558161149051341e-05,
772
+ "loss": 0.4316,
773
+ "step": 126
774
+ },
775
+ {
776
+ "epoch": 0.48,
777
+ "learning_rate": 3.55040795222226e-05,
778
+ "loss": 0.3516,
779
+ "step": 127
780
+ },
781
+ {
782
+ "epoch": 0.49,
783
+ "learning_rate": 3.542595924694362e-05,
784
+ "loss": 0.3535,
785
+ "step": 128
786
+ },
787
+ {
788
+ "epoch": 0.49,
789
+ "learning_rate": 3.534725362897394e-05,
790
+ "loss": 0.1748,
791
+ "step": 129
792
+ },
793
+ {
794
+ "epoch": 0.49,
795
+ "learning_rate": 3.526796565482206e-05,
796
+ "loss": 0.1611,
797
+ "step": 130
798
+ },
799
+ {
800
+ "epoch": 0.5,
801
+ "learning_rate": 3.5188098333094145e-05,
802
+ "loss": 0.1885,
803
+ "step": 131
804
+ },
805
+ {
806
+ "epoch": 0.5,
807
+ "learning_rate": 3.5107654694379873e-05,
808
+ "loss": 0.1553,
809
+ "step": 132
810
+ },
811
+ {
812
+ "epoch": 0.51,
813
+ "learning_rate": 3.502663779113747e-05,
814
+ "loss": 0.2158,
815
+ "step": 133
816
+ },
817
+ {
818
+ "epoch": 0.51,
819
+ "learning_rate": 3.494505069757782e-05,
820
+ "loss": 0.4922,
821
+ "step": 134
822
+ },
823
+ {
824
+ "epoch": 0.51,
825
+ "learning_rate": 3.4862896509547886e-05,
826
+ "loss": 0.3711,
827
+ "step": 135
828
+ },
829
+ {
830
+ "epoch": 0.52,
831
+ "learning_rate": 3.478017834441319e-05,
832
+ "loss": 0.3398,
833
+ "step": 136
834
+ },
835
+ {
836
+ "epoch": 0.52,
837
+ "learning_rate": 3.4696899340939517e-05,
838
+ "loss": 0.2617,
839
+ "step": 137
840
+ },
841
+ {
842
+ "epoch": 0.52,
843
+ "learning_rate": 3.4613062659173865e-05,
844
+ "loss": 0.2637,
845
+ "step": 138
846
+ },
847
+ {
848
+ "epoch": 0.53,
849
+ "learning_rate": 3.452867148032449e-05,
850
+ "loss": 0.3066,
851
+ "step": 139
852
+ },
853
+ {
854
+ "epoch": 0.53,
855
+ "learning_rate": 3.4443729006640186e-05,
856
+ "loss": 0.3496,
857
+ "step": 140
858
+ },
859
+ {
860
+ "epoch": 0.54,
861
+ "learning_rate": 3.435823846128884e-05,
862
+ "loss": 0.2598,
863
+ "step": 141
864
+ },
865
+ {
866
+ "epoch": 0.54,
867
+ "learning_rate": 3.427220308823505e-05,
868
+ "loss": 0.1396,
869
+ "step": 142
870
+ },
871
+ {
872
+ "epoch": 0.54,
873
+ "learning_rate": 3.418562615211707e-05,
874
+ "loss": 0.2969,
875
+ "step": 143
876
+ },
877
+ {
878
+ "epoch": 0.55,
879
+ "learning_rate": 3.409851093812295e-05,
880
+ "loss": 0.1514,
881
+ "step": 144
882
+ },
883
+ {
884
+ "epoch": 0.55,
885
+ "learning_rate": 3.401086075186582e-05,
886
+ "loss": 0.3027,
887
+ "step": 145
888
+ },
889
+ {
890
+ "epoch": 0.55,
891
+ "learning_rate": 3.392267891925854e-05,
892
+ "loss": 0.1826,
893
+ "step": 146
894
+ },
895
+ {
896
+ "epoch": 0.56,
897
+ "learning_rate": 3.383396878638741e-05,
898
+ "loss": 0.3203,
899
+ "step": 147
900
+ },
901
+ {
902
+ "epoch": 0.56,
903
+ "learning_rate": 3.374473371938526e-05,
904
+ "loss": 0.3242,
905
+ "step": 148
906
+ },
907
+ {
908
+ "epoch": 0.57,
909
+ "learning_rate": 3.365497710430371e-05,
910
+ "loss": 0.3984,
911
+ "step": 149
912
+ },
913
+ {
914
+ "epoch": 0.57,
915
+ "learning_rate": 3.356470234698468e-05,
916
+ "loss": 0.3066,
917
+ "step": 150
918
+ },
919
+ {
920
+ "epoch": 0.57,
921
+ "learning_rate": 3.347391287293115e-05,
922
+ "loss": 0.2451,
923
+ "step": 151
924
+ },
925
+ {
926
+ "epoch": 0.58,
927
+ "learning_rate": 3.3382612127177166e-05,
928
+ "loss": 0.2275,
929
+ "step": 152
930
+ },
931
+ {
932
+ "epoch": 0.58,
933
+ "learning_rate": 3.329080357415716e-05,
934
+ "loss": 0.2949,
935
+ "step": 153
936
+ },
937
+ {
938
+ "epoch": 0.58,
939
+ "learning_rate": 3.319849069757446e-05,
940
+ "loss": 0.2129,
941
+ "step": 154
942
+ },
943
+ {
944
+ "epoch": 0.59,
945
+ "learning_rate": 3.310567700026908e-05,
946
+ "loss": 0.1436,
947
+ "step": 155
948
+ },
949
+ {
950
+ "epoch": 0.59,
951
+ "learning_rate": 3.301236600408484e-05,
952
+ "loss": 0.3359,
953
+ "step": 156
954
+ },
955
+ {
956
+ "epoch": 0.6,
957
+ "learning_rate": 3.291856124973575e-05,
958
+ "loss": 0.1689,
959
+ "step": 157
960
+ },
961
+ {
962
+ "epoch": 0.6,
963
+ "learning_rate": 3.282426629667157e-05,
964
+ "loss": 0.2402,
965
+ "step": 158
966
+ },
967
+ {
968
+ "epoch": 0.6,
969
+ "learning_rate": 3.272948472294283e-05,
970
+ "loss": 0.3652,
971
+ "step": 159
972
+ },
973
+ {
974
+ "epoch": 0.61,
975
+ "learning_rate": 3.263422012506502e-05,
976
+ "loss": 0.3242,
977
+ "step": 160
978
+ },
979
+ {
980
+ "epoch": 0.61,
981
+ "learning_rate": 3.253847611788214e-05,
982
+ "loss": 0.1035,
983
+ "step": 161
984
+ },
985
+ {
986
+ "epoch": 0.62,
987
+ "learning_rate": 3.2442256334429484e-05,
988
+ "loss": 0.1982,
989
+ "step": 162
990
+ },
991
+ {
992
+ "epoch": 0.62,
993
+ "learning_rate": 3.234556442579586e-05,
994
+ "loss": 0.3242,
995
+ "step": 163
996
+ },
997
+ {
998
+ "epoch": 0.62,
999
+ "learning_rate": 3.2248404060985e-05,
1000
+ "loss": 0.2148,
1001
+ "step": 164
1002
+ },
1003
+ {
1004
+ "epoch": 0.63,
1005
+ "learning_rate": 3.215077892677634e-05,
1006
+ "loss": 0.1357,
1007
+ "step": 165
1008
+ },
1009
+ {
1010
+ "epoch": 0.63,
1011
+ "learning_rate": 3.205269272758513e-05,
1012
+ "loss": 0.1631,
1013
+ "step": 166
1014
+ },
1015
+ {
1016
+ "epoch": 0.63,
1017
+ "learning_rate": 3.195414918532187e-05,
1018
+ "loss": 0.4336,
1019
+ "step": 167
1020
+ },
1021
+ {
1022
+ "epoch": 0.64,
1023
+ "learning_rate": 3.18551520392511e-05,
1024
+ "loss": 0.2773,
1025
+ "step": 168
1026
+ },
1027
+ {
1028
+ "epoch": 0.64,
1029
+ "learning_rate": 3.1755705045849465e-05,
1030
+ "loss": 0.1504,
1031
+ "step": 169
1032
+ },
1033
+ {
1034
+ "epoch": 0.65,
1035
+ "learning_rate": 3.165581197866322e-05,
1036
+ "loss": 0.1855,
1037
+ "step": 170
1038
+ },
1039
+ {
1040
+ "epoch": 0.65,
1041
+ "learning_rate": 3.155547662816503e-05,
1042
+ "loss": 0.2676,
1043
+ "step": 171
1044
+ },
1045
+ {
1046
+ "epoch": 0.65,
1047
+ "learning_rate": 3.145470280161011e-05,
1048
+ "loss": 0.1641,
1049
+ "step": 172
1050
+ },
1051
+ {
1052
+ "epoch": 0.66,
1053
+ "learning_rate": 3.1353494322891806e-05,
1054
+ "loss": 0.1226,
1055
+ "step": 173
1056
+ },
1057
+ {
1058
+ "epoch": 0.66,
1059
+ "learning_rate": 3.125185503239647e-05,
1060
+ "loss": 0.291,
1061
+ "step": 174
1062
+ },
1063
+ {
1064
+ "epoch": 0.66,
1065
+ "learning_rate": 3.114978878685771e-05,
1066
+ "loss": 0.2969,
1067
+ "step": 175
1068
+ },
1069
+ {
1070
+ "epoch": 0.67,
1071
+ "learning_rate": 3.104729945921012e-05,
1072
+ "loss": 0.3242,
1073
+ "step": 176
1074
+ },
1075
+ {
1076
+ "epoch": 0.67,
1077
+ "learning_rate": 3.094439093844223e-05,
1078
+ "loss": 0.3359,
1079
+ "step": 177
1080
+ },
1081
+ {
1082
+ "epoch": 0.68,
1083
+ "learning_rate": 3.084106712944899e-05,
1084
+ "loss": 0.291,
1085
+ "step": 178
1086
+ },
1087
+ {
1088
+ "epoch": 0.68,
1089
+ "learning_rate": 3.0737331952883605e-05,
1090
+ "loss": 0.3008,
1091
+ "step": 179
1092
+ },
1093
+ {
1094
+ "epoch": 0.68,
1095
+ "learning_rate": 3.0633189345008723e-05,
1096
+ "loss": 0.3027,
1097
+ "step": 180
1098
+ },
1099
+ {
1100
+ "epoch": 0.69,
1101
+ "learning_rate": 3.052864325754712e-05,
1102
+ "loss": 0.4414,
1103
+ "step": 181
1104
+ },
1105
+ {
1106
+ "epoch": 0.69,
1107
+ "learning_rate": 3.0423697657531704e-05,
1108
+ "loss": 0.2148,
1109
+ "step": 182
1110
+ },
1111
+ {
1112
+ "epoch": 0.69,
1113
+ "learning_rate": 3.0318356527155024e-05,
1114
+ "loss": 0.4238,
1115
+ "step": 183
1116
+ },
1117
+ {
1118
+ "epoch": 0.7,
1119
+ "learning_rate": 3.021262386361814e-05,
1120
+ "loss": 0.1992,
1121
+ "step": 184
1122
+ },
1123
+ {
1124
+ "epoch": 0.7,
1125
+ "learning_rate": 3.0106503678978963e-05,
1126
+ "loss": 0.2412,
1127
+ "step": 185
1128
+ },
1129
+ {
1130
+ "epoch": 0.71,
1131
+ "learning_rate": 3.0000000000000004e-05,
1132
+ "loss": 0.3047,
1133
+ "step": 186
1134
+ },
1135
+ {
1136
+ "epoch": 0.71,
1137
+ "learning_rate": 2.9893116867995583e-05,
1138
+ "loss": 0.3047,
1139
+ "step": 187
1140
+ },
1141
+ {
1142
+ "epoch": 0.71,
1143
+ "learning_rate": 2.9785858338678474e-05,
1144
+ "loss": 0.5508,
1145
+ "step": 188
1146
+ },
1147
+ {
1148
+ "epoch": 0.72,
1149
+ "learning_rate": 2.9678228482006033e-05,
1150
+ "loss": 0.3008,
1151
+ "step": 189
1152
+ },
1153
+ {
1154
+ "epoch": 0.72,
1155
+ "learning_rate": 2.9570231382025732e-05,
1156
+ "loss": 0.3047,
1157
+ "step": 190
1158
+ },
1159
+ {
1160
+ "epoch": 0.73,
1161
+ "learning_rate": 2.9461871136720205e-05,
1162
+ "loss": 0.167,
1163
+ "step": 191
1164
+ },
1165
+ {
1166
+ "epoch": 0.73,
1167
+ "learning_rate": 2.9353151857851738e-05,
1168
+ "loss": 0.2275,
1169
+ "step": 192
1170
+ },
1171
+ {
1172
+ "epoch": 0.73,
1173
+ "learning_rate": 2.924407767080627e-05,
1174
+ "loss": 0.2051,
1175
+ "step": 193
1176
+ },
1177
+ {
1178
+ "epoch": 0.74,
1179
+ "learning_rate": 2.9134652714436817e-05,
1180
+ "loss": 0.3887,
1181
+ "step": 194
1182
+ },
1183
+ {
1184
+ "epoch": 0.74,
1185
+ "learning_rate": 2.902488114090646e-05,
1186
+ "loss": 0.2969,
1187
+ "step": 195
1188
+ },
1189
+ {
1190
+ "epoch": 0.74,
1191
+ "learning_rate": 2.891476711553077e-05,
1192
+ "loss": 0.105,
1193
+ "step": 196
1194
+ },
1195
+ {
1196
+ "epoch": 0.75,
1197
+ "learning_rate": 2.880431481661975e-05,
1198
+ "loss": 0.2402,
1199
+ "step": 197
1200
+ },
1201
+ {
1202
+ "epoch": 0.75,
1203
+ "learning_rate": 2.8693528435319304e-05,
1204
+ "loss": 0.4238,
1205
+ "step": 198
1206
+ },
1207
+ {
1208
+ "epoch": 0.76,
1209
+ "learning_rate": 2.858241217545218e-05,
1210
+ "loss": 0.249,
1211
+ "step": 199
1212
+ },
1213
+ {
1214
+ "epoch": 0.76,
1215
+ "learning_rate": 2.8470970253358488e-05,
1216
+ "loss": 0.1338,
1217
+ "step": 200
1218
+ },
1219
+ {
1220
+ "epoch": 0.76,
1221
+ "learning_rate": 2.8359206897735673e-05,
1222
+ "loss": 0.2812,
1223
+ "step": 201
1224
+ },
1225
+ {
1226
+ "epoch": 0.77,
1227
+ "learning_rate": 2.8247126349478073e-05,
1228
+ "loss": 0.3691,
1229
+ "step": 202
1230
+ },
1231
+ {
1232
+ "epoch": 0.77,
1233
+ "learning_rate": 2.813473286151601e-05,
1234
+ "loss": 0.2031,
1235
+ "step": 203
1236
+ },
1237
+ {
1238
+ "epoch": 0.77,
1239
+ "learning_rate": 2.8022030698654377e-05,
1240
+ "loss": 0.3887,
1241
+ "step": 204
1242
+ },
1243
+ {
1244
+ "epoch": 0.78,
1245
+ "learning_rate": 2.790902413741085e-05,
1246
+ "loss": 0.3066,
1247
+ "step": 205
1248
+ },
1249
+ {
1250
+ "epoch": 0.78,
1251
+ "learning_rate": 2.7795717465853588e-05,
1252
+ "loss": 0.3633,
1253
+ "step": 206
1254
+ },
1255
+ {
1256
+ "epoch": 0.79,
1257
+ "learning_rate": 2.7682114983438522e-05,
1258
+ "loss": 0.1641,
1259
+ "step": 207
1260
+ },
1261
+ {
1262
+ "epoch": 0.79,
1263
+ "learning_rate": 2.756822100084621e-05,
1264
+ "loss": 0.2207,
1265
+ "step": 208
1266
+ },
1267
+ {
1268
+ "epoch": 0.79,
1269
+ "learning_rate": 2.745403983981828e-05,
1270
+ "loss": 0.1768,
1271
+ "step": 209
1272
+ },
1273
+ {
1274
+ "epoch": 0.8,
1275
+ "learning_rate": 2.7339575832993444e-05,
1276
+ "loss": 0.1494,
1277
+ "step": 210
1278
+ },
1279
+ {
1280
+ "epoch": 0.8,
1281
+ "learning_rate": 2.7224833323743064e-05,
1282
+ "loss": 0.1475,
1283
+ "step": 211
1284
+ },
1285
+ {
1286
+ "epoch": 0.81,
1287
+ "learning_rate": 2.710981666600636e-05,
1288
+ "loss": 0.1904,
1289
+ "step": 212
1290
+ },
1291
+ {
1292
+ "epoch": 0.81,
1293
+ "learning_rate": 2.6994530224125225e-05,
1294
+ "loss": 0.2637,
1295
+ "step": 213
1296
+ },
1297
+ {
1298
+ "epoch": 0.81,
1299
+ "learning_rate": 2.6878978372678567e-05,
1300
+ "loss": 0.2334,
1301
+ "step": 214
1302
+ },
1303
+ {
1304
+ "epoch": 0.82,
1305
+ "learning_rate": 2.6763165496316346e-05,
1306
+ "loss": 0.3945,
1307
+ "step": 215
1308
+ },
1309
+ {
1310
+ "epoch": 0.82,
1311
+ "learning_rate": 2.6647095989593194e-05,
1312
+ "loss": 0.1855,
1313
+ "step": 216
1314
+ },
1315
+ {
1316
+ "epoch": 0.82,
1317
+ "learning_rate": 2.6530774256801666e-05,
1318
+ "loss": 0.2734,
1319
+ "step": 217
1320
+ },
1321
+ {
1322
+ "epoch": 0.83,
1323
+ "learning_rate": 2.6414204711805106e-05,
1324
+ "loss": 0.2852,
1325
+ "step": 218
1326
+ },
1327
+ {
1328
+ "epoch": 0.83,
1329
+ "learning_rate": 2.629739177787016e-05,
1330
+ "loss": 0.2676,
1331
+ "step": 219
1332
+ },
1333
+ {
1334
+ "epoch": 0.84,
1335
+ "learning_rate": 2.618033988749895e-05,
1336
+ "loss": 0.2393,
1337
+ "step": 220
1338
+ },
1339
+ {
1340
+ "epoch": 0.84,
1341
+ "learning_rate": 2.606305348226087e-05,
1342
+ "loss": 0.208,
1343
+ "step": 221
1344
+ },
1345
+ {
1346
+ "epoch": 0.84,
1347
+ "learning_rate": 2.5945537012624056e-05,
1348
+ "loss": 0.2598,
1349
+ "step": 222
1350
+ },
1351
+ {
1352
+ "epoch": 0.85,
1353
+ "learning_rate": 2.5827794937786497e-05,
1354
+ "loss": 0.2832,
1355
+ "step": 223
1356
+ },
1357
+ {
1358
+ "epoch": 0.85,
1359
+ "learning_rate": 2.5709831725506847e-05,
1360
+ "loss": 0.4355,
1361
+ "step": 224
1362
+ },
1363
+ {
1364
+ "epoch": 0.85,
1365
+ "learning_rate": 2.559165185193488e-05,
1366
+ "loss": 0.1855,
1367
+ "step": 225
1368
+ },
1369
+ {
1370
+ "epoch": 0.86,
1371
+ "learning_rate": 2.5473259801441663e-05,
1372
+ "loss": 0.2402,
1373
+ "step": 226
1374
+ },
1375
+ {
1376
+ "epoch": 0.86,
1377
+ "learning_rate": 2.5354660066449362e-05,
1378
+ "loss": 0.2295,
1379
+ "step": 227
1380
+ },
1381
+ {
1382
+ "epoch": 0.87,
1383
+ "learning_rate": 2.523585714726081e-05,
1384
+ "loss": 0.2168,
1385
+ "step": 228
1386
+ },
1387
+ {
1388
+ "epoch": 0.87,
1389
+ "learning_rate": 2.5116855551888715e-05,
1390
+ "loss": 0.2041,
1391
+ "step": 229
1392
+ },
1393
+ {
1394
+ "epoch": 0.87,
1395
+ "learning_rate": 2.4997659795884616e-05,
1396
+ "loss": 0.2266,
1397
+ "step": 230
1398
+ },
1399
+ {
1400
+ "epoch": 0.88,
1401
+ "learning_rate": 2.4878274402167544e-05,
1402
+ "loss": 0.1875,
1403
+ "step": 231
1404
+ },
1405
+ {
1406
+ "epoch": 0.88,
1407
+ "learning_rate": 2.4758703900852376e-05,
1408
+ "loss": 0.1445,
1409
+ "step": 232
1410
+ },
1411
+ {
1412
+ "epoch": 0.88,
1413
+ "learning_rate": 2.4638952829077964e-05,
1414
+ "loss": 0.2373,
1415
+ "step": 233
1416
+ },
1417
+ {
1418
+ "epoch": 0.89,
1419
+ "learning_rate": 2.4519025730834957e-05,
1420
+ "loss": 0.1865,
1421
+ "step": 234
1422
+ },
1423
+ {
1424
+ "epoch": 0.89,
1425
+ "learning_rate": 2.4398927156793376e-05,
1426
+ "loss": 0.2441,
1427
+ "step": 235
1428
+ },
1429
+ {
1430
+ "epoch": 0.9,
1431
+ "learning_rate": 2.427866166412995e-05,
1432
+ "loss": 0.1338,
1433
+ "step": 236
1434
+ },
1435
+ {
1436
+ "epoch": 0.9,
1437
+ "learning_rate": 2.4158233816355185e-05,
1438
+ "loss": 0.291,
1439
+ "step": 237
1440
+ },
1441
+ {
1442
+ "epoch": 0.9,
1443
+ "learning_rate": 2.4037648183140205e-05,
1444
+ "loss": 0.2021,
1445
+ "step": 238
1446
+ },
1447
+ {
1448
+ "epoch": 0.91,
1449
+ "learning_rate": 2.3916909340143342e-05,
1450
+ "loss": 0.2178,
1451
+ "step": 239
1452
+ },
1453
+ {
1454
+ "epoch": 0.91,
1455
+ "learning_rate": 2.3796021868836522e-05,
1456
+ "loss": 0.0654,
1457
+ "step": 240
1458
+ },
1459
+ {
1460
+ "epoch": 0.91,
1461
+ "eval_loss": 0.4184834361076355,
1462
+ "eval_runtime": 574.9023,
1463
+ "eval_samples_per_second": 1.48,
1464
+ "eval_steps_per_second": 0.741,
1465
+ "step": 240
1466
+ }
1467
+ ],
1468
+ "logging_steps": 1,
1469
+ "max_steps": 526,
1470
+ "num_input_tokens_seen": 0,
1471
+ "num_train_epochs": 2,
1472
+ "save_steps": 120,
1473
+ "total_flos": 1.4990970412793856e+16,
1474
+ "train_batch_size": 2,
1475
+ "trial_name": null,
1476
+ "trial_params": null
1477
+ }
checkpoints/co_trPMC_llava-v1.6-mistral/checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9913b0fa2827270ea372341b96ee23bbe0d559362a657e71620bd85903e8c36
3
+ size 4792
coslakevqa/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /workspace/PMC_llava-v1.6-mistral
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
coslakevqa/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/PMC_llava-v1.6-mistral",
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": 64,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": [
21
+ "mm_projector"
22
+ ],
23
+ "peft_type": "LORA",
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "down_proj",
30
+ "gate_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": null,
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
coslakevqa/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f352b1bc2b1578187e48cc8654a2522aaaade50687185b90d6bde160173dce
3
+ size 202470344
coslakevqa/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9913b0fa2827270ea372341b96ee23bbe0d559362a657e71620bd85903e8c36
3
+ size 4792