Theon1130 commited on
Commit
97eda29
1 Parent(s): 3bb5add
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/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
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/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": 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
+ "down_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "gate_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": null,
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4424d204cf7b1da05f638456c73e234c45b0c8baf417af47f6040b7fb8de54
3
+ size 202470344
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ff2184783dcec0146faa6f6fbe107d98cc72bd9ae174cb838f1b04e50230cc
3
+ size 386238366
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0660d743e5f67f346fee763a4640e358c76c961a7f17a7ac6ca6a97a1a72e54
3
+ size 14244
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c743ff517303f4ef02a3d7a67dd35a655917395fd4980e9d9da96ef2409834
3
+ size 1000
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/trainer_state.json ADDED
@@ -0,0 +1,473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.12878087162971497,
3
+ "best_model_checkpoint": "/workspace/checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60",
4
+ "epoch": 0.7804878048780488,
5
+ "eval_steps": 15,
6
+ "global_step": 60,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013008130081300813,
13
+ "grad_norm": 1.875,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.0669,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.026016260162601626,
20
+ "grad_norm": 2.03125,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.0549,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03902439024390244,
27
+ "grad_norm": 1.9609375,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.0732,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.05203252032520325,
34
+ "grad_norm": 1.953125,
35
+ "learning_rate": 9.995370575511151e-06,
36
+ "loss": 0.0596,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.06504065040650407,
41
+ "grad_norm": 2.359375,
42
+ "learning_rate": 9.98149087467304e-06,
43
+ "loss": 0.0898,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.07804878048780488,
48
+ "grad_norm": 2.734375,
49
+ "learning_rate": 9.95838659949645e-06,
50
+ "loss": 0.1064,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0910569105691057,
55
+ "grad_norm": 2.484375,
56
+ "learning_rate": 9.926100533780304e-06,
57
+ "loss": 0.0742,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.1040650406504065,
62
+ "grad_norm": 2.421875,
63
+ "learning_rate": 9.88469246388591e-06,
64
+ "loss": 0.0698,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.11707317073170732,
69
+ "grad_norm": 2.09375,
70
+ "learning_rate": 9.834239068026388e-06,
71
+ "loss": 0.0625,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.13008130081300814,
76
+ "grad_norm": 1.78125,
77
+ "learning_rate": 9.774833774276278e-06,
78
+ "loss": 0.0369,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.14308943089430895,
83
+ "grad_norm": 2.859375,
84
+ "learning_rate": 9.706586587564236e-06,
85
+ "loss": 0.127,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.15609756097560976,
90
+ "grad_norm": 3.21875,
91
+ "learning_rate": 9.62962388596925e-06,
92
+ "loss": 0.1025,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.16910569105691056,
97
+ "grad_norm": 3.59375,
98
+ "learning_rate": 9.544088186697515e-06,
99
+ "loss": 0.0713,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.1821138211382114,
104
+ "grad_norm": 3.171875,
105
+ "learning_rate": 9.450137882173385e-06,
106
+ "loss": 0.1118,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1951219512195122,
111
+ "grad_norm": 2.171875,
112
+ "learning_rate": 9.347946946733055e-06,
113
+ "loss": 0.0659,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1951219512195122,
118
+ "eval_loss": 0.14803729951381683,
119
+ "eval_runtime": 1994.1875,
120
+ "eval_samples_per_second": 0.528,
121
+ "eval_steps_per_second": 0.132,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.208130081300813,
126
+ "grad_norm": 3.5625,
127
+ "learning_rate": 9.237704614464157e-06,
128
+ "loss": 0.1201,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.22113821138211381,
133
+ "grad_norm": 1.84375,
134
+ "learning_rate": 9.119615028787771e-06,
135
+ "loss": 0.0659,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.23414634146341465,
140
+ "grad_norm": 2.65625,
141
+ "learning_rate": 8.993896864431825e-06,
142
+ "loss": 0.1035,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.24715447154471545,
147
+ "grad_norm": 2.046875,
148
+ "learning_rate": 8.860782922495821e-06,
149
+ "loss": 0.0747,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.2601626016260163,
154
+ "grad_norm": 1.921875,
155
+ "learning_rate": 8.720519699356804e-06,
156
+ "loss": 0.0869,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.2731707317073171,
161
+ "grad_norm": 1.765625,
162
+ "learning_rate": 8.573366930214807e-06,
163
+ "loss": 0.0405,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.2861788617886179,
168
+ "grad_norm": 1.7578125,
169
+ "learning_rate": 8.419597108123054e-06,
170
+ "loss": 0.0549,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.2991869918699187,
175
+ "grad_norm": 2.609375,
176
+ "learning_rate": 8.259494979393563e-06,
177
+ "loss": 0.0859,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.3121951219512195,
182
+ "grad_norm": 3.359375,
183
+ "learning_rate": 8.093357016312518e-06,
184
+ "loss": 0.103,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.3252032520325203,
189
+ "grad_norm": 2.4375,
190
+ "learning_rate": 7.921490868141843e-06,
191
+ "loss": 0.0928,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.3382113821138211,
196
+ "grad_norm": 2.0,
197
+ "learning_rate": 7.744214791423597e-06,
198
+ "loss": 0.0603,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.35121951219512193,
203
+ "grad_norm": 1.734375,
204
+ "learning_rate": 7.56185706064212e-06,
205
+ "loss": 0.0559,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.3642276422764228,
210
+ "grad_norm": 2.9375,
211
+ "learning_rate": 7.374755360335253e-06,
212
+ "loss": 0.0781,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.3772357723577236,
217
+ "grad_norm": 1.8671875,
218
+ "learning_rate": 7.183256159780321e-06,
219
+ "loss": 0.0723,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.3902439024390244,
224
+ "grad_norm": 1.4453125,
225
+ "learning_rate": 6.987714071412781e-06,
226
+ "loss": 0.0364,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.3902439024390244,
231
+ "eval_loss": 0.13480448722839355,
232
+ "eval_runtime": 1949.6926,
233
+ "eval_samples_per_second": 0.54,
234
+ "eval_steps_per_second": 0.135,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.4032520325203252,
239
+ "grad_norm": 2.046875,
240
+ "learning_rate": 6.788491194165629e-06,
241
+ "loss": 0.0552,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.416260162601626,
246
+ "grad_norm": 1.2109375,
247
+ "learning_rate": 6.585956442945531e-06,
248
+ "loss": 0.0432,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.4292682926829268,
253
+ "grad_norm": 3.640625,
254
+ "learning_rate": 6.380484865487346e-06,
255
+ "loss": 0.1191,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.44227642276422763,
260
+ "grad_norm": 2.21875,
261
+ "learning_rate": 6.1724569478520495e-06,
262
+ "loss": 0.0903,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.45528455284552843,
267
+ "grad_norm": 1.328125,
268
+ "learning_rate": 5.96225790985415e-06,
269
+ "loss": 0.083,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.4682926829268293,
274
+ "grad_norm": 2.984375,
275
+ "learning_rate": 5.7502769917232635e-06,
276
+ "loss": 0.0825,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.4813008130081301,
281
+ "grad_norm": 2.109375,
282
+ "learning_rate": 5.536906733320816e-06,
283
+ "loss": 0.085,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.4943089430894309,
288
+ "grad_norm": 2.53125,
289
+ "learning_rate": 5.322542247246583e-06,
290
+ "loss": 0.1406,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.5073170731707317,
295
+ "grad_norm": 2.3125,
296
+ "learning_rate": 5.107580487181112e-06,
297
+ "loss": 0.1099,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.5203252032520326,
302
+ "grad_norm": 1.7421875,
303
+ "learning_rate": 4.89241951281889e-06,
304
+ "loss": 0.0654,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.5333333333333333,
309
+ "grad_norm": 2.171875,
310
+ "learning_rate": 4.6774577527534195e-06,
311
+ "loss": 0.0845,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.5463414634146342,
316
+ "grad_norm": 2.28125,
317
+ "learning_rate": 4.463093266679185e-06,
318
+ "loss": 0.0786,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.5593495934959349,
323
+ "grad_norm": 3.078125,
324
+ "learning_rate": 4.249723008276737e-06,
325
+ "loss": 0.0874,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.5723577235772358,
330
+ "grad_norm": 2.078125,
331
+ "learning_rate": 4.037742090145851e-06,
332
+ "loss": 0.0693,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.5853658536585366,
337
+ "grad_norm": 2.09375,
338
+ "learning_rate": 3.827543052147952e-06,
339
+ "loss": 0.0645,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.5853658536585366,
344
+ "eval_loss": 0.13093312084674835,
345
+ "eval_runtime": 1950.5511,
346
+ "eval_samples_per_second": 0.54,
347
+ "eval_steps_per_second": 0.135,
348
+ "step": 45
349
+ },
350
+ {
351
+ "epoch": 0.5983739837398374,
352
+ "grad_norm": 1.8203125,
353
+ "learning_rate": 3.6195151345126556e-06,
354
+ "loss": 0.0603,
355
+ "step": 46
356
+ },
357
+ {
358
+ "epoch": 0.6113821138211382,
359
+ "grad_norm": 2.140625,
360
+ "learning_rate": 3.4140435570544708e-06,
361
+ "loss": 0.0703,
362
+ "step": 47
363
+ },
364
+ {
365
+ "epoch": 0.624390243902439,
366
+ "grad_norm": 2.421875,
367
+ "learning_rate": 3.2115088058343725e-06,
368
+ "loss": 0.0732,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 0.6373983739837399,
373
+ "grad_norm": 2.25,
374
+ "learning_rate": 3.0122859285872214e-06,
375
+ "loss": 0.0649,
376
+ "step": 49
377
+ },
378
+ {
379
+ "epoch": 0.6504065040650406,
380
+ "grad_norm": 3.671875,
381
+ "learning_rate": 2.816743840219681e-06,
382
+ "loss": 0.1572,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.6634146341463415,
387
+ "grad_norm": 3.1875,
388
+ "learning_rate": 2.6252446396647503e-06,
389
+ "loss": 0.0898,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.6764227642276422,
394
+ "grad_norm": 1.765625,
395
+ "learning_rate": 2.438142939357882e-06,
396
+ "loss": 0.0518,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.6894308943089431,
401
+ "grad_norm": 2.203125,
402
+ "learning_rate": 2.2557852085764053e-06,
403
+ "loss": 0.0845,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.7024390243902439,
408
+ "grad_norm": 2.578125,
409
+ "learning_rate": 2.0785091318581577e-06,
410
+ "loss": 0.0728,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.7154471544715447,
415
+ "grad_norm": 2.25,
416
+ "learning_rate": 1.9066429836874844e-06,
417
+ "loss": 0.0713,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.7284552845528456,
422
+ "grad_norm": 1.6640625,
423
+ "learning_rate": 1.7405050206064372e-06,
424
+ "loss": 0.0625,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.7414634146341463,
429
+ "grad_norm": 2.90625,
430
+ "learning_rate": 1.5804028918769488e-06,
431
+ "loss": 0.1079,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.7544715447154472,
436
+ "grad_norm": 1.9609375,
437
+ "learning_rate": 1.4266330697851955e-06,
438
+ "loss": 0.0996,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.767479674796748,
443
+ "grad_norm": 2.375,
444
+ "learning_rate": 1.2794803006431984e-06,
445
+ "loss": 0.0684,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.7804878048780488,
450
+ "grad_norm": 1.4140625,
451
+ "learning_rate": 1.1392170775041788e-06,
452
+ "loss": 0.0371,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.7804878048780488,
457
+ "eval_loss": 0.12878087162971497,
458
+ "eval_runtime": 1967.3809,
459
+ "eval_samples_per_second": 0.535,
460
+ "eval_steps_per_second": 0.134,
461
+ "step": 60
462
+ }
463
+ ],
464
+ "logging_steps": 1,
465
+ "max_steps": 76,
466
+ "num_input_tokens_seen": 0,
467
+ "num_train_epochs": 1,
468
+ "save_steps": 30,
469
+ "total_flos": 7891564556894208.0,
470
+ "train_batch_size": 4,
471
+ "trial_name": null,
472
+ "trial_params": null
473
+ }
checkpoints_7fu/futher7_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e84838e2fb31aaa52c48657377221e5fbac79df833ea8adc0cdf4d6c7f4fc01
3
+ size 5112
futherloraslake/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
futherloraslake/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": 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
+ "down_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "gate_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": null,
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
futherloraslake/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4424d204cf7b1da05f638456c73e234c45b0c8baf417af47f6040b7fb8de54
3
+ size 202470344
futherloraslake/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e84838e2fb31aaa52c48657377221e5fbac79df833ea8adc0cdf4d6c7f4fc01
3
+ size 5112