yigagilbert commited on
Commit
080aab9
·
verified ·
1 Parent(s): f643557

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+
2
+
metadata.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_id": "yigagilbert/image_quality_dataset",
3
+ "value_column_name": "quality_score",
4
+ "test_split": 0.2,
5
+ "num_train_epochs": 3,
6
+ "learning_rate": 5e-05,
7
+ "max_value": 54.02313232
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0980b36be84a6a761f5340335825c0fc35ff7bb4cb8f5d638a2927d297611d31
3
+ size 345583444
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd82b8a52e390d8368a49f37a825748fe88d0d541255b4eecc615e289144f4a
3
+ size 686562746
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92cbfc27f2e1534a4dcb29a4e3cadfdf1c177cd4bb10da410a2f400ca18a097
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 201,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14925373134328357,
13
+ "grad_norm": 19.874767303466797,
14
+ "learning_rate": 4.7512437810945275e-05,
15
+ "loss": 0.4626,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.29850746268656714,
20
+ "grad_norm": 2.962965488433838,
21
+ "learning_rate": 4.502487562189055e-05,
22
+ "loss": 0.0398,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.44776119402985076,
27
+ "grad_norm": 7.356692790985107,
28
+ "learning_rate": 4.253731343283582e-05,
29
+ "loss": 0.0239,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.5970149253731343,
34
+ "grad_norm": 6.064937591552734,
35
+ "learning_rate": 4.00497512437811e-05,
36
+ "loss": 0.0357,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.746268656716418,
41
+ "grad_norm": 9.119353294372559,
42
+ "learning_rate": 3.756218905472637e-05,
43
+ "loss": 0.0316,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.8955223880597015,
48
+ "grad_norm": 7.955826282501221,
49
+ "learning_rate": 3.5074626865671645e-05,
50
+ "loss": 0.0496,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_loss": 0.05542003735899925,
56
+ "eval_mse": 0.05542004108428955,
57
+ "eval_runtime": 13.3429,
58
+ "eval_samples_per_second": 10.043,
59
+ "eval_steps_per_second": 1.274,
60
+ "step": 67
61
+ },
62
+ {
63
+ "epoch": 1.044776119402985,
64
+ "grad_norm": 0.8896350860595703,
65
+ "learning_rate": 3.258706467661692e-05,
66
+ "loss": 0.0319,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.1940298507462686,
71
+ "grad_norm": 6.134321212768555,
72
+ "learning_rate": 3.009950248756219e-05,
73
+ "loss": 0.0244,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.3432835820895521,
78
+ "grad_norm": 2.1838057041168213,
79
+ "learning_rate": 2.7611940298507467e-05,
80
+ "loss": 0.0174,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.4925373134328357,
85
+ "grad_norm": 4.814957618713379,
86
+ "learning_rate": 2.512437810945274e-05,
87
+ "loss": 0.0127,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.6417910447761193,
92
+ "grad_norm": 0.4210551381111145,
93
+ "learning_rate": 2.2636815920398012e-05,
94
+ "loss": 0.0318,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 1.7910447761194028,
99
+ "grad_norm": 1.4994094371795654,
100
+ "learning_rate": 2.0149253731343285e-05,
101
+ "loss": 0.0068,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 1.9402985074626866,
106
+ "grad_norm": 5.756369113922119,
107
+ "learning_rate": 1.7661691542288558e-05,
108
+ "loss": 0.0228,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 2.0,
113
+ "eval_loss": 0.015796519815921783,
114
+ "eval_mse": 0.015796517953276634,
115
+ "eval_runtime": 13.4371,
116
+ "eval_samples_per_second": 9.972,
117
+ "eval_steps_per_second": 1.265,
118
+ "step": 134
119
+ },
120
+ {
121
+ "epoch": 2.08955223880597,
122
+ "grad_norm": 3.0607242584228516,
123
+ "learning_rate": 1.5174129353233832e-05,
124
+ "loss": 0.01,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 2.2388059701492535,
129
+ "grad_norm": 1.876637578010559,
130
+ "learning_rate": 1.2686567164179105e-05,
131
+ "loss": 0.0061,
132
+ "step": 150
133
+ },
134
+ {
135
+ "epoch": 2.388059701492537,
136
+ "grad_norm": 0.6131510734558105,
137
+ "learning_rate": 1.0199004975124378e-05,
138
+ "loss": 0.0124,
139
+ "step": 160
140
+ },
141
+ {
142
+ "epoch": 2.5373134328358207,
143
+ "grad_norm": 2.405625104904175,
144
+ "learning_rate": 7.711442786069652e-06,
145
+ "loss": 0.007,
146
+ "step": 170
147
+ },
148
+ {
149
+ "epoch": 2.6865671641791042,
150
+ "grad_norm": 2.386357069015503,
151
+ "learning_rate": 5.2238805970149255e-06,
152
+ "loss": 0.0065,
153
+ "step": 180
154
+ },
155
+ {
156
+ "epoch": 2.835820895522388,
157
+ "grad_norm": 2.0660793781280518,
158
+ "learning_rate": 2.736318407960199e-06,
159
+ "loss": 0.0047,
160
+ "step": 190
161
+ },
162
+ {
163
+ "epoch": 2.9850746268656714,
164
+ "grad_norm": 2.1462905406951904,
165
+ "learning_rate": 2.4875621890547267e-07,
166
+ "loss": 0.0069,
167
+ "step": 200
168
+ }
169
+ ],
170
+ "logging_steps": 10,
171
+ "max_steps": 201,
172
+ "num_input_tokens_seen": 0,
173
+ "num_train_epochs": 3,
174
+ "save_steps": 10,
175
+ "stateful_callbacks": {
176
+ "TrainerControl": {
177
+ "args": {
178
+ "should_epoch_stop": false,
179
+ "should_evaluate": false,
180
+ "should_log": false,
181
+ "should_save": true,
182
+ "should_training_stop": true
183
+ },
184
+ "attributes": {}
185
+ }
186
+ },
187
+ "total_flos": 0.0,
188
+ "train_batch_size": 8,
189
+ "trial_name": null,
190
+ "trial_params": null
191
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5e9224cb42079c1ce18eae2108460d6b14fda29fd43c0720ae0e2ce3d1284e
3
+ size 5176