kaanyvvz commited on
Commit
e90907d
1 Parent(s): 8358f9c

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.997393570807994,
3
+ "eval_accuracy": 0.9552567237163814,
4
+ "eval_loss": 0.13006699085235596,
5
+ "eval_runtime": 57.2962,
6
+ "eval_samples_per_second": 71.383,
7
+ "eval_steps_per_second": 2.234,
8
+ "total_flos": 3.760030331457189e+19,
9
+ "train_loss": 0.4662683892333134,
10
+ "train_runtime": 8157.4316,
11
+ "train_samples_per_second": 45.124,
12
+ "train_steps_per_second": 0.352
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.997393570807994,
3
+ "eval_accuracy": 0.9552567237163814,
4
+ "eval_loss": 0.13006699085235596,
5
+ "eval_runtime": 57.2962,
6
+ "eval_samples_per_second": 71.383,
7
+ "eval_steps_per_second": 2.234
8
+ }
runs/Dec16_19-05-16_593ea901dc76/events.out.tfevents.1734384171.593ea901dc76.241.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d68c6353e529303856c23dd7f5a2e94e1109fb461c209b6aedb8dbe8f36056
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.997393570807994,
3
+ "total_flos": 3.760030331457189e+19,
4
+ "train_loss": 0.4662683892333134,
5
+ "train_runtime": 8157.4316,
6
+ "train_samples_per_second": 45.124,
7
+ "train_steps_per_second": 0.352
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9552567237163814,
3
+ "best_model_checkpoint": "ky-finetuned-skindiseasefinal/checkpoint-2870",
4
+ "epoch": 9.997393570807994,
5
+ "eval_steps": 500,
6
+ "global_step": 2870,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9973935708079931,
13
+ "grad_norm": 157.15570068359375,
14
+ "learning_rate": 5e-05,
15
+ "loss": 1.4949,
16
+ "step": 287
17
+ },
18
+ {
19
+ "epoch": 0.9973935708079931,
20
+ "eval_accuracy": 0.7770171149144254,
21
+ "eval_loss": 0.6911987662315369,
22
+ "eval_runtime": 57.7326,
23
+ "eval_samples_per_second": 70.844,
24
+ "eval_steps_per_second": 2.217,
25
+ "step": 287
26
+ },
27
+ {
28
+ "epoch": 1.997393570807993,
29
+ "grad_norm": 102.32886505126953,
30
+ "learning_rate": 4.4444444444444447e-05,
31
+ "loss": 0.7268,
32
+ "step": 574
33
+ },
34
+ {
35
+ "epoch": 1.997393570807993,
36
+ "eval_accuracy": 0.8775061124694377,
37
+ "eval_loss": 0.3927457332611084,
38
+ "eval_runtime": 57.5408,
39
+ "eval_samples_per_second": 71.08,
40
+ "eval_steps_per_second": 2.225,
41
+ "step": 574
42
+ },
43
+ {
44
+ "epoch": 2.997393570807993,
45
+ "grad_norm": 66.3480224609375,
46
+ "learning_rate": 3.888888888888889e-05,
47
+ "loss": 0.5179,
48
+ "step": 861
49
+ },
50
+ {
51
+ "epoch": 2.997393570807993,
52
+ "eval_accuracy": 0.8982885085574572,
53
+ "eval_loss": 0.3185364305973053,
54
+ "eval_runtime": 57.3788,
55
+ "eval_samples_per_second": 71.281,
56
+ "eval_steps_per_second": 2.231,
57
+ "step": 861
58
+ },
59
+ {
60
+ "epoch": 3.997393570807993,
61
+ "grad_norm": 62.946006774902344,
62
+ "learning_rate": 3.3333333333333335e-05,
63
+ "loss": 0.4193,
64
+ "step": 1148
65
+ },
66
+ {
67
+ "epoch": 3.997393570807993,
68
+ "eval_accuracy": 0.9190709046454768,
69
+ "eval_loss": 0.24387270212173462,
70
+ "eval_runtime": 57.2167,
71
+ "eval_samples_per_second": 71.483,
72
+ "eval_steps_per_second": 2.237,
73
+ "step": 1148
74
+ },
75
+ {
76
+ "epoch": 4.9973935708079935,
77
+ "grad_norm": 67.98648834228516,
78
+ "learning_rate": 2.777777777777778e-05,
79
+ "loss": 0.3576,
80
+ "step": 1435
81
+ },
82
+ {
83
+ "epoch": 4.9973935708079935,
84
+ "eval_accuracy": 0.9300733496332518,
85
+ "eval_loss": 0.210697740316391,
86
+ "eval_runtime": 57.3323,
87
+ "eval_samples_per_second": 71.339,
88
+ "eval_steps_per_second": 2.233,
89
+ "step": 1435
90
+ },
91
+ {
92
+ "epoch": 5.9973935708079935,
93
+ "grad_norm": 47.05820083618164,
94
+ "learning_rate": 2.2222222222222223e-05,
95
+ "loss": 0.3015,
96
+ "step": 1722
97
+ },
98
+ {
99
+ "epoch": 5.9973935708079935,
100
+ "eval_accuracy": 0.9386308068459658,
101
+ "eval_loss": 0.1821407824754715,
102
+ "eval_runtime": 57.2098,
103
+ "eval_samples_per_second": 71.491,
104
+ "eval_steps_per_second": 2.237,
105
+ "step": 1722
106
+ },
107
+ {
108
+ "epoch": 6.9973935708079935,
109
+ "grad_norm": 60.36362838745117,
110
+ "learning_rate": 1.6666666666666667e-05,
111
+ "loss": 0.2648,
112
+ "step": 2009
113
+ },
114
+ {
115
+ "epoch": 6.9973935708079935,
116
+ "eval_accuracy": 0.9410757946210269,
117
+ "eval_loss": 0.16846108436584473,
118
+ "eval_runtime": 57.4289,
119
+ "eval_samples_per_second": 71.218,
120
+ "eval_steps_per_second": 2.229,
121
+ "step": 2009
122
+ },
123
+ {
124
+ "epoch": 7.9973935708079935,
125
+ "grad_norm": 49.73932647705078,
126
+ "learning_rate": 1.1111111111111112e-05,
127
+ "loss": 0.2228,
128
+ "step": 2296
129
+ },
130
+ {
131
+ "epoch": 7.9973935708079935,
132
+ "eval_accuracy": 0.9486552567237164,
133
+ "eval_loss": 0.1497160643339157,
134
+ "eval_runtime": 57.6175,
135
+ "eval_samples_per_second": 70.985,
136
+ "eval_steps_per_second": 2.222,
137
+ "step": 2296
138
+ },
139
+ {
140
+ "epoch": 8.997393570807994,
141
+ "grad_norm": 32.87363052368164,
142
+ "learning_rate": 5.555555555555556e-06,
143
+ "loss": 0.1946,
144
+ "step": 2583
145
+ },
146
+ {
147
+ "epoch": 8.997393570807994,
148
+ "eval_accuracy": 0.9493887530562347,
149
+ "eval_loss": 0.140727236866951,
150
+ "eval_runtime": 57.5534,
151
+ "eval_samples_per_second": 71.064,
152
+ "eval_steps_per_second": 2.224,
153
+ "step": 2583
154
+ },
155
+ {
156
+ "epoch": 9.997393570807994,
157
+ "grad_norm": 49.652774810791016,
158
+ "learning_rate": 0.0,
159
+ "loss": 0.1625,
160
+ "step": 2870
161
+ },
162
+ {
163
+ "epoch": 9.997393570807994,
164
+ "eval_accuracy": 0.9552567237163814,
165
+ "eval_loss": 0.13006699085235596,
166
+ "eval_runtime": 57.869,
167
+ "eval_samples_per_second": 70.677,
168
+ "eval_steps_per_second": 2.212,
169
+ "step": 2870
170
+ },
171
+ {
172
+ "epoch": 9.997393570807994,
173
+ "step": 2870,
174
+ "total_flos": 3.760030331457189e+19,
175
+ "train_loss": 0.4662683892333134,
176
+ "train_runtime": 8157.4316,
177
+ "train_samples_per_second": 45.124,
178
+ "train_steps_per_second": 0.352
179
+ }
180
+ ],
181
+ "logging_steps": 10,
182
+ "max_steps": 2870,
183
+ "num_input_tokens_seen": 0,
184
+ "num_train_epochs": 10,
185
+ "save_steps": 500,
186
+ "stateful_callbacks": {
187
+ "TrainerControl": {
188
+ "args": {
189
+ "should_epoch_stop": false,
190
+ "should_evaluate": false,
191
+ "should_log": false,
192
+ "should_save": true,
193
+ "should_training_stop": true
194
+ },
195
+ "attributes": {}
196
+ }
197
+ },
198
+ "total_flos": 3.760030331457189e+19,
199
+ "train_batch_size": 32,
200
+ "trial_name": null,
201
+ "trial_params": null
202
+ }