MoSouguir commited on
Commit
2ed83fd
1 Parent(s): 314ba5a

Training in progress, epoch 0

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9846153846153847,
3
+ "total_flos": 7.898720659019366e+17,
4
+ "train_loss": 0.6530564023866686,
5
+ "train_runtime": 529.8812,
6
+ "train_samples_per_second": 70.51,
7
+ "train_steps_per_second": 0.549
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36b1cec803e7d2fbaf07bc234d90985a790f4b85e0c437f7635bf9ea359440ea
3
  size 94302952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09f77c36fbefeeaaa63444d050174a74d30edbbddffbe045a10d977e3ef82fe
3
  size 94302952
runs/May10_09-22-52_Mohamed-IC/events.out.tfevents.1715329373.Mohamed-IC.27792.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7e9b64badabec42816f8d1f8d4fbc9d054ab6cddd90d8f356de7a15abbc51c
3
+ size 4819
runs/May10_12-38-21_Mohamed-IC/events.out.tfevents.1715341132.Mohamed-IC.7731.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e808ac742c5ec945d5c39d0631abbd353d2129d56c4d846df08c906ca1ab484a
3
+ size 4819
runs/May10_13-11-58_Mohamed-IC/events.out.tfevents.1715343119.Mohamed-IC.14101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9fae1d5024c71656c90341fe6dff33e20bc9805885e1bd6b3cee9487cd809f
3
+ size 5026
runs/May10_14-05-46_Mohamed-IC/events.out.tfevents.1715346356.Mohamed-IC.19175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c33956c656acdcfda923a298d6886e008569e66cd129f8c76d1bb74b2ae488
3
+ size 9550
runs/May10_14-05-46_Mohamed-IC/events.out.tfevents.1715347389.Mohamed-IC.19175.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58af474281258c1cb6ccfe73024da7fad99c551d6682413238a69de7bf9e3ad
3
+ size 12207
runs/May10_14-39-54_Mohamed-IC/events.out.tfevents.1715348395.Mohamed-IC.19175.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777f91e41277348e8202eed3f6f431e993439d06ea09aa502a2732cba55d04c6
3
+ size 10265
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9846153846153847,
3
+ "total_flos": 7.898720659019366e+17,
4
+ "train_loss": 0.6530564023866686,
5
+ "train_runtime": 529.8812,
6
+ "train_samples_per_second": 70.51,
7
+ "train_steps_per_second": 0.549
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6416184971098265,
3
+ "best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-97",
4
+ "epoch": 2.9846153846153847,
5
+ "eval_steps": 500,
6
+ "global_step": 291,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.10256410256410256,
13
+ "grad_norm": 0.4352456331253052,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 0.6926,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.20512820512820512,
20
+ "grad_norm": 0.80888432264328,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 0.6876,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.3076923076923077,
27
+ "grad_norm": 0.7256971597671509,
28
+ "learning_rate": 5e-05,
29
+ "loss": 0.6791,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.41025641025641024,
34
+ "grad_norm": 0.7818945050239563,
35
+ "learning_rate": 4.8084291187739464e-05,
36
+ "loss": 0.6602,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.5128205128205128,
41
+ "grad_norm": 0.5908713340759277,
42
+ "learning_rate": 4.616858237547893e-05,
43
+ "loss": 0.6622,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.6153846153846154,
48
+ "grad_norm": 0.570097804069519,
49
+ "learning_rate": 4.4252873563218394e-05,
50
+ "loss": 0.6582,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.717948717948718,
55
+ "grad_norm": 0.7440472841262817,
56
+ "learning_rate": 4.2337164750957856e-05,
57
+ "loss": 0.646,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.8205128205128205,
62
+ "grad_norm": 0.5741876363754272,
63
+ "learning_rate": 4.0421455938697324e-05,
64
+ "loss": 0.6599,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.9230769230769231,
69
+ "grad_norm": 0.6604257822036743,
70
+ "learning_rate": 3.850574712643678e-05,
71
+ "loss": 0.6486,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.9948717948717949,
76
+ "eval_accuracy": 0.6416184971098265,
77
+ "eval_loss": 0.6518892645835876,
78
+ "eval_runtime": 17.6276,
79
+ "eval_samples_per_second": 78.513,
80
+ "eval_steps_per_second": 2.496,
81
+ "step": 97
82
+ },
83
+ {
84
+ "epoch": 1.0256410256410255,
85
+ "grad_norm": 0.8966683149337769,
86
+ "learning_rate": 3.659003831417625e-05,
87
+ "loss": 0.6356,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.1282051282051282,
92
+ "grad_norm": 0.7184256911277771,
93
+ "learning_rate": 3.467432950191571e-05,
94
+ "loss": 0.6409,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 1.2307692307692308,
99
+ "grad_norm": 0.9605466723442078,
100
+ "learning_rate": 3.275862068965517e-05,
101
+ "loss": 0.6452,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 1.3333333333333333,
106
+ "grad_norm": 0.6847850680351257,
107
+ "learning_rate": 3.084291187739464e-05,
108
+ "loss": 0.6562,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 1.435897435897436,
113
+ "grad_norm": 0.7334717512130737,
114
+ "learning_rate": 2.89272030651341e-05,
115
+ "loss": 0.631,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 1.5384615384615383,
120
+ "grad_norm": 0.962297797203064,
121
+ "learning_rate": 2.7011494252873566e-05,
122
+ "loss": 0.6496,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 1.641025641025641,
127
+ "grad_norm": 0.8398529887199402,
128
+ "learning_rate": 2.5095785440613027e-05,
129
+ "loss": 0.6555,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 1.7435897435897436,
134
+ "grad_norm": 0.8672203421592712,
135
+ "learning_rate": 2.3180076628352492e-05,
136
+ "loss": 0.6496,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 1.8461538461538463,
141
+ "grad_norm": 0.9078596830368042,
142
+ "learning_rate": 2.1264367816091954e-05,
143
+ "loss": 0.6404,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 1.9487179487179487,
148
+ "grad_norm": 1.1112207174301147,
149
+ "learning_rate": 1.934865900383142e-05,
150
+ "loss": 0.6518,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 2.0,
155
+ "eval_accuracy": 0.6416184971098265,
156
+ "eval_loss": 0.6501337885856628,
157
+ "eval_runtime": 15.5449,
158
+ "eval_samples_per_second": 89.032,
159
+ "eval_steps_per_second": 2.831,
160
+ "step": 195
161
+ },
162
+ {
163
+ "epoch": 2.051282051282051,
164
+ "grad_norm": 1.176990032196045,
165
+ "learning_rate": 1.743295019157088e-05,
166
+ "loss": 0.6564,
167
+ "step": 200
168
+ },
169
+ {
170
+ "epoch": 2.1538461538461537,
171
+ "grad_norm": 0.9637936353683472,
172
+ "learning_rate": 1.5517241379310346e-05,
173
+ "loss": 0.6496,
174
+ "step": 210
175
+ },
176
+ {
177
+ "epoch": 2.2564102564102564,
178
+ "grad_norm": 0.6943733096122742,
179
+ "learning_rate": 1.360153256704981e-05,
180
+ "loss": 0.6496,
181
+ "step": 220
182
+ },
183
+ {
184
+ "epoch": 2.358974358974359,
185
+ "grad_norm": 0.8282309770584106,
186
+ "learning_rate": 1.1685823754789272e-05,
187
+ "loss": 0.6412,
188
+ "step": 230
189
+ },
190
+ {
191
+ "epoch": 2.4615384615384617,
192
+ "grad_norm": 0.7222530841827393,
193
+ "learning_rate": 9.770114942528738e-06,
194
+ "loss": 0.6454,
195
+ "step": 240
196
+ },
197
+ {
198
+ "epoch": 2.564102564102564,
199
+ "grad_norm": 0.9417911171913147,
200
+ "learning_rate": 7.854406130268199e-06,
201
+ "loss": 0.6406,
202
+ "step": 250
203
+ },
204
+ {
205
+ "epoch": 2.6666666666666665,
206
+ "grad_norm": 0.8182082176208496,
207
+ "learning_rate": 5.938697318007663e-06,
208
+ "loss": 0.6594,
209
+ "step": 260
210
+ },
211
+ {
212
+ "epoch": 2.769230769230769,
213
+ "grad_norm": 0.8655200600624084,
214
+ "learning_rate": 4.022988505747127e-06,
215
+ "loss": 0.6452,
216
+ "step": 270
217
+ },
218
+ {
219
+ "epoch": 2.871794871794872,
220
+ "grad_norm": 0.6346496939659119,
221
+ "learning_rate": 2.1072796934865904e-06,
222
+ "loss": 0.6435,
223
+ "step": 280
224
+ },
225
+ {
226
+ "epoch": 2.9743589743589745,
227
+ "grad_norm": 0.5316995978355408,
228
+ "learning_rate": 1.9157088122605365e-07,
229
+ "loss": 0.6562,
230
+ "step": 290
231
+ },
232
+ {
233
+ "epoch": 2.9846153846153847,
234
+ "eval_accuracy": 0.6416184971098265,
235
+ "eval_loss": 0.6498913168907166,
236
+ "eval_runtime": 16.5397,
237
+ "eval_samples_per_second": 83.678,
238
+ "eval_steps_per_second": 2.66,
239
+ "step": 291
240
+ },
241
+ {
242
+ "epoch": 2.9846153846153847,
243
+ "step": 291,
244
+ "total_flos": 7.898720659019366e+17,
245
+ "train_loss": 0.6530564023866686,
246
+ "train_runtime": 529.8812,
247
+ "train_samples_per_second": 70.51,
248
+ "train_steps_per_second": 0.549
249
+ }
250
+ ],
251
+ "logging_steps": 10,
252
+ "max_steps": 291,
253
+ "num_input_tokens_seen": 0,
254
+ "num_train_epochs": 3,
255
+ "save_steps": 500,
256
+ "total_flos": 7.898720659019366e+17,
257
+ "train_batch_size": 32,
258
+ "trial_name": null,
259
+ "trial_params": null
260
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fa4505efa69cacf94ca5e6f920f0c4b3bcc790a42d41a322737840080ff1b10
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f17a7fbecd89a3318644e90a2c37de6de8506c85ac9e0f648b98c6ac3234e9
3
  size 5048