ChasingMercer commited on
Commit
7e3621e
1 Parent(s): d2a17f6

Training in progress, epoch 0

Browse files
.ipynb_checkpoints/train_results-checkpoint.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.2743012151733248e+18,
4
+ "train_loss": 0.393069394557332,
5
+ "train_runtime": 1296.2409,
6
+ "train_samples_per_second": 12.704,
7
+ "train_steps_per_second": 0.396
8
+ }
.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
@@ -0,0 +1,358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9373634377276038,
3
+ "best_model_checkpoint": "./weather-base/checkpoint-342",
4
+ "epoch": 2.995633187772926,
5
+ "global_step": 513,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 9.615384615384616e-06,
13
+ "loss": 2.5162,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.12,
18
+ "learning_rate": 1.923076923076923e-05,
19
+ "loss": 2.2089,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.17,
24
+ "learning_rate": 2.8846153846153845e-05,
25
+ "loss": 1.744,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.23,
30
+ "learning_rate": 3.846153846153846e-05,
31
+ "loss": 1.1145,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.29,
36
+ "learning_rate": 4.8076923076923084e-05,
37
+ "loss": 0.7667,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.35,
42
+ "learning_rate": 4.9132321041214754e-05,
43
+ "loss": 0.6373,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.41,
48
+ "learning_rate": 4.804772234273319e-05,
49
+ "loss": 0.4996,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.47,
54
+ "learning_rate": 4.696312364425163e-05,
55
+ "loss": 0.429,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.52,
60
+ "learning_rate": 4.587852494577007e-05,
61
+ "loss": 0.4243,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.58,
66
+ "learning_rate": 4.47939262472885e-05,
67
+ "loss": 0.3769,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.64,
72
+ "learning_rate": 4.370932754880694e-05,
73
+ "loss": 0.4072,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.7,
78
+ "learning_rate": 4.262472885032538e-05,
79
+ "loss": 0.3406,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.76,
84
+ "learning_rate": 4.154013015184382e-05,
85
+ "loss": 0.3224,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.82,
90
+ "learning_rate": 4.045553145336225e-05,
91
+ "loss": 0.4434,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.87,
96
+ "learning_rate": 3.9370932754880696e-05,
97
+ "loss": 0.3797,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.93,
102
+ "learning_rate": 3.828633405639914e-05,
103
+ "loss": 0.316,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.99,
108
+ "learning_rate": 3.720173535791757e-05,
109
+ "loss": 0.3277,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.0,
114
+ "eval_accuracy": 0.9002184996358339,
115
+ "eval_loss": 0.29298296570777893,
116
+ "eval_runtime": 34.0636,
117
+ "eval_samples_per_second": 40.307,
118
+ "eval_steps_per_second": 5.049,
119
+ "step": 171
120
+ },
121
+ {
122
+ "epoch": 1.05,
123
+ "learning_rate": 3.611713665943601e-05,
124
+ "loss": 0.3201,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 1.11,
129
+ "learning_rate": 3.503253796095445e-05,
130
+ "loss": 0.3002,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.17,
135
+ "learning_rate": 3.394793926247289e-05,
136
+ "loss": 0.2141,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.23,
141
+ "learning_rate": 3.286334056399132e-05,
142
+ "loss": 0.2718,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.29,
147
+ "learning_rate": 3.1778741865509765e-05,
148
+ "loss": 0.2551,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.34,
153
+ "learning_rate": 3.06941431670282e-05,
154
+ "loss": 0.2694,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.4,
159
+ "learning_rate": 2.960954446854664e-05,
160
+ "loss": 0.3507,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.46,
165
+ "learning_rate": 2.8524945770065074e-05,
166
+ "loss": 0.2558,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.52,
171
+ "learning_rate": 2.7440347071583517e-05,
172
+ "loss": 0.185,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.58,
177
+ "learning_rate": 2.635574837310195e-05,
178
+ "loss": 0.2202,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.63,
183
+ "learning_rate": 2.5271149674620394e-05,
184
+ "loss": 0.2468,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.69,
189
+ "learning_rate": 2.418655097613883e-05,
190
+ "loss": 0.2374,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.75,
195
+ "learning_rate": 2.3101952277657267e-05,
196
+ "loss": 0.2063,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.81,
201
+ "learning_rate": 2.2017353579175707e-05,
202
+ "loss": 0.1711,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.87,
207
+ "learning_rate": 2.0932754880694143e-05,
208
+ "loss": 0.2644,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.93,
213
+ "learning_rate": 1.9848156182212583e-05,
214
+ "loss": 0.2194,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.98,
219
+ "learning_rate": 1.876355748373102e-05,
220
+ "loss": 0.2401,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 2.0,
225
+ "eval_accuracy": 0.9373634377276038,
226
+ "eval_loss": 0.19143207371234894,
227
+ "eval_runtime": 72.116,
228
+ "eval_samples_per_second": 19.039,
229
+ "eval_steps_per_second": 2.385,
230
+ "step": 342
231
+ },
232
+ {
233
+ "epoch": 2.05,
234
+ "learning_rate": 1.767895878524946e-05,
235
+ "loss": 0.1665,
236
+ "step": 350
237
+ },
238
+ {
239
+ "epoch": 2.1,
240
+ "learning_rate": 1.6594360086767896e-05,
241
+ "loss": 0.1463,
242
+ "step": 360
243
+ },
244
+ {
245
+ "epoch": 2.16,
246
+ "learning_rate": 1.5509761388286336e-05,
247
+ "loss": 0.1939,
248
+ "step": 370
249
+ },
250
+ {
251
+ "epoch": 2.22,
252
+ "learning_rate": 1.4425162689804772e-05,
253
+ "loss": 0.2001,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.28,
258
+ "learning_rate": 1.334056399132321e-05,
259
+ "loss": 0.2046,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.34,
264
+ "learning_rate": 1.225596529284165e-05,
265
+ "loss": 0.172,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.4,
270
+ "learning_rate": 1.1171366594360088e-05,
271
+ "loss": 0.1597,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.45,
276
+ "learning_rate": 1.0086767895878525e-05,
277
+ "loss": 0.1624,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.51,
282
+ "learning_rate": 9.002169197396963e-06,
283
+ "loss": 0.1609,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.57,
288
+ "learning_rate": 7.917570498915401e-06,
289
+ "loss": 0.1972,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.63,
294
+ "learning_rate": 6.832971800433839e-06,
295
+ "loss": 0.1007,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.69,
300
+ "learning_rate": 5.748373101952278e-06,
301
+ "loss": 0.0885,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.75,
306
+ "learning_rate": 4.663774403470715e-06,
307
+ "loss": 0.1321,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.8,
312
+ "learning_rate": 3.5791757049891544e-06,
313
+ "loss": 0.1699,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.86,
318
+ "learning_rate": 2.4945770065075926e-06,
319
+ "loss": 0.1647,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.92,
324
+ "learning_rate": 1.4099783080260303e-06,
325
+ "loss": 0.1175,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.98,
330
+ "learning_rate": 3.2537960954446857e-07,
331
+ "loss": 0.1036,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 3.0,
336
+ "eval_accuracy": 0.9359067734887109,
337
+ "eval_loss": 0.18145906925201416,
338
+ "eval_runtime": 29.9478,
339
+ "eval_samples_per_second": 45.846,
340
+ "eval_steps_per_second": 5.743,
341
+ "step": 513
342
+ },
343
+ {
344
+ "epoch": 3.0,
345
+ "step": 513,
346
+ "total_flos": 1.2743012151733248e+18,
347
+ "train_loss": 0.393069394557332,
348
+ "train_runtime": 1296.2409,
349
+ "train_samples_per_second": 12.704,
350
+ "train_steps_per_second": 0.396
351
+ }
352
+ ],
353
+ "max_steps": 513,
354
+ "num_train_epochs": 3,
355
+ "total_flos": 1.2743012151733248e+18,
356
+ "trial_name": null,
357
+ "trial_params": null
358
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.2743012151733248e+18,
4
+ "train_loss": 0.393069394557332,
5
+ "train_runtime": 1296.2409,
6
+ "train_samples_per_second": 12.704,
7
+ "train_steps_per_second": 0.396
8
+ }
config.json CHANGED
@@ -13,33 +13,33 @@
13
  "hidden_dropout_prob": 0.0,
14
  "hidden_size": 768,
15
  "id2label": {
16
- "0": "LABEL_0",
17
- "1": "LABEL_1",
18
- "2": "LABEL_2",
19
- "3": "LABEL_3",
20
- "4": "LABEL_4",
21
- "5": "LABEL_5",
22
- "6": "LABEL_6",
23
- "7": "LABEL_7",
24
- "8": "LABEL_8",
25
- "9": "LABEL_9",
26
- "10": "LABEL_10"
27
  },
28
  "image_size": 224,
29
  "initializer_range": 0.02,
30
  "intermediate_size": 3072,
31
  "label2id": {
32
- "LABEL_0": 0,
33
- "LABEL_1": 1,
34
- "LABEL_10": 10,
35
- "LABEL_2": 2,
36
- "LABEL_3": 3,
37
- "LABEL_4": 4,
38
- "LABEL_5": 5,
39
- "LABEL_6": 6,
40
- "LABEL_7": 7,
41
- "LABEL_8": 8,
42
- "LABEL_9": 9
43
  },
44
  "layer_norm_eps": 1e-12,
45
  "layer_scale_init_value": 0.1,
 
13
  "hidden_dropout_prob": 0.0,
14
  "hidden_size": 768,
15
  "id2label": {
16
+ "0": "dew",
17
+ "1": "fogsmog",
18
+ "2": "frost",
19
+ "3": "glaze",
20
+ "4": "hail",
21
+ "5": "lightning",
22
+ "6": "rain",
23
+ "7": "rainbow",
24
+ "8": "rime",
25
+ "9": "sandstorm",
26
+ "10": "snow"
27
  },
28
  "image_size": 224,
29
  "initializer_range": 0.02,
30
  "intermediate_size": 3072,
31
  "label2id": {
32
+ "dew": 0,
33
+ "fogsmog": 1,
34
+ "frost": 2,
35
+ "glaze": 3,
36
+ "hail": 4,
37
+ "lightning": 5,
38
+ "rain": 6,
39
+ "rainbow": 7,
40
+ "rime": 8,
41
+ "sandstorm": 9,
42
+ "snow": 10
43
  },
44
  "layer_norm_eps": 1e-12,
45
  "layer_scale_init_value": 0.1,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8459e7cdc3e4c28647c1aa4660ea7389bd65e9ddbcc5a9e22a193a083e5a915
3
  size 346888057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c87f68a0a57af6f1603aa44f1c025ae2743dc2b81dca53289cc2d4e9f582d6
3
  size 346888057
runs/Mar06_20-27-29_pop-os/events.out.tfevents.1678138748.pop-os.6196.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95987de583f564a55504a51983e490661424240ebbac4f1dd33a11d584cce2c7
3
+ size 411
runs/Mar07_13-53-02_pop-os/events.out.tfevents.1678197251.pop-os.7668.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e4e39f06e9231919cda4fa4724c225de457e3f1dc74a7e530cf21761e71cb3
3
+ size 862
runs/Mar07_13-53-02_pop-os/events.out.tfevents.1678197956.pop-os.7668.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c58967cfc1336ed645b76f6801cfc052ca4b8b215d8fe43c0fd5eeee055a696
3
+ size 346
runs/Mar07_14-05-09_pop-os/1678198251.5063524/events.out.tfevents.1678198251.pop-os.7668.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785f575deeed53ced09d72b97a10530fcb7735e9437756fc52e33ffd23cf3b91
3
+ size 5704
runs/Mar07_14-05-09_pop-os/events.out.tfevents.1678198063.pop-os.7668.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbac53de7ffb298fadf73954d95dc61b2b4f2e007a2fcaf66c5ba2b352edf497
3
+ size 346
runs/Mar07_14-05-09_pop-os/events.out.tfevents.1678198251.pop-os.7668.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddaf63746f4c80aec4005afdd47b7dd29ad7b054210e7bf3373df8742e876bf
3
+ size 4724
runs/Mar07_14-11-04_pop-os/1678198277.4953692/events.out.tfevents.1678198277.pop-os.7668.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b57a9936d5980141fc8043ee5a7dad8f3ee4678618be8670863eff7209be06
3
+ size 5704
runs/Mar07_14-11-04_pop-os/events.out.tfevents.1678198277.pop-os.7668.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ea0beb513330b21d9181f2e29cc4fff6bfce3881f003ca18a318215f973e49
3
+ size 7680
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.2743012151733248e+18,
4
+ "train_loss": 0.393069394557332,
5
+ "train_runtime": 1296.2409,
6
+ "train_samples_per_second": 12.704,
7
+ "train_steps_per_second": 0.396
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9373634377276038,
3
+ "best_model_checkpoint": "./weather-base/checkpoint-342",
4
+ "epoch": 2.995633187772926,
5
+ "global_step": 513,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 9.615384615384616e-06,
13
+ "loss": 2.5162,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.12,
18
+ "learning_rate": 1.923076923076923e-05,
19
+ "loss": 2.2089,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.17,
24
+ "learning_rate": 2.8846153846153845e-05,
25
+ "loss": 1.744,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.23,
30
+ "learning_rate": 3.846153846153846e-05,
31
+ "loss": 1.1145,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.29,
36
+ "learning_rate": 4.8076923076923084e-05,
37
+ "loss": 0.7667,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.35,
42
+ "learning_rate": 4.9132321041214754e-05,
43
+ "loss": 0.6373,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.41,
48
+ "learning_rate": 4.804772234273319e-05,
49
+ "loss": 0.4996,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.47,
54
+ "learning_rate": 4.696312364425163e-05,
55
+ "loss": 0.429,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.52,
60
+ "learning_rate": 4.587852494577007e-05,
61
+ "loss": 0.4243,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.58,
66
+ "learning_rate": 4.47939262472885e-05,
67
+ "loss": 0.3769,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.64,
72
+ "learning_rate": 4.370932754880694e-05,
73
+ "loss": 0.4072,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.7,
78
+ "learning_rate": 4.262472885032538e-05,
79
+ "loss": 0.3406,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.76,
84
+ "learning_rate": 4.154013015184382e-05,
85
+ "loss": 0.3224,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.82,
90
+ "learning_rate": 4.045553145336225e-05,
91
+ "loss": 0.4434,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.87,
96
+ "learning_rate": 3.9370932754880696e-05,
97
+ "loss": 0.3797,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.93,
102
+ "learning_rate": 3.828633405639914e-05,
103
+ "loss": 0.316,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.99,
108
+ "learning_rate": 3.720173535791757e-05,
109
+ "loss": 0.3277,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.0,
114
+ "eval_accuracy": 0.9002184996358339,
115
+ "eval_loss": 0.29298296570777893,
116
+ "eval_runtime": 34.0636,
117
+ "eval_samples_per_second": 40.307,
118
+ "eval_steps_per_second": 5.049,
119
+ "step": 171
120
+ },
121
+ {
122
+ "epoch": 1.05,
123
+ "learning_rate": 3.611713665943601e-05,
124
+ "loss": 0.3201,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 1.11,
129
+ "learning_rate": 3.503253796095445e-05,
130
+ "loss": 0.3002,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.17,
135
+ "learning_rate": 3.394793926247289e-05,
136
+ "loss": 0.2141,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.23,
141
+ "learning_rate": 3.286334056399132e-05,
142
+ "loss": 0.2718,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.29,
147
+ "learning_rate": 3.1778741865509765e-05,
148
+ "loss": 0.2551,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.34,
153
+ "learning_rate": 3.06941431670282e-05,
154
+ "loss": 0.2694,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.4,
159
+ "learning_rate": 2.960954446854664e-05,
160
+ "loss": 0.3507,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.46,
165
+ "learning_rate": 2.8524945770065074e-05,
166
+ "loss": 0.2558,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.52,
171
+ "learning_rate": 2.7440347071583517e-05,
172
+ "loss": 0.185,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.58,
177
+ "learning_rate": 2.635574837310195e-05,
178
+ "loss": 0.2202,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.63,
183
+ "learning_rate": 2.5271149674620394e-05,
184
+ "loss": 0.2468,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.69,
189
+ "learning_rate": 2.418655097613883e-05,
190
+ "loss": 0.2374,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.75,
195
+ "learning_rate": 2.3101952277657267e-05,
196
+ "loss": 0.2063,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.81,
201
+ "learning_rate": 2.2017353579175707e-05,
202
+ "loss": 0.1711,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.87,
207
+ "learning_rate": 2.0932754880694143e-05,
208
+ "loss": 0.2644,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.93,
213
+ "learning_rate": 1.9848156182212583e-05,
214
+ "loss": 0.2194,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.98,
219
+ "learning_rate": 1.876355748373102e-05,
220
+ "loss": 0.2401,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 2.0,
225
+ "eval_accuracy": 0.9373634377276038,
226
+ "eval_loss": 0.19143207371234894,
227
+ "eval_runtime": 72.116,
228
+ "eval_samples_per_second": 19.039,
229
+ "eval_steps_per_second": 2.385,
230
+ "step": 342
231
+ },
232
+ {
233
+ "epoch": 2.05,
234
+ "learning_rate": 1.767895878524946e-05,
235
+ "loss": 0.1665,
236
+ "step": 350
237
+ },
238
+ {
239
+ "epoch": 2.1,
240
+ "learning_rate": 1.6594360086767896e-05,
241
+ "loss": 0.1463,
242
+ "step": 360
243
+ },
244
+ {
245
+ "epoch": 2.16,
246
+ "learning_rate": 1.5509761388286336e-05,
247
+ "loss": 0.1939,
248
+ "step": 370
249
+ },
250
+ {
251
+ "epoch": 2.22,
252
+ "learning_rate": 1.4425162689804772e-05,
253
+ "loss": 0.2001,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.28,
258
+ "learning_rate": 1.334056399132321e-05,
259
+ "loss": 0.2046,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.34,
264
+ "learning_rate": 1.225596529284165e-05,
265
+ "loss": 0.172,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.4,
270
+ "learning_rate": 1.1171366594360088e-05,
271
+ "loss": 0.1597,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.45,
276
+ "learning_rate": 1.0086767895878525e-05,
277
+ "loss": 0.1624,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.51,
282
+ "learning_rate": 9.002169197396963e-06,
283
+ "loss": 0.1609,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.57,
288
+ "learning_rate": 7.917570498915401e-06,
289
+ "loss": 0.1972,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.63,
294
+ "learning_rate": 6.832971800433839e-06,
295
+ "loss": 0.1007,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.69,
300
+ "learning_rate": 5.748373101952278e-06,
301
+ "loss": 0.0885,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.75,
306
+ "learning_rate": 4.663774403470715e-06,
307
+ "loss": 0.1321,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.8,
312
+ "learning_rate": 3.5791757049891544e-06,
313
+ "loss": 0.1699,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.86,
318
+ "learning_rate": 2.4945770065075926e-06,
319
+ "loss": 0.1647,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.92,
324
+ "learning_rate": 1.4099783080260303e-06,
325
+ "loss": 0.1175,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.98,
330
+ "learning_rate": 3.2537960954446857e-07,
331
+ "loss": 0.1036,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 3.0,
336
+ "eval_accuracy": 0.9359067734887109,
337
+ "eval_loss": 0.18145906925201416,
338
+ "eval_runtime": 29.9478,
339
+ "eval_samples_per_second": 45.846,
340
+ "eval_steps_per_second": 5.743,
341
+ "step": 513
342
+ },
343
+ {
344
+ "epoch": 3.0,
345
+ "step": 513,
346
+ "total_flos": 1.2743012151733248e+18,
347
+ "train_loss": 0.393069394557332,
348
+ "train_runtime": 1296.2409,
349
+ "train_samples_per_second": 12.704,
350
+ "train_steps_per_second": 0.396
351
+ }
352
+ ],
353
+ "max_steps": 513,
354
+ "num_train_epochs": 3,
355
+ "total_flos": 1.2743012151733248e+18,
356
+ "trial_name": null,
357
+ "trial_params": null
358
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b055c8f159a84bc34a5370a55b3bca5340a1365dc9045c40b1593491008163f
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465c7388a74f286a54712bf921471f74f71cbc8f46aa3b7452041738835f202e
3
  size 3515