SanketJadhav commited on
Commit
aafcd07
1 Parent(s): dd591f8

Training in progress, epoch 0

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 7.483912529986142e+18,
4
+ "train_loss": 1.0602939221811207,
5
+ "train_runtime": 5306.8618,
6
+ "train_samples_per_second": 66.23,
7
+ "train_steps_per_second": 0.517
8
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02fc34c61e64d114a8dbddfcef2b8abb5039950783f1b3e9e7c217f818e50c83
3
  size 94670029
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27192b2af6561147410b4e61f0ece45bbaf463e65749d97d0bc22d2b54b662e0
3
  size 94670029
runs/May01_11-37-02_f493e3a4fb8c/1682946572.6019552/events.out.tfevents.1682946572.f493e3a4fb8c.8992.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3db7b100ba726f00025216481013ed765542e0ace6fe119b651db8cac97c92
3
+ size 5907
runs/May01_11-37-02_f493e3a4fb8c/1682946612.619405/events.out.tfevents.1682946612.f493e3a4fb8c.8992.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a19011feb79b7be9161bb021df656d6e4327a58b5c2462ffc3fa6dca17d845a
3
+ size 5907
runs/May01_11-37-02_f493e3a4fb8c/events.out.tfevents.1682946572.f493e3a4fb8c.8992.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278256417afd4d8d521dc7a5db0f4c30aceb10f680bfd59df9bd41f8ad98fd25
3
+ size 22697
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 7.483912529986142e+18,
4
+ "train_loss": 1.0602939221811207,
5
+ "train_runtime": 5306.8618,
6
+ "train_samples_per_second": 66.23,
7
+ "train_steps_per_second": 0.517
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9624402458456636,
3
+ "best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-2745",
4
+ "epoch": 4.997724169321803,
5
+ "global_step": 2745,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1.818181818181818e-06,
13
+ "loss": 3.6408,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 3.636363636363636e-06,
19
+ "loss": 3.6412,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 5.4545454545454545e-06,
25
+ "loss": 3.641,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 7.272727272727272e-06,
31
+ "loss": 3.6404,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 9.090909090909091e-06,
37
+ "loss": 3.6347,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 1.0909090909090909e-05,
43
+ "loss": 3.6377,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.13,
48
+ "learning_rate": 1.2727272727272727e-05,
49
+ "loss": 3.6316,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.15,
54
+ "learning_rate": 1.4545454545454545e-05,
55
+ "loss": 3.6339,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.16,
60
+ "learning_rate": 1.6363636363636366e-05,
61
+ "loss": 3.6301,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.18,
66
+ "learning_rate": 1.8181818181818182e-05,
67
+ "loss": 3.626,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.2,
72
+ "learning_rate": 2e-05,
73
+ "loss": 3.621,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.22,
78
+ "learning_rate": 2.1818181818181818e-05,
79
+ "loss": 3.6206,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.24,
84
+ "learning_rate": 2.3636363636363637e-05,
85
+ "loss": 3.6118,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.25,
90
+ "learning_rate": 2.5454545454545454e-05,
91
+ "loss": 3.6068,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.27,
96
+ "learning_rate": 2.7272727272727273e-05,
97
+ "loss": 3.598,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.29,
102
+ "learning_rate": 2.909090909090909e-05,
103
+ "loss": 3.5991,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.31,
108
+ "learning_rate": 3.090909090909091e-05,
109
+ "loss": 3.5924,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.33,
114
+ "learning_rate": 3.272727272727273e-05,
115
+ "loss": 3.5819,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.35,
120
+ "learning_rate": 3.454545454545455e-05,
121
+ "loss": 3.5726,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.36,
126
+ "learning_rate": 3.6363636363636364e-05,
127
+ "loss": 3.5638,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.38,
132
+ "learning_rate": 3.818181818181819e-05,
133
+ "loss": 3.5568,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.4,
138
+ "learning_rate": 4e-05,
139
+ "loss": 3.5451,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.42,
144
+ "learning_rate": 4.181818181818182e-05,
145
+ "loss": 3.5333,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.44,
150
+ "learning_rate": 4.3636363636363636e-05,
151
+ "loss": 3.5256,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.46,
156
+ "learning_rate": 4.545454545454546e-05,
157
+ "loss": 3.5079,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.47,
162
+ "learning_rate": 4.7272727272727275e-05,
163
+ "loss": 3.4865,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.49,
168
+ "learning_rate": 4.909090909090909e-05,
169
+ "loss": 3.4667,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.51,
174
+ "learning_rate": 4.989878542510122e-05,
175
+ "loss": 3.4516,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.53,
180
+ "learning_rate": 4.9696356275303645e-05,
181
+ "loss": 3.427,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.55,
186
+ "learning_rate": 4.9493927125506076e-05,
187
+ "loss": 3.3999,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.56,
192
+ "learning_rate": 4.9291497975708506e-05,
193
+ "loss": 3.3732,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.58,
198
+ "learning_rate": 4.908906882591093e-05,
199
+ "loss": 3.3437,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.6,
204
+ "learning_rate": 4.888663967611336e-05,
205
+ "loss": 3.2873,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.62,
210
+ "learning_rate": 4.868421052631579e-05,
211
+ "loss": 3.2593,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.64,
216
+ "learning_rate": 4.848178137651822e-05,
217
+ "loss": 3.2006,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.66,
222
+ "learning_rate": 4.8279352226720646e-05,
223
+ "loss": 3.1593,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.67,
228
+ "learning_rate": 4.8076923076923084e-05,
229
+ "loss": 3.1129,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.69,
234
+ "learning_rate": 4.787449392712551e-05,
235
+ "loss": 3.0435,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.71,
240
+ "learning_rate": 4.767206477732794e-05,
241
+ "loss": 2.9742,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.73,
246
+ "learning_rate": 4.746963562753037e-05,
247
+ "loss": 2.9306,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.75,
252
+ "learning_rate": 4.726720647773279e-05,
253
+ "loss": 2.8627,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.76,
258
+ "learning_rate": 4.7064777327935223e-05,
259
+ "loss": 2.8301,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.78,
264
+ "learning_rate": 4.6862348178137654e-05,
265
+ "loss": 2.7201,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.8,
270
+ "learning_rate": 4.6659919028340085e-05,
271
+ "loss": 2.6538,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.82,
276
+ "learning_rate": 4.6457489878542516e-05,
277
+ "loss": 2.5858,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.84,
282
+ "learning_rate": 4.625506072874494e-05,
283
+ "loss": 2.4747,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.86,
288
+ "learning_rate": 4.605263157894737e-05,
289
+ "loss": 2.41,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.87,
294
+ "learning_rate": 4.58502024291498e-05,
295
+ "loss": 2.366,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.89,
300
+ "learning_rate": 4.564777327935223e-05,
301
+ "loss": 2.3017,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.91,
306
+ "learning_rate": 4.5445344129554655e-05,
307
+ "loss": 2.2318,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.93,
312
+ "learning_rate": 4.524291497975709e-05,
313
+ "loss": 2.1774,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.95,
318
+ "learning_rate": 4.504048582995952e-05,
319
+ "loss": 2.089,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.96,
324
+ "learning_rate": 4.483805668016194e-05,
325
+ "loss": 2.0213,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.98,
330
+ "learning_rate": 4.463562753036438e-05,
331
+ "loss": 1.9386,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 1.0,
336
+ "eval_accuracy": 0.7653084452538129,
337
+ "eval_loss": 1.521803379058838,
338
+ "eval_runtime": 116.2062,
339
+ "eval_samples_per_second": 151.214,
340
+ "eval_steps_per_second": 4.733,
341
+ "step": 549
342
+ },
343
+ {
344
+ "epoch": 1.0,
345
+ "learning_rate": 4.44331983805668e-05,
346
+ "loss": 1.9215,
347
+ "step": 550
348
+ },
349
+ {
350
+ "epoch": 1.02,
351
+ "learning_rate": 4.423076923076923e-05,
352
+ "loss": 1.8288,
353
+ "step": 560
354
+ },
355
+ {
356
+ "epoch": 1.04,
357
+ "learning_rate": 4.402834008097166e-05,
358
+ "loss": 1.761,
359
+ "step": 570
360
+ },
361
+ {
362
+ "epoch": 1.06,
363
+ "learning_rate": 4.3825910931174094e-05,
364
+ "loss": 1.7306,
365
+ "step": 580
366
+ },
367
+ {
368
+ "epoch": 1.07,
369
+ "learning_rate": 4.362348178137652e-05,
370
+ "loss": 1.6337,
371
+ "step": 590
372
+ },
373
+ {
374
+ "epoch": 1.09,
375
+ "learning_rate": 4.342105263157895e-05,
376
+ "loss": 1.5869,
377
+ "step": 600
378
+ },
379
+ {
380
+ "epoch": 1.11,
381
+ "learning_rate": 4.321862348178138e-05,
382
+ "loss": 1.5347,
383
+ "step": 610
384
+ },
385
+ {
386
+ "epoch": 1.13,
387
+ "learning_rate": 4.30161943319838e-05,
388
+ "loss": 1.4658,
389
+ "step": 620
390
+ },
391
+ {
392
+ "epoch": 1.15,
393
+ "learning_rate": 4.281376518218624e-05,
394
+ "loss": 1.444,
395
+ "step": 630
396
+ },
397
+ {
398
+ "epoch": 1.17,
399
+ "learning_rate": 4.2611336032388664e-05,
400
+ "loss": 1.3742,
401
+ "step": 640
402
+ },
403
+ {
404
+ "epoch": 1.18,
405
+ "learning_rate": 4.2408906882591095e-05,
406
+ "loss": 1.3474,
407
+ "step": 650
408
+ },
409
+ {
410
+ "epoch": 1.2,
411
+ "learning_rate": 4.2206477732793526e-05,
412
+ "loss": 1.3503,
413
+ "step": 660
414
+ },
415
+ {
416
+ "epoch": 1.22,
417
+ "learning_rate": 4.200404858299595e-05,
418
+ "loss": 1.2557,
419
+ "step": 670
420
+ },
421
+ {
422
+ "epoch": 1.24,
423
+ "learning_rate": 4.180161943319838e-05,
424
+ "loss": 1.2054,
425
+ "step": 680
426
+ },
427
+ {
428
+ "epoch": 1.26,
429
+ "learning_rate": 4.159919028340081e-05,
430
+ "loss": 1.253,
431
+ "step": 690
432
+ },
433
+ {
434
+ "epoch": 1.27,
435
+ "learning_rate": 4.139676113360324e-05,
436
+ "loss": 1.1814,
437
+ "step": 700
438
+ },
439
+ {
440
+ "epoch": 1.29,
441
+ "learning_rate": 4.1194331983805666e-05,
442
+ "loss": 1.1699,
443
+ "step": 710
444
+ },
445
+ {
446
+ "epoch": 1.31,
447
+ "learning_rate": 4.09919028340081e-05,
448
+ "loss": 1.1464,
449
+ "step": 720
450
+ },
451
+ {
452
+ "epoch": 1.33,
453
+ "learning_rate": 4.078947368421053e-05,
454
+ "loss": 1.1289,
455
+ "step": 730
456
+ },
457
+ {
458
+ "epoch": 1.35,
459
+ "learning_rate": 4.058704453441296e-05,
460
+ "loss": 1.0347,
461
+ "step": 740
462
+ },
463
+ {
464
+ "epoch": 1.37,
465
+ "learning_rate": 4.038461538461539e-05,
466
+ "loss": 1.0617,
467
+ "step": 750
468
+ },
469
+ {
470
+ "epoch": 1.38,
471
+ "learning_rate": 4.018218623481781e-05,
472
+ "loss": 1.0069,
473
+ "step": 760
474
+ },
475
+ {
476
+ "epoch": 1.4,
477
+ "learning_rate": 3.997975708502025e-05,
478
+ "loss": 0.9519,
479
+ "step": 770
480
+ },
481
+ {
482
+ "epoch": 1.42,
483
+ "learning_rate": 3.9777327935222674e-05,
484
+ "loss": 0.9229,
485
+ "step": 780
486
+ },
487
+ {
488
+ "epoch": 1.44,
489
+ "learning_rate": 3.9574898785425104e-05,
490
+ "loss": 0.9309,
491
+ "step": 790
492
+ },
493
+ {
494
+ "epoch": 1.46,
495
+ "learning_rate": 3.9372469635627535e-05,
496
+ "loss": 0.8647,
497
+ "step": 800
498
+ },
499
+ {
500
+ "epoch": 1.47,
501
+ "learning_rate": 3.917004048582996e-05,
502
+ "loss": 0.8625,
503
+ "step": 810
504
+ },
505
+ {
506
+ "epoch": 1.49,
507
+ "learning_rate": 3.896761133603239e-05,
508
+ "loss": 0.9097,
509
+ "step": 820
510
+ },
511
+ {
512
+ "epoch": 1.51,
513
+ "learning_rate": 3.876518218623482e-05,
514
+ "loss": 0.8751,
515
+ "step": 830
516
+ },
517
+ {
518
+ "epoch": 1.53,
519
+ "learning_rate": 3.856275303643725e-05,
520
+ "loss": 0.8613,
521
+ "step": 840
522
+ },
523
+ {
524
+ "epoch": 1.55,
525
+ "learning_rate": 3.8360323886639675e-05,
526
+ "loss": 0.8289,
527
+ "step": 850
528
+ },
529
+ {
530
+ "epoch": 1.57,
531
+ "learning_rate": 3.815789473684211e-05,
532
+ "loss": 0.8145,
533
+ "step": 860
534
+ },
535
+ {
536
+ "epoch": 1.58,
537
+ "learning_rate": 3.7955465587044536e-05,
538
+ "loss": 0.8031,
539
+ "step": 870
540
+ },
541
+ {
542
+ "epoch": 1.6,
543
+ "learning_rate": 3.775303643724697e-05,
544
+ "loss": 0.844,
545
+ "step": 880
546
+ },
547
+ {
548
+ "epoch": 1.62,
549
+ "learning_rate": 3.75506072874494e-05,
550
+ "loss": 0.8124,
551
+ "step": 890
552
+ },
553
+ {
554
+ "epoch": 1.64,
555
+ "learning_rate": 3.734817813765182e-05,
556
+ "loss": 0.7609,
557
+ "step": 900
558
+ },
559
+ {
560
+ "epoch": 1.66,
561
+ "learning_rate": 3.714574898785425e-05,
562
+ "loss": 0.7603,
563
+ "step": 910
564
+ },
565
+ {
566
+ "epoch": 1.68,
567
+ "learning_rate": 3.694331983805668e-05,
568
+ "loss": 0.7959,
569
+ "step": 920
570
+ },
571
+ {
572
+ "epoch": 1.69,
573
+ "learning_rate": 3.6740890688259113e-05,
574
+ "loss": 0.719,
575
+ "step": 930
576
+ },
577
+ {
578
+ "epoch": 1.71,
579
+ "learning_rate": 3.653846153846154e-05,
580
+ "loss": 0.7447,
581
+ "step": 940
582
+ },
583
+ {
584
+ "epoch": 1.73,
585
+ "learning_rate": 3.633603238866397e-05,
586
+ "loss": 0.7588,
587
+ "step": 950
588
+ },
589
+ {
590
+ "epoch": 1.75,
591
+ "learning_rate": 3.61336032388664e-05,
592
+ "loss": 0.6941,
593
+ "step": 960
594
+ },
595
+ {
596
+ "epoch": 1.77,
597
+ "learning_rate": 3.593117408906882e-05,
598
+ "loss": 0.709,
599
+ "step": 970
600
+ },
601
+ {
602
+ "epoch": 1.78,
603
+ "learning_rate": 3.572874493927126e-05,
604
+ "loss": 0.7446,
605
+ "step": 980
606
+ },
607
+ {
608
+ "epoch": 1.8,
609
+ "learning_rate": 3.5526315789473684e-05,
610
+ "loss": 0.6729,
611
+ "step": 990
612
+ },
613
+ {
614
+ "epoch": 1.82,
615
+ "learning_rate": 3.5323886639676115e-05,
616
+ "loss": 0.6262,
617
+ "step": 1000
618
+ },
619
+ {
620
+ "epoch": 1.84,
621
+ "learning_rate": 3.5121457489878545e-05,
622
+ "loss": 0.6725,
623
+ "step": 1010
624
+ },
625
+ {
626
+ "epoch": 1.86,
627
+ "learning_rate": 3.491902834008097e-05,
628
+ "loss": 0.6287,
629
+ "step": 1020
630
+ },
631
+ {
632
+ "epoch": 1.88,
633
+ "learning_rate": 3.47165991902834e-05,
634
+ "loss": 0.6443,
635
+ "step": 1030
636
+ },
637
+ {
638
+ "epoch": 1.89,
639
+ "learning_rate": 3.451417004048583e-05,
640
+ "loss": 0.6444,
641
+ "step": 1040
642
+ },
643
+ {
644
+ "epoch": 1.91,
645
+ "learning_rate": 3.431174089068826e-05,
646
+ "loss": 0.6219,
647
+ "step": 1050
648
+ },
649
+ {
650
+ "epoch": 1.93,
651
+ "learning_rate": 3.410931174089069e-05,
652
+ "loss": 0.6271,
653
+ "step": 1060
654
+ },
655
+ {
656
+ "epoch": 1.95,
657
+ "learning_rate": 3.390688259109312e-05,
658
+ "loss": 0.6186,
659
+ "step": 1070
660
+ },
661
+ {
662
+ "epoch": 1.97,
663
+ "learning_rate": 3.3704453441295546e-05,
664
+ "loss": 0.5921,
665
+ "step": 1080
666
+ },
667
+ {
668
+ "epoch": 1.98,
669
+ "learning_rate": 3.350202429149798e-05,
670
+ "loss": 0.5662,
671
+ "step": 1090
672
+ },
673
+ {
674
+ "epoch": 2.0,
675
+ "eval_accuracy": 0.9288071932620078,
676
+ "eval_loss": 0.33246490359306335,
677
+ "eval_runtime": 116.3356,
678
+ "eval_samples_per_second": 151.046,
679
+ "eval_steps_per_second": 4.728,
680
+ "step": 1098
681
+ },
682
+ {
683
+ "epoch": 2.0,
684
+ "learning_rate": 3.329959514170041e-05,
685
+ "loss": 0.6063,
686
+ "step": 1100
687
+ },
688
+ {
689
+ "epoch": 2.02,
690
+ "learning_rate": 3.309716599190283e-05,
691
+ "loss": 0.5733,
692
+ "step": 1110
693
+ },
694
+ {
695
+ "epoch": 2.04,
696
+ "learning_rate": 3.289473684210527e-05,
697
+ "loss": 0.5662,
698
+ "step": 1120
699
+ },
700
+ {
701
+ "epoch": 2.06,
702
+ "learning_rate": 3.269230769230769e-05,
703
+ "loss": 0.5893,
704
+ "step": 1130
705
+ },
706
+ {
707
+ "epoch": 2.08,
708
+ "learning_rate": 3.2489878542510124e-05,
709
+ "loss": 0.5498,
710
+ "step": 1140
711
+ },
712
+ {
713
+ "epoch": 2.09,
714
+ "learning_rate": 3.2287449392712554e-05,
715
+ "loss": 0.5416,
716
+ "step": 1150
717
+ },
718
+ {
719
+ "epoch": 2.11,
720
+ "learning_rate": 3.208502024291498e-05,
721
+ "loss": 0.5271,
722
+ "step": 1160
723
+ },
724
+ {
725
+ "epoch": 2.13,
726
+ "learning_rate": 3.188259109311741e-05,
727
+ "loss": 0.5506,
728
+ "step": 1170
729
+ },
730
+ {
731
+ "epoch": 2.15,
732
+ "learning_rate": 3.168016194331984e-05,
733
+ "loss": 0.5227,
734
+ "step": 1180
735
+ },
736
+ {
737
+ "epoch": 2.17,
738
+ "learning_rate": 3.147773279352227e-05,
739
+ "loss": 0.5379,
740
+ "step": 1190
741
+ },
742
+ {
743
+ "epoch": 2.18,
744
+ "learning_rate": 3.1275303643724694e-05,
745
+ "loss": 0.4872,
746
+ "step": 1200
747
+ },
748
+ {
749
+ "epoch": 2.2,
750
+ "learning_rate": 3.107287449392713e-05,
751
+ "loss": 0.5166,
752
+ "step": 1210
753
+ },
754
+ {
755
+ "epoch": 2.22,
756
+ "learning_rate": 3.0870445344129556e-05,
757
+ "loss": 0.5416,
758
+ "step": 1220
759
+ },
760
+ {
761
+ "epoch": 2.24,
762
+ "learning_rate": 3.0668016194331986e-05,
763
+ "loss": 0.5171,
764
+ "step": 1230
765
+ },
766
+ {
767
+ "epoch": 2.26,
768
+ "learning_rate": 3.0465587044534417e-05,
769
+ "loss": 0.4827,
770
+ "step": 1240
771
+ },
772
+ {
773
+ "epoch": 2.28,
774
+ "learning_rate": 3.0263157894736844e-05,
775
+ "loss": 0.5535,
776
+ "step": 1250
777
+ },
778
+ {
779
+ "epoch": 2.29,
780
+ "learning_rate": 3.006072874493927e-05,
781
+ "loss": 0.5095,
782
+ "step": 1260
783
+ },
784
+ {
785
+ "epoch": 2.31,
786
+ "learning_rate": 2.9858299595141702e-05,
787
+ "loss": 0.4874,
788
+ "step": 1270
789
+ },
790
+ {
791
+ "epoch": 2.33,
792
+ "learning_rate": 2.965587044534413e-05,
793
+ "loss": 0.4798,
794
+ "step": 1280
795
+ },
796
+ {
797
+ "epoch": 2.35,
798
+ "learning_rate": 2.9453441295546557e-05,
799
+ "loss": 0.487,
800
+ "step": 1290
801
+ },
802
+ {
803
+ "epoch": 2.37,
804
+ "learning_rate": 2.925101214574899e-05,
805
+ "loss": 0.4855,
806
+ "step": 1300
807
+ },
808
+ {
809
+ "epoch": 2.39,
810
+ "learning_rate": 2.9048582995951418e-05,
811
+ "loss": 0.4818,
812
+ "step": 1310
813
+ },
814
+ {
815
+ "epoch": 2.4,
816
+ "learning_rate": 2.8846153846153845e-05,
817
+ "loss": 0.4359,
818
+ "step": 1320
819
+ },
820
+ {
821
+ "epoch": 2.42,
822
+ "learning_rate": 2.8643724696356276e-05,
823
+ "loss": 0.4553,
824
+ "step": 1330
825
+ },
826
+ {
827
+ "epoch": 2.44,
828
+ "learning_rate": 2.8441295546558703e-05,
829
+ "loss": 0.4566,
830
+ "step": 1340
831
+ },
832
+ {
833
+ "epoch": 2.46,
834
+ "learning_rate": 2.823886639676113e-05,
835
+ "loss": 0.468,
836
+ "step": 1350
837
+ },
838
+ {
839
+ "epoch": 2.48,
840
+ "learning_rate": 2.8036437246963565e-05,
841
+ "loss": 0.4448,
842
+ "step": 1360
843
+ },
844
+ {
845
+ "epoch": 2.49,
846
+ "learning_rate": 2.7834008097165992e-05,
847
+ "loss": 0.4629,
848
+ "step": 1370
849
+ },
850
+ {
851
+ "epoch": 2.51,
852
+ "learning_rate": 2.7631578947368426e-05,
853
+ "loss": 0.4876,
854
+ "step": 1380
855
+ },
856
+ {
857
+ "epoch": 2.53,
858
+ "learning_rate": 2.7429149797570853e-05,
859
+ "loss": 0.4499,
860
+ "step": 1390
861
+ },
862
+ {
863
+ "epoch": 2.55,
864
+ "learning_rate": 2.722672064777328e-05,
865
+ "loss": 0.4449,
866
+ "step": 1400
867
+ },
868
+ {
869
+ "epoch": 2.57,
870
+ "learning_rate": 2.702429149797571e-05,
871
+ "loss": 0.404,
872
+ "step": 1410
873
+ },
874
+ {
875
+ "epoch": 2.59,
876
+ "learning_rate": 2.682186234817814e-05,
877
+ "loss": 0.4521,
878
+ "step": 1420
879
+ },
880
+ {
881
+ "epoch": 2.6,
882
+ "learning_rate": 2.6619433198380566e-05,
883
+ "loss": 0.4075,
884
+ "step": 1430
885
+ },
886
+ {
887
+ "epoch": 2.62,
888
+ "learning_rate": 2.6417004048583e-05,
889
+ "loss": 0.4528,
890
+ "step": 1440
891
+ },
892
+ {
893
+ "epoch": 2.64,
894
+ "learning_rate": 2.6214574898785427e-05,
895
+ "loss": 0.4615,
896
+ "step": 1450
897
+ },
898
+ {
899
+ "epoch": 2.66,
900
+ "learning_rate": 2.6012145748987855e-05,
901
+ "loss": 0.4654,
902
+ "step": 1460
903
+ },
904
+ {
905
+ "epoch": 2.68,
906
+ "learning_rate": 2.5809716599190285e-05,
907
+ "loss": 0.425,
908
+ "step": 1470
909
+ },
910
+ {
911
+ "epoch": 2.69,
912
+ "learning_rate": 2.5607287449392713e-05,
913
+ "loss": 0.409,
914
+ "step": 1480
915
+ },
916
+ {
917
+ "epoch": 2.71,
918
+ "learning_rate": 2.540485829959514e-05,
919
+ "loss": 0.4284,
920
+ "step": 1490
921
+ },
922
+ {
923
+ "epoch": 2.73,
924
+ "learning_rate": 2.5202429149797574e-05,
925
+ "loss": 0.4122,
926
+ "step": 1500
927
+ },
928
+ {
929
+ "epoch": 2.75,
930
+ "learning_rate": 2.5e-05,
931
+ "loss": 0.4273,
932
+ "step": 1510
933
+ },
934
+ {
935
+ "epoch": 2.77,
936
+ "learning_rate": 2.4797570850202432e-05,
937
+ "loss": 0.3865,
938
+ "step": 1520
939
+ },
940
+ {
941
+ "epoch": 2.79,
942
+ "learning_rate": 2.459514170040486e-05,
943
+ "loss": 0.378,
944
+ "step": 1530
945
+ },
946
+ {
947
+ "epoch": 2.8,
948
+ "learning_rate": 2.439271255060729e-05,
949
+ "loss": 0.4051,
950
+ "step": 1540
951
+ },
952
+ {
953
+ "epoch": 2.82,
954
+ "learning_rate": 2.4190283400809717e-05,
955
+ "loss": 0.4127,
956
+ "step": 1550
957
+ },
958
+ {
959
+ "epoch": 2.84,
960
+ "learning_rate": 2.3987854251012144e-05,
961
+ "loss": 0.4141,
962
+ "step": 1560
963
+ },
964
+ {
965
+ "epoch": 2.86,
966
+ "learning_rate": 2.3785425101214575e-05,
967
+ "loss": 0.3842,
968
+ "step": 1570
969
+ },
970
+ {
971
+ "epoch": 2.88,
972
+ "learning_rate": 2.3582995951417006e-05,
973
+ "loss": 0.423,
974
+ "step": 1580
975
+ },
976
+ {
977
+ "epoch": 2.89,
978
+ "learning_rate": 2.3380566801619436e-05,
979
+ "loss": 0.3714,
980
+ "step": 1590
981
+ },
982
+ {
983
+ "epoch": 2.91,
984
+ "learning_rate": 2.3178137651821864e-05,
985
+ "loss": 0.3949,
986
+ "step": 1600
987
+ },
988
+ {
989
+ "epoch": 2.93,
990
+ "learning_rate": 2.2975708502024294e-05,
991
+ "loss": 0.398,
992
+ "step": 1610
993
+ },
994
+ {
995
+ "epoch": 2.95,
996
+ "learning_rate": 2.2773279352226722e-05,
997
+ "loss": 0.3838,
998
+ "step": 1620
999
+ },
1000
+ {
1001
+ "epoch": 2.97,
1002
+ "learning_rate": 2.257085020242915e-05,
1003
+ "loss": 0.365,
1004
+ "step": 1630
1005
+ },
1006
+ {
1007
+ "epoch": 2.99,
1008
+ "learning_rate": 2.236842105263158e-05,
1009
+ "loss": 0.4104,
1010
+ "step": 1640
1011
+ },
1012
+ {
1013
+ "epoch": 3.0,
1014
+ "eval_accuracy": 0.9561233781015251,
1015
+ "eval_loss": 0.18532179296016693,
1016
+ "eval_runtime": 113.1925,
1017
+ "eval_samples_per_second": 155.24,
1018
+ "eval_steps_per_second": 4.859,
1019
+ "step": 1647
1020
+ },
1021
+ {
1022
+ "epoch": 3.0,
1023
+ "learning_rate": 2.216599190283401e-05,
1024
+ "loss": 0.4087,
1025
+ "step": 1650
1026
+ },
1027
+ {
1028
+ "epoch": 3.02,
1029
+ "learning_rate": 2.1963562753036438e-05,
1030
+ "loss": 0.3953,
1031
+ "step": 1660
1032
+ },
1033
+ {
1034
+ "epoch": 3.04,
1035
+ "learning_rate": 2.1761133603238868e-05,
1036
+ "loss": 0.3972,
1037
+ "step": 1670
1038
+ },
1039
+ {
1040
+ "epoch": 3.06,
1041
+ "learning_rate": 2.15587044534413e-05,
1042
+ "loss": 0.4105,
1043
+ "step": 1680
1044
+ },
1045
+ {
1046
+ "epoch": 3.08,
1047
+ "learning_rate": 2.1356275303643726e-05,
1048
+ "loss": 0.3761,
1049
+ "step": 1690
1050
+ },
1051
+ {
1052
+ "epoch": 3.1,
1053
+ "learning_rate": 2.1153846153846154e-05,
1054
+ "loss": 0.3555,
1055
+ "step": 1700
1056
+ },
1057
+ {
1058
+ "epoch": 3.11,
1059
+ "learning_rate": 2.0951417004048584e-05,
1060
+ "loss": 0.3801,
1061
+ "step": 1710
1062
+ },
1063
+ {
1064
+ "epoch": 3.13,
1065
+ "learning_rate": 2.074898785425101e-05,
1066
+ "loss": 0.402,
1067
+ "step": 1720
1068
+ },
1069
+ {
1070
+ "epoch": 3.15,
1071
+ "learning_rate": 2.0546558704453442e-05,
1072
+ "loss": 0.3929,
1073
+ "step": 1730
1074
+ },
1075
+ {
1076
+ "epoch": 3.17,
1077
+ "learning_rate": 2.0344129554655873e-05,
1078
+ "loss": 0.3884,
1079
+ "step": 1740
1080
+ },
1081
+ {
1082
+ "epoch": 3.19,
1083
+ "learning_rate": 2.0141700404858304e-05,
1084
+ "loss": 0.3853,
1085
+ "step": 1750
1086
+ },
1087
+ {
1088
+ "epoch": 3.2,
1089
+ "learning_rate": 1.9939271255060727e-05,
1090
+ "loss": 0.3869,
1091
+ "step": 1760
1092
+ },
1093
+ {
1094
+ "epoch": 3.22,
1095
+ "learning_rate": 1.9736842105263158e-05,
1096
+ "loss": 0.3758,
1097
+ "step": 1770
1098
+ },
1099
+ {
1100
+ "epoch": 3.24,
1101
+ "learning_rate": 1.953441295546559e-05,
1102
+ "loss": 0.3961,
1103
+ "step": 1780
1104
+ },
1105
+ {
1106
+ "epoch": 3.26,
1107
+ "learning_rate": 1.9331983805668016e-05,
1108
+ "loss": 0.3389,
1109
+ "step": 1790
1110
+ },
1111
+ {
1112
+ "epoch": 3.28,
1113
+ "learning_rate": 1.9129554655870447e-05,
1114
+ "loss": 0.3624,
1115
+ "step": 1800
1116
+ },
1117
+ {
1118
+ "epoch": 3.3,
1119
+ "learning_rate": 1.8927125506072877e-05,
1120
+ "loss": 0.3905,
1121
+ "step": 1810
1122
+ },
1123
+ {
1124
+ "epoch": 3.31,
1125
+ "learning_rate": 1.8724696356275305e-05,
1126
+ "loss": 0.3685,
1127
+ "step": 1820
1128
+ },
1129
+ {
1130
+ "epoch": 3.33,
1131
+ "learning_rate": 1.8522267206477732e-05,
1132
+ "loss": 0.3582,
1133
+ "step": 1830
1134
+ },
1135
+ {
1136
+ "epoch": 3.35,
1137
+ "learning_rate": 1.8319838056680163e-05,
1138
+ "loss": 0.3785,
1139
+ "step": 1840
1140
+ },
1141
+ {
1142
+ "epoch": 3.37,
1143
+ "learning_rate": 1.811740890688259e-05,
1144
+ "loss": 0.3758,
1145
+ "step": 1850
1146
+ },
1147
+ {
1148
+ "epoch": 3.39,
1149
+ "learning_rate": 1.791497975708502e-05,
1150
+ "loss": 0.386,
1151
+ "step": 1860
1152
+ },
1153
+ {
1154
+ "epoch": 3.4,
1155
+ "learning_rate": 1.771255060728745e-05,
1156
+ "loss": 0.3565,
1157
+ "step": 1870
1158
+ },
1159
+ {
1160
+ "epoch": 3.42,
1161
+ "learning_rate": 1.751012145748988e-05,
1162
+ "loss": 0.3423,
1163
+ "step": 1880
1164
+ },
1165
+ {
1166
+ "epoch": 3.44,
1167
+ "learning_rate": 1.730769230769231e-05,
1168
+ "loss": 0.3859,
1169
+ "step": 1890
1170
+ },
1171
+ {
1172
+ "epoch": 3.46,
1173
+ "learning_rate": 1.7105263157894737e-05,
1174
+ "loss": 0.3606,
1175
+ "step": 1900
1176
+ },
1177
+ {
1178
+ "epoch": 3.48,
1179
+ "learning_rate": 1.6902834008097167e-05,
1180
+ "loss": 0.3829,
1181
+ "step": 1910
1182
+ },
1183
+ {
1184
+ "epoch": 3.5,
1185
+ "learning_rate": 1.6700404858299595e-05,
1186
+ "loss": 0.3409,
1187
+ "step": 1920
1188
+ },
1189
+ {
1190
+ "epoch": 3.51,
1191
+ "learning_rate": 1.6497975708502025e-05,
1192
+ "loss": 0.358,
1193
+ "step": 1930
1194
+ },
1195
+ {
1196
+ "epoch": 3.53,
1197
+ "learning_rate": 1.6295546558704456e-05,
1198
+ "loss": 0.3182,
1199
+ "step": 1940
1200
+ },
1201
+ {
1202
+ "epoch": 3.55,
1203
+ "learning_rate": 1.6093117408906883e-05,
1204
+ "loss": 0.3595,
1205
+ "step": 1950
1206
+ },
1207
+ {
1208
+ "epoch": 3.57,
1209
+ "learning_rate": 1.5890688259109314e-05,
1210
+ "loss": 0.3536,
1211
+ "step": 1960
1212
+ },
1213
+ {
1214
+ "epoch": 3.59,
1215
+ "learning_rate": 1.568825910931174e-05,
1216
+ "loss": 0.3818,
1217
+ "step": 1970
1218
+ },
1219
+ {
1220
+ "epoch": 3.6,
1221
+ "learning_rate": 1.548582995951417e-05,
1222
+ "loss": 0.3401,
1223
+ "step": 1980
1224
+ },
1225
+ {
1226
+ "epoch": 3.62,
1227
+ "learning_rate": 1.52834008097166e-05,
1228
+ "loss": 0.3554,
1229
+ "step": 1990
1230
+ },
1231
+ {
1232
+ "epoch": 3.64,
1233
+ "learning_rate": 1.508097165991903e-05,
1234
+ "loss": 0.3465,
1235
+ "step": 2000
1236
+ },
1237
+ {
1238
+ "epoch": 3.66,
1239
+ "learning_rate": 1.4878542510121457e-05,
1240
+ "loss": 0.3482,
1241
+ "step": 2010
1242
+ },
1243
+ {
1244
+ "epoch": 3.68,
1245
+ "learning_rate": 1.4676113360323888e-05,
1246
+ "loss": 0.3492,
1247
+ "step": 2020
1248
+ },
1249
+ {
1250
+ "epoch": 3.7,
1251
+ "learning_rate": 1.4473684210526317e-05,
1252
+ "loss": 0.3366,
1253
+ "step": 2030
1254
+ },
1255
+ {
1256
+ "epoch": 3.71,
1257
+ "learning_rate": 1.4271255060728744e-05,
1258
+ "loss": 0.3392,
1259
+ "step": 2040
1260
+ },
1261
+ {
1262
+ "epoch": 3.73,
1263
+ "learning_rate": 1.4068825910931175e-05,
1264
+ "loss": 0.3593,
1265
+ "step": 2050
1266
+ },
1267
+ {
1268
+ "epoch": 3.75,
1269
+ "learning_rate": 1.3866396761133604e-05,
1270
+ "loss": 0.3961,
1271
+ "step": 2060
1272
+ },
1273
+ {
1274
+ "epoch": 3.77,
1275
+ "learning_rate": 1.3663967611336034e-05,
1276
+ "loss": 0.3996,
1277
+ "step": 2070
1278
+ },
1279
+ {
1280
+ "epoch": 3.79,
1281
+ "learning_rate": 1.3461538461538462e-05,
1282
+ "loss": 0.3178,
1283
+ "step": 2080
1284
+ },
1285
+ {
1286
+ "epoch": 3.81,
1287
+ "learning_rate": 1.3259109311740892e-05,
1288
+ "loss": 0.3641,
1289
+ "step": 2090
1290
+ },
1291
+ {
1292
+ "epoch": 3.82,
1293
+ "learning_rate": 1.3056680161943321e-05,
1294
+ "loss": 0.3176,
1295
+ "step": 2100
1296
+ },
1297
+ {
1298
+ "epoch": 3.84,
1299
+ "learning_rate": 1.2854251012145749e-05,
1300
+ "loss": 0.3189,
1301
+ "step": 2110
1302
+ },
1303
+ {
1304
+ "epoch": 3.86,
1305
+ "learning_rate": 1.265182186234818e-05,
1306
+ "loss": 0.3663,
1307
+ "step": 2120
1308
+ },
1309
+ {
1310
+ "epoch": 3.88,
1311
+ "learning_rate": 1.2449392712550607e-05,
1312
+ "loss": 0.3105,
1313
+ "step": 2130
1314
+ },
1315
+ {
1316
+ "epoch": 3.9,
1317
+ "learning_rate": 1.2246963562753037e-05,
1318
+ "loss": 0.3479,
1319
+ "step": 2140
1320
+ },
1321
+ {
1322
+ "epoch": 3.91,
1323
+ "learning_rate": 1.2044534412955466e-05,
1324
+ "loss": 0.3301,
1325
+ "step": 2150
1326
+ },
1327
+ {
1328
+ "epoch": 3.93,
1329
+ "learning_rate": 1.1842105263157895e-05,
1330
+ "loss": 0.3344,
1331
+ "step": 2160
1332
+ },
1333
+ {
1334
+ "epoch": 3.95,
1335
+ "learning_rate": 1.1639676113360324e-05,
1336
+ "loss": 0.3169,
1337
+ "step": 2170
1338
+ },
1339
+ {
1340
+ "epoch": 3.97,
1341
+ "learning_rate": 1.1437246963562753e-05,
1342
+ "loss": 0.3486,
1343
+ "step": 2180
1344
+ },
1345
+ {
1346
+ "epoch": 3.99,
1347
+ "learning_rate": 1.1234817813765184e-05,
1348
+ "loss": 0.3551,
1349
+ "step": 2190
1350
+ },
1351
+ {
1352
+ "epoch": 4.0,
1353
+ "eval_accuracy": 0.9622695196904165,
1354
+ "eval_loss": 0.14936527609825134,
1355
+ "eval_runtime": 112.1506,
1356
+ "eval_samples_per_second": 156.682,
1357
+ "eval_steps_per_second": 4.904,
1358
+ "step": 2197
1359
+ },
1360
+ {
1361
+ "epoch": 4.01,
1362
+ "learning_rate": 1.1032388663967611e-05,
1363
+ "loss": 0.3307,
1364
+ "step": 2200
1365
+ },
1366
+ {
1367
+ "epoch": 4.02,
1368
+ "learning_rate": 1.082995951417004e-05,
1369
+ "loss": 0.3035,
1370
+ "step": 2210
1371
+ },
1372
+ {
1373
+ "epoch": 4.04,
1374
+ "learning_rate": 1.062753036437247e-05,
1375
+ "loss": 0.3192,
1376
+ "step": 2220
1377
+ },
1378
+ {
1379
+ "epoch": 4.06,
1380
+ "learning_rate": 1.04251012145749e-05,
1381
+ "loss": 0.3357,
1382
+ "step": 2230
1383
+ },
1384
+ {
1385
+ "epoch": 4.08,
1386
+ "learning_rate": 1.0222672064777327e-05,
1387
+ "loss": 0.3081,
1388
+ "step": 2240
1389
+ },
1390
+ {
1391
+ "epoch": 4.1,
1392
+ "learning_rate": 1.0020242914979758e-05,
1393
+ "loss": 0.3343,
1394
+ "step": 2250
1395
+ },
1396
+ {
1397
+ "epoch": 4.11,
1398
+ "learning_rate": 9.817813765182187e-06,
1399
+ "loss": 0.3438,
1400
+ "step": 2260
1401
+ },
1402
+ {
1403
+ "epoch": 4.13,
1404
+ "learning_rate": 9.615384615384616e-06,
1405
+ "loss": 0.2939,
1406
+ "step": 2270
1407
+ },
1408
+ {
1409
+ "epoch": 4.15,
1410
+ "learning_rate": 9.412955465587045e-06,
1411
+ "loss": 0.2954,
1412
+ "step": 2280
1413
+ },
1414
+ {
1415
+ "epoch": 4.17,
1416
+ "learning_rate": 9.210526315789474e-06,
1417
+ "loss": 0.3206,
1418
+ "step": 2290
1419
+ },
1420
+ {
1421
+ "epoch": 4.19,
1422
+ "learning_rate": 9.008097165991904e-06,
1423
+ "loss": 0.3116,
1424
+ "step": 2300
1425
+ },
1426
+ {
1427
+ "epoch": 4.21,
1428
+ "learning_rate": 8.805668016194332e-06,
1429
+ "loss": 0.3201,
1430
+ "step": 2310
1431
+ },
1432
+ {
1433
+ "epoch": 4.22,
1434
+ "learning_rate": 8.60323886639676e-06,
1435
+ "loss": 0.3439,
1436
+ "step": 2320
1437
+ },
1438
+ {
1439
+ "epoch": 4.24,
1440
+ "learning_rate": 8.400809716599191e-06,
1441
+ "loss": 0.3503,
1442
+ "step": 2330
1443
+ },
1444
+ {
1445
+ "epoch": 4.26,
1446
+ "learning_rate": 8.19838056680162e-06,
1447
+ "loss": 0.317,
1448
+ "step": 2340
1449
+ },
1450
+ {
1451
+ "epoch": 4.28,
1452
+ "learning_rate": 7.99595141700405e-06,
1453
+ "loss": 0.3113,
1454
+ "step": 2350
1455
+ },
1456
+ {
1457
+ "epoch": 4.3,
1458
+ "learning_rate": 7.793522267206478e-06,
1459
+ "loss": 0.311,
1460
+ "step": 2360
1461
+ },
1462
+ {
1463
+ "epoch": 4.31,
1464
+ "learning_rate": 7.591093117408906e-06,
1465
+ "loss": 0.3083,
1466
+ "step": 2370
1467
+ },
1468
+ {
1469
+ "epoch": 4.33,
1470
+ "learning_rate": 7.388663967611337e-06,
1471
+ "loss": 0.3165,
1472
+ "step": 2380
1473
+ },
1474
+ {
1475
+ "epoch": 4.35,
1476
+ "learning_rate": 7.186234817813765e-06,
1477
+ "loss": 0.3547,
1478
+ "step": 2390
1479
+ },
1480
+ {
1481
+ "epoch": 4.37,
1482
+ "learning_rate": 6.983805668016195e-06,
1483
+ "loss": 0.3071,
1484
+ "step": 2400
1485
+ },
1486
+ {
1487
+ "epoch": 4.39,
1488
+ "learning_rate": 6.781376518218624e-06,
1489
+ "loss": 0.3028,
1490
+ "step": 2410
1491
+ },
1492
+ {
1493
+ "epoch": 4.41,
1494
+ "learning_rate": 6.578947368421053e-06,
1495
+ "loss": 0.3215,
1496
+ "step": 2420
1497
+ },
1498
+ {
1499
+ "epoch": 4.42,
1500
+ "learning_rate": 6.376518218623483e-06,
1501
+ "loss": 0.3259,
1502
+ "step": 2430
1503
+ },
1504
+ {
1505
+ "epoch": 4.44,
1506
+ "learning_rate": 6.174089068825911e-06,
1507
+ "loss": 0.3515,
1508
+ "step": 2440
1509
+ },
1510
+ {
1511
+ "epoch": 4.46,
1512
+ "learning_rate": 5.971659919028341e-06,
1513
+ "loss": 0.3158,
1514
+ "step": 2450
1515
+ },
1516
+ {
1517
+ "epoch": 4.48,
1518
+ "learning_rate": 5.76923076923077e-06,
1519
+ "loss": 0.3067,
1520
+ "step": 2460
1521
+ },
1522
+ {
1523
+ "epoch": 4.5,
1524
+ "learning_rate": 5.566801619433199e-06,
1525
+ "loss": 0.324,
1526
+ "step": 2470
1527
+ },
1528
+ {
1529
+ "epoch": 4.52,
1530
+ "learning_rate": 5.364372469635628e-06,
1531
+ "loss": 0.3271,
1532
+ "step": 2480
1533
+ },
1534
+ {
1535
+ "epoch": 4.53,
1536
+ "learning_rate": 5.161943319838057e-06,
1537
+ "loss": 0.3367,
1538
+ "step": 2490
1539
+ },
1540
+ {
1541
+ "epoch": 4.55,
1542
+ "learning_rate": 4.9595141700404865e-06,
1543
+ "loss": 0.3166,
1544
+ "step": 2500
1545
+ },
1546
+ {
1547
+ "epoch": 4.57,
1548
+ "learning_rate": 4.757085020242915e-06,
1549
+ "loss": 0.3264,
1550
+ "step": 2510
1551
+ },
1552
+ {
1553
+ "epoch": 4.59,
1554
+ "learning_rate": 4.5546558704453445e-06,
1555
+ "loss": 0.3129,
1556
+ "step": 2520
1557
+ },
1558
+ {
1559
+ "epoch": 4.61,
1560
+ "learning_rate": 4.3522267206477735e-06,
1561
+ "loss": 0.3114,
1562
+ "step": 2530
1563
+ },
1564
+ {
1565
+ "epoch": 4.62,
1566
+ "learning_rate": 4.149797570850203e-06,
1567
+ "loss": 0.2751,
1568
+ "step": 2540
1569
+ },
1570
+ {
1571
+ "epoch": 4.64,
1572
+ "learning_rate": 3.9473684210526315e-06,
1573
+ "loss": 0.3191,
1574
+ "step": 2550
1575
+ },
1576
+ {
1577
+ "epoch": 4.66,
1578
+ "learning_rate": 3.744939271255061e-06,
1579
+ "loss": 0.3171,
1580
+ "step": 2560
1581
+ },
1582
+ {
1583
+ "epoch": 4.68,
1584
+ "learning_rate": 3.5425101214574903e-06,
1585
+ "loss": 0.2981,
1586
+ "step": 2570
1587
+ },
1588
+ {
1589
+ "epoch": 4.7,
1590
+ "learning_rate": 3.3400809716599197e-06,
1591
+ "loss": 0.3169,
1592
+ "step": 2580
1593
+ },
1594
+ {
1595
+ "epoch": 4.72,
1596
+ "learning_rate": 3.1376518218623482e-06,
1597
+ "loss": 0.304,
1598
+ "step": 2590
1599
+ },
1600
+ {
1601
+ "epoch": 4.73,
1602
+ "learning_rate": 2.9352226720647772e-06,
1603
+ "loss": 0.3021,
1604
+ "step": 2600
1605
+ },
1606
+ {
1607
+ "epoch": 4.75,
1608
+ "learning_rate": 2.7327935222672066e-06,
1609
+ "loss": 0.3106,
1610
+ "step": 2610
1611
+ },
1612
+ {
1613
+ "epoch": 4.77,
1614
+ "learning_rate": 2.5303643724696356e-06,
1615
+ "loss": 0.3066,
1616
+ "step": 2620
1617
+ },
1618
+ {
1619
+ "epoch": 4.79,
1620
+ "learning_rate": 2.327935222672065e-06,
1621
+ "loss": 0.3117,
1622
+ "step": 2630
1623
+ },
1624
+ {
1625
+ "epoch": 4.81,
1626
+ "learning_rate": 2.125506072874494e-06,
1627
+ "loss": 0.3079,
1628
+ "step": 2640
1629
+ },
1630
+ {
1631
+ "epoch": 4.82,
1632
+ "learning_rate": 1.9230769230769234e-06,
1633
+ "loss": 0.3316,
1634
+ "step": 2650
1635
+ },
1636
+ {
1637
+ "epoch": 4.84,
1638
+ "learning_rate": 1.7206477732793522e-06,
1639
+ "loss": 0.3103,
1640
+ "step": 2660
1641
+ },
1642
+ {
1643
+ "epoch": 4.86,
1644
+ "learning_rate": 1.5182186234817814e-06,
1645
+ "loss": 0.3034,
1646
+ "step": 2670
1647
+ },
1648
+ {
1649
+ "epoch": 4.88,
1650
+ "learning_rate": 1.3157894736842106e-06,
1651
+ "loss": 0.294,
1652
+ "step": 2680
1653
+ },
1654
+ {
1655
+ "epoch": 4.9,
1656
+ "learning_rate": 1.1133603238866398e-06,
1657
+ "loss": 0.3151,
1658
+ "step": 2690
1659
+ },
1660
+ {
1661
+ "epoch": 4.92,
1662
+ "learning_rate": 9.109311740890688e-07,
1663
+ "loss": 0.3544,
1664
+ "step": 2700
1665
+ },
1666
+ {
1667
+ "epoch": 4.93,
1668
+ "learning_rate": 7.08502024291498e-07,
1669
+ "loss": 0.3365,
1670
+ "step": 2710
1671
+ },
1672
+ {
1673
+ "epoch": 4.95,
1674
+ "learning_rate": 5.060728744939271e-07,
1675
+ "loss": 0.3181,
1676
+ "step": 2720
1677
+ },
1678
+ {
1679
+ "epoch": 4.97,
1680
+ "learning_rate": 3.036437246963563e-07,
1681
+ "loss": 0.303,
1682
+ "step": 2730
1683
+ },
1684
+ {
1685
+ "epoch": 4.99,
1686
+ "learning_rate": 1.0121457489878543e-07,
1687
+ "loss": 0.3174,
1688
+ "step": 2740
1689
+ },
1690
+ {
1691
+ "epoch": 5.0,
1692
+ "eval_accuracy": 0.9624402458456636,
1693
+ "eval_loss": 0.1446385681629181,
1694
+ "eval_runtime": 113.1571,
1695
+ "eval_samples_per_second": 155.288,
1696
+ "eval_steps_per_second": 4.86,
1697
+ "step": 2745
1698
+ },
1699
+ {
1700
+ "epoch": 5.0,
1701
+ "step": 2745,
1702
+ "total_flos": 7.483912529986142e+18,
1703
+ "train_loss": 1.0602939221811207,
1704
+ "train_runtime": 5306.8618,
1705
+ "train_samples_per_second": 66.23,
1706
+ "train_steps_per_second": 0.517
1707
+ }
1708
+ ],
1709
+ "max_steps": 2745,
1710
+ "num_train_epochs": 5,
1711
+ "total_flos": 7.483912529986142e+18,
1712
+ "trial_name": null,
1713
+ "trial_params": null
1714
+ }