ShengdingHu commited on
Commit
a9caf40
1 Parent(s): a773a88

Training in progress, step 200

Browse files
all_results.json CHANGED
@@ -1,20 +1,20 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.5091743119266054,
4
  "eval_average_metrics": 60.099999999999994,
5
- "eval_loss": 1.2113580703735352,
6
- "eval_runtime": 1.554,
7
  "eval_samples": 872,
8
- "eval_samples_per_second": 561.145,
9
- "eval_steps_per_second": 18.018,
10
  "test_accuracy": 58.142201834862384,
11
  "test_average_metrics": 58.142201834862384,
12
  "test_loss": 0.2752912938594818,
13
  "test_runtime": 3.1391,
14
  "test_samples_per_second": 277.783,
15
- "train_loss": 1.4194242838348365,
16
- "train_runtime": 1125.0881,
17
  "train_samples": 67349,
18
- "train_samples_per_second": 179.583,
19
- "train_steps_per_second": 5.613
20
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.5172018348623854,
4
  "eval_average_metrics": 60.099999999999994,
5
+ "eval_loss": 3.1630539894104004,
6
+ "eval_runtime": 12.2812,
7
  "eval_samples": 872,
8
+ "eval_samples_per_second": 71.003,
9
+ "eval_steps_per_second": 8.875,
10
  "test_accuracy": 58.142201834862384,
11
  "test_average_metrics": 58.142201834862384,
12
  "test_loss": 0.2752912938594818,
13
  "test_runtime": 3.1391,
14
  "test_samples_per_second": 277.783,
15
+ "train_loss": 1.708119561667774,
16
+ "train_runtime": 7791.0638,
17
  "train_samples": 67349,
18
+ "train_samples_per_second": 25.933,
19
+ "train_steps_per_second": 3.242
20
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.5091743119266054,
4
- "eval_loss": 1.2113580703735352,
5
- "eval_runtime": 1.554,
6
  "eval_samples": 872,
7
- "eval_samples_per_second": 561.145,
8
- "eval_steps_per_second": 18.018
9
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.5172018348623854,
4
+ "eval_loss": 3.1630539894104004,
5
+ "eval_runtime": 12.2812,
6
  "eval_samples": 872,
7
+ "eval_samples_per_second": 71.003,
8
+ "eval_steps_per_second": 8.875
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:982eb6e9f0b5f201b67d112c1121ff20d4ac3fbb58a822987f9ca99286cb10f2
3
  size 655267
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13647882dd4902cea8e1390cc506a6f287431443c812b5ffb2b1cd6082e4ef4b
3
  size 655267
runs/Feb04_19-15-19_node1/events.out.tfevents.1643973374.node1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c3e11e434c5e46a6bf6b2f49af5c596ad107f74ab747e7617e74147ed2f927c
3
- size 52265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa340a9a5668b5f63411c9751580f8f74eadad5e3235657b944868bd05f35566
3
+ size 52954
runs/Feb04_19-15-19_node1/events.out.tfevents.1643981177.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf713f93392ed1124e2a1aacbb380172a8d8996d1a6204c8c1f2c04dcf0ced9
3
+ size 369
runs/Feb04_22-28-59_node1/1643985001.4569914/events.out.tfevents.1643985001.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc00f5afca30d553498c1b28cb4c4f99f5dcf79cc5cd4d5e367fac0c88da9d89
3
+ size 4618
runs/Feb04_22-28-59_node1/events.out.tfevents.1643985001.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55416cadd322e8efc494d0fcd725a1b41caf97582de6c1a35ec9215e98a430d1
3
+ size 3725
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 1.4194242838348365,
4
- "train_runtime": 1125.0881,
5
  "train_samples": 67349,
6
- "train_samples_per_second": 179.583,
7
- "train_steps_per_second": 5.613
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 1.708119561667774,
4
+ "train_runtime": 7791.0638,
5
  "train_samples": 67349,
6
+ "train_samples_per_second": 25.933,
7
+ "train_steps_per_second": 3.242
8
  }
trainer_state.json CHANGED
@@ -1,376 +1,1459 @@
1
  {
2
- "best_metric": 0.5091743119266054,
3
- "best_model_checkpoint": "outputs/soft_prompt/roberta-base/sst2/checkpoint-200",
4
  "epoch": 3.0,
5
- "global_step": 6315,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.1,
12
  "eval_accuracy": 0.5091743119266054,
13
- "eval_loss": 1.2113580703735352,
14
- "eval_runtime": 1.5734,
15
- "eval_samples_per_second": 554.211,
16
- "eval_steps_per_second": 17.796,
17
  "step": 200
18
  },
19
  {
20
- "epoch": 0.19,
21
- "eval_accuracy": 0.5091743119266054,
22
- "eval_loss": 1.1833394765853882,
23
- "eval_runtime": 1.3274,
24
- "eval_samples_per_second": 656.934,
25
- "eval_steps_per_second": 21.094,
26
  "step": 400
27
  },
28
  {
29
- "epoch": 0.24,
30
- "learning_rate": 0.027624703087885987,
31
- "loss": 1.7048,
32
  "step": 500
33
  },
34
  {
35
- "epoch": 0.29,
36
  "eval_accuracy": 0.5091743119266054,
37
- "eval_loss": 1.4068197011947632,
38
- "eval_runtime": 1.6024,
39
- "eval_samples_per_second": 544.198,
40
- "eval_steps_per_second": 17.474,
41
  "step": 600
42
  },
43
  {
44
- "epoch": 0.38,
45
  "eval_accuracy": 0.5091743119266054,
46
- "eval_loss": 1.2358722686767578,
47
- "eval_runtime": 1.3312,
48
- "eval_samples_per_second": 655.031,
49
- "eval_steps_per_second": 21.033,
50
  "step": 800
51
  },
52
  {
53
- "epoch": 0.48,
54
- "learning_rate": 0.02524940617577197,
55
- "loss": 1.4721,
56
  "step": 1000
57
  },
58
  {
59
- "epoch": 0.48,
60
  "eval_accuracy": 0.4908256880733945,
61
- "eval_loss": 1.5192540884017944,
62
- "eval_runtime": 1.4576,
63
- "eval_samples_per_second": 598.233,
64
- "eval_steps_per_second": 19.209,
65
  "step": 1000
66
  },
67
  {
68
- "epoch": 0.57,
69
- "eval_accuracy": 0.4908256880733945,
70
- "eval_loss": 1.0336543321609497,
71
- "eval_runtime": 1.7394,
72
- "eval_samples_per_second": 501.315,
73
- "eval_steps_per_second": 16.097,
74
  "step": 1200
75
  },
76
  {
77
- "epoch": 0.67,
78
- "eval_accuracy": 0.5091743119266054,
79
- "eval_loss": 2.6292548179626465,
80
- "eval_runtime": 1.5911,
81
- "eval_samples_per_second": 548.047,
82
- "eval_steps_per_second": 17.598,
83
  "step": 1400
84
  },
85
  {
86
- "epoch": 0.71,
87
- "learning_rate": 0.022874109263657957,
88
- "loss": 1.821,
89
  "step": 1500
90
  },
91
  {
92
- "epoch": 0.76,
93
  "eval_accuracy": 0.4908256880733945,
94
- "eval_loss": 1.309380054473877,
95
- "eval_runtime": 1.4381,
96
- "eval_samples_per_second": 606.369,
97
- "eval_steps_per_second": 19.471,
98
  "step": 1600
99
  },
100
  {
101
- "epoch": 0.86,
102
  "eval_accuracy": 0.4908256880733945,
103
- "eval_loss": 1.0032501220703125,
104
- "eval_runtime": 1.3929,
105
- "eval_samples_per_second": 626.051,
106
- "eval_steps_per_second": 20.103,
107
  "step": 1800
108
  },
109
  {
110
- "epoch": 0.95,
111
- "learning_rate": 0.02049881235154394,
112
- "loss": 1.6669,
113
  "step": 2000
114
  },
115
  {
116
- "epoch": 0.95,
117
  "eval_accuracy": 0.5091743119266054,
118
- "eval_loss": 2.3615148067474365,
119
- "eval_runtime": 1.4549,
120
- "eval_samples_per_second": 599.336,
121
- "eval_steps_per_second": 19.245,
122
  "step": 2000
123
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
124
  {
125
  "epoch": 1.05,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126
  "eval_accuracy": 0.4908256880733945,
127
- "eval_loss": 1.1986268758773804,
128
- "eval_runtime": 1.518,
129
- "eval_samples_per_second": 574.444,
130
- "eval_steps_per_second": 18.445,
131
- "step": 2200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
132
  },
133
  {
134
  "epoch": 1.14,
135
  "eval_accuracy": 0.4908256880733945,
136
- "eval_loss": 0.9300673007965088,
137
- "eval_runtime": 1.4024,
138
- "eval_samples_per_second": 621.772,
139
- "eval_steps_per_second": 19.965,
140
- "step": 2400
 
 
 
 
 
 
 
 
 
141
  },
142
  {
143
  "epoch": 1.19,
144
- "learning_rate": 0.01812351543942993,
145
- "loss": 1.5726,
146
- "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  },
148
  {
149
  "epoch": 1.24,
150
  "eval_accuracy": 0.4908256880733945,
151
- "eval_loss": 1.1378525495529175,
152
- "eval_runtime": 1.3734,
153
- "eval_samples_per_second": 634.927,
154
- "eval_steps_per_second": 20.388,
155
- "step": 2600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
156
  },
157
  {
158
  "epoch": 1.33,
159
  "eval_accuracy": 0.4908256880733945,
160
- "eval_loss": 0.8935280442237854,
161
- "eval_runtime": 1.4758,
162
- "eval_samples_per_second": 590.85,
163
- "eval_steps_per_second": 18.972,
164
- "step": 2800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165
  },
166
  {
167
  "epoch": 1.43,
168
- "learning_rate": 0.015748218527315914,
169
- "loss": 2.2264,
170
- "step": 3000
171
  },
172
  {
173
  "epoch": 1.43,
 
 
 
 
 
 
 
 
 
174
  "eval_accuracy": 0.4908256880733945,
175
- "eval_loss": 0.8003481030464172,
176
- "eval_runtime": 1.4567,
177
- "eval_samples_per_second": 598.601,
178
- "eval_steps_per_second": 19.221,
179
- "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
180
  },
181
  {
182
  "epoch": 1.52,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  "eval_accuracy": 0.5091743119266054,
184
- "eval_loss": 1.1951367855072021,
185
- "eval_runtime": 1.2323,
186
- "eval_samples_per_second": 707.612,
187
- "eval_steps_per_second": 22.721,
188
- "step": 3200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  },
190
  {
191
  "epoch": 1.62,
192
  "eval_accuracy": 0.5091743119266054,
193
- "eval_loss": 1.1763222217559814,
194
- "eval_runtime": 1.3939,
195
- "eval_samples_per_second": 625.563,
196
- "eval_steps_per_second": 20.087,
197
- "step": 3400
 
 
 
 
 
 
 
 
 
198
  },
199
  {
200
  "epoch": 1.66,
201
- "learning_rate": 0.0133729216152019,
202
- "loss": 1.5653,
203
- "step": 3500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
204
  },
205
  {
206
  "epoch": 1.71,
207
  "eval_accuracy": 0.5091743119266054,
208
- "eval_loss": 1.1043964624404907,
209
- "eval_runtime": 1.3672,
210
- "eval_samples_per_second": 637.781,
211
- "eval_steps_per_second": 20.479,
212
- "step": 3600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
213
  },
214
  {
215
  "epoch": 1.81,
216
  "eval_accuracy": 0.4908256880733945,
217
- "eval_loss": 2.281111717224121,
218
- "eval_runtime": 1.6251,
219
- "eval_samples_per_second": 536.597,
220
- "eval_steps_per_second": 17.23,
221
- "step": 3800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
222
  },
223
  {
224
  "epoch": 1.9,
225
- "learning_rate": 0.010997624703087886,
226
- "loss": 1.3918,
227
- "step": 4000
228
  },
229
  {
230
  "epoch": 1.9,
231
  "eval_accuracy": 0.4908256880733945,
232
- "eval_loss": 1.7353538274765015,
233
- "eval_runtime": 1.3011,
234
- "eval_samples_per_second": 670.193,
235
- "eval_steps_per_second": 21.52,
236
- "step": 4000
237
  },
238
  {
239
- "epoch": 2.0,
240
  "eval_accuracy": 0.5091743119266054,
241
- "eval_loss": 2.1966099739074707,
242
- "eval_runtime": 1.3231,
243
- "eval_samples_per_second": 659.044,
244
- "eval_steps_per_second": 21.162,
245
- "step": 4200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
246
  },
247
  {
248
  "epoch": 2.09,
249
  "eval_accuracy": 0.5091743119266054,
250
- "eval_loss": 0.9623039364814758,
251
- "eval_runtime": 1.428,
252
- "eval_samples_per_second": 610.649,
253
- "eval_steps_per_second": 19.608,
254
- "step": 4400
 
 
 
 
 
 
 
 
 
255
  },
256
  {
257
  "epoch": 2.14,
258
- "learning_rate": 0.008622327790973872,
259
- "loss": 1.3465,
260
- "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
261
  },
262
  {
263
  "epoch": 2.19,
264
  "eval_accuracy": 0.5091743119266054,
265
- "eval_loss": 0.7837328314781189,
266
- "eval_runtime": 1.6722,
267
- "eval_samples_per_second": 521.453,
268
- "eval_steps_per_second": 16.744,
269
- "step": 4600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
270
  },
271
  {
272
  "epoch": 2.28,
 
 
 
 
 
 
 
 
 
273
  "eval_accuracy": 0.4908256880733945,
274
- "eval_loss": 0.6955246329307556,
275
- "eval_runtime": 1.5518,
276
- "eval_samples_per_second": 561.939,
277
- "eval_steps_per_second": 18.044,
278
- "step": 4800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  },
280
  {
281
  "epoch": 2.38,
282
- "learning_rate": 0.006247030878859857,
283
- "loss": 1.0154,
284
- "step": 5000
285
  },
286
  {
287
  "epoch": 2.38,
 
 
 
 
 
 
 
 
 
288
  "eval_accuracy": 0.5091743119266054,
289
- "eval_loss": 1.5205951929092407,
290
- "eval_runtime": 1.4264,
291
- "eval_samples_per_second": 611.325,
292
- "eval_steps_per_second": 19.63,
293
- "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
294
  },
295
  {
296
  "epoch": 2.47,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
297
  "eval_accuracy": 0.4908256880733945,
298
- "eval_loss": 1.8486016988754272,
299
- "eval_runtime": 1.5808,
300
- "eval_samples_per_second": 551.633,
301
- "eval_steps_per_second": 17.713,
302
- "step": 5200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
303
  },
304
  {
305
  "epoch": 2.57,
 
 
 
 
 
 
 
 
 
306
  "eval_accuracy": 0.5091743119266054,
307
- "eval_loss": 0.806239128112793,
308
- "eval_runtime": 1.0228,
309
- "eval_samples_per_second": 852.573,
310
- "eval_steps_per_second": 27.376,
311
- "step": 5400
312
  },
313
  {
314
  "epoch": 2.61,
315
- "learning_rate": 0.003871733966745843,
316
- "loss": 0.892,
317
- "step": 5500
318
  },
319
  {
320
- "epoch": 2.66,
321
  "eval_accuracy": 0.4908256880733945,
322
- "eval_loss": 0.7133888602256775,
323
- "eval_runtime": 1.4851,
324
- "eval_samples_per_second": 587.161,
325
- "eval_steps_per_second": 18.854,
326
- "step": 5600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
327
  },
328
  {
329
  "epoch": 2.76,
330
  "eval_accuracy": 0.5091743119266054,
331
- "eval_loss": 0.8787677884101868,
332
- "eval_runtime": 1.0808,
333
- "eval_samples_per_second": 806.785,
334
- "eval_steps_per_second": 25.906,
335
- "step": 5800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
336
  },
337
  {
338
  "epoch": 2.85,
339
- "learning_rate": 0.001496437054631829,
340
- "loss": 0.784,
341
- "step": 6000
342
  },
343
  {
344
  "epoch": 2.85,
 
 
 
 
 
 
 
 
 
345
  "eval_accuracy": 0.4908256880733945,
346
- "eval_loss": 0.8426281809806824,
347
- "eval_runtime": 1.6584,
348
- "eval_samples_per_second": 525.823,
349
- "eval_steps_per_second": 16.884,
350
- "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351
  },
352
  {
353
  "epoch": 2.95,
354
  "eval_accuracy": 0.5091743119266054,
355
- "eval_loss": 0.8049508333206177,
356
- "eval_runtime": 1.4457,
357
- "eval_samples_per_second": 603.185,
358
- "eval_steps_per_second": 19.368,
359
- "step": 6200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360
  },
361
  {
362
  "epoch": 3.0,
363
- "step": 6315,
364
- "total_flos": 1.330211706755328e+16,
365
- "train_loss": 1.4194242838348365,
366
- "train_runtime": 1125.0881,
367
- "train_samples_per_second": 179.583,
368
- "train_steps_per_second": 5.613
369
  }
370
  ],
371
- "max_steps": 6315,
372
  "num_train_epochs": 3,
373
- "total_flos": 1.330211706755328e+16,
374
  "trial_name": null,
375
  "trial_params": null
376
  }
 
1
  {
2
+ "best_metric": 0.5172018348623854,
3
+ "best_model_checkpoint": "outputs/soft_prompt/deberta-v2-xlarge/sst2/checkpoint-3400",
4
  "epoch": 3.0,
5
+ "global_step": 25257,
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
  "eval_accuracy": 0.5091743119266054,
13
+ "eval_loss": 2.831559658050537,
14
+ "eval_runtime": 12.4014,
15
+ "eval_samples_per_second": 70.315,
16
+ "eval_steps_per_second": 8.789,
17
  "step": 200
18
  },
19
  {
20
+ "epoch": 0.05,
21
+ "eval_accuracy": 0.4908256880733945,
22
+ "eval_loss": 0.7252020835876465,
23
+ "eval_runtime": 12.5411,
24
+ "eval_samples_per_second": 69.532,
25
+ "eval_steps_per_second": 8.691,
26
  "step": 400
27
  },
28
  {
29
+ "epoch": 0.06,
30
+ "learning_rate": 0.0294061052381518,
31
+ "loss": 2.7746,
32
  "step": 500
33
  },
34
  {
35
+ "epoch": 0.07,
36
  "eval_accuracy": 0.5091743119266054,
37
+ "eval_loss": 6.318162441253662,
38
+ "eval_runtime": 12.2524,
39
+ "eval_samples_per_second": 71.17,
40
+ "eval_steps_per_second": 8.896,
41
  "step": 600
42
  },
43
  {
44
+ "epoch": 0.1,
45
  "eval_accuracy": 0.5091743119266054,
46
+ "eval_loss": 1.9581830501556396,
47
+ "eval_runtime": 13.2254,
48
+ "eval_samples_per_second": 65.934,
49
+ "eval_steps_per_second": 8.242,
50
  "step": 800
51
  },
52
  {
53
+ "epoch": 0.12,
54
+ "learning_rate": 0.0288122104763036,
55
+ "loss": 2.8668,
56
  "step": 1000
57
  },
58
  {
59
+ "epoch": 0.12,
60
  "eval_accuracy": 0.4908256880733945,
61
+ "eval_loss": 0.97942715883255,
62
+ "eval_runtime": 12.2204,
63
+ "eval_samples_per_second": 71.356,
64
+ "eval_steps_per_second": 8.92,
65
  "step": 1000
66
  },
67
  {
68
+ "epoch": 0.14,
69
+ "eval_accuracy": 0.5091743119266054,
70
+ "eval_loss": 9.121758460998535,
71
+ "eval_runtime": 12.6821,
72
+ "eval_samples_per_second": 68.758,
73
+ "eval_steps_per_second": 8.595,
74
  "step": 1200
75
  },
76
  {
77
+ "epoch": 0.17,
78
+ "eval_accuracy": 0.4908256880733945,
79
+ "eval_loss": 2.1010525226593018,
80
+ "eval_runtime": 13.3142,
81
+ "eval_samples_per_second": 65.494,
82
+ "eval_steps_per_second": 8.187,
83
  "step": 1400
84
  },
85
  {
86
+ "epoch": 0.18,
87
+ "learning_rate": 0.0282183157144554,
88
+ "loss": 3.0595,
89
  "step": 1500
90
  },
91
  {
92
+ "epoch": 0.19,
93
  "eval_accuracy": 0.4908256880733945,
94
+ "eval_loss": 2.240478754043579,
95
+ "eval_runtime": 11.7539,
96
+ "eval_samples_per_second": 74.188,
97
+ "eval_steps_per_second": 9.274,
98
  "step": 1600
99
  },
100
  {
101
+ "epoch": 0.21,
102
  "eval_accuracy": 0.4908256880733945,
103
+ "eval_loss": 2.822434663772583,
104
+ "eval_runtime": 11.937,
105
+ "eval_samples_per_second": 73.05,
106
+ "eval_steps_per_second": 9.131,
107
  "step": 1800
108
  },
109
  {
110
+ "epoch": 0.24,
111
+ "learning_rate": 0.027624420952607195,
112
+ "loss": 2.7406,
113
  "step": 2000
114
  },
115
  {
116
+ "epoch": 0.24,
117
  "eval_accuracy": 0.5091743119266054,
118
+ "eval_loss": 2.2581450939178467,
119
+ "eval_runtime": 12.944,
120
+ "eval_samples_per_second": 67.367,
121
+ "eval_steps_per_second": 8.421,
122
  "step": 2000
123
  },
124
+ {
125
+ "epoch": 0.26,
126
+ "eval_accuracy": 0.5091743119266054,
127
+ "eval_loss": 5.0679168701171875,
128
+ "eval_runtime": 12.8993,
129
+ "eval_samples_per_second": 67.6,
130
+ "eval_steps_per_second": 8.45,
131
+ "step": 2200
132
+ },
133
+ {
134
+ "epoch": 0.29,
135
+ "eval_accuracy": 0.5091743119266054,
136
+ "eval_loss": 4.079117774963379,
137
+ "eval_runtime": 12.6438,
138
+ "eval_samples_per_second": 68.966,
139
+ "eval_steps_per_second": 8.621,
140
+ "step": 2400
141
+ },
142
+ {
143
+ "epoch": 0.3,
144
+ "learning_rate": 0.027030526190758998,
145
+ "loss": 2.341,
146
+ "step": 2500
147
+ },
148
+ {
149
+ "epoch": 0.31,
150
+ "eval_accuracy": 0.5091743119266054,
151
+ "eval_loss": 6.498974800109863,
152
+ "eval_runtime": 11.7875,
153
+ "eval_samples_per_second": 73.977,
154
+ "eval_steps_per_second": 9.247,
155
+ "step": 2600
156
+ },
157
+ {
158
+ "epoch": 0.33,
159
+ "eval_accuracy": 0.5091743119266054,
160
+ "eval_loss": 2.2673330307006836,
161
+ "eval_runtime": 12.4045,
162
+ "eval_samples_per_second": 70.297,
163
+ "eval_steps_per_second": 8.787,
164
+ "step": 2800
165
+ },
166
+ {
167
+ "epoch": 0.36,
168
+ "learning_rate": 0.026436631428910798,
169
+ "loss": 2.5017,
170
+ "step": 3000
171
+ },
172
+ {
173
+ "epoch": 0.36,
174
+ "eval_accuracy": 0.4908256880733945,
175
+ "eval_loss": 2.775005340576172,
176
+ "eval_runtime": 12.8935,
177
+ "eval_samples_per_second": 67.631,
178
+ "eval_steps_per_second": 8.454,
179
+ "step": 3000
180
+ },
181
+ {
182
+ "epoch": 0.38,
183
+ "eval_accuracy": 0.5126146788990825,
184
+ "eval_loss": 0.8905919790267944,
185
+ "eval_runtime": 11.7168,
186
+ "eval_samples_per_second": 74.423,
187
+ "eval_steps_per_second": 9.303,
188
+ "step": 3200
189
+ },
190
+ {
191
+ "epoch": 0.4,
192
+ "eval_accuracy": 0.5172018348623854,
193
+ "eval_loss": 3.1630539894104004,
194
+ "eval_runtime": 12.3677,
195
+ "eval_samples_per_second": 70.506,
196
+ "eval_steps_per_second": 8.813,
197
+ "step": 3400
198
+ },
199
+ {
200
+ "epoch": 0.42,
201
+ "learning_rate": 0.025842736667062594,
202
+ "loss": 2.587,
203
+ "step": 3500
204
+ },
205
+ {
206
+ "epoch": 0.43,
207
+ "eval_accuracy": 0.4908256880733945,
208
+ "eval_loss": 1.8831442594528198,
209
+ "eval_runtime": 12.7491,
210
+ "eval_samples_per_second": 68.397,
211
+ "eval_steps_per_second": 8.55,
212
+ "step": 3600
213
+ },
214
+ {
215
+ "epoch": 0.45,
216
+ "eval_accuracy": 0.5091743119266054,
217
+ "eval_loss": 1.40650475025177,
218
+ "eval_runtime": 11.8781,
219
+ "eval_samples_per_second": 73.412,
220
+ "eval_steps_per_second": 9.177,
221
+ "step": 3800
222
+ },
223
+ {
224
+ "epoch": 0.48,
225
+ "learning_rate": 0.025248841905214398,
226
+ "loss": 2.2272,
227
+ "step": 4000
228
+ },
229
+ {
230
+ "epoch": 0.48,
231
+ "eval_accuracy": 0.5091743119266054,
232
+ "eval_loss": 5.7484235763549805,
233
+ "eval_runtime": 12.2084,
234
+ "eval_samples_per_second": 71.426,
235
+ "eval_steps_per_second": 8.928,
236
+ "step": 4000
237
+ },
238
+ {
239
+ "epoch": 0.5,
240
+ "eval_accuracy": 0.4908256880733945,
241
+ "eval_loss": 3.051417589187622,
242
+ "eval_runtime": 13.0485,
243
+ "eval_samples_per_second": 66.828,
244
+ "eval_steps_per_second": 8.353,
245
+ "step": 4200
246
+ },
247
+ {
248
+ "epoch": 0.52,
249
+ "eval_accuracy": 0.5091743119266054,
250
+ "eval_loss": 1.1735517978668213,
251
+ "eval_runtime": 12.52,
252
+ "eval_samples_per_second": 69.648,
253
+ "eval_steps_per_second": 8.706,
254
+ "step": 4400
255
+ },
256
+ {
257
+ "epoch": 0.53,
258
+ "learning_rate": 0.024654947143366194,
259
+ "loss": 2.474,
260
+ "step": 4500
261
+ },
262
+ {
263
+ "epoch": 0.55,
264
+ "eval_accuracy": 0.5091743119266054,
265
+ "eval_loss": 3.5813305377960205,
266
+ "eval_runtime": 12.4532,
267
+ "eval_samples_per_second": 70.022,
268
+ "eval_steps_per_second": 8.753,
269
+ "step": 4600
270
+ },
271
+ {
272
+ "epoch": 0.57,
273
+ "eval_accuracy": 0.4908256880733945,
274
+ "eval_loss": 3.0905096530914307,
275
+ "eval_runtime": 12.1764,
276
+ "eval_samples_per_second": 71.614,
277
+ "eval_steps_per_second": 8.952,
278
+ "step": 4800
279
+ },
280
+ {
281
+ "epoch": 0.59,
282
+ "learning_rate": 0.024061052381517994,
283
+ "loss": 2.6958,
284
+ "step": 5000
285
+ },
286
+ {
287
+ "epoch": 0.59,
288
+ "eval_accuracy": 0.5091743119266054,
289
+ "eval_loss": 1.6613879203796387,
290
+ "eval_runtime": 13.0709,
291
+ "eval_samples_per_second": 66.713,
292
+ "eval_steps_per_second": 8.339,
293
+ "step": 5000
294
+ },
295
+ {
296
+ "epoch": 0.62,
297
+ "eval_accuracy": 0.5091743119266054,
298
+ "eval_loss": 0.9912046194076538,
299
+ "eval_runtime": 11.0684,
300
+ "eval_samples_per_second": 78.783,
301
+ "eval_steps_per_second": 9.848,
302
+ "step": 5200
303
+ },
304
+ {
305
+ "epoch": 0.64,
306
+ "eval_accuracy": 0.5091743119266054,
307
+ "eval_loss": 2.708740711212158,
308
+ "eval_runtime": 12.3098,
309
+ "eval_samples_per_second": 70.838,
310
+ "eval_steps_per_second": 8.855,
311
+ "step": 5400
312
+ },
313
+ {
314
+ "epoch": 0.65,
315
+ "learning_rate": 0.023467157619669794,
316
+ "loss": 2.4571,
317
+ "step": 5500
318
+ },
319
+ {
320
+ "epoch": 0.67,
321
+ "eval_accuracy": 0.4908256880733945,
322
+ "eval_loss": 0.9453651309013367,
323
+ "eval_runtime": 12.5807,
324
+ "eval_samples_per_second": 69.313,
325
+ "eval_steps_per_second": 8.664,
326
+ "step": 5600
327
+ },
328
+ {
329
+ "epoch": 0.69,
330
+ "eval_accuracy": 0.4908256880733945,
331
+ "eval_loss": 0.9460629820823669,
332
+ "eval_runtime": 12.3033,
333
+ "eval_samples_per_second": 70.875,
334
+ "eval_steps_per_second": 8.859,
335
+ "step": 5800
336
+ },
337
+ {
338
+ "epoch": 0.71,
339
+ "learning_rate": 0.022873262857821593,
340
+ "loss": 2.4046,
341
+ "step": 6000
342
+ },
343
+ {
344
+ "epoch": 0.71,
345
+ "eval_accuracy": 0.5034403669724771,
346
+ "eval_loss": 0.7613060474395752,
347
+ "eval_runtime": 12.922,
348
+ "eval_samples_per_second": 67.482,
349
+ "eval_steps_per_second": 8.435,
350
+ "step": 6000
351
+ },
352
+ {
353
+ "epoch": 0.74,
354
+ "eval_accuracy": 0.5091743119266054,
355
+ "eval_loss": 3.473540782928467,
356
+ "eval_runtime": 12.5608,
357
+ "eval_samples_per_second": 69.423,
358
+ "eval_steps_per_second": 8.678,
359
+ "step": 6200
360
+ },
361
+ {
362
+ "epoch": 0.76,
363
+ "eval_accuracy": 0.4908256880733945,
364
+ "eval_loss": 0.8309389352798462,
365
+ "eval_runtime": 12.3028,
366
+ "eval_samples_per_second": 70.878,
367
+ "eval_steps_per_second": 8.86,
368
+ "step": 6400
369
+ },
370
+ {
371
+ "epoch": 0.77,
372
+ "learning_rate": 0.022279368095973393,
373
+ "loss": 1.9778,
374
+ "step": 6500
375
+ },
376
+ {
377
+ "epoch": 0.78,
378
+ "eval_accuracy": 0.5091743119266054,
379
+ "eval_loss": 2.345905303955078,
380
+ "eval_runtime": 12.6993,
381
+ "eval_samples_per_second": 68.665,
382
+ "eval_steps_per_second": 8.583,
383
+ "step": 6600
384
+ },
385
+ {
386
+ "epoch": 0.81,
387
+ "eval_accuracy": 0.5091743119266054,
388
+ "eval_loss": 1.992404818534851,
389
+ "eval_runtime": 11.8953,
390
+ "eval_samples_per_second": 73.306,
391
+ "eval_steps_per_second": 9.163,
392
+ "step": 6800
393
+ },
394
+ {
395
+ "epoch": 0.83,
396
+ "learning_rate": 0.02168547333412519,
397
+ "loss": 1.9132,
398
+ "step": 7000
399
+ },
400
+ {
401
+ "epoch": 0.83,
402
+ "eval_accuracy": 0.48394495412844035,
403
+ "eval_loss": 0.7653124928474426,
404
+ "eval_runtime": 12.5926,
405
+ "eval_samples_per_second": 69.247,
406
+ "eval_steps_per_second": 8.656,
407
+ "step": 7000
408
+ },
409
+ {
410
+ "epoch": 0.86,
411
+ "eval_accuracy": 0.4908256880733945,
412
+ "eval_loss": 1.6025058031082153,
413
+ "eval_runtime": 12.8694,
414
+ "eval_samples_per_second": 67.757,
415
+ "eval_steps_per_second": 8.47,
416
+ "step": 7200
417
+ },
418
+ {
419
+ "epoch": 0.88,
420
+ "eval_accuracy": 0.5091743119266054,
421
+ "eval_loss": 2.3198583126068115,
422
+ "eval_runtime": 12.2526,
423
+ "eval_samples_per_second": 71.168,
424
+ "eval_steps_per_second": 8.896,
425
+ "step": 7400
426
+ },
427
+ {
428
+ "epoch": 0.89,
429
+ "learning_rate": 0.021091578572276993,
430
+ "loss": 2.1041,
431
+ "step": 7500
432
+ },
433
+ {
434
+ "epoch": 0.9,
435
+ "eval_accuracy": 0.5091743119266054,
436
+ "eval_loss": 0.9014425277709961,
437
+ "eval_runtime": 12.1923,
438
+ "eval_samples_per_second": 71.52,
439
+ "eval_steps_per_second": 8.94,
440
+ "step": 7600
441
+ },
442
+ {
443
+ "epoch": 0.93,
444
+ "eval_accuracy": 0.4908256880733945,
445
+ "eval_loss": 1.1414848566055298,
446
+ "eval_runtime": 12.2534,
447
+ "eval_samples_per_second": 71.164,
448
+ "eval_steps_per_second": 8.896,
449
+ "step": 7800
450
+ },
451
+ {
452
+ "epoch": 0.95,
453
+ "learning_rate": 0.020497683810428793,
454
+ "loss": 2.2236,
455
+ "step": 8000
456
+ },
457
+ {
458
+ "epoch": 0.95,
459
+ "eval_accuracy": 0.4908256880733945,
460
+ "eval_loss": 0.9049626588821411,
461
+ "eval_runtime": 12.5976,
462
+ "eval_samples_per_second": 69.219,
463
+ "eval_steps_per_second": 8.652,
464
+ "step": 8000
465
+ },
466
+ {
467
+ "epoch": 0.97,
468
+ "eval_accuracy": 0.4908256880733945,
469
+ "eval_loss": 2.53812575340271,
470
+ "eval_runtime": 12.192,
471
+ "eval_samples_per_second": 71.522,
472
+ "eval_steps_per_second": 8.94,
473
+ "step": 8200
474
+ },
475
+ {
476
+ "epoch": 1.0,
477
+ "eval_accuracy": 0.4908256880733945,
478
+ "eval_loss": 3.9090523719787598,
479
+ "eval_runtime": 12.1436,
480
+ "eval_samples_per_second": 71.807,
481
+ "eval_steps_per_second": 8.976,
482
+ "step": 8400
483
+ },
484
+ {
485
+ "epoch": 1.01,
486
+ "learning_rate": 0.01990378904858059,
487
+ "loss": 1.9257,
488
+ "step": 8500
489
+ },
490
+ {
491
+ "epoch": 1.02,
492
+ "eval_accuracy": 0.44380733944954126,
493
+ "eval_loss": 1.3826260566711426,
494
+ "eval_runtime": 12.394,
495
+ "eval_samples_per_second": 70.357,
496
+ "eval_steps_per_second": 8.795,
497
+ "step": 8600
498
+ },
499
  {
500
  "epoch": 1.05,
501
+ "eval_accuracy": 0.5091743119266054,
502
+ "eval_loss": 0.7106401920318604,
503
+ "eval_runtime": 12.254,
504
+ "eval_samples_per_second": 71.161,
505
+ "eval_steps_per_second": 8.895,
506
+ "step": 8800
507
+ },
508
+ {
509
+ "epoch": 1.07,
510
+ "learning_rate": 0.019309894286732392,
511
+ "loss": 1.9533,
512
+ "step": 9000
513
+ },
514
+ {
515
+ "epoch": 1.07,
516
+ "eval_accuracy": 0.5091743119266054,
517
+ "eval_loss": 1.6487476825714111,
518
+ "eval_runtime": 13.5392,
519
+ "eval_samples_per_second": 64.406,
520
+ "eval_steps_per_second": 8.051,
521
+ "step": 9000
522
+ },
523
+ {
524
+ "epoch": 1.09,
525
  "eval_accuracy": 0.4908256880733945,
526
+ "eval_loss": 1.4527719020843506,
527
+ "eval_runtime": 12.2271,
528
+ "eval_samples_per_second": 71.317,
529
+ "eval_steps_per_second": 8.915,
530
+ "step": 9200
531
+ },
532
+ {
533
+ "epoch": 1.12,
534
+ "eval_accuracy": 0.4908256880733945,
535
+ "eval_loss": 1.1699163913726807,
536
+ "eval_runtime": 12.1388,
537
+ "eval_samples_per_second": 71.836,
538
+ "eval_steps_per_second": 8.979,
539
+ "step": 9400
540
+ },
541
+ {
542
+ "epoch": 1.13,
543
+ "learning_rate": 0.01871599952488419,
544
+ "loss": 1.7969,
545
+ "step": 9500
546
  },
547
  {
548
  "epoch": 1.14,
549
  "eval_accuracy": 0.4908256880733945,
550
+ "eval_loss": 1.155882716178894,
551
+ "eval_runtime": 12.1707,
552
+ "eval_samples_per_second": 71.648,
553
+ "eval_steps_per_second": 8.956,
554
+ "step": 9600
555
+ },
556
+ {
557
+ "epoch": 1.16,
558
+ "eval_accuracy": 0.4908256880733945,
559
+ "eval_loss": 1.0576764345169067,
560
+ "eval_runtime": 12.3024,
561
+ "eval_samples_per_second": 70.88,
562
+ "eval_steps_per_second": 8.86,
563
+ "step": 9800
564
  },
565
  {
566
  "epoch": 1.19,
567
+ "learning_rate": 0.01812210476303599,
568
+ "loss": 1.8048,
569
+ "step": 10000
570
+ },
571
+ {
572
+ "epoch": 1.19,
573
+ "eval_accuracy": 0.4908256880733945,
574
+ "eval_loss": 1.1585994958877563,
575
+ "eval_runtime": 12.8412,
576
+ "eval_samples_per_second": 67.906,
577
+ "eval_steps_per_second": 8.488,
578
+ "step": 10000
579
+ },
580
+ {
581
+ "epoch": 1.21,
582
+ "eval_accuracy": 0.4908256880733945,
583
+ "eval_loss": 0.7068227529525757,
584
+ "eval_runtime": 12.4262,
585
+ "eval_samples_per_second": 70.174,
586
+ "eval_steps_per_second": 8.772,
587
+ "step": 10200
588
  },
589
  {
590
  "epoch": 1.24,
591
  "eval_accuracy": 0.4908256880733945,
592
+ "eval_loss": 0.7638933658599854,
593
+ "eval_runtime": 12.0016,
594
+ "eval_samples_per_second": 72.657,
595
+ "eval_steps_per_second": 9.082,
596
+ "step": 10400
597
+ },
598
+ {
599
+ "epoch": 1.25,
600
+ "learning_rate": 0.01752821000118779,
601
+ "loss": 2.0729,
602
+ "step": 10500
603
+ },
604
+ {
605
+ "epoch": 1.26,
606
+ "eval_accuracy": 0.5091743119266054,
607
+ "eval_loss": 1.188310146331787,
608
+ "eval_runtime": 13.0443,
609
+ "eval_samples_per_second": 66.849,
610
+ "eval_steps_per_second": 8.356,
611
+ "step": 10600
612
+ },
613
+ {
614
+ "epoch": 1.28,
615
+ "eval_accuracy": 0.5091743119266054,
616
+ "eval_loss": 0.6973594427108765,
617
+ "eval_runtime": 11.5707,
618
+ "eval_samples_per_second": 75.363,
619
+ "eval_steps_per_second": 9.42,
620
+ "step": 10800
621
+ },
622
+ {
623
+ "epoch": 1.31,
624
+ "learning_rate": 0.016934315239339588,
625
+ "loss": 1.7558,
626
+ "step": 11000
627
+ },
628
+ {
629
+ "epoch": 1.31,
630
+ "eval_accuracy": 0.4908256880733945,
631
+ "eval_loss": 1.8548436164855957,
632
+ "eval_runtime": 13.0206,
633
+ "eval_samples_per_second": 66.971,
634
+ "eval_steps_per_second": 8.371,
635
+ "step": 11000
636
  },
637
  {
638
  "epoch": 1.33,
639
  "eval_accuracy": 0.4908256880733945,
640
+ "eval_loss": 0.7331790924072266,
641
+ "eval_runtime": 12.107,
642
+ "eval_samples_per_second": 72.024,
643
+ "eval_steps_per_second": 9.003,
644
+ "step": 11200
645
+ },
646
+ {
647
+ "epoch": 1.35,
648
+ "eval_accuracy": 0.5091743119266054,
649
+ "eval_loss": 1.7065454721450806,
650
+ "eval_runtime": 12.0677,
651
+ "eval_samples_per_second": 72.259,
652
+ "eval_steps_per_second": 9.032,
653
+ "step": 11400
654
+ },
655
+ {
656
+ "epoch": 1.37,
657
+ "learning_rate": 0.016340420477491388,
658
+ "loss": 1.931,
659
+ "step": 11500
660
+ },
661
+ {
662
+ "epoch": 1.38,
663
+ "eval_accuracy": 0.5091743119266054,
664
+ "eval_loss": 3.5782742500305176,
665
+ "eval_runtime": 12.3183,
666
+ "eval_samples_per_second": 70.789,
667
+ "eval_steps_per_second": 8.849,
668
+ "step": 11600
669
+ },
670
+ {
671
+ "epoch": 1.4,
672
+ "eval_accuracy": 0.4908256880733945,
673
+ "eval_loss": 2.2677643299102783,
674
+ "eval_runtime": 11.6938,
675
+ "eval_samples_per_second": 74.569,
676
+ "eval_steps_per_second": 9.321,
677
+ "step": 11800
678
  },
679
  {
680
  "epoch": 1.43,
681
+ "learning_rate": 0.015746525715643188,
682
+ "loss": 1.739,
683
+ "step": 12000
684
  },
685
  {
686
  "epoch": 1.43,
687
+ "eval_accuracy": 0.5091743119266054,
688
+ "eval_loss": 1.367167353630066,
689
+ "eval_runtime": 12.6396,
690
+ "eval_samples_per_second": 68.99,
691
+ "eval_steps_per_second": 8.624,
692
+ "step": 12000
693
+ },
694
+ {
695
+ "epoch": 1.45,
696
  "eval_accuracy": 0.4908256880733945,
697
+ "eval_loss": 1.4737409353256226,
698
+ "eval_runtime": 12.3657,
699
+ "eval_samples_per_second": 70.517,
700
+ "eval_steps_per_second": 8.815,
701
+ "step": 12200
702
+ },
703
+ {
704
+ "epoch": 1.47,
705
+ "eval_accuracy": 0.4908256880733945,
706
+ "eval_loss": 0.8329254984855652,
707
+ "eval_runtime": 12.1625,
708
+ "eval_samples_per_second": 71.696,
709
+ "eval_steps_per_second": 8.962,
710
+ "step": 12400
711
+ },
712
+ {
713
+ "epoch": 1.48,
714
+ "learning_rate": 0.015152630953794988,
715
+ "loss": 1.655,
716
+ "step": 12500
717
+ },
718
+ {
719
+ "epoch": 1.5,
720
+ "eval_accuracy": 0.5091743119266054,
721
+ "eval_loss": 2.237131118774414,
722
+ "eval_runtime": 12.2197,
723
+ "eval_samples_per_second": 71.36,
724
+ "eval_steps_per_second": 8.92,
725
+ "step": 12600
726
  },
727
  {
728
  "epoch": 1.52,
729
+ "eval_accuracy": 0.4908256880733945,
730
+ "eval_loss": 3.846944570541382,
731
+ "eval_runtime": 12.0155,
732
+ "eval_samples_per_second": 72.573,
733
+ "eval_steps_per_second": 9.072,
734
+ "step": 12800
735
+ },
736
+ {
737
+ "epoch": 1.54,
738
+ "learning_rate": 0.014558736191946788,
739
+ "loss": 1.7284,
740
+ "step": 13000
741
+ },
742
+ {
743
+ "epoch": 1.54,
744
  "eval_accuracy": 0.5091743119266054,
745
+ "eval_loss": 1.403191328048706,
746
+ "eval_runtime": 12.6645,
747
+ "eval_samples_per_second": 68.854,
748
+ "eval_steps_per_second": 8.607,
749
+ "step": 13000
750
+ },
751
+ {
752
+ "epoch": 1.57,
753
+ "eval_accuracy": 0.5091743119266054,
754
+ "eval_loss": 1.1265949010849,
755
+ "eval_runtime": 12.3046,
756
+ "eval_samples_per_second": 70.868,
757
+ "eval_steps_per_second": 8.859,
758
+ "step": 13200
759
+ },
760
+ {
761
+ "epoch": 1.59,
762
+ "eval_accuracy": 0.4908256880733945,
763
+ "eval_loss": 1.9130467176437378,
764
+ "eval_runtime": 12.0511,
765
+ "eval_samples_per_second": 72.359,
766
+ "eval_steps_per_second": 9.045,
767
+ "step": 13400
768
+ },
769
+ {
770
+ "epoch": 1.6,
771
+ "learning_rate": 0.013964841430098586,
772
+ "loss": 1.5742,
773
+ "step": 13500
774
  },
775
  {
776
  "epoch": 1.62,
777
  "eval_accuracy": 0.5091743119266054,
778
+ "eval_loss": 0.832761824131012,
779
+ "eval_runtime": 12.2374,
780
+ "eval_samples_per_second": 71.257,
781
+ "eval_steps_per_second": 8.907,
782
+ "step": 13600
783
+ },
784
+ {
785
+ "epoch": 1.64,
786
+ "eval_accuracy": 0.5091743119266054,
787
+ "eval_loss": 3.8501062393188477,
788
+ "eval_runtime": 12.573,
789
+ "eval_samples_per_second": 69.355,
790
+ "eval_steps_per_second": 8.669,
791
+ "step": 13800
792
  },
793
  {
794
  "epoch": 1.66,
795
+ "learning_rate": 0.013370946668250385,
796
+ "loss": 1.7039,
797
+ "step": 14000
798
+ },
799
+ {
800
+ "epoch": 1.66,
801
+ "eval_accuracy": 0.4908256880733945,
802
+ "eval_loss": 1.2914493083953857,
803
+ "eval_runtime": 12.0326,
804
+ "eval_samples_per_second": 72.47,
805
+ "eval_steps_per_second": 9.059,
806
+ "step": 14000
807
+ },
808
+ {
809
+ "epoch": 1.69,
810
+ "eval_accuracy": 0.4908256880733945,
811
+ "eval_loss": 1.136923909187317,
812
+ "eval_runtime": 11.7256,
813
+ "eval_samples_per_second": 74.367,
814
+ "eval_steps_per_second": 9.296,
815
+ "step": 14200
816
  },
817
  {
818
  "epoch": 1.71,
819
  "eval_accuracy": 0.5091743119266054,
820
+ "eval_loss": 0.7574475407600403,
821
+ "eval_runtime": 12.2584,
822
+ "eval_samples_per_second": 71.135,
823
+ "eval_steps_per_second": 8.892,
824
+ "step": 14400
825
+ },
826
+ {
827
+ "epoch": 1.72,
828
+ "learning_rate": 0.012777051906402184,
829
+ "loss": 1.4352,
830
+ "step": 14500
831
+ },
832
+ {
833
+ "epoch": 1.73,
834
+ "eval_accuracy": 0.5091743119266054,
835
+ "eval_loss": 0.7623356580734253,
836
+ "eval_runtime": 12.706,
837
+ "eval_samples_per_second": 68.629,
838
+ "eval_steps_per_second": 8.579,
839
+ "step": 14600
840
+ },
841
+ {
842
+ "epoch": 1.76,
843
+ "eval_accuracy": 0.5091743119266054,
844
+ "eval_loss": 1.6579828262329102,
845
+ "eval_runtime": 12.16,
846
+ "eval_samples_per_second": 71.71,
847
+ "eval_steps_per_second": 8.964,
848
+ "step": 14800
849
+ },
850
+ {
851
+ "epoch": 1.78,
852
+ "learning_rate": 0.012183157144553985,
853
+ "loss": 1.6328,
854
+ "step": 15000
855
+ },
856
+ {
857
+ "epoch": 1.78,
858
+ "eval_accuracy": 0.481651376146789,
859
+ "eval_loss": 0.693511426448822,
860
+ "eval_runtime": 12.7779,
861
+ "eval_samples_per_second": 68.243,
862
+ "eval_steps_per_second": 8.53,
863
+ "step": 15000
864
  },
865
  {
866
  "epoch": 1.81,
867
  "eval_accuracy": 0.4908256880733945,
868
+ "eval_loss": 0.6989684700965881,
869
+ "eval_runtime": 12.0393,
870
+ "eval_samples_per_second": 72.43,
871
+ "eval_steps_per_second": 9.054,
872
+ "step": 15200
873
+ },
874
+ {
875
+ "epoch": 1.83,
876
+ "eval_accuracy": 0.5091743119266054,
877
+ "eval_loss": 0.7303033471107483,
878
+ "eval_runtime": 12.3696,
879
+ "eval_samples_per_second": 70.496,
880
+ "eval_steps_per_second": 8.812,
881
+ "step": 15400
882
+ },
883
+ {
884
+ "epoch": 1.84,
885
+ "learning_rate": 0.011589262382705785,
886
+ "loss": 1.4498,
887
+ "step": 15500
888
+ },
889
+ {
890
+ "epoch": 1.85,
891
+ "eval_accuracy": 0.4908256880733945,
892
+ "eval_loss": 1.675624132156372,
893
+ "eval_runtime": 12.6317,
894
+ "eval_samples_per_second": 69.032,
895
+ "eval_steps_per_second": 8.629,
896
+ "step": 15600
897
+ },
898
+ {
899
+ "epoch": 1.88,
900
+ "eval_accuracy": 0.4908256880733945,
901
+ "eval_loss": 1.0083491802215576,
902
+ "eval_runtime": 12.349,
903
+ "eval_samples_per_second": 70.613,
904
+ "eval_steps_per_second": 8.827,
905
+ "step": 15800
906
  },
907
  {
908
  "epoch": 1.9,
909
+ "learning_rate": 0.010995367620857583,
910
+ "loss": 1.4022,
911
+ "step": 16000
912
  },
913
  {
914
  "epoch": 1.9,
915
  "eval_accuracy": 0.4908256880733945,
916
+ "eval_loss": 0.7790195345878601,
917
+ "eval_runtime": 11.9659,
918
+ "eval_samples_per_second": 72.874,
919
+ "eval_steps_per_second": 9.109,
920
+ "step": 16000
921
  },
922
  {
923
+ "epoch": 1.92,
924
  "eval_accuracy": 0.5091743119266054,
925
+ "eval_loss": 1.296112060546875,
926
+ "eval_runtime": 13.0796,
927
+ "eval_samples_per_second": 66.669,
928
+ "eval_steps_per_second": 8.334,
929
+ "step": 16200
930
+ },
931
+ {
932
+ "epoch": 1.95,
933
+ "eval_accuracy": 0.4908256880733945,
934
+ "eval_loss": 0.7208316326141357,
935
+ "eval_runtime": 12.4652,
936
+ "eval_samples_per_second": 69.955,
937
+ "eval_steps_per_second": 8.744,
938
+ "step": 16400
939
+ },
940
+ {
941
+ "epoch": 1.96,
942
+ "learning_rate": 0.010401472859009383,
943
+ "loss": 1.4503,
944
+ "step": 16500
945
+ },
946
+ {
947
+ "epoch": 1.97,
948
+ "eval_accuracy": 0.4908256880733945,
949
+ "eval_loss": 0.8011333346366882,
950
+ "eval_runtime": 12.77,
951
+ "eval_samples_per_second": 68.285,
952
+ "eval_steps_per_second": 8.536,
953
+ "step": 16600
954
+ },
955
+ {
956
+ "epoch": 2.0,
957
+ "eval_accuracy": 0.4908256880733945,
958
+ "eval_loss": 0.8194194436073303,
959
+ "eval_runtime": 12.2506,
960
+ "eval_samples_per_second": 71.18,
961
+ "eval_steps_per_second": 8.898,
962
+ "step": 16800
963
+ },
964
+ {
965
+ "epoch": 2.02,
966
+ "learning_rate": 0.009807578097161183,
967
+ "loss": 1.3401,
968
+ "step": 17000
969
+ },
970
+ {
971
+ "epoch": 2.02,
972
+ "eval_accuracy": 0.4908256880733945,
973
+ "eval_loss": 0.9209619760513306,
974
+ "eval_runtime": 12.7245,
975
+ "eval_samples_per_second": 68.529,
976
+ "eval_steps_per_second": 8.566,
977
+ "step": 17000
978
+ },
979
+ {
980
+ "epoch": 2.04,
981
+ "eval_accuracy": 0.4954128440366973,
982
+ "eval_loss": 2.172947645187378,
983
+ "eval_runtime": 13.3907,
984
+ "eval_samples_per_second": 65.12,
985
+ "eval_steps_per_second": 8.14,
986
+ "step": 17200
987
+ },
988
+ {
989
+ "epoch": 2.07,
990
+ "eval_accuracy": 0.4908256880733945,
991
+ "eval_loss": 2.8217873573303223,
992
+ "eval_runtime": 12.0414,
993
+ "eval_samples_per_second": 72.417,
994
+ "eval_steps_per_second": 9.052,
995
+ "step": 17400
996
+ },
997
+ {
998
+ "epoch": 2.08,
999
+ "learning_rate": 0.009213683335312983,
1000
+ "loss": 1.515,
1001
+ "step": 17500
1002
  },
1003
  {
1004
  "epoch": 2.09,
1005
  "eval_accuracy": 0.5091743119266054,
1006
+ "eval_loss": 1.8880350589752197,
1007
+ "eval_runtime": 12.7892,
1008
+ "eval_samples_per_second": 68.183,
1009
+ "eval_steps_per_second": 8.523,
1010
+ "step": 17600
1011
+ },
1012
+ {
1013
+ "epoch": 2.11,
1014
+ "eval_accuracy": 0.4908256880733945,
1015
+ "eval_loss": 0.8059159517288208,
1016
+ "eval_runtime": 12.8563,
1017
+ "eval_samples_per_second": 67.827,
1018
+ "eval_steps_per_second": 8.478,
1019
+ "step": 17800
1020
  },
1021
  {
1022
  "epoch": 2.14,
1023
+ "learning_rate": 0.008619788573464782,
1024
+ "loss": 1.2519,
1025
+ "step": 18000
1026
+ },
1027
+ {
1028
+ "epoch": 2.14,
1029
+ "eval_accuracy": 0.5091743119266054,
1030
+ "eval_loss": 1.1668144464492798,
1031
+ "eval_runtime": 12.0845,
1032
+ "eval_samples_per_second": 72.158,
1033
+ "eval_steps_per_second": 9.02,
1034
+ "step": 18000
1035
+ },
1036
+ {
1037
+ "epoch": 2.16,
1038
+ "eval_accuracy": 0.5091743119266054,
1039
+ "eval_loss": 0.8440486192703247,
1040
+ "eval_runtime": 11.5453,
1041
+ "eval_samples_per_second": 75.529,
1042
+ "eval_steps_per_second": 9.441,
1043
+ "step": 18200
1044
  },
1045
  {
1046
  "epoch": 2.19,
1047
  "eval_accuracy": 0.5091743119266054,
1048
+ "eval_loss": 1.482177972793579,
1049
+ "eval_runtime": 11.5533,
1050
+ "eval_samples_per_second": 75.476,
1051
+ "eval_steps_per_second": 9.435,
1052
+ "step": 18400
1053
+ },
1054
+ {
1055
+ "epoch": 2.2,
1056
+ "learning_rate": 0.008025893811616582,
1057
+ "loss": 1.2221,
1058
+ "step": 18500
1059
+ },
1060
+ {
1061
+ "epoch": 2.21,
1062
+ "eval_accuracy": 0.5091743119266054,
1063
+ "eval_loss": 0.6977333426475525,
1064
+ "eval_runtime": 12.3902,
1065
+ "eval_samples_per_second": 70.378,
1066
+ "eval_steps_per_second": 8.797,
1067
+ "step": 18600
1068
+ },
1069
+ {
1070
+ "epoch": 2.23,
1071
+ "eval_accuracy": 0.5091743119266054,
1072
+ "eval_loss": 1.3418121337890625,
1073
+ "eval_runtime": 12.4195,
1074
+ "eval_samples_per_second": 70.212,
1075
+ "eval_steps_per_second": 8.776,
1076
+ "step": 18800
1077
+ },
1078
+ {
1079
+ "epoch": 2.26,
1080
+ "learning_rate": 0.00743199904976838,
1081
+ "loss": 1.1201,
1082
+ "step": 19000
1083
+ },
1084
+ {
1085
+ "epoch": 2.26,
1086
+ "eval_accuracy": 0.4908256880733945,
1087
+ "eval_loss": 0.7915144562721252,
1088
+ "eval_runtime": 12.717,
1089
+ "eval_samples_per_second": 68.57,
1090
+ "eval_steps_per_second": 8.571,
1091
+ "step": 19000
1092
  },
1093
  {
1094
  "epoch": 2.28,
1095
+ "eval_accuracy": 0.5091743119266054,
1096
+ "eval_loss": 0.961918830871582,
1097
+ "eval_runtime": 13.173,
1098
+ "eval_samples_per_second": 66.196,
1099
+ "eval_steps_per_second": 8.275,
1100
+ "step": 19200
1101
+ },
1102
+ {
1103
+ "epoch": 2.3,
1104
  "eval_accuracy": 0.4908256880733945,
1105
+ "eval_loss": 1.220428228378296,
1106
+ "eval_runtime": 12.2958,
1107
+ "eval_samples_per_second": 70.918,
1108
+ "eval_steps_per_second": 8.865,
1109
+ "step": 19400
1110
+ },
1111
+ {
1112
+ "epoch": 2.32,
1113
+ "learning_rate": 0.006838104287920181,
1114
+ "loss": 1.0869,
1115
+ "step": 19500
1116
+ },
1117
+ {
1118
+ "epoch": 2.33,
1119
+ "eval_accuracy": 0.5091743119266054,
1120
+ "eval_loss": 1.6541168689727783,
1121
+ "eval_runtime": 12.5954,
1122
+ "eval_samples_per_second": 69.232,
1123
+ "eval_steps_per_second": 8.654,
1124
+ "step": 19600
1125
+ },
1126
+ {
1127
+ "epoch": 2.35,
1128
+ "eval_accuracy": 0.5091743119266054,
1129
+ "eval_loss": 2.7402684688568115,
1130
+ "eval_runtime": 12.7516,
1131
+ "eval_samples_per_second": 68.383,
1132
+ "eval_steps_per_second": 8.548,
1133
+ "step": 19800
1134
  },
1135
  {
1136
  "epoch": 2.38,
1137
+ "learning_rate": 0.00624420952607198,
1138
+ "loss": 1.0804,
1139
+ "step": 20000
1140
  },
1141
  {
1142
  "epoch": 2.38,
1143
+ "eval_accuracy": 0.4908256880733945,
1144
+ "eval_loss": 1.2037415504455566,
1145
+ "eval_runtime": 13.138,
1146
+ "eval_samples_per_second": 66.372,
1147
+ "eval_steps_per_second": 8.297,
1148
+ "step": 20000
1149
+ },
1150
+ {
1151
+ "epoch": 2.4,
1152
  "eval_accuracy": 0.5091743119266054,
1153
+ "eval_loss": 0.7337152361869812,
1154
+ "eval_runtime": 11.6201,
1155
+ "eval_samples_per_second": 75.043,
1156
+ "eval_steps_per_second": 9.38,
1157
+ "step": 20200
1158
+ },
1159
+ {
1160
+ "epoch": 2.42,
1161
+ "eval_accuracy": 0.5091743119266054,
1162
+ "eval_loss": 0.8853695392608643,
1163
+ "eval_runtime": 13.0127,
1164
+ "eval_samples_per_second": 67.012,
1165
+ "eval_steps_per_second": 8.376,
1166
+ "step": 20400
1167
+ },
1168
+ {
1169
+ "epoch": 2.43,
1170
+ "learning_rate": 0.005650314764223779,
1171
+ "loss": 1.0025,
1172
+ "step": 20500
1173
+ },
1174
+ {
1175
+ "epoch": 2.45,
1176
+ "eval_accuracy": 0.5091743119266054,
1177
+ "eval_loss": 0.7113233804702759,
1178
+ "eval_runtime": 12.2168,
1179
+ "eval_samples_per_second": 71.377,
1180
+ "eval_steps_per_second": 8.922,
1181
+ "step": 20600
1182
  },
1183
  {
1184
  "epoch": 2.47,
1185
+ "eval_accuracy": 0.5091743119266054,
1186
+ "eval_loss": 1.0583016872406006,
1187
+ "eval_runtime": 12.0017,
1188
+ "eval_samples_per_second": 72.657,
1189
+ "eval_steps_per_second": 9.082,
1190
+ "step": 20800
1191
+ },
1192
+ {
1193
+ "epoch": 2.49,
1194
+ "learning_rate": 0.005056420002375579,
1195
+ "loss": 0.9856,
1196
+ "step": 21000
1197
+ },
1198
+ {
1199
+ "epoch": 2.49,
1200
+ "eval_accuracy": 0.5091743119266054,
1201
+ "eval_loss": 0.7113476395606995,
1202
+ "eval_runtime": 12.9697,
1203
+ "eval_samples_per_second": 67.234,
1204
+ "eval_steps_per_second": 8.404,
1205
+ "step": 21000
1206
+ },
1207
+ {
1208
+ "epoch": 2.52,
1209
  "eval_accuracy": 0.4908256880733945,
1210
+ "eval_loss": 0.7482680678367615,
1211
+ "eval_runtime": 12.7958,
1212
+ "eval_samples_per_second": 68.147,
1213
+ "eval_steps_per_second": 8.518,
1214
+ "step": 21200
1215
+ },
1216
+ {
1217
+ "epoch": 2.54,
1218
+ "eval_accuracy": 0.5091743119266054,
1219
+ "eval_loss": 0.6966097950935364,
1220
+ "eval_runtime": 12.2964,
1221
+ "eval_samples_per_second": 70.915,
1222
+ "eval_steps_per_second": 8.864,
1223
+ "step": 21400
1224
+ },
1225
+ {
1226
+ "epoch": 2.55,
1227
+ "learning_rate": 0.004462525240527379,
1228
+ "loss": 1.0364,
1229
+ "step": 21500
1230
  },
1231
  {
1232
  "epoch": 2.57,
1233
+ "eval_accuracy": 0.4908256880733945,
1234
+ "eval_loss": 1.0607110261917114,
1235
+ "eval_runtime": 12.067,
1236
+ "eval_samples_per_second": 72.263,
1237
+ "eval_steps_per_second": 9.033,
1238
+ "step": 21600
1239
+ },
1240
+ {
1241
+ "epoch": 2.59,
1242
  "eval_accuracy": 0.5091743119266054,
1243
+ "eval_loss": 1.1381345987319946,
1244
+ "eval_runtime": 12.2151,
1245
+ "eval_samples_per_second": 71.387,
1246
+ "eval_steps_per_second": 8.923,
1247
+ "step": 21800
1248
  },
1249
  {
1250
  "epoch": 2.61,
1251
+ "learning_rate": 0.003868630478679178,
1252
+ "loss": 0.9683,
1253
+ "step": 22000
1254
  },
1255
  {
1256
+ "epoch": 2.61,
1257
  "eval_accuracy": 0.4908256880733945,
1258
+ "eval_loss": 0.7138826847076416,
1259
+ "eval_runtime": 12.7162,
1260
+ "eval_samples_per_second": 68.574,
1261
+ "eval_steps_per_second": 8.572,
1262
+ "step": 22000
1263
+ },
1264
+ {
1265
+ "epoch": 2.64,
1266
+ "eval_accuracy": 0.4908256880733945,
1267
+ "eval_loss": 1.6361145973205566,
1268
+ "eval_runtime": 11.8698,
1269
+ "eval_samples_per_second": 73.464,
1270
+ "eval_steps_per_second": 9.183,
1271
+ "step": 22200
1272
+ },
1273
+ {
1274
+ "epoch": 2.66,
1275
+ "eval_accuracy": 0.5091743119266054,
1276
+ "eval_loss": 1.1421782970428467,
1277
+ "eval_runtime": 11.321,
1278
+ "eval_samples_per_second": 77.025,
1279
+ "eval_steps_per_second": 9.628,
1280
+ "step": 22400
1281
+ },
1282
+ {
1283
+ "epoch": 2.67,
1284
+ "learning_rate": 0.0032747357168309774,
1285
+ "loss": 0.908,
1286
+ "step": 22500
1287
+ },
1288
+ {
1289
+ "epoch": 2.68,
1290
+ "eval_accuracy": 0.5091743119266054,
1291
+ "eval_loss": 0.7317955493927002,
1292
+ "eval_runtime": 12.2644,
1293
+ "eval_samples_per_second": 71.1,
1294
+ "eval_steps_per_second": 8.888,
1295
+ "step": 22600
1296
+ },
1297
+ {
1298
+ "epoch": 2.71,
1299
+ "eval_accuracy": 0.5091743119266054,
1300
+ "eval_loss": 0.6962340474128723,
1301
+ "eval_runtime": 11.822,
1302
+ "eval_samples_per_second": 73.761,
1303
+ "eval_steps_per_second": 9.22,
1304
+ "step": 22800
1305
+ },
1306
+ {
1307
+ "epoch": 2.73,
1308
+ "learning_rate": 0.0026808409549827768,
1309
+ "loss": 0.8761,
1310
+ "step": 23000
1311
+ },
1312
+ {
1313
+ "epoch": 2.73,
1314
+ "eval_accuracy": 0.5091743119266054,
1315
+ "eval_loss": 0.9568504691123962,
1316
+ "eval_runtime": 12.3037,
1317
+ "eval_samples_per_second": 70.873,
1318
+ "eval_steps_per_second": 8.859,
1319
+ "step": 23000
1320
  },
1321
  {
1322
  "epoch": 2.76,
1323
  "eval_accuracy": 0.5091743119266054,
1324
+ "eval_loss": 0.9744265675544739,
1325
+ "eval_runtime": 11.9452,
1326
+ "eval_samples_per_second": 73.0,
1327
+ "eval_steps_per_second": 9.125,
1328
+ "step": 23200
1329
+ },
1330
+ {
1331
+ "epoch": 2.78,
1332
+ "eval_accuracy": 0.4908256880733945,
1333
+ "eval_loss": 1.091610312461853,
1334
+ "eval_runtime": 12.8562,
1335
+ "eval_samples_per_second": 67.827,
1336
+ "eval_steps_per_second": 8.478,
1337
+ "step": 23400
1338
+ },
1339
+ {
1340
+ "epoch": 2.79,
1341
+ "learning_rate": 0.0020869461931345766,
1342
+ "loss": 0.8209,
1343
+ "step": 23500
1344
+ },
1345
+ {
1346
+ "epoch": 2.8,
1347
+ "eval_accuracy": 0.4908256880733945,
1348
+ "eval_loss": 0.8106526136398315,
1349
+ "eval_runtime": 11.7827,
1350
+ "eval_samples_per_second": 74.007,
1351
+ "eval_steps_per_second": 9.251,
1352
+ "step": 23600
1353
+ },
1354
+ {
1355
+ "epoch": 2.83,
1356
+ "eval_accuracy": 0.5091743119266054,
1357
+ "eval_loss": 0.7210954427719116,
1358
+ "eval_runtime": 11.3303,
1359
+ "eval_samples_per_second": 76.962,
1360
+ "eval_steps_per_second": 9.62,
1361
+ "step": 23800
1362
  },
1363
  {
1364
  "epoch": 2.85,
1365
+ "learning_rate": 0.001493051431286376,
1366
+ "loss": 0.8008,
1367
+ "step": 24000
1368
  },
1369
  {
1370
  "epoch": 2.85,
1371
+ "eval_accuracy": 0.49770642201834864,
1372
+ "eval_loss": 0.6930689811706543,
1373
+ "eval_runtime": 12.4553,
1374
+ "eval_samples_per_second": 70.01,
1375
+ "eval_steps_per_second": 8.751,
1376
+ "step": 24000
1377
+ },
1378
+ {
1379
+ "epoch": 2.87,
1380
  "eval_accuracy": 0.4908256880733945,
1381
+ "eval_loss": 0.7184925675392151,
1382
+ "eval_runtime": 12.3113,
1383
+ "eval_samples_per_second": 70.829,
1384
+ "eval_steps_per_second": 8.854,
1385
+ "step": 24200
1386
+ },
1387
+ {
1388
+ "epoch": 2.9,
1389
+ "eval_accuracy": 0.5091743119266054,
1390
+ "eval_loss": 0.729166567325592,
1391
+ "eval_runtime": 11.2952,
1392
+ "eval_samples_per_second": 77.201,
1393
+ "eval_steps_per_second": 9.65,
1394
+ "step": 24400
1395
+ },
1396
+ {
1397
+ "epoch": 2.91,
1398
+ "learning_rate": 0.0008991566694381756,
1399
+ "loss": 0.7738,
1400
+ "step": 24500
1401
+ },
1402
+ {
1403
+ "epoch": 2.92,
1404
+ "eval_accuracy": 0.5091743119266054,
1405
+ "eval_loss": 0.7178325057029724,
1406
+ "eval_runtime": 12.4374,
1407
+ "eval_samples_per_second": 70.111,
1408
+ "eval_steps_per_second": 8.764,
1409
+ "step": 24600
1410
  },
1411
  {
1412
  "epoch": 2.95,
1413
  "eval_accuracy": 0.5091743119266054,
1414
+ "eval_loss": 0.6961101293563843,
1415
+ "eval_runtime": 12.5193,
1416
+ "eval_samples_per_second": 69.652,
1417
+ "eval_steps_per_second": 8.707,
1418
+ "step": 24800
1419
+ },
1420
+ {
1421
+ "epoch": 2.97,
1422
+ "learning_rate": 0.00030526190758997505,
1423
+ "loss": 0.755,
1424
+ "step": 25000
1425
+ },
1426
+ {
1427
+ "epoch": 2.97,
1428
+ "eval_accuracy": 0.5091743119266054,
1429
+ "eval_loss": 0.7101095914840698,
1430
+ "eval_runtime": 12.5702,
1431
+ "eval_samples_per_second": 69.371,
1432
+ "eval_steps_per_second": 8.671,
1433
+ "step": 25000
1434
+ },
1435
+ {
1436
+ "epoch": 2.99,
1437
+ "eval_accuracy": 0.5091743119266054,
1438
+ "eval_loss": 0.7049440145492554,
1439
+ "eval_runtime": 11.2857,
1440
+ "eval_samples_per_second": 77.266,
1441
+ "eval_steps_per_second": 9.658,
1442
+ "step": 25200
1443
  },
1444
  {
1445
  "epoch": 3.0,
1446
+ "step": 25257,
1447
+ "total_flos": 1.070008779996841e+17,
1448
+ "train_loss": 1.708119561667774,
1449
+ "train_runtime": 7791.0638,
1450
+ "train_samples_per_second": 25.933,
1451
+ "train_steps_per_second": 3.242
1452
  }
1453
  ],
1454
+ "max_steps": 25257,
1455
  "num_train_epochs": 3,
1456
+ "total_flos": 1.070008779996841e+17,
1457
  "trial_name": null,
1458
  "trial_params": null
1459
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20e570580c930ab842d019d7b8cc933aefcd162f21276c346107920486e67f50
3
  size 2991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c79dd5728a0dfd88f174d77a75a2ec83b9fb55f13139f90613419cca48d0477
3
  size 2991