File size: 5,746 Bytes
13c7552
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
{
  "best_metric": 0.6963669061660767,
  "best_model_checkpoint": "hBERTv2_sst2/checkpoint-2376",
  "epoch": 14.0,
  "global_step": 3696,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9003787878787885e-05,
      "loss": 0.6916,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6998637914657593,
      "eval_runtime": 1.0361,
      "eval_samples_per_second": 841.637,
      "eval_steps_per_second": 3.861,
      "step": 264
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.800378787878788e-05,
      "loss": 0.6885,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6977964639663696,
      "eval_runtime": 1.037,
      "eval_samples_per_second": 840.878,
      "eval_steps_per_second": 3.857,
      "step": 528
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7003787878787884e-05,
      "loss": 0.6871,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.698425829410553,
      "eval_runtime": 1.0359,
      "eval_samples_per_second": 841.809,
      "eval_steps_per_second": 3.862,
      "step": 792
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600378787878788e-05,
      "loss": 0.6869,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.69902503490448,
      "eval_runtime": 1.0372,
      "eval_samples_per_second": 840.699,
      "eval_steps_per_second": 3.856,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5003787878787876e-05,
      "loss": 0.6868,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6974067091941833,
      "eval_runtime": 1.0355,
      "eval_samples_per_second": 842.083,
      "eval_steps_per_second": 3.863,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4003787878787885e-05,
      "loss": 0.6869,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6980025172233582,
      "eval_runtime": 1.0358,
      "eval_samples_per_second": 841.851,
      "eval_steps_per_second": 3.862,
      "step": 1584
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.300378787878788e-05,
      "loss": 0.6867,
      "step": 1848
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6984168887138367,
      "eval_runtime": 1.0568,
      "eval_samples_per_second": 825.136,
      "eval_steps_per_second": 3.785,
      "step": 1848
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2003787878787884e-05,
      "loss": 0.6868,
      "step": 2112
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6974700093269348,
      "eval_runtime": 1.0448,
      "eval_samples_per_second": 834.6,
      "eval_steps_per_second": 3.828,
      "step": 2112
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.100378787878788e-05,
      "loss": 0.6868,
      "step": 2376
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6963669061660767,
      "eval_runtime": 1.037,
      "eval_samples_per_second": 840.85,
      "eval_steps_per_second": 3.857,
      "step": 2376
    },
    {
      "epoch": 10.0,
      "learning_rate": 4.0003787878787876e-05,
      "loss": 0.6865,
      "step": 2640
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6977964639663696,
      "eval_runtime": 1.0355,
      "eval_samples_per_second": 842.138,
      "eval_steps_per_second": 3.863,
      "step": 2640
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.900378787878788e-05,
      "loss": 0.6868,
      "step": 2904
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6980271935462952,
      "eval_runtime": 1.0325,
      "eval_samples_per_second": 844.563,
      "eval_steps_per_second": 3.874,
      "step": 2904
    },
    {
      "epoch": 12.0,
      "learning_rate": 3.800378787878788e-05,
      "loss": 0.6865,
      "step": 3168
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.700083315372467,
      "eval_runtime": 1.0347,
      "eval_samples_per_second": 842.747,
      "eval_steps_per_second": 3.866,
      "step": 3168
    },
    {
      "epoch": 13.0,
      "learning_rate": 3.7003787878787885e-05,
      "loss": 0.6867,
      "step": 3432
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6965734958648682,
      "eval_runtime": 1.032,
      "eval_samples_per_second": 844.972,
      "eval_steps_per_second": 3.876,
      "step": 3432
    },
    {
      "epoch": 14.0,
      "learning_rate": 3.600378787878788e-05,
      "loss": 0.6867,
      "step": 3696
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.5091743119266054,
      "eval_loss": 0.6980003118515015,
      "eval_runtime": 1.0332,
      "eval_samples_per_second": 843.945,
      "eval_steps_per_second": 3.871,
      "step": 3696
    },
    {
      "epoch": 14.0,
      "step": 3696,
      "total_flos": 1.1743968521879552e+17,
      "train_loss": 0.6872374216715494,
      "train_runtime": 3475.6313,
      "train_samples_per_second": 968.874,
      "train_steps_per_second": 3.798
    }
  ],
  "max_steps": 13200,
  "num_train_epochs": 50,
  "total_flos": 1.1743968521879552e+17,
  "trial_name": null,
  "trial_params": null
}