File size: 4,802 Bytes
f50308f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.18199852108955383,
  "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-1620",
  "epoch": 13.995391705069125,
  "global_step": 1890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 9e-06,
      "loss": 0.5633,
      "step": 135
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.25235414505004883,
      "eval_runtime": 12.2006,
      "eval_samples_per_second": 254.085,
      "eval_steps_per_second": 31.802,
      "step": 135
    },
    {
      "epoch": 2.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2589,
      "step": 270
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.21927106380462646,
      "eval_runtime": 11.2792,
      "eval_samples_per_second": 274.842,
      "eval_steps_per_second": 34.4,
      "step": 270
    },
    {
      "epoch": 3.0,
      "learning_rate": 7e-06,
      "loss": 0.2307,
      "step": 405
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.19929151237010956,
      "eval_runtime": 11.2313,
      "eval_samples_per_second": 276.016,
      "eval_steps_per_second": 34.546,
      "step": 405
    },
    {
      "epoch": 4.0,
      "learning_rate": 6e-06,
      "loss": 0.2171,
      "step": 540
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.20016591250896454,
      "eval_runtime": 11.0923,
      "eval_samples_per_second": 279.473,
      "eval_steps_per_second": 34.979,
      "step": 540
    },
    {
      "epoch": 5.0,
      "learning_rate": 5e-06,
      "loss": 0.2027,
      "step": 675
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.19366399943828583,
      "eval_runtime": 11.2232,
      "eval_samples_per_second": 276.213,
      "eval_steps_per_second": 34.571,
      "step": 675
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1946,
      "step": 810
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.19715721905231476,
      "eval_runtime": 11.2739,
      "eval_samples_per_second": 274.973,
      "eval_steps_per_second": 34.416,
      "step": 810
    },
    {
      "epoch": 7.0,
      "learning_rate": 3e-06,
      "loss": 0.1874,
      "step": 945
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.19172348082065582,
      "eval_runtime": 11.1804,
      "eval_samples_per_second": 277.27,
      "eval_steps_per_second": 34.704,
      "step": 945
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1853,
      "step": 1080
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.1867838054895401,
      "eval_runtime": 11.2543,
      "eval_samples_per_second": 275.451,
      "eval_steps_per_second": 34.476,
      "step": 1080
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1811,
      "step": 1215
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.18896569311618805,
      "eval_runtime": 11.6639,
      "eval_samples_per_second": 265.777,
      "eval_steps_per_second": 33.265,
      "step": 1215
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.1776,
      "step": 1350
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.18712429702281952,
      "eval_runtime": 11.9321,
      "eval_samples_per_second": 259.803,
      "eval_steps_per_second": 32.517,
      "step": 1350
    },
    {
      "epoch": 11.0,
      "learning_rate": 4.5e-06,
      "loss": 0.1798,
      "step": 1485
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.18577729165554047,
      "eval_runtime": 11.5191,
      "eval_samples_per_second": 269.117,
      "eval_steps_per_second": 33.683,
      "step": 1485
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1745,
      "step": 1620
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.18199852108955383,
      "eval_runtime": 11.54,
      "eval_samples_per_second": 268.63,
      "eval_steps_per_second": 33.622,
      "step": 1620
    },
    {
      "epoch": 13.0,
      "learning_rate": 3.5e-06,
      "loss": 0.1689,
      "step": 1755
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.18266141414642334,
      "eval_runtime": 11.4865,
      "eval_samples_per_second": 269.881,
      "eval_steps_per_second": 33.779,
      "step": 1755
    },
    {
      "epoch": 14.0,
      "learning_rate": 3e-06,
      "loss": 0.1707,
      "step": 1890
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.18427973985671997,
      "eval_runtime": 11.7088,
      "eval_samples_per_second": 264.757,
      "eval_steps_per_second": 33.137,
      "step": 1890
    }
  ],
  "max_steps": 2700,
  "num_train_epochs": 20,
  "total_flos": 7535299402874880.0,
  "trial_name": null,
  "trial_params": null
}