File size: 6,040 Bytes
e3753fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.8632057597574839,
  "best_model_checkpoint": "wav2vec2-base/checkpoint-5500",
  "epoch": 32.0,
  "global_step": 6336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.53,
      "learning_rate": 2.3659305993690853e-05,
      "loss": 4.3647,
      "step": 500
    },
    {
      "epoch": 2.53,
      "eval_accuracy": 0.011746873815839333,
      "eval_f1": 0.0031732207431106035,
      "eval_loss": 4.820202350616455,
      "eval_precision": 0.013376466669245454,
      "eval_runtime": 109.2278,
      "eval_samples_per_second": 24.161,
      "eval_steps_per_second": 0.806,
      "step": 500
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.8074359873728517e-05,
      "loss": 2.6202,
      "step": 1000
    },
    {
      "epoch": 5.05,
      "eval_accuracy": 0.06252368321333839,
      "eval_f1": 0.035540285078168796,
      "eval_loss": 4.223803520202637,
      "eval_precision": 0.07806791077535753,
      "eval_runtime": 106.4124,
      "eval_samples_per_second": 24.8,
      "eval_steps_per_second": 0.827,
      "step": 1000
    },
    {
      "epoch": 7.58,
      "learning_rate": 2.5443703963521573e-05,
      "loss": 1.38,
      "step": 1500
    },
    {
      "epoch": 7.58,
      "eval_accuracy": 0.2940507768093975,
      "eval_f1": 0.31740258677108446,
      "eval_loss": 3.6391522884368896,
      "eval_precision": 0.5210640247794917,
      "eval_runtime": 107.4509,
      "eval_samples_per_second": 24.56,
      "eval_steps_per_second": 0.819,
      "step": 1500
    },
    {
      "epoch": 10.1,
      "learning_rate": 2.2813048053314627e-05,
      "loss": 0.8601,
      "step": 2000
    },
    {
      "epoch": 10.1,
      "eval_accuracy": 0.4907161803713528,
      "eval_f1": 0.5656528274556744,
      "eval_loss": 2.7952940464019775,
      "eval_precision": 0.7446099073666071,
      "eval_runtime": 108.5624,
      "eval_samples_per_second": 24.309,
      "eval_steps_per_second": 0.811,
      "step": 2000
    },
    {
      "epoch": 12.63,
      "learning_rate": 2.0182392143107683e-05,
      "loss": 0.5645,
      "step": 2500
    },
    {
      "epoch": 12.63,
      "eval_accuracy": 0.6862447896930656,
      "eval_f1": 0.7421301241460049,
      "eval_loss": 1.9828652143478394,
      "eval_precision": 0.836316121433408,
      "eval_runtime": 101.2702,
      "eval_samples_per_second": 26.059,
      "eval_steps_per_second": 0.869,
      "step": 2500
    },
    {
      "epoch": 15.15,
      "learning_rate": 1.7551736232900737e-05,
      "loss": 0.4009,
      "step": 3000
    },
    {
      "epoch": 15.15,
      "eval_accuracy": 0.7635467980295566,
      "eval_f1": 0.8174024577222706,
      "eval_loss": 1.453549861907959,
      "eval_precision": 0.9000157931943787,
      "eval_runtime": 107.7592,
      "eval_samples_per_second": 24.49,
      "eval_steps_per_second": 0.817,
      "step": 3000
    },
    {
      "epoch": 17.68,
      "learning_rate": 1.4921080322693792e-05,
      "loss": 0.3054,
      "step": 3500
    },
    {
      "epoch": 17.68,
      "eval_accuracy": 0.7881773399014779,
      "eval_f1": 0.8297806830083403,
      "eval_loss": 1.1425673961639404,
      "eval_precision": 0.905752007054303,
      "eval_runtime": 106.3252,
      "eval_samples_per_second": 24.82,
      "eval_steps_per_second": 0.828,
      "step": 3500
    },
    {
      "epoch": 20.2,
      "learning_rate": 1.2290424412486847e-05,
      "loss": 0.2448,
      "step": 4000
    },
    {
      "epoch": 20.2,
      "eval_accuracy": 0.8188707843880257,
      "eval_f1": 0.8593023386044745,
      "eval_loss": 0.9859854578971863,
      "eval_precision": 0.9206175798530246,
      "eval_runtime": 107.5476,
      "eval_samples_per_second": 24.538,
      "eval_steps_per_second": 0.818,
      "step": 4000
    },
    {
      "epoch": 22.73,
      "learning_rate": 9.659768502279902e-06,
      "loss": 0.2116,
      "step": 4500
    },
    {
      "epoch": 22.73,
      "eval_accuracy": 0.8325123152709359,
      "eval_f1": 0.8711410752519451,
      "eval_loss": 0.8820037841796875,
      "eval_precision": 0.9261488248866633,
      "eval_runtime": 107.1712,
      "eval_samples_per_second": 24.624,
      "eval_steps_per_second": 0.821,
      "step": 4500
    },
    {
      "epoch": 25.25,
      "learning_rate": 7.029112592072957e-06,
      "loss": 0.1863,
      "step": 5000
    },
    {
      "epoch": 25.25,
      "eval_accuracy": 0.8465327775672603,
      "eval_f1": 0.8848136570821419,
      "eval_loss": 0.8190948367118835,
      "eval_precision": 0.9366165612791744,
      "eval_runtime": 101.4217,
      "eval_samples_per_second": 26.02,
      "eval_steps_per_second": 0.868,
      "step": 5000
    },
    {
      "epoch": 27.78,
      "learning_rate": 4.398456681866012e-06,
      "loss": 0.1701,
      "step": 5500
    },
    {
      "epoch": 27.78,
      "eval_accuracy": 0.8632057597574839,
      "eval_f1": 0.8953598709937869,
      "eval_loss": 0.7504324913024902,
      "eval_precision": 0.9379743242290526,
      "eval_runtime": 106.5347,
      "eval_samples_per_second": 24.771,
      "eval_steps_per_second": 0.826,
      "step": 5500
    },
    {
      "epoch": 30.3,
      "learning_rate": 1.767800771659067e-06,
      "loss": 0.1558,
      "step": 6000
    },
    {
      "epoch": 30.3,
      "eval_accuracy": 0.8609321712769988,
      "eval_f1": 0.8955970854963186,
      "eval_loss": 0.7665356993675232,
      "eval_precision": 0.9398430168070748,
      "eval_runtime": 106.7434,
      "eval_samples_per_second": 24.723,
      "eval_steps_per_second": 0.824,
      "step": 6000
    },
    {
      "epoch": 32.0,
      "step": 6336,
      "total_flos": 3.804433776973221e+19,
      "train_loss": 0.9127645113251426,
      "train_runtime": 39385.6266,
      "train_samples_per_second": 19.295,
      "train_steps_per_second": 0.161
    }
  ],
  "max_steps": 6336,
  "num_train_epochs": 32,
  "total_flos": 3.804433776973221e+19,
  "trial_name": null,
  "trial_params": null
}