File size: 6,024 Bytes
ffc6710
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6782872300113679,
  "best_model_checkpoint": "wavlm-base/checkpoint-5000",
  "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": 4.4506,
      "step": 500
    },
    {
      "epoch": 2.53,
      "eval_accuracy": 0.02235695339143615,
      "eval_f1": 0.006616186351103852,
      "eval_loss": 4.86008358001709,
      "eval_precision": 0.013553337387865622,
      "eval_runtime": 71.9324,
      "eval_samples_per_second": 36.687,
      "eval_steps_per_second": 1.223,
      "step": 500
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.8074359873728517e-05,
      "loss": 3.0523,
      "step": 1000
    },
    {
      "epoch": 5.05,
      "eval_accuracy": 0.07199696854869268,
      "eval_f1": 0.03943960465213343,
      "eval_loss": 4.667360305786133,
      "eval_precision": 0.0460329111931258,
      "eval_runtime": 71.0687,
      "eval_samples_per_second": 37.133,
      "eval_steps_per_second": 1.238,
      "step": 1000
    },
    {
      "epoch": 7.58,
      "learning_rate": 2.5443703963521573e-05,
      "loss": 1.949,
      "step": 1500
    },
    {
      "epoch": 7.58,
      "eval_accuracy": 0.11557408109132247,
      "eval_f1": 0.10642928153043356,
      "eval_loss": 4.153301239013672,
      "eval_precision": 0.18473852089235457,
      "eval_runtime": 71.0445,
      "eval_samples_per_second": 37.146,
      "eval_steps_per_second": 1.239,
      "step": 1500
    },
    {
      "epoch": 10.1,
      "learning_rate": 2.2813048053314627e-05,
      "loss": 1.3427,
      "step": 2000
    },
    {
      "epoch": 10.1,
      "eval_accuracy": 0.14475179992421372,
      "eval_f1": 0.1346763066246049,
      "eval_loss": 3.8172836303710938,
      "eval_precision": 0.23822785193835883,
      "eval_runtime": 74.8027,
      "eval_samples_per_second": 35.279,
      "eval_steps_per_second": 1.176,
      "step": 2000
    },
    {
      "epoch": 12.63,
      "learning_rate": 2.0182392143107683e-05,
      "loss": 1.0064,
      "step": 2500
    },
    {
      "epoch": 12.63,
      "eval_accuracy": 0.2182644941265631,
      "eval_f1": 0.23851786199348127,
      "eval_loss": 3.5546185970306396,
      "eval_precision": 0.44639974594463316,
      "eval_runtime": 71.1082,
      "eval_samples_per_second": 37.112,
      "eval_steps_per_second": 1.238,
      "step": 2500
    },
    {
      "epoch": 15.15,
      "learning_rate": 1.7551736232900737e-05,
      "loss": 0.7985,
      "step": 3000
    },
    {
      "epoch": 15.15,
      "eval_accuracy": 0.3842364532019704,
      "eval_f1": 0.4258289880546809,
      "eval_loss": 3.117234230041504,
      "eval_precision": 0.6336488091054493,
      "eval_runtime": 70.3629,
      "eval_samples_per_second": 37.506,
      "eval_steps_per_second": 1.251,
      "step": 3000
    },
    {
      "epoch": 17.68,
      "learning_rate": 1.4921080322693792e-05,
      "loss": 0.6505,
      "step": 3500
    },
    {
      "epoch": 17.68,
      "eval_accuracy": 0.5164835164835165,
      "eval_f1": 0.5994643376487049,
      "eval_loss": 2.9230926036834717,
      "eval_precision": 0.7677367523432096,
      "eval_runtime": 70.3236,
      "eval_samples_per_second": 37.527,
      "eval_steps_per_second": 1.251,
      "step": 3500
    },
    {
      "epoch": 20.2,
      "learning_rate": 1.2290424412486847e-05,
      "loss": 0.5367,
      "step": 4000
    },
    {
      "epoch": 20.2,
      "eval_accuracy": 0.5960591133004927,
      "eval_f1": 0.6755266051820856,
      "eval_loss": 2.4934628009796143,
      "eval_precision": 0.818165400699518,
      "eval_runtime": 69.6955,
      "eval_samples_per_second": 37.865,
      "eval_steps_per_second": 1.263,
      "step": 4000
    },
    {
      "epoch": 22.73,
      "learning_rate": 9.659768502279902e-06,
      "loss": 0.465,
      "step": 4500
    },
    {
      "epoch": 22.73,
      "eval_accuracy": 0.6411519514967791,
      "eval_f1": 0.7272288000165434,
      "eval_loss": 2.241117238998413,
      "eval_precision": 0.86241474957474,
      "eval_runtime": 70.29,
      "eval_samples_per_second": 37.544,
      "eval_steps_per_second": 1.252,
      "step": 4500
    },
    {
      "epoch": 25.25,
      "learning_rate": 7.029112592072957e-06,
      "loss": 0.4075,
      "step": 5000
    },
    {
      "epoch": 25.25,
      "eval_accuracy": 0.6782872300113679,
      "eval_f1": 0.76152721933526,
      "eval_loss": 2.134546995162964,
      "eval_precision": 0.8773557553113618,
      "eval_runtime": 70.2432,
      "eval_samples_per_second": 37.569,
      "eval_steps_per_second": 1.253,
      "step": 5000
    },
    {
      "epoch": 27.78,
      "learning_rate": 4.398456681866012e-06,
      "loss": 0.3793,
      "step": 5500
    },
    {
      "epoch": 27.78,
      "eval_accuracy": 0.6680560818491853,
      "eval_f1": 0.7542953137768733,
      "eval_loss": 2.2534902095794678,
      "eval_precision": 0.8791790950841867,
      "eval_runtime": 70.1811,
      "eval_samples_per_second": 37.603,
      "eval_steps_per_second": 1.254,
      "step": 5500
    },
    {
      "epoch": 30.3,
      "learning_rate": 1.767800771659067e-06,
      "loss": 0.3418,
      "step": 6000
    },
    {
      "epoch": 30.3,
      "eval_accuracy": 0.6661614247821145,
      "eval_f1": 0.7575999245015367,
      "eval_loss": 2.3390462398529053,
      "eval_precision": 0.8904662594400684,
      "eval_runtime": 70.3334,
      "eval_samples_per_second": 37.521,
      "eval_steps_per_second": 1.251,
      "step": 6000
    },
    {
      "epoch": 32.0,
      "step": 6336,
      "total_flos": 3.804690514724178e+19,
      "train_loss": 1.2320244793940072,
      "train_runtime": 19932.9865,
      "train_samples_per_second": 38.125,
      "train_steps_per_second": 0.318
    }
  ],
  "max_steps": 6336,
  "num_train_epochs": 32,
  "total_flos": 3.804690514724178e+19,
  "trial_name": null,
  "trial_params": null
}