File size: 4,947 Bytes
312248e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8596961572832886,
  "eval_steps": 200,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 2e-05,
      "loss": 0.5179,
      "step": 100
    },
    {
      "epoch": 0.36,
      "learning_rate": 4e-05,
      "loss": 0.4435,
      "step": 200
    },
    {
      "epoch": 0.36,
      "eval_f1_score": 0.4513274336283186,
      "eval_label_f1": 0.7168141592920354,
      "eval_loss": 0.4356614947319031,
      "eval_runtime": 45.8378,
      "eval_samples_per_second": 2.182,
      "eval_steps_per_second": 0.087,
      "eval_wer": 0.059877955758962625,
      "step": 200
    },
    {
      "epoch": 0.54,
      "learning_rate": 6e-05,
      "loss": 0.4296,
      "step": 300
    },
    {
      "epoch": 0.71,
      "learning_rate": 8e-05,
      "loss": 0.4309,
      "step": 400
    },
    {
      "epoch": 0.71,
      "eval_f1_score": 0.6751054852320675,
      "eval_label_f1": 0.8354430379746836,
      "eval_loss": 0.43058258295059204,
      "eval_runtime": 45.2842,
      "eval_samples_per_second": 2.208,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 0.4262,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4235,
      "step": 600
    },
    {
      "epoch": 1.07,
      "eval_f1_score": 0.6721991701244813,
      "eval_label_f1": 0.8547717842323652,
      "eval_loss": 0.42819398641586304,
      "eval_runtime": 45.2307,
      "eval_samples_per_second": 2.211,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 600
    },
    {
      "epoch": 1.25,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.423,
      "step": 700
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4267,
      "step": 800
    },
    {
      "epoch": 1.43,
      "eval_f1_score": 0.7073170731707317,
      "eval_label_f1": 0.845528455284553,
      "eval_loss": 0.4269372224807739,
      "eval_runtime": 45.2446,
      "eval_samples_per_second": 2.21,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 800
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4283,
      "step": 900
    },
    {
      "epoch": 1.79,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4254,
      "step": 1000
    },
    {
      "epoch": 1.79,
      "eval_f1_score": 0.7272727272727273,
      "eval_label_f1": 0.8677685950413223,
      "eval_loss": 0.42638763785362244,
      "eval_runtime": 45.2086,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 1000
    },
    {
      "epoch": 1.97,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.4225,
      "step": 1100
    },
    {
      "epoch": 2.14,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.4264,
      "step": 1200
    },
    {
      "epoch": 2.14,
      "eval_f1_score": 0.7398373983739838,
      "eval_label_f1": 0.8780487804878049,
      "eval_loss": 0.42636168003082275,
      "eval_runtime": 45.2052,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 1200
    },
    {
      "epoch": 2.32,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4263,
      "step": 1300
    },
    {
      "epoch": 2.5,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4206,
      "step": 1400
    },
    {
      "epoch": 2.5,
      "eval_f1_score": 0.7206477732793523,
      "eval_label_f1": 0.8582995951417003,
      "eval_loss": 0.4262264370918274,
      "eval_runtime": 45.2829,
      "eval_samples_per_second": 2.208,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 1400
    },
    {
      "epoch": 2.68,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4244,
      "step": 1500
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.4232,
      "step": 1600
    },
    {
      "epoch": 2.86,
      "eval_f1_score": 0.7410358565737052,
      "eval_label_f1": 0.8685258964143426,
      "eval_loss": 0.42596718668937683,
      "eval_runtime": 45.2943,
      "eval_samples_per_second": 2.208,
      "eval_steps_per_second": 0.088,
      "eval_wer": 0.059877955758962625,
      "step": 1600
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 200,
  "total_flos": 4.383735905718576e+20,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}