ivangtorre commited on
Commit
cd3386c
1 Parent(s): fd1c892

Add model files

Browse files

Files changed (5) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +1 -1
  3. trainer_state.json +11 -221
  4. training_args.bin +1 -1
  5. vocab.json +1 -1
config.json CHANGED
@@ -71,6 +71,6 @@
71
  "num_feat_extract_layers": 7,
72
  "num_hidden_layers": 24,
73
  "pad_token_id": 30,
74
- "transformers_version": "4.4.2",
75
  "vocab_size": 31
76
  }
71
  "num_feat_extract_layers": 7,
72
  "num_hidden_layers": 24,
73
  "pad_token_id": 30,
74
+ "transformers_version": "4.5.0.dev0",
75
  "vocab_size": 31
76
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab46384537a8ea6bbfd53bb2a4715eb721a0de52c3746a25aa3d5931eae1a37
3
  size 1262055847
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e816e78ee7fd0e498f93f933dd0b18034841e0ba38042639fceb7d006be4270
3
  size 1262055847
trainer_state.json CHANGED
@@ -1,240 +1,30 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 18.95583596214511,
5
- "global_step": 8000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.18,
12
- "learning_rate": 0.00011848341232227489,
13
- "loss": 5.8456,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.18,
18
- "eval_loss": 2.693875551223755,
19
- "eval_runtime": 1054.431,
20
- "eval_samples_per_second": 4.905,
21
- "eval_wer": 1.0,
22
  "step": 500
23
- },
24
- {
25
- "epoch": 2.37,
26
- "learning_rate": 0.00023696682464454977,
27
- "loss": 0.5706,
28
- "step": 1000
29
- },
30
- {
31
- "epoch": 2.37,
32
- "eval_loss": 0.19720512628555298,
33
- "eval_runtime": 965.5246,
34
- "eval_samples_per_second": 5.357,
35
- "eval_wer": 0.4136704756426013,
36
- "step": 1000
37
- },
38
- {
39
- "epoch": 3.55,
40
- "learning_rate": 0.0003554502369668247,
41
- "loss": 0.2135,
42
- "step": 1500
43
- },
44
- {
45
- "epoch": 3.55,
46
- "eval_loss": 0.17894236743450165,
47
- "eval_runtime": 829.9805,
48
- "eval_samples_per_second": 6.231,
49
- "eval_wer": 0.3831812357817117,
50
- "step": 1500
51
- },
52
- {
53
- "epoch": 4.74,
54
- "learning_rate": 0.00039178515007898897,
55
- "loss": 0.1761,
56
- "step": 2000
57
- },
58
- {
59
- "epoch": 4.74,
60
- "eval_loss": 0.1792241483926773,
61
- "eval_runtime": 839.1507,
62
- "eval_samples_per_second": 6.163,
63
- "eval_wer": 0.3637789922338729,
64
- "step": 2000
65
- },
66
- {
67
- "epoch": 5.92,
68
- "learning_rate": 0.0003786203264876251,
69
- "loss": 0.1403,
70
- "step": 2500
71
- },
72
- {
73
- "epoch": 5.92,
74
- "eval_loss": 0.16667363047599792,
75
- "eval_runtime": 773.0615,
76
- "eval_samples_per_second": 6.69,
77
- "eval_wer": 0.3549407734748843,
78
- "step": 2500
79
- },
80
- {
81
- "epoch": 7.11,
82
- "learning_rate": 0.00036545550289626125,
83
- "loss": 0.1206,
84
- "step": 3000
85
- },
86
- {
87
- "epoch": 7.11,
88
- "eval_loss": 0.16922971606254578,
89
- "eval_runtime": 754.7522,
90
- "eval_samples_per_second": 6.853,
91
- "eval_wer": 0.35033862406191985,
92
- "step": 3000
93
- },
94
- {
95
- "epoch": 8.29,
96
- "learning_rate": 0.00035229067930489733,
97
- "loss": 0.1065,
98
- "step": 3500
99
- },
100
- {
101
- "epoch": 8.29,
102
- "eval_loss": 0.17697516083717346,
103
- "eval_runtime": 830.9983,
104
- "eval_samples_per_second": 6.224,
105
- "eval_wer": 0.34748842925502704,
106
- "step": 3500
107
- },
108
- {
109
- "epoch": 9.48,
110
- "learning_rate": 0.00033912585571353347,
111
- "loss": 0.0949,
112
- "step": 4000
113
- },
114
- {
115
- "epoch": 9.48,
116
- "eval_loss": 0.17623142898082733,
117
- "eval_runtime": 808.622,
118
- "eval_samples_per_second": 6.396,
119
- "eval_wer": 0.34633789190178593,
120
- "step": 4000
121
- },
122
- {
123
- "epoch": 10.66,
124
- "learning_rate": 0.0003259610321221696,
125
- "loss": 0.0834,
126
- "step": 4500
127
- },
128
- {
129
- "epoch": 10.66,
130
- "eval_loss": 0.17101719975471497,
131
- "eval_runtime": 805.7401,
132
- "eval_samples_per_second": 6.419,
133
- "eval_wer": 0.33004732892294014,
134
- "step": 4500
135
- },
136
- {
137
- "epoch": 11.85,
138
- "learning_rate": 0.0003127962085308057,
139
- "loss": 0.0781,
140
- "step": 5000
141
- },
142
- {
143
- "epoch": 11.85,
144
- "eval_loss": 0.1730242371559143,
145
- "eval_runtime": 801.4866,
146
- "eval_samples_per_second": 6.453,
147
- "eval_wer": 0.3337342781685537,
148
- "step": 5000
149
- },
150
- {
151
- "epoch": 13.03,
152
- "learning_rate": 0.00029963138493944183,
153
- "loss": 0.0702,
154
- "step": 5500
155
- },
156
- {
157
- "epoch": 13.03,
158
- "eval_loss": 0.1908612698316574,
159
- "eval_runtime": 817.2678,
160
- "eval_samples_per_second": 6.328,
161
- "eval_wer": 0.3248437622571451,
162
- "step": 5500
163
- },
164
- {
165
- "epoch": 14.22,
166
- "learning_rate": 0.00028646656134807797,
167
- "loss": 0.065,
168
- "step": 6000
169
- },
170
- {
171
- "epoch": 14.22,
172
- "eval_loss": 0.19133996963500977,
173
- "eval_runtime": 815.1424,
174
- "eval_samples_per_second": 6.345,
175
- "eval_wer": 0.3376304160238475,
176
- "step": 6000
177
- },
178
- {
179
- "epoch": 15.4,
180
- "learning_rate": 0.00027330173775671406,
181
- "loss": 0.0634,
182
- "step": 6500
183
- },
184
- {
185
- "epoch": 15.4,
186
- "eval_loss": 0.17903825640678406,
187
- "eval_runtime": 788.5559,
188
- "eval_samples_per_second": 6.559,
189
- "eval_wer": 0.32520984232408545,
190
- "step": 6500
191
- },
192
- {
193
- "epoch": 16.59,
194
- "learning_rate": 0.0002601369141653502,
195
- "loss": 0.0574,
196
- "step": 7000
197
- },
198
- {
199
- "epoch": 16.59,
200
- "eval_loss": 0.2020258903503418,
201
- "eval_runtime": 1572.1771,
202
- "eval_samples_per_second": 3.29,
203
- "eval_wer": 0.33182543210522186,
204
- "step": 7000
205
- },
206
- {
207
- "epoch": 17.77,
208
- "learning_rate": 0.00024697209057398633,
209
- "loss": 0.0539,
210
- "step": 7500
211
- },
212
- {
213
- "epoch": 17.77,
214
- "eval_loss": 0.18831460177898407,
215
- "eval_runtime": 887.0107,
216
- "eval_samples_per_second": 5.831,
217
- "eval_wer": 0.3172083780038177,
218
- "step": 7500
219
- },
220
- {
221
- "epoch": 18.96,
222
- "learning_rate": 0.00023380726698262242,
223
- "loss": 0.0518,
224
- "step": 8000
225
- },
226
- {
227
- "epoch": 18.96,
228
- "eval_loss": 0.19699327647686005,
229
- "eval_runtime": 927.4568,
230
- "eval_samples_per_second": 5.577,
231
- "eval_wer": 0.31524723478806577,
232
- "step": 8000
233
  }
234
  ],
235
- "max_steps": 16880,
236
- "num_train_epochs": 40,
237
- "total_flos": 3.909573475423295e+19,
238
  "trial_name": null,
239
  "trial_params": null
240
  }
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.1845425867507886,
5
+ "global_step": 500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.18,
12
+ "learning_rate": 0.0003470916966876807,
13
+ "loss": 1.587,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.18,
18
+ "eval_loss": 0.2940497398376465,
19
+ "eval_runtime": 783.4997,
20
+ "eval_samples_per_second": 6.601,
21
+ "eval_wer": 0.5440472766257878,
22
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
+ "max_steps": 2110,
26
+ "num_train_epochs": 5,
27
+ "total_flos": 2.4510852111832704e+18,
28
  "trial_name": null,
29
  "trial_params": null
30
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ff2eca68c59215249e3d45e21b893cb00ca2fcf912465cd2d8b55458c36c22
3
  size 2287
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474caa22f1c7f0c4e89880f0d02b07015187ad5c2b1a354e1f8340ea7bbd6181
3
  size 2287
vocab.json CHANGED
@@ -1 +1 @@
1
- {"c": 0, "\u00f1": 1, "f": 2, "i": 3, "m": 4, "a": 5, "w": 6, "n": 7, "g": 8, "e": 9, "t": 10, "d": 11, "o": 12, "v": 13, "j": 14, "z": 16, "b": 17, "h": 18, "k": 19, "p": 20, "q": 21, "r": 22, "l": 23, "y": 24, "s": 25, "x": 26, "\u00ed": 27, "u": 28, "|": 15, "[UNK]": 29, "[PAD]": 30}
1
+ {"r": 0, "w": 1, "e": 2, "a": 3, "b": 4, "p": 5, "m": 7, "x": 8, "q": 9, "d": 10, "g": 11, "h": 12, "f": 13, "\u00ed": 14, "v": 15, "c": 16, "\u00f1": 17, "i": 18, "t": 19, "y": 20, "n": 21, "z": 22, "o": 23, "l": 24, "s": 25, "k": 26, "j": 27, "u": 28, "|": 6, "[UNK]": 29, "[PAD]": 30}