fsicoli commited on
Commit
2cec1bb
1 Parent(s): 675eaa1

Upload 11 files

Browse files
config.json CHANGED
@@ -43,7 +43,7 @@
43
  "num_mel_bins": 128,
44
  "pad_token_id": 50256,
45
  "scale_embedding": false,
46
- "torch_dtype": "float16",
47
  "transformers_version": "4.37.0.dev0",
48
  "use_cache": true,
49
  "use_weighted_layer_sum": false,
 
43
  "num_mel_bins": 128,
44
  "pad_token_id": 50256,
45
  "scale_embedding": false,
46
+ "torch_dtype": "float32",
47
  "transformers_version": "4.37.0.dev0",
48
  "use_cache": true,
49
  "use_weighted_layer_sum": false,
generation_config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 7,
5
+ 0
6
+ ],
7
+ [
8
+ 10,
9
+ 17
10
+ ],
11
+ [
12
+ 12,
13
+ 18
14
+ ],
15
+ [
16
+ 13,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 1
22
+ ],
23
+ [
24
+ 17,
25
+ 14
26
+ ],
27
+ [
28
+ 19,
29
+ 11
30
+ ],
31
+ [
32
+ 21,
33
+ 4
34
+ ],
35
+ [
36
+ 24,
37
+ 1
38
+ ],
39
+ [
40
+ 25,
41
+ 6
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50360
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|yue|>": 50358,
162
+ "<|zh|>": 50260
163
+ },
164
+ "max_initial_timestamp_index": 1,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50364,
167
+ "pad_token_id": 50257,
168
+ "return_timestamps": false,
169
+ "suppress_tokens": [
170
+ 1,
171
+ 2,
172
+ 7,
173
+ 8,
174
+ 9,
175
+ 10,
176
+ 14,
177
+ 25,
178
+ 26,
179
+ 27,
180
+ 28,
181
+ 29,
182
+ 31,
183
+ 58,
184
+ 59,
185
+ 60,
186
+ 61,
187
+ 62,
188
+ 63,
189
+ 90,
190
+ 91,
191
+ 92,
192
+ 93,
193
+ 359,
194
+ 503,
195
+ 522,
196
+ 542,
197
+ 873,
198
+ 893,
199
+ 902,
200
+ 918,
201
+ 922,
202
+ 931,
203
+ 1350,
204
+ 1853,
205
+ 1982,
206
+ 2460,
207
+ 2627,
208
+ 3246,
209
+ 3253,
210
+ 3268,
211
+ 3536,
212
+ 3846,
213
+ 3961,
214
+ 4183,
215
+ 4667,
216
+ 6585,
217
+ 6647,
218
+ 7273,
219
+ 9061,
220
+ 9383,
221
+ 10428,
222
+ 10929,
223
+ 11938,
224
+ 12033,
225
+ 12331,
226
+ 12562,
227
+ 13793,
228
+ 14157,
229
+ 14635,
230
+ 15265,
231
+ 15618,
232
+ 16553,
233
+ 16604,
234
+ 18362,
235
+ 18956,
236
+ 20075,
237
+ 21675,
238
+ 22520,
239
+ 26130,
240
+ 26161,
241
+ 26435,
242
+ 28279,
243
+ 29464,
244
+ 31650,
245
+ 32302,
246
+ 32470,
247
+ 36865,
248
+ 42863,
249
+ 47425,
250
+ 49870,
251
+ 50254,
252
+ 50258,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362,
257
+ 50363
258
+ ],
259
+ "task_to_id": {
260
+ "transcribe": 50360,
261
+ "translate": 50359
262
+ },
263
+ "transformers_version": "4.37.0.dev0"
264
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14da2025731d949006200c34abfb6aa1be4cc2350ecc27dc6af559603a86225d
3
+ size 4993448880
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b38b2d250388274dbab6a134b7ff4184cb3525599666efa7cdefed5c99d82c
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b7a6a42c8f342e4252296a6744e5aeb820e8d8de08a16c9dd10adc396c1293
3
+ size 12333660476
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94dabcf3aa6388cb7358095beeacf8c08e10d0c57c65e895222ff8e1688faa47
3
+ size 14308
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734304bd0e6dc36b41c4ccbd3af99b577906c8419c323945dce4562d0d94fb39
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.25806451612903225,
5
+ "eval_steps": 1000,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1.1499999999999999e-08,
14
+ "loss": 0.7822,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.4e-08,
20
+ "loss": 1.3149,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3.6499999999999996e-08,
26
+ "loss": 0.7809,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 4.9e-08,
32
+ "loss": 1.2916,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 6.15e-08,
38
+ "loss": 0.7645,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 7.399999999999999e-08,
44
+ "loss": 1.3379,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 8.649999999999999e-08,
50
+ "loss": 0.7722,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 9.9e-08,
56
+ "loss": 1.281,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 1.115e-07,
62
+ "loss": 0.6998,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 1.24e-07,
68
+ "loss": 1.1532,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 1.365e-07,
74
+ "loss": 0.583,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 0.08,
79
+ "learning_rate": 1.49e-07,
80
+ "loss": 0.6693,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 1.615e-07,
86
+ "loss": 0.3395,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 0.09,
91
+ "learning_rate": 1.7399999999999997e-07,
92
+ "loss": 0.3597,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "learning_rate": 1.8649999999999998e-07,
98
+ "loss": 0.22,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 1.99e-07,
104
+ "loss": 0.3449,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 0.11,
109
+ "learning_rate": 2.1149999999999998e-07,
110
+ "loss": 0.2123,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 0.12,
115
+ "learning_rate": 2.24e-07,
116
+ "loss": 0.3362,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 0.12,
121
+ "learning_rate": 2.3649999999999998e-07,
122
+ "loss": 0.175,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 0.13,
127
+ "learning_rate": 2.4899999999999997e-07,
128
+ "loss": 0.3051,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 0.14,
133
+ "learning_rate": 2.615e-07,
134
+ "loss": 0.176,
135
+ "step": 525
136
+ },
137
+ {
138
+ "epoch": 0.14,
139
+ "learning_rate": 2.74e-07,
140
+ "loss": 0.2517,
141
+ "step": 550
142
+ },
143
+ {
144
+ "epoch": 0.15,
145
+ "learning_rate": 2.865e-07,
146
+ "loss": 0.1863,
147
+ "step": 575
148
+ },
149
+ {
150
+ "epoch": 0.15,
151
+ "learning_rate": 2.9899999999999996e-07,
152
+ "loss": 0.2614,
153
+ "step": 600
154
+ },
155
+ {
156
+ "epoch": 0.16,
157
+ "learning_rate": 3.115e-07,
158
+ "loss": 0.1942,
159
+ "step": 625
160
+ },
161
+ {
162
+ "epoch": 0.17,
163
+ "learning_rate": 3.24e-07,
164
+ "loss": 0.2901,
165
+ "step": 650
166
+ },
167
+ {
168
+ "epoch": 0.17,
169
+ "learning_rate": 3.3650000000000003e-07,
170
+ "loss": 0.1587,
171
+ "step": 675
172
+ },
173
+ {
174
+ "epoch": 0.18,
175
+ "learning_rate": 3.4899999999999996e-07,
176
+ "loss": 0.2128,
177
+ "step": 700
178
+ },
179
+ {
180
+ "epoch": 0.19,
181
+ "learning_rate": 3.6149999999999995e-07,
182
+ "loss": 0.1647,
183
+ "step": 725
184
+ },
185
+ {
186
+ "epoch": 0.19,
187
+ "learning_rate": 3.74e-07,
188
+ "loss": 0.2473,
189
+ "step": 750
190
+ },
191
+ {
192
+ "epoch": 0.2,
193
+ "learning_rate": 3.8649999999999997e-07,
194
+ "loss": 0.1415,
195
+ "step": 775
196
+ },
197
+ {
198
+ "epoch": 0.21,
199
+ "learning_rate": 3.99e-07,
200
+ "loss": 0.2367,
201
+ "step": 800
202
+ },
203
+ {
204
+ "epoch": 0.21,
205
+ "learning_rate": 4.1149999999999995e-07,
206
+ "loss": 0.1498,
207
+ "step": 825
208
+ },
209
+ {
210
+ "epoch": 0.22,
211
+ "learning_rate": 4.24e-07,
212
+ "loss": 0.2161,
213
+ "step": 850
214
+ },
215
+ {
216
+ "epoch": 0.23,
217
+ "learning_rate": 4.3649999999999997e-07,
218
+ "loss": 0.144,
219
+ "step": 875
220
+ },
221
+ {
222
+ "epoch": 0.23,
223
+ "learning_rate": 4.49e-07,
224
+ "loss": 0.2316,
225
+ "step": 900
226
+ },
227
+ {
228
+ "epoch": 0.24,
229
+ "learning_rate": 4.615e-07,
230
+ "loss": 0.1449,
231
+ "step": 925
232
+ },
233
+ {
234
+ "epoch": 0.25,
235
+ "learning_rate": 4.7399999999999993e-07,
236
+ "loss": 0.1513,
237
+ "step": 950
238
+ },
239
+ {
240
+ "epoch": 0.25,
241
+ "learning_rate": 4.864999999999999e-07,
242
+ "loss": 0.1855,
243
+ "step": 975
244
+ },
245
+ {
246
+ "epoch": 0.26,
247
+ "learning_rate": 4.99e-07,
248
+ "loss": 0.199,
249
+ "step": 1000
250
+ },
251
+ {
252
+ "epoch": 0.26,
253
+ "eval_loss": 0.15628743171691895,
254
+ "eval_runtime": 184706.1006,
255
+ "eval_samples_per_second": 0.051,
256
+ "eval_steps_per_second": 0.006,
257
+ "eval_wer": 0.1124272786037492,
258
+ "step": 1000
259
+ }
260
+ ],
261
+ "logging_steps": 25,
262
+ "max_steps": 5000,
263
+ "num_input_tokens_seen": 0,
264
+ "num_train_epochs": 2,
265
+ "save_steps": 1000,
266
+ "total_flos": 2.717998645248e+19,
267
+ "train_batch_size": 8,
268
+ "trial_name": null,
269
+ "trial_params": null
270
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7333482a7c3f07f0c77f8cb008cb1f8732d2c0821c26cc6972eb4ef6e08368a7
3
+ size 4856