warmestman commited on
Commit
10a580e
·
verified ·
1 Parent(s): 718f264

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large-v3",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 1280,
17
+ "decoder_attention_heads": 20,
18
+ "decoder_ffn_dim": 5120,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 32,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 32,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 32,
43
+ "num_mel_bins": 128,
44
+ "pad_token_id": 50256,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.38.0.dev0",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51866
52
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 50,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50364,
167
+ "pad_token_id": 50257,
168
+ "prev_sot_token_id": 50362,
169
+ "return_timestamps": false,
170
+ "suppress_tokens": [
171
+ 1,
172
+ 2,
173
+ 7,
174
+ 8,
175
+ 9,
176
+ 10,
177
+ 14,
178
+ 25,
179
+ 26,
180
+ 27,
181
+ 28,
182
+ 29,
183
+ 31,
184
+ 58,
185
+ 59,
186
+ 60,
187
+ 61,
188
+ 62,
189
+ 63,
190
+ 90,
191
+ 91,
192
+ 92,
193
+ 93,
194
+ 359,
195
+ 503,
196
+ 522,
197
+ 542,
198
+ 873,
199
+ 893,
200
+ 902,
201
+ 918,
202
+ 922,
203
+ 931,
204
+ 1350,
205
+ 1853,
206
+ 1982,
207
+ 2460,
208
+ 2627,
209
+ 3246,
210
+ 3253,
211
+ 3268,
212
+ 3536,
213
+ 3846,
214
+ 3961,
215
+ 4183,
216
+ 4667,
217
+ 6585,
218
+ 6647,
219
+ 7273,
220
+ 9061,
221
+ 9383,
222
+ 10428,
223
+ 10929,
224
+ 11938,
225
+ 12033,
226
+ 12331,
227
+ 12562,
228
+ 13793,
229
+ 14157,
230
+ 14635,
231
+ 15265,
232
+ 15618,
233
+ 16553,
234
+ 16604,
235
+ 18362,
236
+ 18956,
237
+ 20075,
238
+ 21675,
239
+ 22520,
240
+ 26130,
241
+ 26161,
242
+ 26435,
243
+ 28279,
244
+ 29464,
245
+ 31650,
246
+ 32302,
247
+ 32470,
248
+ 36865,
249
+ 42863,
250
+ 47425,
251
+ 49870,
252
+ 50254,
253
+ 50258,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362,
258
+ 50363
259
+ ],
260
+ "task_to_id": {
261
+ "transcribe": 50360,
262
+ "translate": 50359
263
+ },
264
+ "transformers_version": "4.38.0.dev0"
265
+ }
last-checkpoint/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2d0e6dc3a0a3cb0e78c67a617f73907c8782cfdb1d92576f72fe63fe84ce1d
3
+ size 4993448880
last-checkpoint/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f09bb99c6964c0121b34c9f37c63e5bcf6766e01d4f789e5b6ad5bef47ff520
3
+ size 1180663192
last-checkpoint/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d1730c3ecc75ca8b98338f8305200732ffa3ff6c6f8d8301f20b5d21e51360
3
+ size 3095446256
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943488f319c579b17e95c507cdca4305465e095da760375c2bd0063ba7eb635c
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160e35db71592c700222e3cea1c8f7a567a820242110e1c69d8a8d82e01ac9b2
3
+ size 1064
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 41.504867719047354,
3
+ "best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-1000",
4
+ "epoch": 5.9880239520958085,
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": 0.15,
13
+ "learning_rate": 5e-06,
14
+ "loss": 1.1872,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.3,
19
+ "learning_rate": 1e-05,
20
+ "loss": 0.7033,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.45,
25
+ "learning_rate": 1.5e-05,
26
+ "loss": 0.4953,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.6,
31
+ "learning_rate": 2e-05,
32
+ "loss": 0.3952,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.75,
37
+ "learning_rate": 2.5e-05,
38
+ "loss": 0.3674,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.9,
43
+ "learning_rate": 3e-05,
44
+ "loss": 0.3351,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 1.05,
49
+ "learning_rate": 3.5e-05,
50
+ "loss": 0.2835,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 1.2,
55
+ "learning_rate": 4e-05,
56
+ "loss": 0.2188,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 1.35,
61
+ "learning_rate": 4.5e-05,
62
+ "loss": 0.2255,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 1.5,
67
+ "learning_rate": 5e-05,
68
+ "loss": 0.22,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 1.65,
73
+ "learning_rate": 5.500000000000001e-05,
74
+ "loss": 0.236,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 1.8,
79
+ "learning_rate": 6e-05,
80
+ "loss": 0.2212,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 1.95,
85
+ "learning_rate": 6.500000000000001e-05,
86
+ "loss": 0.2182,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 2.1,
91
+ "learning_rate": 7e-05,
92
+ "loss": 0.1616,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 2.25,
97
+ "learning_rate": 7.500000000000001e-05,
98
+ "loss": 0.1583,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 2.4,
103
+ "learning_rate": 8e-05,
104
+ "loss": 0.1514,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 2.54,
109
+ "learning_rate": 8.5e-05,
110
+ "loss": 0.1729,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 2.69,
115
+ "learning_rate": 9e-05,
116
+ "loss": 0.1626,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 2.84,
121
+ "learning_rate": 9.5e-05,
122
+ "loss": 0.1807,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 2.99,
127
+ "learning_rate": 0.0001,
128
+ "loss": 0.1821,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 3.14,
133
+ "learning_rate": 9.973684210526316e-05,
134
+ "loss": 0.1437,
135
+ "step": 525
136
+ },
137
+ {
138
+ "epoch": 3.29,
139
+ "learning_rate": 9.947368421052632e-05,
140
+ "loss": 0.1333,
141
+ "step": 550
142
+ },
143
+ {
144
+ "epoch": 3.44,
145
+ "learning_rate": 9.921052631578947e-05,
146
+ "loss": 0.1411,
147
+ "step": 575
148
+ },
149
+ {
150
+ "epoch": 3.59,
151
+ "learning_rate": 9.894736842105263e-05,
152
+ "loss": 0.1341,
153
+ "step": 600
154
+ },
155
+ {
156
+ "epoch": 3.74,
157
+ "learning_rate": 9.868421052631579e-05,
158
+ "loss": 0.1371,
159
+ "step": 625
160
+ },
161
+ {
162
+ "epoch": 3.89,
163
+ "learning_rate": 9.842105263157894e-05,
164
+ "loss": 0.1365,
165
+ "step": 650
166
+ },
167
+ {
168
+ "epoch": 4.04,
169
+ "learning_rate": 9.815789473684211e-05,
170
+ "loss": 0.118,
171
+ "step": 675
172
+ },
173
+ {
174
+ "epoch": 4.19,
175
+ "learning_rate": 9.789473684210527e-05,
176
+ "loss": 0.0827,
177
+ "step": 700
178
+ },
179
+ {
180
+ "epoch": 4.34,
181
+ "learning_rate": 9.763157894736843e-05,
182
+ "loss": 0.0879,
183
+ "step": 725
184
+ },
185
+ {
186
+ "epoch": 4.49,
187
+ "learning_rate": 9.736842105263158e-05,
188
+ "loss": 0.0937,
189
+ "step": 750
190
+ },
191
+ {
192
+ "epoch": 4.64,
193
+ "learning_rate": 9.710526315789474e-05,
194
+ "loss": 0.0887,
195
+ "step": 775
196
+ },
197
+ {
198
+ "epoch": 4.79,
199
+ "learning_rate": 9.68421052631579e-05,
200
+ "loss": 0.0946,
201
+ "step": 800
202
+ },
203
+ {
204
+ "epoch": 4.94,
205
+ "learning_rate": 9.657894736842105e-05,
206
+ "loss": 0.1032,
207
+ "step": 825
208
+ },
209
+ {
210
+ "epoch": 5.09,
211
+ "learning_rate": 9.631578947368421e-05,
212
+ "loss": 0.077,
213
+ "step": 850
214
+ },
215
+ {
216
+ "epoch": 5.24,
217
+ "learning_rate": 9.605263157894737e-05,
218
+ "loss": 0.0592,
219
+ "step": 875
220
+ },
221
+ {
222
+ "epoch": 5.39,
223
+ "learning_rate": 9.578947368421052e-05,
224
+ "loss": 0.0664,
225
+ "step": 900
226
+ },
227
+ {
228
+ "epoch": 5.54,
229
+ "learning_rate": 9.552631578947369e-05,
230
+ "loss": 0.066,
231
+ "step": 925
232
+ },
233
+ {
234
+ "epoch": 5.69,
235
+ "learning_rate": 9.526315789473685e-05,
236
+ "loss": 0.0641,
237
+ "step": 950
238
+ },
239
+ {
240
+ "epoch": 5.84,
241
+ "learning_rate": 9.5e-05,
242
+ "loss": 0.0662,
243
+ "step": 975
244
+ },
245
+ {
246
+ "epoch": 5.99,
247
+ "learning_rate": 9.473684210526316e-05,
248
+ "loss": 0.0691,
249
+ "step": 1000
250
+ },
251
+ {
252
+ "epoch": 5.99,
253
+ "eval_loss": 0.45974645018577576,
254
+ "eval_runtime": 585.199,
255
+ "eval_samples_per_second": 0.716,
256
+ "eval_steps_per_second": 0.091,
257
+ "eval_wer": 41.504867719047354,
258
+ "step": 1000
259
+ }
260
+ ],
261
+ "logging_steps": 25,
262
+ "max_steps": 10000,
263
+ "num_input_tokens_seen": 0,
264
+ "num_train_epochs": 60,
265
+ "save_steps": 1000,
266
+ "total_flos": 5.43090104303616e+19,
267
+ "train_batch_size": 16,
268
+ "trial_name": null,
269
+ "trial_params": null
270
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1972f394bef5f2dfba82d719e660c110d5e82dd9389cd87393cdd1f35c3201be
3
+ size 5112