mabdelm2 commited on
Commit
8e94cef
·
1 Parent(s): 77014f2

Training in progress, step 1000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1e87178b78f5707919d7f2583923dbac591035a6b4d3a527c9846dc4378c9fa
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace45ef8bdefbf122e0cb756edc31486cf7c4a21f46930e062f8861b242e0251
3
  size 966995080
run 1 checkpoint-1000/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
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": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
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": 12,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.36.0.dev0",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51865
52
+ }
run 1 checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
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
+ 50359
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
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 1,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "return_timestamps": false,
168
+ "suppress_tokens": [
169
+ 1,
170
+ 2,
171
+ 7,
172
+ 8,
173
+ 9,
174
+ 10,
175
+ 14,
176
+ 25,
177
+ 26,
178
+ 27,
179
+ 28,
180
+ 29,
181
+ 31,
182
+ 58,
183
+ 59,
184
+ 60,
185
+ 61,
186
+ 62,
187
+ 63,
188
+ 90,
189
+ 91,
190
+ 92,
191
+ 93,
192
+ 359,
193
+ 503,
194
+ 522,
195
+ 542,
196
+ 873,
197
+ 893,
198
+ 902,
199
+ 918,
200
+ 922,
201
+ 931,
202
+ 1350,
203
+ 1853,
204
+ 1982,
205
+ 2460,
206
+ 2627,
207
+ 3246,
208
+ 3253,
209
+ 3268,
210
+ 3536,
211
+ 3846,
212
+ 3961,
213
+ 4183,
214
+ 4667,
215
+ 6585,
216
+ 6647,
217
+ 7273,
218
+ 9061,
219
+ 9383,
220
+ 10428,
221
+ 10929,
222
+ 11938,
223
+ 12033,
224
+ 12331,
225
+ 12562,
226
+ 13793,
227
+ 14157,
228
+ 14635,
229
+ 15265,
230
+ 15618,
231
+ 16553,
232
+ 16604,
233
+ 18362,
234
+ 18956,
235
+ 20075,
236
+ 21675,
237
+ 22520,
238
+ 26130,
239
+ 26161,
240
+ 26435,
241
+ 28279,
242
+ 29464,
243
+ 31650,
244
+ 32302,
245
+ 32470,
246
+ 36865,
247
+ 42863,
248
+ 47425,
249
+ 49870,
250
+ 50254,
251
+ 50258,
252
+ 50358,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362
257
+ ],
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "transformers_version": "4.36.0.dev0"
263
+ }
run 1 checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace45ef8bdefbf122e0cb756edc31486cf7c4a21f46930e062f8861b242e0251
3
+ size 966995080
run 1 checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3967fea6743f1d218ab74f7acdb6f7f69774006a624ed83158e60ae26cb3e01
3
+ size 1925064044
run 1 checkpoint-1000/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
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
+ }
run 1 checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3540179bbcfe2a2e55d05fad49c806615d68122d33b057e8a5ff20ca08833829
3
+ size 14244
run 1 checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5101d8c1f86d6f48167e50b1164b9ba363ab76694ff2d5c1e326e3d5f94ecaef
3
+ size 1064
run 1 checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 35.4355371201219,
3
+ "best_model_checkpoint": "./content/drive/MyDrive/whisper-small-hi/checkpoint-1000",
4
+ "epoch": 2.444987775061125,
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": 0.06,
13
+ "learning_rate": 4.4e-07,
14
+ "loss": 2.073,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 9.400000000000001e-07,
20
+ "loss": 1.6171,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.18,
25
+ "learning_rate": 1.44e-06,
26
+ "loss": 1.1505,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.24,
31
+ "learning_rate": 1.94e-06,
32
+ "loss": 0.8303,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.31,
37
+ "learning_rate": 2.4400000000000004e-06,
38
+ "loss": 0.6825,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.37,
43
+ "learning_rate": 2.9400000000000002e-06,
44
+ "loss": 0.6282,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.43,
49
+ "learning_rate": 3.44e-06,
50
+ "loss": 0.5957,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.49,
55
+ "learning_rate": 3.94e-06,
56
+ "loss": 0.5421,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.55,
61
+ "learning_rate": 4.440000000000001e-06,
62
+ "loss": 0.4863,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 0.61,
67
+ "learning_rate": 4.94e-06,
68
+ "loss": 0.4577,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 0.67,
73
+ "learning_rate": 5.4400000000000004e-06,
74
+ "loss": 0.4241,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 0.73,
79
+ "learning_rate": 5.94e-06,
80
+ "loss": 0.3798,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 0.79,
85
+ "learning_rate": 6.440000000000001e-06,
86
+ "loss": 0.3282,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 0.86,
91
+ "learning_rate": 6.9400000000000005e-06,
92
+ "loss": 0.2936,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 0.92,
97
+ "learning_rate": 7.440000000000001e-06,
98
+ "loss": 0.2704,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 0.98,
103
+ "learning_rate": 7.94e-06,
104
+ "loss": 0.2582,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 1.04,
109
+ "learning_rate": 8.44e-06,
110
+ "loss": 0.218,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 1.1,
115
+ "learning_rate": 8.94e-06,
116
+ "loss": 0.1932,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 1.16,
121
+ "learning_rate": 9.440000000000001e-06,
122
+ "loss": 0.1963,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 1.22,
127
+ "learning_rate": 9.940000000000001e-06,
128
+ "loss": 0.1856,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 1.28,
133
+ "learning_rate": 9.937142857142858e-06,
134
+ "loss": 0.1859,
135
+ "step": 525
136
+ },
137
+ {
138
+ "epoch": 1.34,
139
+ "learning_rate": 9.865714285714285e-06,
140
+ "loss": 0.1849,
141
+ "step": 550
142
+ },
143
+ {
144
+ "epoch": 1.41,
145
+ "learning_rate": 9.794285714285714e-06,
146
+ "loss": 0.1733,
147
+ "step": 575
148
+ },
149
+ {
150
+ "epoch": 1.47,
151
+ "learning_rate": 9.722857142857143e-06,
152
+ "loss": 0.1758,
153
+ "step": 600
154
+ },
155
+ {
156
+ "epoch": 1.53,
157
+ "learning_rate": 9.651428571428572e-06,
158
+ "loss": 0.1719,
159
+ "step": 625
160
+ },
161
+ {
162
+ "epoch": 1.59,
163
+ "learning_rate": 9.58e-06,
164
+ "loss": 0.1663,
165
+ "step": 650
166
+ },
167
+ {
168
+ "epoch": 1.65,
169
+ "learning_rate": 9.508571428571429e-06,
170
+ "loss": 0.1743,
171
+ "step": 675
172
+ },
173
+ {
174
+ "epoch": 1.71,
175
+ "learning_rate": 9.437142857142858e-06,
176
+ "loss": 0.164,
177
+ "step": 700
178
+ },
179
+ {
180
+ "epoch": 1.77,
181
+ "learning_rate": 9.365714285714287e-06,
182
+ "loss": 0.1464,
183
+ "step": 725
184
+ },
185
+ {
186
+ "epoch": 1.83,
187
+ "learning_rate": 9.294285714285714e-06,
188
+ "loss": 0.1725,
189
+ "step": 750
190
+ },
191
+ {
192
+ "epoch": 1.89,
193
+ "learning_rate": 9.222857142857143e-06,
194
+ "loss": 0.1588,
195
+ "step": 775
196
+ },
197
+ {
198
+ "epoch": 1.96,
199
+ "learning_rate": 9.151428571428572e-06,
200
+ "loss": 0.1598,
201
+ "step": 800
202
+ },
203
+ {
204
+ "epoch": 2.02,
205
+ "learning_rate": 9.080000000000001e-06,
206
+ "loss": 0.133,
207
+ "step": 825
208
+ },
209
+ {
210
+ "epoch": 2.08,
211
+ "learning_rate": 9.00857142857143e-06,
212
+ "loss": 0.0881,
213
+ "step": 850
214
+ },
215
+ {
216
+ "epoch": 2.14,
217
+ "learning_rate": 8.937142857142857e-06,
218
+ "loss": 0.0899,
219
+ "step": 875
220
+ },
221
+ {
222
+ "epoch": 2.2,
223
+ "learning_rate": 8.865714285714287e-06,
224
+ "loss": 0.0875,
225
+ "step": 900
226
+ },
227
+ {
228
+ "epoch": 2.26,
229
+ "learning_rate": 8.794285714285716e-06,
230
+ "loss": 0.0796,
231
+ "step": 925
232
+ },
233
+ {
234
+ "epoch": 2.32,
235
+ "learning_rate": 8.722857142857145e-06,
236
+ "loss": 0.0873,
237
+ "step": 950
238
+ },
239
+ {
240
+ "epoch": 2.38,
241
+ "learning_rate": 8.651428571428572e-06,
242
+ "loss": 0.0855,
243
+ "step": 975
244
+ },
245
+ {
246
+ "epoch": 2.44,
247
+ "learning_rate": 8.580000000000001e-06,
248
+ "loss": 0.0825,
249
+ "step": 1000
250
+ },
251
+ {
252
+ "epoch": 2.44,
253
+ "eval_loss": 0.2965221107006073,
254
+ "eval_runtime": 1430.9073,
255
+ "eval_samples_per_second": 2.022,
256
+ "eval_steps_per_second": 0.253,
257
+ "eval_wer": 35.4355371201219,
258
+ "step": 1000
259
+ }
260
+ ],
261
+ "logging_steps": 25,
262
+ "max_steps": 4000,
263
+ "num_input_tokens_seen": 0,
264
+ "num_train_epochs": 10,
265
+ "save_steps": 1000,
266
+ "total_flos": 4.61505772191744e+18,
267
+ "trial_name": null,
268
+ "trial_params": null
269
+ }
run 1 checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7dd0878fdb53a8915b8b50536cccca48d61b29c290ff26b81a971b711bc365d
3
+ size 4856
run 1 checkpoint-2000/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
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": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
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": 12,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.36.0.dev0",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51865
52
+ }
run 1 checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
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
+ 50359
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
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 1,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "return_timestamps": false,
168
+ "suppress_tokens": [
169
+ 1,
170
+ 2,
171
+ 7,
172
+ 8,
173
+ 9,
174
+ 10,
175
+ 14,
176
+ 25,
177
+ 26,
178
+ 27,
179
+ 28,
180
+ 29,
181
+ 31,
182
+ 58,
183
+ 59,
184
+ 60,
185
+ 61,
186
+ 62,
187
+ 63,
188
+ 90,
189
+ 91,
190
+ 92,
191
+ 93,
192
+ 359,
193
+ 503,
194
+ 522,
195
+ 542,
196
+ 873,
197
+ 893,
198
+ 902,
199
+ 918,
200
+ 922,
201
+ 931,
202
+ 1350,
203
+ 1853,
204
+ 1982,
205
+ 2460,
206
+ 2627,
207
+ 3246,
208
+ 3253,
209
+ 3268,
210
+ 3536,
211
+ 3846,
212
+ 3961,
213
+ 4183,
214
+ 4667,
215
+ 6585,
216
+ 6647,
217
+ 7273,
218
+ 9061,
219
+ 9383,
220
+ 10428,
221
+ 10929,
222
+ 11938,
223
+ 12033,
224
+ 12331,
225
+ 12562,
226
+ 13793,
227
+ 14157,
228
+ 14635,
229
+ 15265,
230
+ 15618,
231
+ 16553,
232
+ 16604,
233
+ 18362,
234
+ 18956,
235
+ 20075,
236
+ 21675,
237
+ 22520,
238
+ 26130,
239
+ 26161,
240
+ 26435,
241
+ 28279,
242
+ 29464,
243
+ 31650,
244
+ 32302,
245
+ 32470,
246
+ 36865,
247
+ 42863,
248
+ 47425,
249
+ 49870,
250
+ 50254,
251
+ 50258,
252
+ 50358,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362
257
+ ],
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "transformers_version": "4.36.0.dev0"
263
+ }
run 1 checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e87178b78f5707919d7f2583923dbac591035a6b4d3a527c9846dc4378c9fa
3
+ size 966995080
run 1 checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c438623cc730e2b7bb70e6e0f44c24a5833960824c493d1dabd8a8a5798697cc
3
+ size 1925064044
run 1 checkpoint-2000/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
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
+ }
run 1 checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830da7d6cf5c27b731f87279d1d54a1d29a59fab11ab019d34021e73ccb0dde7
3
+ size 14244
run 1 checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80a609c64a12b4db2f38941ea479b9a30f9351b7aac74f4956e8686dc338317
3
+ size 1064
run 1 checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,518 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 34.22500634893761,
3
+ "best_model_checkpoint": "./content/drive/MyDrive/whisper-small-hi/checkpoint-2000",
4
+ "epoch": 4.88997555012225,
5
+ "eval_steps": 1000,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 4.4e-07,
14
+ "loss": 2.073,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 9.400000000000001e-07,
20
+ "loss": 1.6171,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.18,
25
+ "learning_rate": 1.44e-06,
26
+ "loss": 1.1505,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.24,
31
+ "learning_rate": 1.94e-06,
32
+ "loss": 0.8303,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.31,
37
+ "learning_rate": 2.4400000000000004e-06,
38
+ "loss": 0.6825,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.37,
43
+ "learning_rate": 2.9400000000000002e-06,
44
+ "loss": 0.6282,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.43,
49
+ "learning_rate": 3.44e-06,
50
+ "loss": 0.5957,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.49,
55
+ "learning_rate": 3.94e-06,
56
+ "loss": 0.5421,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.55,
61
+ "learning_rate": 4.440000000000001e-06,
62
+ "loss": 0.4863,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 0.61,
67
+ "learning_rate": 4.94e-06,
68
+ "loss": 0.4577,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 0.67,
73
+ "learning_rate": 5.4400000000000004e-06,
74
+ "loss": 0.4241,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 0.73,
79
+ "learning_rate": 5.94e-06,
80
+ "loss": 0.3798,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 0.79,
85
+ "learning_rate": 6.440000000000001e-06,
86
+ "loss": 0.3282,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 0.86,
91
+ "learning_rate": 6.9400000000000005e-06,
92
+ "loss": 0.2936,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 0.92,
97
+ "learning_rate": 7.440000000000001e-06,
98
+ "loss": 0.2704,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 0.98,
103
+ "learning_rate": 7.94e-06,
104
+ "loss": 0.2582,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 1.04,
109
+ "learning_rate": 8.44e-06,
110
+ "loss": 0.218,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 1.1,
115
+ "learning_rate": 8.94e-06,
116
+ "loss": 0.1932,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 1.16,
121
+ "learning_rate": 9.440000000000001e-06,
122
+ "loss": 0.1963,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 1.22,
127
+ "learning_rate": 9.940000000000001e-06,
128
+ "loss": 0.1856,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 1.28,
133
+ "learning_rate": 9.937142857142858e-06,
134
+ "loss": 0.1859,
135
+ "step": 525
136
+ },
137
+ {
138
+ "epoch": 1.34,
139
+ "learning_rate": 9.865714285714285e-06,
140
+ "loss": 0.1849,
141
+ "step": 550
142
+ },
143
+ {
144
+ "epoch": 1.41,
145
+ "learning_rate": 9.794285714285714e-06,
146
+ "loss": 0.1733,
147
+ "step": 575
148
+ },
149
+ {
150
+ "epoch": 1.47,
151
+ "learning_rate": 9.722857142857143e-06,
152
+ "loss": 0.1758,
153
+ "step": 600
154
+ },
155
+ {
156
+ "epoch": 1.53,
157
+ "learning_rate": 9.651428571428572e-06,
158
+ "loss": 0.1719,
159
+ "step": 625
160
+ },
161
+ {
162
+ "epoch": 1.59,
163
+ "learning_rate": 9.58e-06,
164
+ "loss": 0.1663,
165
+ "step": 650
166
+ },
167
+ {
168
+ "epoch": 1.65,
169
+ "learning_rate": 9.508571428571429e-06,
170
+ "loss": 0.1743,
171
+ "step": 675
172
+ },
173
+ {
174
+ "epoch": 1.71,
175
+ "learning_rate": 9.437142857142858e-06,
176
+ "loss": 0.164,
177
+ "step": 700
178
+ },
179
+ {
180
+ "epoch": 1.77,
181
+ "learning_rate": 9.365714285714287e-06,
182
+ "loss": 0.1464,
183
+ "step": 725
184
+ },
185
+ {
186
+ "epoch": 1.83,
187
+ "learning_rate": 9.294285714285714e-06,
188
+ "loss": 0.1725,
189
+ "step": 750
190
+ },
191
+ {
192
+ "epoch": 1.89,
193
+ "learning_rate": 9.222857142857143e-06,
194
+ "loss": 0.1588,
195
+ "step": 775
196
+ },
197
+ {
198
+ "epoch": 1.96,
199
+ "learning_rate": 9.151428571428572e-06,
200
+ "loss": 0.1598,
201
+ "step": 800
202
+ },
203
+ {
204
+ "epoch": 2.02,
205
+ "learning_rate": 9.080000000000001e-06,
206
+ "loss": 0.133,
207
+ "step": 825
208
+ },
209
+ {
210
+ "epoch": 2.08,
211
+ "learning_rate": 9.00857142857143e-06,
212
+ "loss": 0.0881,
213
+ "step": 850
214
+ },
215
+ {
216
+ "epoch": 2.14,
217
+ "learning_rate": 8.937142857142857e-06,
218
+ "loss": 0.0899,
219
+ "step": 875
220
+ },
221
+ {
222
+ "epoch": 2.2,
223
+ "learning_rate": 8.865714285714287e-06,
224
+ "loss": 0.0875,
225
+ "step": 900
226
+ },
227
+ {
228
+ "epoch": 2.26,
229
+ "learning_rate": 8.794285714285716e-06,
230
+ "loss": 0.0796,
231
+ "step": 925
232
+ },
233
+ {
234
+ "epoch": 2.32,
235
+ "learning_rate": 8.722857142857145e-06,
236
+ "loss": 0.0873,
237
+ "step": 950
238
+ },
239
+ {
240
+ "epoch": 2.38,
241
+ "learning_rate": 8.651428571428572e-06,
242
+ "loss": 0.0855,
243
+ "step": 975
244
+ },
245
+ {
246
+ "epoch": 2.44,
247
+ "learning_rate": 8.580000000000001e-06,
248
+ "loss": 0.0825,
249
+ "step": 1000
250
+ },
251
+ {
252
+ "epoch": 2.44,
253
+ "eval_loss": 0.2965221107006073,
254
+ "eval_runtime": 1430.9073,
255
+ "eval_samples_per_second": 2.022,
256
+ "eval_steps_per_second": 0.253,
257
+ "eval_wer": 35.4355371201219,
258
+ "step": 1000
259
+ },
260
+ {
261
+ "epoch": 2.51,
262
+ "learning_rate": 8.50857142857143e-06,
263
+ "loss": 0.0807,
264
+ "step": 1025
265
+ },
266
+ {
267
+ "epoch": 2.57,
268
+ "learning_rate": 8.437142857142859e-06,
269
+ "loss": 0.0894,
270
+ "step": 1050
271
+ },
272
+ {
273
+ "epoch": 2.63,
274
+ "learning_rate": 8.365714285714286e-06,
275
+ "loss": 0.0875,
276
+ "step": 1075
277
+ },
278
+ {
279
+ "epoch": 2.69,
280
+ "learning_rate": 8.294285714285715e-06,
281
+ "loss": 0.0869,
282
+ "step": 1100
283
+ },
284
+ {
285
+ "epoch": 2.75,
286
+ "learning_rate": 8.222857142857144e-06,
287
+ "loss": 0.0915,
288
+ "step": 1125
289
+ },
290
+ {
291
+ "epoch": 2.81,
292
+ "learning_rate": 8.151428571428572e-06,
293
+ "loss": 0.0779,
294
+ "step": 1150
295
+ },
296
+ {
297
+ "epoch": 2.87,
298
+ "learning_rate": 8.08e-06,
299
+ "loss": 0.0855,
300
+ "step": 1175
301
+ },
302
+ {
303
+ "epoch": 2.93,
304
+ "learning_rate": 8.00857142857143e-06,
305
+ "loss": 0.0836,
306
+ "step": 1200
307
+ },
308
+ {
309
+ "epoch": 3.0,
310
+ "learning_rate": 7.937142857142857e-06,
311
+ "loss": 0.0844,
312
+ "step": 1225
313
+ },
314
+ {
315
+ "epoch": 3.06,
316
+ "learning_rate": 7.865714285714286e-06,
317
+ "loss": 0.0469,
318
+ "step": 1250
319
+ },
320
+ {
321
+ "epoch": 3.12,
322
+ "learning_rate": 7.794285714285715e-06,
323
+ "loss": 0.0405,
324
+ "step": 1275
325
+ },
326
+ {
327
+ "epoch": 3.18,
328
+ "learning_rate": 7.722857142857142e-06,
329
+ "loss": 0.039,
330
+ "step": 1300
331
+ },
332
+ {
333
+ "epoch": 3.24,
334
+ "learning_rate": 7.651428571428571e-06,
335
+ "loss": 0.045,
336
+ "step": 1325
337
+ },
338
+ {
339
+ "epoch": 3.3,
340
+ "learning_rate": 7.58e-06,
341
+ "loss": 0.0443,
342
+ "step": 1350
343
+ },
344
+ {
345
+ "epoch": 3.36,
346
+ "learning_rate": 7.508571428571429e-06,
347
+ "loss": 0.0406,
348
+ "step": 1375
349
+ },
350
+ {
351
+ "epoch": 3.42,
352
+ "learning_rate": 7.4371428571428575e-06,
353
+ "loss": 0.0442,
354
+ "step": 1400
355
+ },
356
+ {
357
+ "epoch": 3.48,
358
+ "learning_rate": 7.365714285714286e-06,
359
+ "loss": 0.0468,
360
+ "step": 1425
361
+ },
362
+ {
363
+ "epoch": 3.55,
364
+ "learning_rate": 7.294285714285715e-06,
365
+ "loss": 0.0462,
366
+ "step": 1450
367
+ },
368
+ {
369
+ "epoch": 3.61,
370
+ "learning_rate": 7.222857142857144e-06,
371
+ "loss": 0.0407,
372
+ "step": 1475
373
+ },
374
+ {
375
+ "epoch": 3.67,
376
+ "learning_rate": 7.151428571428573e-06,
377
+ "loss": 0.041,
378
+ "step": 1500
379
+ },
380
+ {
381
+ "epoch": 3.73,
382
+ "learning_rate": 7.08e-06,
383
+ "loss": 0.0408,
384
+ "step": 1525
385
+ },
386
+ {
387
+ "epoch": 3.79,
388
+ "learning_rate": 7.008571428571429e-06,
389
+ "loss": 0.0446,
390
+ "step": 1550
391
+ },
392
+ {
393
+ "epoch": 3.85,
394
+ "learning_rate": 6.937142857142858e-06,
395
+ "loss": 0.0392,
396
+ "step": 1575
397
+ },
398
+ {
399
+ "epoch": 3.91,
400
+ "learning_rate": 6.865714285714287e-06,
401
+ "loss": 0.0398,
402
+ "step": 1600
403
+ },
404
+ {
405
+ "epoch": 3.97,
406
+ "learning_rate": 6.794285714285714e-06,
407
+ "loss": 0.04,
408
+ "step": 1625
409
+ },
410
+ {
411
+ "epoch": 4.03,
412
+ "learning_rate": 6.722857142857143e-06,
413
+ "loss": 0.0281,
414
+ "step": 1650
415
+ },
416
+ {
417
+ "epoch": 4.1,
418
+ "learning_rate": 6.651428571428572e-06,
419
+ "loss": 0.0233,
420
+ "step": 1675
421
+ },
422
+ {
423
+ "epoch": 4.16,
424
+ "learning_rate": 6.5800000000000005e-06,
425
+ "loss": 0.0199,
426
+ "step": 1700
427
+ },
428
+ {
429
+ "epoch": 4.22,
430
+ "learning_rate": 6.5085714285714295e-06,
431
+ "loss": 0.0194,
432
+ "step": 1725
433
+ },
434
+ {
435
+ "epoch": 4.28,
436
+ "learning_rate": 6.437142857142858e-06,
437
+ "loss": 0.0203,
438
+ "step": 1750
439
+ },
440
+ {
441
+ "epoch": 4.34,
442
+ "learning_rate": 6.365714285714286e-06,
443
+ "loss": 0.0207,
444
+ "step": 1775
445
+ },
446
+ {
447
+ "epoch": 4.4,
448
+ "learning_rate": 6.294285714285715e-06,
449
+ "loss": 0.02,
450
+ "step": 1800
451
+ },
452
+ {
453
+ "epoch": 4.46,
454
+ "learning_rate": 6.222857142857144e-06,
455
+ "loss": 0.0203,
456
+ "step": 1825
457
+ },
458
+ {
459
+ "epoch": 4.52,
460
+ "learning_rate": 6.151428571428571e-06,
461
+ "loss": 0.0178,
462
+ "step": 1850
463
+ },
464
+ {
465
+ "epoch": 4.58,
466
+ "learning_rate": 6.08e-06,
467
+ "loss": 0.0222,
468
+ "step": 1875
469
+ },
470
+ {
471
+ "epoch": 4.65,
472
+ "learning_rate": 6.008571428571429e-06,
473
+ "loss": 0.0214,
474
+ "step": 1900
475
+ },
476
+ {
477
+ "epoch": 4.71,
478
+ "learning_rate": 5.937142857142858e-06,
479
+ "loss": 0.0225,
480
+ "step": 1925
481
+ },
482
+ {
483
+ "epoch": 4.77,
484
+ "learning_rate": 5.865714285714286e-06,
485
+ "loss": 0.0181,
486
+ "step": 1950
487
+ },
488
+ {
489
+ "epoch": 4.83,
490
+ "learning_rate": 5.794285714285715e-06,
491
+ "loss": 0.0215,
492
+ "step": 1975
493
+ },
494
+ {
495
+ "epoch": 4.89,
496
+ "learning_rate": 5.722857142857144e-06,
497
+ "loss": 0.022,
498
+ "step": 2000
499
+ },
500
+ {
501
+ "epoch": 4.89,
502
+ "eval_loss": 0.3495931327342987,
503
+ "eval_runtime": 1434.3119,
504
+ "eval_samples_per_second": 2.018,
505
+ "eval_steps_per_second": 0.252,
506
+ "eval_wer": 34.22500634893761,
507
+ "step": 2000
508
+ }
509
+ ],
510
+ "logging_steps": 25,
511
+ "max_steps": 4000,
512
+ "num_input_tokens_seen": 0,
513
+ "num_train_epochs": 10,
514
+ "save_steps": 1000,
515
+ "total_flos": 9.23011544383488e+18,
516
+ "trial_name": null,
517
+ "trial_params": null
518
+ }
run 1 checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7dd0878fdb53a8915b8b50536cccca48d61b29c290ff26b81a971b711bc365d
3
+ size 4856
runs/Dec02_00-11-08_3cb9a703c289/events.out.tfevents.1701476236.3cb9a703c289.23443.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31ee0d5340887345fc3c128b89a189f33b2ef50634d3166a610e42bd587a48c5
3
- size 18400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197c8e70d54543cd0213dfa5f4f695c789a0b82b753f26554e0d8a6f7080af0f
3
+ size 24680
runs/Dec02_04-45-03_3cb9a703c289/events.out.tfevents.1701492336.3cb9a703c289.94593.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f325ff61be37504a0780dd76d4e5feddfe381eb4256aca8474221c0728a8d1d8
3
+ size 11959
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7dd0878fdb53a8915b8b50536cccca48d61b29c290ff26b81a971b711bc365d
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1517e3f151826ba095d1c9f25fbd8cc2c213e4bb6f1c2f8c9f5b89b5fcd22a7c
3
  size 4856