DazMashaly commited on
Commit
cadb911
1 Parent(s): b97e998

Upload folder

Browse files
checkpoint-1060/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/new_downloads/checkpoint-951",
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": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 4,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.42.3",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
checkpoint-1060/generation_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|zh|>": 50260
136
+ },
137
+ "language": "arabic",
138
+ "max_initial_timestamp_index": 50,
139
+ "max_length": 448,
140
+ "no_timestamps_token_id": 50363,
141
+ "pad_token_id": 50257,
142
+ "prev_sot_token_id": 50361,
143
+ "return_timestamps": false,
144
+ "suppress_tokens": [
145
+ 1,
146
+ 2,
147
+ 7,
148
+ 8,
149
+ 9,
150
+ 10,
151
+ 14,
152
+ 25,
153
+ 26,
154
+ 27,
155
+ 28,
156
+ 29,
157
+ 31,
158
+ 58,
159
+ 59,
160
+ 60,
161
+ 61,
162
+ 62,
163
+ 63,
164
+ 90,
165
+ 91,
166
+ 92,
167
+ 93,
168
+ 359,
169
+ 503,
170
+ 522,
171
+ 542,
172
+ 873,
173
+ 893,
174
+ 902,
175
+ 918,
176
+ 922,
177
+ 931,
178
+ 1350,
179
+ 1853,
180
+ 1982,
181
+ 2460,
182
+ 2627,
183
+ 3246,
184
+ 3253,
185
+ 3268,
186
+ 3536,
187
+ 3846,
188
+ 3961,
189
+ 4183,
190
+ 4667,
191
+ 6585,
192
+ 6647,
193
+ 7273,
194
+ 9061,
195
+ 9383,
196
+ 10428,
197
+ 10929,
198
+ 11938,
199
+ 12033,
200
+ 12331,
201
+ 12562,
202
+ 13793,
203
+ 14157,
204
+ 14635,
205
+ 15265,
206
+ 15618,
207
+ 16553,
208
+ 16604,
209
+ 18362,
210
+ 18956,
211
+ 20075,
212
+ 21675,
213
+ 22520,
214
+ 26130,
215
+ 26161,
216
+ 26435,
217
+ 28279,
218
+ 29464,
219
+ 31650,
220
+ 32302,
221
+ 32470,
222
+ 36865,
223
+ 42863,
224
+ 47425,
225
+ 49870,
226
+ 50254,
227
+ 50258,
228
+ 50358,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362
233
+ ],
234
+ "task": "transcribe",
235
+ "task_to_id": {
236
+ "transcribe": 50359,
237
+ "translate": 50358
238
+ },
239
+ "transformers_version": "4.42.3"
240
+ }
checkpoint-1060/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e093f2cc023251535f66da5dbadc7e2e2213503c2e3e168def5e41123deeea
3
+ size 151061672
checkpoint-1060/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1009879e9675d289feb9c2bbc4bf2e0d1e140e9422570ec3c5a403467b750dd
3
+ size 297616186
checkpoint-1060/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
+ }
checkpoint-1060/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2290b0fa0fc2f3b11e4d1a099487054d3fa8db984334df4db7cfc1f575530bb6
3
+ size 14244
checkpoint-1060/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4936a6542d4d628b675392e2470f6e55aaf8b51494056e097267d9089eb86dcf
3
+ size 1064
checkpoint-1060/trainer_state.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "/kaggle/working/new_downloads22/checkpoint-317",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1060,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07886435331230283,
13
+ "grad_norm": 8.923051834106445,
14
+ "learning_rate": 1.75e-05,
15
+ "loss": 9.5858,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.15772870662460567,
20
+ "grad_norm": 7.801741600036621,
21
+ "learning_rate": 3.8333333333333334e-05,
22
+ "loss": 7.4178,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.23659305993690852,
27
+ "grad_norm": 6.98698091506958,
28
+ "learning_rate": 5.916666666666667e-05,
29
+ "loss": 6.5061,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.31545741324921134,
34
+ "grad_norm": 15.704840660095215,
35
+ "learning_rate": 8e-05,
36
+ "loss": 6.3719,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.3943217665615142,
41
+ "grad_norm": 18.519981384277344,
42
+ "learning_rate": 9.9983922829582e-05,
43
+ "loss": 6.2496,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.47318611987381703,
48
+ "grad_norm": 5.073540210723877,
49
+ "learning_rate": 9.958199356913184e-05,
50
+ "loss": 6.1319,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.5520504731861199,
55
+ "grad_norm": 5.464381217956543,
56
+ "learning_rate": 9.918006430868168e-05,
57
+ "loss": 6.0139,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.6309148264984227,
62
+ "grad_norm": 7.70945405960083,
63
+ "learning_rate": 9.877813504823152e-05,
64
+ "loss": 5.8082,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.7097791798107256,
69
+ "grad_norm": 10.696139335632324,
70
+ "learning_rate": 9.837620578778135e-05,
71
+ "loss": 5.4794,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.7886435331230284,
76
+ "grad_norm": 11.641499519348145,
77
+ "learning_rate": 9.79742765273312e-05,
78
+ "loss": 5.0549,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.8675078864353313,
83
+ "grad_norm": 9.7868013381958,
84
+ "learning_rate": 9.757234726688104e-05,
85
+ "loss": 4.5482,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.9463722397476341,
90
+ "grad_norm": 8.010425567626953,
91
+ "learning_rate": 9.717041800643088e-05,
92
+ "loss": 4.0112,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_cer": 1.0,
98
+ "eval_loss": 3.591109037399292,
99
+ "eval_runtime": 822.2984,
100
+ "eval_samples_per_second": 2.674,
101
+ "eval_steps_per_second": 0.022,
102
+ "eval_wer": 1.0,
103
+ "step": 317
104
+ },
105
+ {
106
+ "epoch": 1.025236593059937,
107
+ "grad_norm": 6.642086982727051,
108
+ "learning_rate": 9.676848874598072e-05,
109
+ "loss": 3.5042,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 1.1041009463722398,
114
+ "grad_norm": 8.283796310424805,
115
+ "learning_rate": 9.636655948553056e-05,
116
+ "loss": 2.9869,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 1.1829652996845426,
121
+ "grad_norm": 6.643803596496582,
122
+ "learning_rate": 9.596463022508039e-05,
123
+ "loss": 2.759,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 1.2618296529968454,
128
+ "grad_norm": 7.243183135986328,
129
+ "learning_rate": 9.556270096463023e-05,
130
+ "loss": 2.5283,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 1.3406940063091484,
135
+ "grad_norm": 6.6391425132751465,
136
+ "learning_rate": 9.516077170418007e-05,
137
+ "loss": 2.3984,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.4195583596214512,
142
+ "grad_norm": 6.673182010650635,
143
+ "learning_rate": 9.47588424437299e-05,
144
+ "loss": 2.2356,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.498422712933754,
149
+ "grad_norm": 6.318761825561523,
150
+ "learning_rate": 9.435691318327976e-05,
151
+ "loss": 2.1016,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 1.5772870662460567,
156
+ "grad_norm": 5.9026360511779785,
157
+ "learning_rate": 9.39549839228296e-05,
158
+ "loss": 2.019,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 1.6561514195583595,
163
+ "grad_norm": 5.887834072113037,
164
+ "learning_rate": 9.355305466237943e-05,
165
+ "loss": 1.9171,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 1.7350157728706623,
170
+ "grad_norm": 5.294543743133545,
171
+ "learning_rate": 9.315112540192927e-05,
172
+ "loss": 1.8466,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 1.8138801261829653,
177
+ "grad_norm": 5.4380364418029785,
178
+ "learning_rate": 9.27491961414791e-05,
179
+ "loss": 1.7883,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 1.8927444794952681,
184
+ "grad_norm": 5.8729777336120605,
185
+ "learning_rate": 9.234726688102894e-05,
186
+ "loss": 1.6805,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 1.971608832807571,
191
+ "grad_norm": 5.349132537841797,
192
+ "learning_rate": 9.194533762057878e-05,
193
+ "loss": 1.6442,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 2.0,
198
+ "eval_cer": 1.0,
199
+ "eval_loss": 2.0905776023864746,
200
+ "eval_runtime": 809.9594,
201
+ "eval_samples_per_second": 2.715,
202
+ "eval_steps_per_second": 0.022,
203
+ "eval_wer": 1.0,
204
+ "step": 634
205
+ },
206
+ {
207
+ "epoch": 2.050473186119874,
208
+ "grad_norm": 4.628177642822266,
209
+ "learning_rate": 9.154340836012862e-05,
210
+ "loss": 1.3757,
211
+ "step": 650
212
+ },
213
+ {
214
+ "epoch": 2.1293375394321767,
215
+ "grad_norm": 4.613383769989014,
216
+ "learning_rate": 9.114147909967846e-05,
217
+ "loss": 1.2338,
218
+ "step": 675
219
+ },
220
+ {
221
+ "epoch": 2.2082018927444795,
222
+ "grad_norm": 4.620671272277832,
223
+ "learning_rate": 9.07395498392283e-05,
224
+ "loss": 1.1955,
225
+ "step": 700
226
+ },
227
+ {
228
+ "epoch": 2.2870662460567823,
229
+ "grad_norm": 5.2364325523376465,
230
+ "learning_rate": 9.033762057877814e-05,
231
+ "loss": 1.1995,
232
+ "step": 725
233
+ },
234
+ {
235
+ "epoch": 2.365930599369085,
236
+ "grad_norm": 4.981749057769775,
237
+ "learning_rate": 8.993569131832798e-05,
238
+ "loss": 1.1839,
239
+ "step": 750
240
+ },
241
+ {
242
+ "epoch": 2.444794952681388,
243
+ "grad_norm": 4.923290252685547,
244
+ "learning_rate": 8.953376205787782e-05,
245
+ "loss": 1.1529,
246
+ "step": 775
247
+ },
248
+ {
249
+ "epoch": 2.5236593059936907,
250
+ "grad_norm": 4.748891830444336,
251
+ "learning_rate": 8.913183279742766e-05,
252
+ "loss": 1.156,
253
+ "step": 800
254
+ },
255
+ {
256
+ "epoch": 2.6025236593059935,
257
+ "grad_norm": 4.635627269744873,
258
+ "learning_rate": 8.872990353697749e-05,
259
+ "loss": 1.152,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 2.6813880126182967,
264
+ "grad_norm": 4.900181770324707,
265
+ "learning_rate": 8.832797427652733e-05,
266
+ "loss": 1.1358,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 2.7602523659305995,
271
+ "grad_norm": 4.697984218597412,
272
+ "learning_rate": 8.792604501607717e-05,
273
+ "loss": 1.1274,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 2.8391167192429023,
278
+ "grad_norm": 4.6810078620910645,
279
+ "learning_rate": 8.752411575562702e-05,
280
+ "loss": 1.1098,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 2.917981072555205,
285
+ "grad_norm": 4.750789165496826,
286
+ "learning_rate": 8.712218649517686e-05,
287
+ "loss": 1.0976,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 2.996845425867508,
292
+ "grad_norm": 4.741580486297607,
293
+ "learning_rate": 8.67202572347267e-05,
294
+ "loss": 1.0836,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 3.0,
299
+ "eval_cer": 1.0,
300
+ "eval_loss": 1.82232666015625,
301
+ "eval_runtime": 816.0044,
302
+ "eval_samples_per_second": 2.695,
303
+ "eval_steps_per_second": 0.022,
304
+ "eval_wer": 1.0,
305
+ "step": 951
306
+ },
307
+ {
308
+ "epoch": 9.0,
309
+ "eval_cer": 1.0,
310
+ "eval_loss": 1.8235459327697754,
311
+ "eval_runtime": 455.7883,
312
+ "eval_samples_per_second": 4.825,
313
+ "eval_steps_per_second": 0.02,
314
+ "eval_wer": 1.0,
315
+ "step": 954
316
+ },
317
+ {
318
+ "epoch": 9.19811320754717,
319
+ "grad_norm": 2.231355667114258,
320
+ "learning_rate": 5.5507246376811594e-05,
321
+ "loss": 0.7112,
322
+ "step": 975
323
+ },
324
+ {
325
+ "epoch": 9.433962264150944,
326
+ "grad_norm": 2.25537109375,
327
+ "learning_rate": 5.4299516908212566e-05,
328
+ "loss": 0.6727,
329
+ "step": 1000
330
+ },
331
+ {
332
+ "epoch": 9.669811320754716,
333
+ "grad_norm": 2.2370407581329346,
334
+ "learning_rate": 5.3091787439613525e-05,
335
+ "loss": 0.6685,
336
+ "step": 1025
337
+ },
338
+ {
339
+ "epoch": 9.90566037735849,
340
+ "grad_norm": 2.113811492919922,
341
+ "learning_rate": 5.18840579710145e-05,
342
+ "loss": 0.6655,
343
+ "step": 1050
344
+ },
345
+ {
346
+ "epoch": 10.0,
347
+ "eval_cer": 1.0,
348
+ "eval_loss": 1.7472871541976929,
349
+ "eval_runtime": 446.3627,
350
+ "eval_samples_per_second": 4.926,
351
+ "eval_steps_per_second": 0.02,
352
+ "eval_wer": 1.0,
353
+ "step": 1060
354
+ }
355
+ ],
356
+ "logging_steps": 25,
357
+ "max_steps": 2120,
358
+ "num_input_tokens_seen": 0,
359
+ "num_train_epochs": 20,
360
+ "save_steps": 500,
361
+ "stateful_callbacks": {
362
+ "TrainerControl": {
363
+ "args": {
364
+ "should_epoch_stop": false,
365
+ "should_evaluate": false,
366
+ "should_log": false,
367
+ "should_save": true,
368
+ "should_training_stop": false
369
+ },
370
+ "attributes": {}
371
+ }
372
+ },
373
+ "total_flos": 5.0255761139712e+18,
374
+ "train_batch_size": 480,
375
+ "trial_name": null,
376
+ "trial_params": null
377
+ }
checkpoint-1060/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03eb3cf1f23e8ad59cebc1ebf99c8a9f327a4c4e80a98d564deed0f412906301
3
+ size 5304
checkpoint-951/trainer_state.json CHANGED
@@ -323,7 +323,7 @@
323
  }
324
  },
325
  "total_flos": 3.7456402765824e+18,
326
- "train_batch_size": 160,
327
  "trial_name": null,
328
  "trial_params": null
329
  }
 
323
  }
324
  },
325
  "total_flos": 3.7456402765824e+18,
326
+ "train_batch_size": 480,
327
  "trial_name": null,
328
  "trial_params": null
329
  }
checkpoint-954/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/new_downloads/checkpoint-951",
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": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 4,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.42.3",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
checkpoint-954/generation_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|zh|>": 50260
136
+ },
137
+ "language": "arabic",
138
+ "max_initial_timestamp_index": 50,
139
+ "max_length": 448,
140
+ "no_timestamps_token_id": 50363,
141
+ "pad_token_id": 50257,
142
+ "prev_sot_token_id": 50361,
143
+ "return_timestamps": false,
144
+ "suppress_tokens": [
145
+ 1,
146
+ 2,
147
+ 7,
148
+ 8,
149
+ 9,
150
+ 10,
151
+ 14,
152
+ 25,
153
+ 26,
154
+ 27,
155
+ 28,
156
+ 29,
157
+ 31,
158
+ 58,
159
+ 59,
160
+ 60,
161
+ 61,
162
+ 62,
163
+ 63,
164
+ 90,
165
+ 91,
166
+ 92,
167
+ 93,
168
+ 359,
169
+ 503,
170
+ 522,
171
+ 542,
172
+ 873,
173
+ 893,
174
+ 902,
175
+ 918,
176
+ 922,
177
+ 931,
178
+ 1350,
179
+ 1853,
180
+ 1982,
181
+ 2460,
182
+ 2627,
183
+ 3246,
184
+ 3253,
185
+ 3268,
186
+ 3536,
187
+ 3846,
188
+ 3961,
189
+ 4183,
190
+ 4667,
191
+ 6585,
192
+ 6647,
193
+ 7273,
194
+ 9061,
195
+ 9383,
196
+ 10428,
197
+ 10929,
198
+ 11938,
199
+ 12033,
200
+ 12331,
201
+ 12562,
202
+ 13793,
203
+ 14157,
204
+ 14635,
205
+ 15265,
206
+ 15618,
207
+ 16553,
208
+ 16604,
209
+ 18362,
210
+ 18956,
211
+ 20075,
212
+ 21675,
213
+ 22520,
214
+ 26130,
215
+ 26161,
216
+ 26435,
217
+ 28279,
218
+ 29464,
219
+ 31650,
220
+ 32302,
221
+ 32470,
222
+ 36865,
223
+ 42863,
224
+ 47425,
225
+ 49870,
226
+ 50254,
227
+ 50258,
228
+ 50358,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362
233
+ ],
234
+ "task": "transcribe",
235
+ "task_to_id": {
236
+ "transcribe": 50359,
237
+ "translate": 50358
238
+ },
239
+ "transformers_version": "4.42.3"
240
+ }
checkpoint-954/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc88f742b07d736967e2de89b6cc28187ff779c6dc6979683de4b571202b3473
3
+ size 151061672
checkpoint-954/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bbf30287722bf1bd6a9247e126be1f2be3a0df6de10bac5d66517c519883d8
3
+ size 297616186
checkpoint-954/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
+ }
checkpoint-954/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5baf1505ec4edab11b52e0d34d2ba6d5c3e66a9f942dfc2ff6f8e94eae4c661
3
+ size 14244
checkpoint-954/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1522de16881c8c428c1b060092eb4f48bbdfcf5cdda11caee6d02f51de4b5f25
3
+ size 1064
checkpoint-954/trainer_state.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "/kaggle/working/new_downloads22/checkpoint-317",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 954,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07886435331230283,
13
+ "grad_norm": 8.923051834106445,
14
+ "learning_rate": 1.75e-05,
15
+ "loss": 9.5858,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.15772870662460567,
20
+ "grad_norm": 7.801741600036621,
21
+ "learning_rate": 3.8333333333333334e-05,
22
+ "loss": 7.4178,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.23659305993690852,
27
+ "grad_norm": 6.98698091506958,
28
+ "learning_rate": 5.916666666666667e-05,
29
+ "loss": 6.5061,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.31545741324921134,
34
+ "grad_norm": 15.704840660095215,
35
+ "learning_rate": 8e-05,
36
+ "loss": 6.3719,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.3943217665615142,
41
+ "grad_norm": 18.519981384277344,
42
+ "learning_rate": 9.9983922829582e-05,
43
+ "loss": 6.2496,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.47318611987381703,
48
+ "grad_norm": 5.073540210723877,
49
+ "learning_rate": 9.958199356913184e-05,
50
+ "loss": 6.1319,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.5520504731861199,
55
+ "grad_norm": 5.464381217956543,
56
+ "learning_rate": 9.918006430868168e-05,
57
+ "loss": 6.0139,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.6309148264984227,
62
+ "grad_norm": 7.70945405960083,
63
+ "learning_rate": 9.877813504823152e-05,
64
+ "loss": 5.8082,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.7097791798107256,
69
+ "grad_norm": 10.696139335632324,
70
+ "learning_rate": 9.837620578778135e-05,
71
+ "loss": 5.4794,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.7886435331230284,
76
+ "grad_norm": 11.641499519348145,
77
+ "learning_rate": 9.79742765273312e-05,
78
+ "loss": 5.0549,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.8675078864353313,
83
+ "grad_norm": 9.7868013381958,
84
+ "learning_rate": 9.757234726688104e-05,
85
+ "loss": 4.5482,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.9463722397476341,
90
+ "grad_norm": 8.010425567626953,
91
+ "learning_rate": 9.717041800643088e-05,
92
+ "loss": 4.0112,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_cer": 1.0,
98
+ "eval_loss": 3.591109037399292,
99
+ "eval_runtime": 822.2984,
100
+ "eval_samples_per_second": 2.674,
101
+ "eval_steps_per_second": 0.022,
102
+ "eval_wer": 1.0,
103
+ "step": 317
104
+ },
105
+ {
106
+ "epoch": 1.025236593059937,
107
+ "grad_norm": 6.642086982727051,
108
+ "learning_rate": 9.676848874598072e-05,
109
+ "loss": 3.5042,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 1.1041009463722398,
114
+ "grad_norm": 8.283796310424805,
115
+ "learning_rate": 9.636655948553056e-05,
116
+ "loss": 2.9869,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 1.1829652996845426,
121
+ "grad_norm": 6.643803596496582,
122
+ "learning_rate": 9.596463022508039e-05,
123
+ "loss": 2.759,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 1.2618296529968454,
128
+ "grad_norm": 7.243183135986328,
129
+ "learning_rate": 9.556270096463023e-05,
130
+ "loss": 2.5283,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 1.3406940063091484,
135
+ "grad_norm": 6.6391425132751465,
136
+ "learning_rate": 9.516077170418007e-05,
137
+ "loss": 2.3984,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.4195583596214512,
142
+ "grad_norm": 6.673182010650635,
143
+ "learning_rate": 9.47588424437299e-05,
144
+ "loss": 2.2356,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.498422712933754,
149
+ "grad_norm": 6.318761825561523,
150
+ "learning_rate": 9.435691318327976e-05,
151
+ "loss": 2.1016,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 1.5772870662460567,
156
+ "grad_norm": 5.9026360511779785,
157
+ "learning_rate": 9.39549839228296e-05,
158
+ "loss": 2.019,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 1.6561514195583595,
163
+ "grad_norm": 5.887834072113037,
164
+ "learning_rate": 9.355305466237943e-05,
165
+ "loss": 1.9171,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 1.7350157728706623,
170
+ "grad_norm": 5.294543743133545,
171
+ "learning_rate": 9.315112540192927e-05,
172
+ "loss": 1.8466,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 1.8138801261829653,
177
+ "grad_norm": 5.4380364418029785,
178
+ "learning_rate": 9.27491961414791e-05,
179
+ "loss": 1.7883,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 1.8927444794952681,
184
+ "grad_norm": 5.8729777336120605,
185
+ "learning_rate": 9.234726688102894e-05,
186
+ "loss": 1.6805,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 1.971608832807571,
191
+ "grad_norm": 5.349132537841797,
192
+ "learning_rate": 9.194533762057878e-05,
193
+ "loss": 1.6442,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 2.0,
198
+ "eval_cer": 1.0,
199
+ "eval_loss": 2.0905776023864746,
200
+ "eval_runtime": 809.9594,
201
+ "eval_samples_per_second": 2.715,
202
+ "eval_steps_per_second": 0.022,
203
+ "eval_wer": 1.0,
204
+ "step": 634
205
+ },
206
+ {
207
+ "epoch": 2.050473186119874,
208
+ "grad_norm": 4.628177642822266,
209
+ "learning_rate": 9.154340836012862e-05,
210
+ "loss": 1.3757,
211
+ "step": 650
212
+ },
213
+ {
214
+ "epoch": 2.1293375394321767,
215
+ "grad_norm": 4.613383769989014,
216
+ "learning_rate": 9.114147909967846e-05,
217
+ "loss": 1.2338,
218
+ "step": 675
219
+ },
220
+ {
221
+ "epoch": 2.2082018927444795,
222
+ "grad_norm": 4.620671272277832,
223
+ "learning_rate": 9.07395498392283e-05,
224
+ "loss": 1.1955,
225
+ "step": 700
226
+ },
227
+ {
228
+ "epoch": 2.2870662460567823,
229
+ "grad_norm": 5.2364325523376465,
230
+ "learning_rate": 9.033762057877814e-05,
231
+ "loss": 1.1995,
232
+ "step": 725
233
+ },
234
+ {
235
+ "epoch": 2.365930599369085,
236
+ "grad_norm": 4.981749057769775,
237
+ "learning_rate": 8.993569131832798e-05,
238
+ "loss": 1.1839,
239
+ "step": 750
240
+ },
241
+ {
242
+ "epoch": 2.444794952681388,
243
+ "grad_norm": 4.923290252685547,
244
+ "learning_rate": 8.953376205787782e-05,
245
+ "loss": 1.1529,
246
+ "step": 775
247
+ },
248
+ {
249
+ "epoch": 2.5236593059936907,
250
+ "grad_norm": 4.748891830444336,
251
+ "learning_rate": 8.913183279742766e-05,
252
+ "loss": 1.156,
253
+ "step": 800
254
+ },
255
+ {
256
+ "epoch": 2.6025236593059935,
257
+ "grad_norm": 4.635627269744873,
258
+ "learning_rate": 8.872990353697749e-05,
259
+ "loss": 1.152,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 2.6813880126182967,
264
+ "grad_norm": 4.900181770324707,
265
+ "learning_rate": 8.832797427652733e-05,
266
+ "loss": 1.1358,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 2.7602523659305995,
271
+ "grad_norm": 4.697984218597412,
272
+ "learning_rate": 8.792604501607717e-05,
273
+ "loss": 1.1274,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 2.8391167192429023,
278
+ "grad_norm": 4.6810078620910645,
279
+ "learning_rate": 8.752411575562702e-05,
280
+ "loss": 1.1098,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 2.917981072555205,
285
+ "grad_norm": 4.750789165496826,
286
+ "learning_rate": 8.712218649517686e-05,
287
+ "loss": 1.0976,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 2.996845425867508,
292
+ "grad_norm": 4.741580486297607,
293
+ "learning_rate": 8.67202572347267e-05,
294
+ "loss": 1.0836,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 3.0,
299
+ "eval_cer": 1.0,
300
+ "eval_loss": 1.82232666015625,
301
+ "eval_runtime": 816.0044,
302
+ "eval_samples_per_second": 2.695,
303
+ "eval_steps_per_second": 0.022,
304
+ "eval_wer": 1.0,
305
+ "step": 951
306
+ },
307
+ {
308
+ "epoch": 9.0,
309
+ "eval_cer": 1.0,
310
+ "eval_loss": 1.8235459327697754,
311
+ "eval_runtime": 455.7883,
312
+ "eval_samples_per_second": 4.825,
313
+ "eval_steps_per_second": 0.02,
314
+ "eval_wer": 1.0,
315
+ "step": 954
316
+ }
317
+ ],
318
+ "logging_steps": 25,
319
+ "max_steps": 2120,
320
+ "num_input_tokens_seen": 0,
321
+ "num_train_epochs": 20,
322
+ "save_steps": 500,
323
+ "stateful_callbacks": {
324
+ "TrainerControl": {
325
+ "args": {
326
+ "should_epoch_stop": false,
327
+ "should_evaluate": false,
328
+ "should_log": false,
329
+ "should_save": true,
330
+ "should_training_stop": false
331
+ },
332
+ "attributes": {}
333
+ }
334
+ },
335
+ "total_flos": 3.7770293551104e+18,
336
+ "train_batch_size": 480,
337
+ "trial_name": null,
338
+ "trial_params": null
339
+ }
checkpoint-954/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03eb3cf1f23e8ad59cebc1ebf99c8a9f327a4c4e80a98d564deed0f412906301
3
+ size 5304
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-tiny",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "/content/new_downloads/checkpoint-951",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c5e24e43531235054b89494c7541d4708bc1ae1e93feeff8c92f9d58df14eb
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e093f2cc023251535f66da5dbadc7e2e2213503c2e3e168def5e41123deeea
3
  size 151061672
runs/Jun30_18-52-25_f203426a13d3/events.out.tfevents.1719773548.f203426a13d3.2014.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158438f404b1fff39a920aff571d28f22f01fddfb4d393c01a77865a231332a4
3
+ size 6651
runs/Jun30_18-55-01_f203426a13d3/events.out.tfevents.1719773705.f203426a13d3.2014.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ae1cc342cb795c483bc9d9a19d1a3bc95b3c9c0aabacfcee89628f38b1bd62
3
+ size 8225
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1fe0c9e466f2d9b3b621976440ce0b7c516c6f60ad8430109d3061dff162d2f
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03eb3cf1f23e8ad59cebc1ebf99c8a9f327a4c4e80a98d564deed0f412906301
3
  size 5304