PranavJosh commited on
Commit
5658d1c
·
verified ·
1 Parent(s): 7de107d

Upload epoch_2 checkpoint

Browse files
epoch_2/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 1024,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 4096,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 24,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 16,
20
+ "encoder_ffn_dim": 4096,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 24,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 24,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
epoch_2/generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 13,
5
+ 15
6
+ ],
7
+ [
8
+ 15,
9
+ 4
10
+ ],
11
+ [
12
+ 15,
13
+ 15
14
+ ],
15
+ [
16
+ 16,
17
+ 1
18
+ ],
19
+ [
20
+ 20,
21
+ 0
22
+ ],
23
+ [
24
+ 23,
25
+ 4
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "Hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
epoch_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfae5f96a24b0034c707ddf4c97de9d40e838afd6527f5ce8fb67417c25a37b
3
+ size 3055544304
epoch_2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b9c6b4c4babedc289e9f279e693ae82d6b966b81afb931124c04550afad738
3
+ size 6111664103
epoch_2/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
epoch_2/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebde1a323f9c0aab7d5734427faea8ce641719458b8b44cdeaabac49507732d4
3
+ size 15728
epoch_2/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3afad85d2819f3c18b813a4b8cf1c1a1a25cf69599719e7f4b635640399a53f
3
+ size 15728
epoch_2/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a399d9d3a1a9242d85f6936c843b6de18d9201d2067ba3d8b87c9b8960349159
3
+ size 15728
epoch_2/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4fa8905fc7d62ac97c248d267ddb323151a204e12c2a83f80df2a0d5b3014ec
3
+ size 15728
epoch_2/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e38b884995dbdfd8f76480bc088935ebd5c76e3899a3a3727bb241aa15a43d
3
+ size 15728
epoch_2/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75b9b9eb0243f8b42074e444d394ca62cb805ae5973856cf3ba36f7fa61d10c
3
+ size 15728
epoch_2/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64b07ea3af7de4807d87d7c0f6407bf222c46bd8f147378c1e67a9dad9c2876
3
+ size 15728
epoch_2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335360d76aafafa4feb9b373891c0567ca9455df77873d8fbcd4a44ad2a63373
3
+ size 1064
epoch_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
epoch_2/tokenizer_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|startoftranscript|>",
11
+ "<|en|>",
12
+ "<|zh|>",
13
+ "<|de|>",
14
+ "<|es|>",
15
+ "<|ru|>",
16
+ "<|ko|>",
17
+ "<|fr|>",
18
+ "<|ja|>",
19
+ "<|pt|>",
20
+ "<|tr|>",
21
+ "<|pl|>",
22
+ "<|ca|>",
23
+ "<|nl|>",
24
+ "<|ar|>",
25
+ "<|sv|>",
26
+ "<|it|>",
27
+ "<|id|>",
28
+ "<|hi|>",
29
+ "<|fi|>",
30
+ "<|vi|>",
31
+ "<|he|>",
32
+ "<|uk|>",
33
+ "<|el|>",
34
+ "<|ms|>",
35
+ "<|cs|>",
36
+ "<|ro|>",
37
+ "<|da|>",
38
+ "<|hu|>",
39
+ "<|ta|>",
40
+ "<|no|>",
41
+ "<|th|>",
42
+ "<|ur|>",
43
+ "<|hr|>",
44
+ "<|bg|>",
45
+ "<|lt|>",
46
+ "<|la|>",
47
+ "<|mi|>",
48
+ "<|ml|>",
49
+ "<|cy|>",
50
+ "<|sk|>",
51
+ "<|te|>",
52
+ "<|fa|>",
53
+ "<|lv|>",
54
+ "<|bn|>",
55
+ "<|sr|>",
56
+ "<|az|>",
57
+ "<|sl|>",
58
+ "<|kn|>",
59
+ "<|et|>",
60
+ "<|mk|>",
61
+ "<|br|>",
62
+ "<|eu|>",
63
+ "<|is|>",
64
+ "<|hy|>",
65
+ "<|ne|>",
66
+ "<|mn|>",
67
+ "<|bs|>",
68
+ "<|kk|>",
69
+ "<|sq|>",
70
+ "<|sw|>",
71
+ "<|gl|>",
72
+ "<|mr|>",
73
+ "<|pa|>",
74
+ "<|si|>",
75
+ "<|km|>",
76
+ "<|sn|>",
77
+ "<|yo|>",
78
+ "<|so|>",
79
+ "<|af|>",
80
+ "<|oc|>",
81
+ "<|ka|>",
82
+ "<|be|>",
83
+ "<|tg|>",
84
+ "<|sd|>",
85
+ "<|gu|>",
86
+ "<|am|>",
87
+ "<|yi|>",
88
+ "<|lo|>",
89
+ "<|uz|>",
90
+ "<|fo|>",
91
+ "<|ht|>",
92
+ "<|ps|>",
93
+ "<|tk|>",
94
+ "<|nn|>",
95
+ "<|mt|>",
96
+ "<|sa|>",
97
+ "<|lb|>",
98
+ "<|my|>",
99
+ "<|bo|>",
100
+ "<|tl|>",
101
+ "<|mg|>",
102
+ "<|as|>",
103
+ "<|tt|>",
104
+ "<|haw|>",
105
+ "<|ln|>",
106
+ "<|ha|>",
107
+ "<|ba|>",
108
+ "<|jw|>",
109
+ "<|su|>",
110
+ "<|translate|>",
111
+ "<|transcribe|>",
112
+ "<|startoflm|>",
113
+ "<|startofprev|>",
114
+ "<|nocaptions|>",
115
+ "<|notimestamps|>"
116
+ ],
117
+ "is_local": false,
118
+ "language": "hindi",
119
+ "model_max_length": 1024,
120
+ "pad_token": "<|endoftext|>",
121
+ "predict_timestamps": false,
122
+ "processor_class": "WhisperProcessor",
123
+ "return_attention_mask": false,
124
+ "task": "transcribe",
125
+ "tokenizer_class": "WhisperTokenizer",
126
+ "unk_token": "<|endoftext|>"
127
+ }
epoch_2/trainer_state.json ADDED
@@ -0,0 +1,782 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2596,
3
+ "best_metric": 21.05581734399,
4
+ "best_model_checkpoint": "./whisper_s_punjabi_ddp_4gpu/checkpoint-2596",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2596,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01926040061633282,
14
+ "grad_norm": 58.414207458496094,
15
+ "learning_rate": 8.000000000000001e-07,
16
+ "loss": 7.913150634765625,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.03852080123266564,
21
+ "grad_norm": 18.150222778320312,
22
+ "learning_rate": 1.6333333333333335e-06,
23
+ "loss": 5.986227416992188,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.05778120184899846,
28
+ "grad_norm": 14.175592422485352,
29
+ "learning_rate": 2.466666666666667e-06,
30
+ "loss": 4.43172119140625,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.07704160246533127,
35
+ "grad_norm": 16.95926284790039,
36
+ "learning_rate": 3.3000000000000006e-06,
37
+ "loss": 3.4311566162109375,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.0963020030816641,
42
+ "grad_norm": 9.69564151763916,
43
+ "learning_rate": 4.133333333333333e-06,
44
+ "loss": 2.0594117736816404,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.11556240369799692,
49
+ "grad_norm": 10.076292991638184,
50
+ "learning_rate": 4.966666666666667e-06,
51
+ "loss": 1.8318702697753906,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.13482280431432975,
56
+ "grad_norm": 9.035318374633789,
57
+ "learning_rate": 5.8e-06,
58
+ "loss": 1.7396725463867186,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.15408320493066255,
63
+ "grad_norm": 10.635228157043457,
64
+ "learning_rate": 6.633333333333334e-06,
65
+ "loss": 1.6932928466796875,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.17334360554699538,
70
+ "grad_norm": 10.217312812805176,
71
+ "learning_rate": 7.4666666666666675e-06,
72
+ "loss": 1.6321292114257813,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 0.1926040061633282,
77
+ "grad_norm": 11.088924407958984,
78
+ "learning_rate": 8.3e-06,
79
+ "loss": 1.5770054626464844,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 0.211864406779661,
84
+ "grad_norm": 10.08351993560791,
85
+ "learning_rate": 9.133333333333335e-06,
86
+ "loss": 1.5158828735351562,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 0.23112480739599384,
91
+ "grad_norm": 9.66342544555664,
92
+ "learning_rate": 9.966666666666667e-06,
93
+ "loss": 1.5335569763183594,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 0.25038520801232667,
98
+ "grad_norm": 10.034809112548828,
99
+ "learning_rate": 9.981072555205049e-06,
100
+ "loss": 1.4476705932617187,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 0.2696456086286595,
105
+ "grad_norm": 7.876269817352295,
106
+ "learning_rate": 9.961356466876972e-06,
107
+ "loss": 1.4681803894042968,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 0.2889060092449923,
112
+ "grad_norm": 10.250846862792969,
113
+ "learning_rate": 9.941640378548896e-06,
114
+ "loss": 1.437877197265625,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 0.3081664098613251,
119
+ "grad_norm": 9.018561363220215,
120
+ "learning_rate": 9.921924290220821e-06,
121
+ "loss": 1.3937382507324219,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 0.3274268104776579,
126
+ "grad_norm": 8.793310165405273,
127
+ "learning_rate": 9.902208201892746e-06,
128
+ "loss": 1.3915924072265624,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 0.34668721109399075,
133
+ "grad_norm": 9.753164291381836,
134
+ "learning_rate": 9.88249211356467e-06,
135
+ "loss": 1.3350201416015626,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 0.3659476117103236,
140
+ "grad_norm": 9.90793514251709,
141
+ "learning_rate": 9.862776025236594e-06,
142
+ "loss": 1.3452024841308594,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 0.3852080123266564,
147
+ "grad_norm": 7.425978660583496,
148
+ "learning_rate": 9.843059936908518e-06,
149
+ "loss": 1.3636004638671875,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 0.40446841294298924,
154
+ "grad_norm": 7.5032501220703125,
155
+ "learning_rate": 9.823343848580441e-06,
156
+ "loss": 1.337528076171875,
157
+ "step": 525
158
+ },
159
+ {
160
+ "epoch": 0.423728813559322,
161
+ "grad_norm": 8.89260482788086,
162
+ "learning_rate": 9.803627760252366e-06,
163
+ "loss": 1.3338491821289062,
164
+ "step": 550
165
+ },
166
+ {
167
+ "epoch": 0.44298921417565484,
168
+ "grad_norm": 8.321249008178711,
169
+ "learning_rate": 9.783911671924291e-06,
170
+ "loss": 1.333787384033203,
171
+ "step": 575
172
+ },
173
+ {
174
+ "epoch": 0.4622496147919877,
175
+ "grad_norm": 8.888858795166016,
176
+ "learning_rate": 9.764195583596216e-06,
177
+ "loss": 1.3222378540039061,
178
+ "step": 600
179
+ },
180
+ {
181
+ "epoch": 0.4815100154083205,
182
+ "grad_norm": 7.648203372955322,
183
+ "learning_rate": 9.74447949526814e-06,
184
+ "loss": 1.3167262268066406,
185
+ "step": 625
186
+ },
187
+ {
188
+ "epoch": 0.5007704160246533,
189
+ "grad_norm": 6.553903102874756,
190
+ "learning_rate": 9.724763406940063e-06,
191
+ "loss": 1.298903045654297,
192
+ "step": 650
193
+ },
194
+ {
195
+ "epoch": 0.5200308166409862,
196
+ "grad_norm": 7.545315265655518,
197
+ "learning_rate": 9.705047318611988e-06,
198
+ "loss": 1.266801223754883,
199
+ "step": 675
200
+ },
201
+ {
202
+ "epoch": 0.539291217257319,
203
+ "grad_norm": 7.492407321929932,
204
+ "learning_rate": 9.685331230283911e-06,
205
+ "loss": 1.2619186401367188,
206
+ "step": 700
207
+ },
208
+ {
209
+ "epoch": 0.5585516178736518,
210
+ "grad_norm": 6.489583969116211,
211
+ "learning_rate": 9.665615141955836e-06,
212
+ "loss": 1.2714739990234376,
213
+ "step": 725
214
+ },
215
+ {
216
+ "epoch": 0.5778120184899846,
217
+ "grad_norm": 8.90630054473877,
218
+ "learning_rate": 9.64589905362776e-06,
219
+ "loss": 1.2946762084960937,
220
+ "step": 750
221
+ },
222
+ {
223
+ "epoch": 0.5970724191063174,
224
+ "grad_norm": 7.635409832000732,
225
+ "learning_rate": 9.626182965299686e-06,
226
+ "loss": 1.269822463989258,
227
+ "step": 775
228
+ },
229
+ {
230
+ "epoch": 0.6163328197226502,
231
+ "grad_norm": 7.459207534790039,
232
+ "learning_rate": 9.60646687697161e-06,
233
+ "loss": 1.2825979614257812,
234
+ "step": 800
235
+ },
236
+ {
237
+ "epoch": 0.635593220338983,
238
+ "grad_norm": 8.159686088562012,
239
+ "learning_rate": 9.586750788643533e-06,
240
+ "loss": 1.2717716217041015,
241
+ "step": 825
242
+ },
243
+ {
244
+ "epoch": 0.6548536209553159,
245
+ "grad_norm": 6.630347728729248,
246
+ "learning_rate": 9.567034700315458e-06,
247
+ "loss": 1.252648162841797,
248
+ "step": 850
249
+ },
250
+ {
251
+ "epoch": 0.6741140215716487,
252
+ "grad_norm": 7.215192794799805,
253
+ "learning_rate": 9.547318611987383e-06,
254
+ "loss": 1.252330093383789,
255
+ "step": 875
256
+ },
257
+ {
258
+ "epoch": 0.6933744221879815,
259
+ "grad_norm": 8.178110122680664,
260
+ "learning_rate": 9.527602523659308e-06,
261
+ "loss": 1.2153298187255859,
262
+ "step": 900
263
+ },
264
+ {
265
+ "epoch": 0.7126348228043143,
266
+ "grad_norm": 6.375010013580322,
267
+ "learning_rate": 9.50788643533123e-06,
268
+ "loss": 1.2400372314453125,
269
+ "step": 925
270
+ },
271
+ {
272
+ "epoch": 0.7318952234206472,
273
+ "grad_norm": 8.464449882507324,
274
+ "learning_rate": 9.488170347003155e-06,
275
+ "loss": 1.2374497222900391,
276
+ "step": 950
277
+ },
278
+ {
279
+ "epoch": 0.75115562403698,
280
+ "grad_norm": 6.5914764404296875,
281
+ "learning_rate": 9.46845425867508e-06,
282
+ "loss": 1.2367049407958985,
283
+ "step": 975
284
+ },
285
+ {
286
+ "epoch": 0.7704160246533128,
287
+ "grad_norm": 6.147579193115234,
288
+ "learning_rate": 9.448738170347003e-06,
289
+ "loss": 1.2031460571289063,
290
+ "step": 1000
291
+ },
292
+ {
293
+ "epoch": 0.7896764252696457,
294
+ "grad_norm": 6.786445617675781,
295
+ "learning_rate": 9.429022082018928e-06,
296
+ "loss": 1.1893964385986329,
297
+ "step": 1025
298
+ },
299
+ {
300
+ "epoch": 0.8089368258859785,
301
+ "grad_norm": 5.8521504402160645,
302
+ "learning_rate": 9.409305993690853e-06,
303
+ "loss": 1.1855683898925782,
304
+ "step": 1050
305
+ },
306
+ {
307
+ "epoch": 0.8281972265023112,
308
+ "grad_norm": 5.927206993103027,
309
+ "learning_rate": 9.389589905362777e-06,
310
+ "loss": 1.2393891906738281,
311
+ "step": 1075
312
+ },
313
+ {
314
+ "epoch": 0.847457627118644,
315
+ "grad_norm": 7.765108108520508,
316
+ "learning_rate": 9.369873817034702e-06,
317
+ "loss": 1.2078982543945314,
318
+ "step": 1100
319
+ },
320
+ {
321
+ "epoch": 0.8667180277349769,
322
+ "grad_norm": 6.578537464141846,
323
+ "learning_rate": 9.350157728706625e-06,
324
+ "loss": 1.2135992431640625,
325
+ "step": 1125
326
+ },
327
+ {
328
+ "epoch": 0.8859784283513097,
329
+ "grad_norm": 6.826841831207275,
330
+ "learning_rate": 9.33044164037855e-06,
331
+ "loss": 1.2246592712402344,
332
+ "step": 1150
333
+ },
334
+ {
335
+ "epoch": 0.9052388289676425,
336
+ "grad_norm": 5.9232611656188965,
337
+ "learning_rate": 9.310725552050473e-06,
338
+ "loss": 1.2366727447509767,
339
+ "step": 1175
340
+ },
341
+ {
342
+ "epoch": 0.9244992295839753,
343
+ "grad_norm": 6.405348777770996,
344
+ "learning_rate": 9.291009463722398e-06,
345
+ "loss": 1.1822604370117187,
346
+ "step": 1200
347
+ },
348
+ {
349
+ "epoch": 0.9437596302003082,
350
+ "grad_norm": 7.846672534942627,
351
+ "learning_rate": 9.271293375394322e-06,
352
+ "loss": 1.1902696228027343,
353
+ "step": 1225
354
+ },
355
+ {
356
+ "epoch": 0.963020030816641,
357
+ "grad_norm": 6.556903839111328,
358
+ "learning_rate": 9.251577287066247e-06,
359
+ "loss": 1.2147691345214844,
360
+ "step": 1250
361
+ },
362
+ {
363
+ "epoch": 0.9822804314329738,
364
+ "grad_norm": 6.414576530456543,
365
+ "learning_rate": 9.231861198738172e-06,
366
+ "loss": 1.1895433044433594,
367
+ "step": 1275
368
+ },
369
+ {
370
+ "epoch": 1.0,
371
+ "eval_loss": 0.1692090779542923,
372
+ "eval_runtime": 1293.6351,
373
+ "eval_samples_per_second": 18.724,
374
+ "eval_steps_per_second": 0.084,
375
+ "eval_wer": 23.27414889831906,
376
+ "step": 1298
377
+ },
378
+ {
379
+ "epoch": 1.0015408320493067,
380
+ "grad_norm": 5.701938152313232,
381
+ "learning_rate": 9.212145110410095e-06,
382
+ "loss": 1.1426918029785156,
383
+ "step": 1300
384
+ },
385
+ {
386
+ "epoch": 1.0208012326656395,
387
+ "grad_norm": 7.372975826263428,
388
+ "learning_rate": 9.19242902208202e-06,
389
+ "loss": 1.0540249633789063,
390
+ "step": 1325
391
+ },
392
+ {
393
+ "epoch": 1.0400616332819723,
394
+ "grad_norm": 6.552262783050537,
395
+ "learning_rate": 9.172712933753945e-06,
396
+ "loss": 1.0437205505371094,
397
+ "step": 1350
398
+ },
399
+ {
400
+ "epoch": 1.0593220338983051,
401
+ "grad_norm": 7.7785444259643555,
402
+ "learning_rate": 9.152996845425868e-06,
403
+ "loss": 1.063336639404297,
404
+ "step": 1375
405
+ },
406
+ {
407
+ "epoch": 1.078582434514638,
408
+ "grad_norm": 6.104959011077881,
409
+ "learning_rate": 9.133280757097792e-06,
410
+ "loss": 1.0619095611572265,
411
+ "step": 1400
412
+ },
413
+ {
414
+ "epoch": 1.0978428351309708,
415
+ "grad_norm": 7.427105903625488,
416
+ "learning_rate": 9.113564668769717e-06,
417
+ "loss": 1.0477345275878907,
418
+ "step": 1425
419
+ },
420
+ {
421
+ "epoch": 1.1171032357473036,
422
+ "grad_norm": 4.97503137588501,
423
+ "learning_rate": 9.093848580441642e-06,
424
+ "loss": 1.0352927398681642,
425
+ "step": 1450
426
+ },
427
+ {
428
+ "epoch": 1.1363636363636362,
429
+ "grad_norm": 6.956381320953369,
430
+ "learning_rate": 9.074132492113565e-06,
431
+ "loss": 1.0552413940429688,
432
+ "step": 1475
433
+ },
434
+ {
435
+ "epoch": 1.1556240369799693,
436
+ "grad_norm": 6.349787712097168,
437
+ "learning_rate": 9.05441640378549e-06,
438
+ "loss": 1.0734415435791016,
439
+ "step": 1500
440
+ },
441
+ {
442
+ "epoch": 1.174884437596302,
443
+ "grad_norm": 6.110345363616943,
444
+ "learning_rate": 9.034700315457414e-06,
445
+ "loss": 1.0556398773193358,
446
+ "step": 1525
447
+ },
448
+ {
449
+ "epoch": 1.1941448382126347,
450
+ "grad_norm": 5.747076511383057,
451
+ "learning_rate": 9.014984227129339e-06,
452
+ "loss": 1.0406858825683594,
453
+ "step": 1550
454
+ },
455
+ {
456
+ "epoch": 1.2134052388289676,
457
+ "grad_norm": 5.9346113204956055,
458
+ "learning_rate": 8.995268138801264e-06,
459
+ "loss": 1.0497844696044922,
460
+ "step": 1575
461
+ },
462
+ {
463
+ "epoch": 1.2326656394453004,
464
+ "grad_norm": 5.690814971923828,
465
+ "learning_rate": 8.975552050473187e-06,
466
+ "loss": 1.0486802673339843,
467
+ "step": 1600
468
+ },
469
+ {
470
+ "epoch": 1.2519260400616332,
471
+ "grad_norm": 5.829971790313721,
472
+ "learning_rate": 8.95583596214511e-06,
473
+ "loss": 1.0496593475341798,
474
+ "step": 1625
475
+ },
476
+ {
477
+ "epoch": 1.271186440677966,
478
+ "grad_norm": 5.7554144859313965,
479
+ "learning_rate": 8.936119873817035e-06,
480
+ "loss": 1.031878204345703,
481
+ "step": 1650
482
+ },
483
+ {
484
+ "epoch": 1.2904468412942989,
485
+ "grad_norm": 5.836212158203125,
486
+ "learning_rate": 8.91640378548896e-06,
487
+ "loss": 1.0397360229492187,
488
+ "step": 1675
489
+ },
490
+ {
491
+ "epoch": 1.3097072419106317,
492
+ "grad_norm": 5.595889091491699,
493
+ "learning_rate": 8.896687697160884e-06,
494
+ "loss": 1.0481429290771485,
495
+ "step": 1700
496
+ },
497
+ {
498
+ "epoch": 1.3289676425269645,
499
+ "grad_norm": 6.345583915710449,
500
+ "learning_rate": 8.876971608832809e-06,
501
+ "loss": 1.0513285064697266,
502
+ "step": 1725
503
+ },
504
+ {
505
+ "epoch": 1.3482280431432974,
506
+ "grad_norm": 6.793821334838867,
507
+ "learning_rate": 8.857255520504732e-06,
508
+ "loss": 1.0579839324951172,
509
+ "step": 1750
510
+ },
511
+ {
512
+ "epoch": 1.3674884437596302,
513
+ "grad_norm": 6.589428901672363,
514
+ "learning_rate": 8.837539432176657e-06,
515
+ "loss": 1.0568167114257812,
516
+ "step": 1775
517
+ },
518
+ {
519
+ "epoch": 1.386748844375963,
520
+ "grad_norm": 6.022590637207031,
521
+ "learning_rate": 8.817823343848581e-06,
522
+ "loss": 1.0284172821044921,
523
+ "step": 1800
524
+ },
525
+ {
526
+ "epoch": 1.4060092449922958,
527
+ "grad_norm": 6.013957500457764,
528
+ "learning_rate": 8.798107255520505e-06,
529
+ "loss": 1.0445652770996094,
530
+ "step": 1825
531
+ },
532
+ {
533
+ "epoch": 1.4252696456086287,
534
+ "grad_norm": 6.47821044921875,
535
+ "learning_rate": 8.77839116719243e-06,
536
+ "loss": 1.0797194671630859,
537
+ "step": 1850
538
+ },
539
+ {
540
+ "epoch": 1.4445300462249615,
541
+ "grad_norm": 5.593505382537842,
542
+ "learning_rate": 8.758675078864354e-06,
543
+ "loss": 1.052033920288086,
544
+ "step": 1875
545
+ },
546
+ {
547
+ "epoch": 1.4637904468412943,
548
+ "grad_norm": 6.251946926116943,
549
+ "learning_rate": 8.738958990536279e-06,
550
+ "loss": 1.070428695678711,
551
+ "step": 1900
552
+ },
553
+ {
554
+ "epoch": 1.4830508474576272,
555
+ "grad_norm": 6.3281755447387695,
556
+ "learning_rate": 8.719242902208202e-06,
557
+ "loss": 1.0281287384033204,
558
+ "step": 1925
559
+ },
560
+ {
561
+ "epoch": 1.50231124807396,
562
+ "grad_norm": 5.988689422607422,
563
+ "learning_rate": 8.699526813880127e-06,
564
+ "loss": 1.0324861907958984,
565
+ "step": 1950
566
+ },
567
+ {
568
+ "epoch": 1.5215716486902928,
569
+ "grad_norm": 6.062340259552002,
570
+ "learning_rate": 8.679810725552051e-06,
571
+ "loss": 1.0550352478027343,
572
+ "step": 1975
573
+ },
574
+ {
575
+ "epoch": 1.5408320493066254,
576
+ "grad_norm": 4.881484031677246,
577
+ "learning_rate": 8.660094637223976e-06,
578
+ "loss": 1.0413783264160157,
579
+ "step": 2000
580
+ },
581
+ {
582
+ "epoch": 1.5600924499229585,
583
+ "grad_norm": 5.4565324783325195,
584
+ "learning_rate": 8.6403785488959e-06,
585
+ "loss": 1.0413751983642578,
586
+ "step": 2025
587
+ },
588
+ {
589
+ "epoch": 1.579352850539291,
590
+ "grad_norm": 5.8962483406066895,
591
+ "learning_rate": 8.620662460567824e-06,
592
+ "loss": 1.0537427520751954,
593
+ "step": 2050
594
+ },
595
+ {
596
+ "epoch": 1.5986132511556241,
597
+ "grad_norm": 5.976631164550781,
598
+ "learning_rate": 8.600946372239749e-06,
599
+ "loss": 1.0484622955322265,
600
+ "step": 2075
601
+ },
602
+ {
603
+ "epoch": 1.6178736517719567,
604
+ "grad_norm": 5.480655670166016,
605
+ "learning_rate": 8.581230283911672e-06,
606
+ "loss": 1.009260482788086,
607
+ "step": 2100
608
+ },
609
+ {
610
+ "epoch": 1.6371340523882898,
611
+ "grad_norm": 5.977313041687012,
612
+ "learning_rate": 8.561514195583596e-06,
613
+ "loss": 1.0521608734130858,
614
+ "step": 2125
615
+ },
616
+ {
617
+ "epoch": 1.6563944530046224,
618
+ "grad_norm": 5.078767776489258,
619
+ "learning_rate": 8.541798107255521e-06,
620
+ "loss": 1.0576594543457032,
621
+ "step": 2150
622
+ },
623
+ {
624
+ "epoch": 1.6756548536209555,
625
+ "grad_norm": 5.783039093017578,
626
+ "learning_rate": 8.522082018927446e-06,
627
+ "loss": 1.029164810180664,
628
+ "step": 2175
629
+ },
630
+ {
631
+ "epoch": 1.694915254237288,
632
+ "grad_norm": 6.353992938995361,
633
+ "learning_rate": 8.50236593059937e-06,
634
+ "loss": 1.0603709411621094,
635
+ "step": 2200
636
+ },
637
+ {
638
+ "epoch": 1.7141756548536211,
639
+ "grad_norm": 5.704638957977295,
640
+ "learning_rate": 8.482649842271294e-06,
641
+ "loss": 1.0352437591552734,
642
+ "step": 2225
643
+ },
644
+ {
645
+ "epoch": 1.7334360554699537,
646
+ "grad_norm": 6.092396259307861,
647
+ "learning_rate": 8.462933753943218e-06,
648
+ "loss": 1.0399227142333984,
649
+ "step": 2250
650
+ },
651
+ {
652
+ "epoch": 1.7526964560862865,
653
+ "grad_norm": 7.1011223793029785,
654
+ "learning_rate": 8.443217665615142e-06,
655
+ "loss": 1.0415158081054687,
656
+ "step": 2275
657
+ },
658
+ {
659
+ "epoch": 1.7719568567026194,
660
+ "grad_norm": 4.735724449157715,
661
+ "learning_rate": 8.423501577287066e-06,
662
+ "loss": 1.0339994049072265,
663
+ "step": 2300
664
+ },
665
+ {
666
+ "epoch": 1.7912172573189522,
667
+ "grad_norm": 6.994238376617432,
668
+ "learning_rate": 8.403785488958991e-06,
669
+ "loss": 1.0387593841552734,
670
+ "step": 2325
671
+ },
672
+ {
673
+ "epoch": 1.810477657935285,
674
+ "grad_norm": 6.1796956062316895,
675
+ "learning_rate": 8.384069400630916e-06,
676
+ "loss": 1.0579666900634765,
677
+ "step": 2350
678
+ },
679
+ {
680
+ "epoch": 1.8297380585516179,
681
+ "grad_norm": 5.0321197509765625,
682
+ "learning_rate": 8.36435331230284e-06,
683
+ "loss": 1.0294721984863282,
684
+ "step": 2375
685
+ },
686
+ {
687
+ "epoch": 1.8489984591679507,
688
+ "grad_norm": 6.216546535491943,
689
+ "learning_rate": 8.344637223974764e-06,
690
+ "loss": 1.0312883758544922,
691
+ "step": 2400
692
+ },
693
+ {
694
+ "epoch": 1.8682588597842835,
695
+ "grad_norm": 5.854124546051025,
696
+ "learning_rate": 8.324921135646688e-06,
697
+ "loss": 1.0346050262451172,
698
+ "step": 2425
699
+ },
700
+ {
701
+ "epoch": 1.8875192604006163,
702
+ "grad_norm": 7.55112361907959,
703
+ "learning_rate": 8.305205047318613e-06,
704
+ "loss": 1.0578290557861327,
705
+ "step": 2450
706
+ },
707
+ {
708
+ "epoch": 1.9067796610169492,
709
+ "grad_norm": 5.812201499938965,
710
+ "learning_rate": 8.285488958990538e-06,
711
+ "loss": 1.0345248413085937,
712
+ "step": 2475
713
+ },
714
+ {
715
+ "epoch": 1.926040061633282,
716
+ "grad_norm": 7.083204746246338,
717
+ "learning_rate": 8.26577287066246e-06,
718
+ "loss": 1.0337892913818358,
719
+ "step": 2500
720
+ },
721
+ {
722
+ "epoch": 1.9453004622496148,
723
+ "grad_norm": 5.301337242126465,
724
+ "learning_rate": 8.246056782334386e-06,
725
+ "loss": 1.0415627288818359,
726
+ "step": 2525
727
+ },
728
+ {
729
+ "epoch": 1.9645608628659477,
730
+ "grad_norm": 5.613387107849121,
731
+ "learning_rate": 8.22634069400631e-06,
732
+ "loss": 1.040993194580078,
733
+ "step": 2550
734
+ },
735
+ {
736
+ "epoch": 1.9838212634822803,
737
+ "grad_norm": 5.031157493591309,
738
+ "learning_rate": 8.206624605678233e-06,
739
+ "loss": 1.0369261932373046,
740
+ "step": 2575
741
+ },
742
+ {
743
+ "epoch": 2.0,
744
+ "eval_loss": 0.16153943538665771,
745
+ "eval_runtime": 1177.5263,
746
+ "eval_samples_per_second": 20.57,
747
+ "eval_steps_per_second": 0.093,
748
+ "eval_wer": 21.05581734399,
749
+ "step": 2596
750
+ }
751
+ ],
752
+ "logging_steps": 25,
753
+ "max_steps": 12980,
754
+ "num_input_tokens_seen": 0,
755
+ "num_train_epochs": 10,
756
+ "save_steps": 500,
757
+ "stateful_callbacks": {
758
+ "EarlyStoppingCallback": {
759
+ "args": {
760
+ "early_stopping_patience": 3,
761
+ "early_stopping_threshold": 0.0
762
+ },
763
+ "attributes": {
764
+ "early_stopping_patience_counter": 0
765
+ }
766
+ },
767
+ "TrainerControl": {
768
+ "args": {
769
+ "should_epoch_stop": false,
770
+ "should_evaluate": false,
771
+ "should_log": false,
772
+ "should_save": true,
773
+ "should_training_stop": false
774
+ },
775
+ "attributes": {}
776
+ }
777
+ },
778
+ "total_flos": 4.45114379815346e+20,
779
+ "train_batch_size": 24,
780
+ "trial_name": null,
781
+ "trial_params": null
782
+ }
epoch_2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e155e74e3785317024df094dc43f1bddfeb30257cc366390dc0635ed1f1d3b
3
+ size 4984