Hugging Face's logo

yusasif
/
whisp

Safetensors
Model card Files
xet
 Community
yusasif commited on
Commit
a3c9eeb
·
verified ·
1 Parent(s): 8d396a8

Auto-upload checkpoint: checkpoint-16000

Browse files
Files changed (9) hide show
  1. checkpoints/checkpoint-16000/config.json +59 -0
  2. checkpoints/checkpoint-16000/generation_config.json +195 -0
  3. checkpoints/checkpoint-16000/model.safetensors +3 -0
  4. checkpoints/checkpoint-16000/optimizer.pt +3 -0
  5. checkpoints/checkpoint-16000/rng_state.pth +3 -0
  6. checkpoints/checkpoint-16000/scaler.pt +3 -0
  7. checkpoints/checkpoint-16000/scheduler.pt +3 -0
  8. checkpoints/checkpoint-16000/trainer_state.json +339 -0
  9. checkpoints/checkpoint-16000/training_args.bin +3 -0
checkpoints/checkpoint-16000/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": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
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": 12,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.1.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
checkpoints/checkpoint-16000/generation_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "assistant_confidence_threshold": 0.4,
45
+ "assistant_lookbehind": 10,
46
+ "begin_suppress_tokens": [
47
+ 220,
48
+ 50257
49
+ ],
50
+ "bos_token_id": 50257,
51
+ "decoder_start_token_id": 50258,
52
+ "diversity_penalty": 0.0,
53
+ "do_sample": false,
54
+ "early_stopping": false,
55
+ "encoder_no_repeat_ngram_size": 0,
56
+ "encoder_repetition_penalty": 1.0,
57
+ "eos_token_id": 50257,
58
+ "epsilon_cutoff": 0.0,
59
+ "eta_cutoff": 0.0,
60
+ "forced_decoder_ids": null,
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
+ "language": "yoruba",
164
+ "length_penalty": 1.0,
165
+ "max_initial_timestamp_index": 50,
166
+ "max_length": 448,
167
+ "min_length": 0,
168
+ "no_repeat_ngram_size": 0,
169
+ "no_timestamps_token_id": 50363,
170
+ "num_assistant_tokens": 20,
171
+ "num_assistant_tokens_schedule": "constant",
172
+ "num_beam_groups": 1,
173
+ "num_beams": 1,
174
+ "num_return_sequences": 1,
175
+ "output_scores": false,
176
+ "pad_token_id": 50257,
177
+ "prev_sot_token_id": 50361,
178
+ "remove_invalid_values": false,
179
+ "repetition_penalty": 1.0,
180
+ "return_dict_in_generate": false,
181
+ "return_timestamps": false,
182
+ "suppress_tokens": [],
183
+ "target_lookbehind": 10,
184
+ "task": "transcribe",
185
+ "task_to_id": {
186
+ "transcribe": 50359,
187
+ "translate": 50358
188
+ },
189
+ "temperature": 1.0,
190
+ "top_k": 50,
191
+ "top_p": 1.0,
192
+ "transformers_version": "5.1.0",
193
+ "typical_p": 1.0,
194
+ "use_cache": true
195
+ }
checkpoints/checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7f0a934046c1eed1145740a3eb8e2c25bd34ffee6dc07b56e50618df05071c
3
+ size 966995080
checkpoints/checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1334bdbb0a7f9ccadbc89ace7b207c314d2c0aa061199a4793e3144ed921375a
3
+ size 1934288064
checkpoints/checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bce64eae3a0cd43afa62c4cb953c8e1e6eefe8ed27d2f6676e0df1027c4639
3
+ size 14645
checkpoints/checkpoint-16000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28d87dc6a09fe5f09ada130d75f4cdf126ee42fbef2dabc9747eff869a8b0a5
3
+ size 1383
checkpoints/checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf08206040ad1db2226a49b752c78b47503e287450e36e63d25d80971014cd66
3
+ size 1465
checkpoints/checkpoint-16000/trainer_state.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 16000,
3
+ "best_metric": 29.040304909818925,
4
+ "best_model_checkpoint": "./whisper-small-yoruba-438h/checkpoint-16000",
5
+ "epoch": 5.850091407678245,
6
+ "eval_steps": 2000,
7
+ "global_step": 16000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.18281535648994515,
14
+ "grad_norm": 23.418228149414062,
15
+ "learning_rate": 2.4950000000000003e-06,
16
+ "loss": 8.61669921875,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.3656307129798903,
21
+ "grad_norm": 18.097488403320312,
22
+ "learning_rate": 4.9950000000000005e-06,
23
+ "loss": 2.76252197265625,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.5484460694698354,
28
+ "grad_norm": 14.418298721313477,
29
+ "learning_rate": 4.980903172380229e-06,
30
+ "loss": 1.8946580810546876,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.7312614259597806,
35
+ "grad_norm": 13.605561256408691,
36
+ "learning_rate": 4.9237526483866514e-06,
37
+ "loss": 1.6098297119140625,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.7312614259597806,
42
+ "eval_loss": 0.37521448731422424,
43
+ "eval_runtime": 6135.7464,
44
+ "eval_samples_per_second": 1.585,
45
+ "eval_steps_per_second": 0.198,
46
+ "eval_wer": 42.951101658018516,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 0.9140767824497258,
51
+ "grad_norm": 13.122516632080078,
52
+ "learning_rate": 4.829424964672522e-06,
53
+ "loss": 1.4408970947265625,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 1.0968921389396709,
58
+ "grad_norm": 11.27369499206543,
59
+ "learning_rate": 4.699366983138475e-06,
60
+ "loss": 1.28490234375,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 1.2797074954296161,
65
+ "grad_norm": 12.354094505310059,
66
+ "learning_rate": 4.535573621193117e-06,
67
+ "loss": 1.175876220703125,
68
+ "step": 3500
69
+ },
70
+ {
71
+ "epoch": 1.4625228519195612,
72
+ "grad_norm": 12.436117172241211,
73
+ "learning_rate": 4.340557252358663e-06,
74
+ "loss": 1.1245360107421876,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 1.4625228519195612,
79
+ "eval_loss": 0.29289114475250244,
80
+ "eval_runtime": 4432.1972,
81
+ "eval_samples_per_second": 2.194,
82
+ "eval_steps_per_second": 0.274,
83
+ "eval_wer": 36.84005795570528,
84
+ "step": 4000
85
+ },
86
+ {
87
+ "epoch": 1.6453382084095063,
88
+ "grad_norm": 11.27859115600586,
89
+ "learning_rate": 4.1173091697842365e-06,
90
+ "loss": 1.087154541015625,
91
+ "step": 4500
92
+ },
93
+ {
94
+ "epoch": 1.8281535648994516,
95
+ "grad_norm": 12.39543628692627,
96
+ "learning_rate": 3.869253703765544e-06,
97
+ "loss": 1.0696717529296875,
98
+ "step": 5000
99
+ },
100
+ {
101
+ "epoch": 2.010968921389397,
102
+ "grad_norm": 10.303967475891113,
103
+ "learning_rate": 3.6001956970475217e-06,
104
+ "loss": 1.0127244873046874,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 2.1937842778793417,
109
+ "grad_norm": 11.98684024810791,
110
+ "learning_rate": 3.3142621435693033e-06,
111
+ "loss": 0.8952516479492187,
112
+ "step": 6000
113
+ },
114
+ {
115
+ "epoch": 2.1937842778793417,
116
+ "eval_loss": 0.26017212867736816,
117
+ "eval_runtime": 4412.3584,
118
+ "eval_samples_per_second": 2.204,
119
+ "eval_steps_per_second": 0.276,
120
+ "eval_wer": 33.975104741376235,
121
+ "step": 6000
122
+ },
123
+ {
124
+ "epoch": 2.376599634369287,
125
+ "grad_norm": 9.57399845123291,
126
+ "learning_rate": 4.481673449215052e-06,
127
+ "loss": 0.8934461059570312,
128
+ "step": 6500
129
+ },
130
+ {
131
+ "epoch": 2.5594149908592323,
132
+ "grad_norm": 12.205296516418457,
133
+ "learning_rate": 4.387349612915318e-06,
134
+ "loss": 0.8670662231445313,
135
+ "step": 7000
136
+ },
137
+ {
138
+ "epoch": 2.742230347349177,
139
+ "grad_norm": 11.39163875579834,
140
+ "learning_rate": 4.286320722991205e-06,
141
+ "loss": 0.86044384765625,
142
+ "step": 7500
143
+ },
144
+ {
145
+ "epoch": 2.9250457038391224,
146
+ "grad_norm": 11.357952117919922,
147
+ "learning_rate": 4.178945697642034e-06,
148
+ "loss": 0.8341318969726562,
149
+ "step": 8000
150
+ },
151
+ {
152
+ "epoch": 2.9250457038391224,
153
+ "eval_loss": 0.24125488102436066,
154
+ "eval_runtime": 4321.5359,
155
+ "eval_samples_per_second": 2.25,
156
+ "eval_steps_per_second": 0.281,
157
+ "eval_wer": 32.54798118580799,
158
+ "step": 8000
159
+ },
160
+ {
161
+ "epoch": 3.1078610603290677,
162
+ "grad_norm": 12.443680763244629,
163
+ "learning_rate": 4.0656060005340766e-06,
164
+ "loss": 0.7627076416015625,
165
+ "step": 8500
166
+ },
167
+ {
168
+ "epoch": 3.2906764168190126,
169
+ "grad_norm": 10.662081718444824,
170
+ "learning_rate": 3.946704285601551e-06,
171
+ "loss": 0.7079920043945312,
172
+ "step": 9000
173
+ },
174
+ {
175
+ "epoch": 3.473491773308958,
176
+ "grad_norm": 13.675153732299805,
177
+ "learning_rate": 3.822662966566427e-06,
178
+ "loss": 0.7093059692382813,
179
+ "step": 9500
180
+ },
181
+ {
182
+ "epoch": 3.656307129798903,
183
+ "grad_norm": 11.558106422424316,
184
+ "learning_rate": 3.6939227162590474e-06,
185
+ "loss": 0.699214599609375,
186
+ "step": 10000
187
+ },
188
+ {
189
+ "epoch": 3.656307129798903,
190
+ "eval_loss": 0.22658970952033997,
191
+ "eval_runtime": 4394.9833,
192
+ "eval_samples_per_second": 2.213,
193
+ "eval_steps_per_second": 0.277,
194
+ "eval_wer": 31.3628155623916,
195
+ "step": 10000
196
+ },
197
+ {
198
+ "epoch": 3.839122486288848,
199
+ "grad_norm": 12.224128723144531,
200
+ "learning_rate": 3.5609409010708955e-06,
201
+ "loss": 0.7020602416992188,
202
+ "step": 10500
203
+ },
204
+ {
205
+ "epoch": 4.021937842778794,
206
+ "grad_norm": 13.084427833557129,
207
+ "learning_rate": 3.4241899561013316e-06,
208
+ "loss": 0.6613292846679687,
209
+ "step": 11000
210
+ },
211
+ {
212
+ "epoch": 4.204753199268739,
213
+ "grad_norm": 10.680255889892578,
214
+ "learning_rate": 3.284155706770791e-06,
215
+ "loss": 0.5683858032226563,
216
+ "step": 11500
217
+ },
218
+ {
219
+ "epoch": 4.387568555758683,
220
+ "grad_norm": 12.943653106689453,
221
+ "learning_rate": 3.1413356428631416e-06,
222
+ "loss": 0.5714318237304687,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 4.387568555758683,
227
+ "eval_loss": 0.21931344270706177,
228
+ "eval_runtime": 4368.7783,
229
+ "eval_samples_per_second": 2.226,
230
+ "eval_steps_per_second": 0.278,
231
+ "eval_wer": 29.561335265190174,
232
+ "step": 12000
233
+ },
234
+ {
235
+ "epoch": 4.570383912248629,
236
+ "grad_norm": 9.87512493133545,
237
+ "learning_rate": 2.996237151128874e-06,
238
+ "loss": 0.5676758422851562,
239
+ "step": 12500
240
+ },
241
+ {
242
+ "epoch": 4.753199268738574,
243
+ "grad_norm": 11.12316608428955,
244
+ "learning_rate": 2.8493757127280436e-06,
245
+ "loss": 0.5684054565429687,
246
+ "step": 13000
247
+ },
248
+ {
249
+ "epoch": 4.936014625228519,
250
+ "grad_norm": 10.787373542785645,
251
+ "learning_rate": 2.701273071916772e-06,
252
+ "loss": 0.5666332397460937,
253
+ "step": 13500
254
+ },
255
+ {
256
+ "epoch": 5.118829981718465,
257
+ "grad_norm": 10.713043212890625,
258
+ "learning_rate": 2.552455382483289e-06,
259
+ "loss": 0.4890457763671875,
260
+ "step": 14000
261
+ },
262
+ {
263
+ "epoch": 5.118829981718465,
264
+ "eval_loss": 0.2142162322998047,
265
+ "eval_runtime": 4395.2429,
266
+ "eval_samples_per_second": 2.213,
267
+ "eval_steps_per_second": 0.277,
268
+ "eval_wer": 29.108467100144892,
269
+ "step": 14000
270
+ },
271
+ {
272
+ "epoch": 5.301645338208409,
273
+ "grad_norm": 10.574690818786621,
274
+ "learning_rate": 2.403451338518546e-06,
275
+ "loss": 0.46753656005859373,
276
+ "step": 14500
277
+ },
278
+ {
279
+ "epoch": 5.484460694698354,
280
+ "grad_norm": 12.801483154296875,
281
+ "learning_rate": 2.2547902961620725e-06,
282
+ "loss": 0.4668481140136719,
283
+ "step": 15000
284
+ },
285
+ {
286
+ "epoch": 5.6672760511883,
287
+ "grad_norm": 12.052448272705078,
288
+ "learning_rate": 2.107000392995815e-06,
289
+ "loss": 0.46311260986328123,
290
+ "step": 15500
291
+ },
292
+ {
293
+ "epoch": 5.850091407678245,
294
+ "grad_norm": 11.316293716430664,
295
+ "learning_rate": 1.960606671767071e-06,
296
+ "loss": 0.45828167724609375,
297
+ "step": 16000
298
+ },
299
+ {
300
+ "epoch": 5.850091407678245,
301
+ "eval_loss": 0.2103041559457779,
302
+ "eval_runtime": 4422.576,
303
+ "eval_samples_per_second": 2.199,
304
+ "eval_steps_per_second": 0.275,
305
+ "eval_wer": 29.040304909818925,
306
+ "step": 16000
307
+ }
308
+ ],
309
+ "logging_steps": 500,
310
+ "max_steps": 27350,
311
+ "num_input_tokens_seen": 0,
312
+ "num_train_epochs": 10,
313
+ "save_steps": 2000,
314
+ "stateful_callbacks": {
315
+ "EarlyStoppingCallback": {
316
+ "args": {
317
+ "early_stopping_patience": 3,
318
+ "early_stopping_threshold": 0.0
319
+ },
320
+ "attributes": {
321
+ "early_stopping_patience_counter": 0
322
+ }
323
+ },
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": 1.477513961828352e+20,
336
+ "train_batch_size": 8,
337
+ "trial_name": null,
338
+ "trial_params": null
339
+ }
checkpoints/checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f60328b4bba74be343c5a5a0e7505532827163ba894af7ff9a1aa36da88e57
3
+ size 5393