Commit
•
07dc93f
1
Parent(s):
2472fda
Upload 10 files
Browse files- config.json +51 -0
- generation_config.json +222 -0
- optimizer.pt +3 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +496 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-medium",
|
| 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": 1024,
|
| 17 |
+
"decoder_attention_heads": 16,
|
| 18 |
+
"decoder_ffn_dim": 4096,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 24,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 24,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": null,
|
| 29 |
+
"init_std": 0.02,
|
| 30 |
+
"is_encoder_decoder": true,
|
| 31 |
+
"mask_feature_length": 10,
|
| 32 |
+
"mask_feature_min_masks": 0,
|
| 33 |
+
"mask_feature_prob": 0.0,
|
| 34 |
+
"mask_time_length": 10,
|
| 35 |
+
"mask_time_min_masks": 2,
|
| 36 |
+
"mask_time_prob": 0.05,
|
| 37 |
+
"max_length": 448,
|
| 38 |
+
"max_source_positions": 1500,
|
| 39 |
+
"max_target_positions": 448,
|
| 40 |
+
"model_type": "whisper",
|
| 41 |
+
"num_hidden_layers": 24,
|
| 42 |
+
"num_mel_bins": 80,
|
| 43 |
+
"pad_token_id": 50257,
|
| 44 |
+
"scale_embedding": false,
|
| 45 |
+
"suppress_tokens": [],
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.27.0.dev0",
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"use_weighted_layer_sum": false,
|
| 50 |
+
"vocab_size": 51865
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"begin_suppress_tokens": [
|
| 3 |
+
220,
|
| 4 |
+
50257
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 50257,
|
| 7 |
+
"decoder_start_token_id": 50258,
|
| 8 |
+
"eos_token_id": 50257,
|
| 9 |
+
"forced_decoder_ids": [
|
| 10 |
+
[
|
| 11 |
+
1,
|
| 12 |
+
null
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
2,
|
| 16 |
+
50359
|
| 17 |
+
],
|
| 18 |
+
[
|
| 19 |
+
3,
|
| 20 |
+
50363
|
| 21 |
+
]
|
| 22 |
+
],
|
| 23 |
+
"is_multilingual": true,
|
| 24 |
+
"lang_to_id": {
|
| 25 |
+
"<|af|>": 50327,
|
| 26 |
+
"<|am|>": 50334,
|
| 27 |
+
"<|ar|>": 50272,
|
| 28 |
+
"<|as|>": 50350,
|
| 29 |
+
"<|az|>": 50304,
|
| 30 |
+
"<|ba|>": 50355,
|
| 31 |
+
"<|be|>": 50330,
|
| 32 |
+
"<|bg|>": 50292,
|
| 33 |
+
"<|bn|>": 50302,
|
| 34 |
+
"<|bo|>": 50347,
|
| 35 |
+
"<|br|>": 50309,
|
| 36 |
+
"<|bs|>": 50315,
|
| 37 |
+
"<|ca|>": 50270,
|
| 38 |
+
"<|cs|>": 50283,
|
| 39 |
+
"<|cy|>": 50297,
|
| 40 |
+
"<|da|>": 50285,
|
| 41 |
+
"<|de|>": 50261,
|
| 42 |
+
"<|el|>": 50281,
|
| 43 |
+
"<|en|>": 50259,
|
| 44 |
+
"<|es|>": 50262,
|
| 45 |
+
"<|et|>": 50307,
|
| 46 |
+
"<|eu|>": 50310,
|
| 47 |
+
"<|fa|>": 50300,
|
| 48 |
+
"<|fi|>": 50277,
|
| 49 |
+
"<|fo|>": 50338,
|
| 50 |
+
"<|fr|>": 50265,
|
| 51 |
+
"<|gl|>": 50319,
|
| 52 |
+
"<|gu|>": 50333,
|
| 53 |
+
"<|haw|>": 50352,
|
| 54 |
+
"<|ha|>": 50354,
|
| 55 |
+
"<|he|>": 50279,
|
| 56 |
+
"<|hi|>": 50276,
|
| 57 |
+
"<|hr|>": 50291,
|
| 58 |
+
"<|ht|>": 50339,
|
| 59 |
+
"<|hu|>": 50286,
|
| 60 |
+
"<|hy|>": 50312,
|
| 61 |
+
"<|id|>": 50275,
|
| 62 |
+
"<|is|>": 50311,
|
| 63 |
+
"<|it|>": 50274,
|
| 64 |
+
"<|ja|>": 50266,
|
| 65 |
+
"<|jw|>": 50356,
|
| 66 |
+
"<|ka|>": 50329,
|
| 67 |
+
"<|kk|>": 50316,
|
| 68 |
+
"<|km|>": 50323,
|
| 69 |
+
"<|kn|>": 50306,
|
| 70 |
+
"<|ko|>": 50264,
|
| 71 |
+
"<|la|>": 50294,
|
| 72 |
+
"<|lb|>": 50345,
|
| 73 |
+
"<|ln|>": 50353,
|
| 74 |
+
"<|lo|>": 50336,
|
| 75 |
+
"<|lt|>": 50293,
|
| 76 |
+
"<|lv|>": 50301,
|
| 77 |
+
"<|mg|>": 50349,
|
| 78 |
+
"<|mi|>": 50295,
|
| 79 |
+
"<|mk|>": 50308,
|
| 80 |
+
"<|ml|>": 50296,
|
| 81 |
+
"<|mn|>": 50314,
|
| 82 |
+
"<|mr|>": 50320,
|
| 83 |
+
"<|ms|>": 50282,
|
| 84 |
+
"<|mt|>": 50343,
|
| 85 |
+
"<|my|>": 50346,
|
| 86 |
+
"<|ne|>": 50313,
|
| 87 |
+
"<|nl|>": 50271,
|
| 88 |
+
"<|nn|>": 50342,
|
| 89 |
+
"<|no|>": 50288,
|
| 90 |
+
"<|oc|>": 50328,
|
| 91 |
+
"<|pa|>": 50321,
|
| 92 |
+
"<|pl|>": 50269,
|
| 93 |
+
"<|ps|>": 50340,
|
| 94 |
+
"<|pt|>": 50267,
|
| 95 |
+
"<|ro|>": 50284,
|
| 96 |
+
"<|ru|>": 50263,
|
| 97 |
+
"<|sa|>": 50344,
|
| 98 |
+
"<|sd|>": 50332,
|
| 99 |
+
"<|si|>": 50322,
|
| 100 |
+
"<|sk|>": 50298,
|
| 101 |
+
"<|sl|>": 50305,
|
| 102 |
+
"<|sn|>": 50324,
|
| 103 |
+
"<|so|>": 50326,
|
| 104 |
+
"<|sq|>": 50317,
|
| 105 |
+
"<|sr|>": 50303,
|
| 106 |
+
"<|su|>": 50357,
|
| 107 |
+
"<|sv|>": 50273,
|
| 108 |
+
"<|sw|>": 50318,
|
| 109 |
+
"<|ta|>": 50287,
|
| 110 |
+
"<|te|>": 50299,
|
| 111 |
+
"<|tg|>": 50331,
|
| 112 |
+
"<|th|>": 50289,
|
| 113 |
+
"<|tk|>": 50341,
|
| 114 |
+
"<|tl|>": 50348,
|
| 115 |
+
"<|tr|>": 50268,
|
| 116 |
+
"<|tt|>": 50351,
|
| 117 |
+
"<|uk|>": 50280,
|
| 118 |
+
"<|ur|>": 50290,
|
| 119 |
+
"<|uz|>": 50337,
|
| 120 |
+
"<|vi|>": 50278,
|
| 121 |
+
"<|yi|>": 50335,
|
| 122 |
+
"<|yo|>": 50325,
|
| 123 |
+
"<|zh|>": 50260
|
| 124 |
+
},
|
| 125 |
+
"max_initial_timestamp_index": 1,
|
| 126 |
+
"max_length": 448,
|
| 127 |
+
"no_timestamps_token_id": 50363,
|
| 128 |
+
"pad_token_id": 50257,
|
| 129 |
+
"suppress_tokens": [
|
| 130 |
+
1,
|
| 131 |
+
2,
|
| 132 |
+
7,
|
| 133 |
+
8,
|
| 134 |
+
9,
|
| 135 |
+
10,
|
| 136 |
+
14,
|
| 137 |
+
25,
|
| 138 |
+
26,
|
| 139 |
+
27,
|
| 140 |
+
28,
|
| 141 |
+
29,
|
| 142 |
+
31,
|
| 143 |
+
58,
|
| 144 |
+
59,
|
| 145 |
+
60,
|
| 146 |
+
61,
|
| 147 |
+
62,
|
| 148 |
+
63,
|
| 149 |
+
90,
|
| 150 |
+
91,
|
| 151 |
+
92,
|
| 152 |
+
93,
|
| 153 |
+
359,
|
| 154 |
+
503,
|
| 155 |
+
522,
|
| 156 |
+
542,
|
| 157 |
+
873,
|
| 158 |
+
893,
|
| 159 |
+
902,
|
| 160 |
+
918,
|
| 161 |
+
922,
|
| 162 |
+
931,
|
| 163 |
+
1350,
|
| 164 |
+
1853,
|
| 165 |
+
1982,
|
| 166 |
+
2460,
|
| 167 |
+
2627,
|
| 168 |
+
3246,
|
| 169 |
+
3253,
|
| 170 |
+
3268,
|
| 171 |
+
3536,
|
| 172 |
+
3846,
|
| 173 |
+
3961,
|
| 174 |
+
4183,
|
| 175 |
+
4667,
|
| 176 |
+
6585,
|
| 177 |
+
6647,
|
| 178 |
+
7273,
|
| 179 |
+
9061,
|
| 180 |
+
9383,
|
| 181 |
+
10428,
|
| 182 |
+
10929,
|
| 183 |
+
11938,
|
| 184 |
+
12033,
|
| 185 |
+
12331,
|
| 186 |
+
12562,
|
| 187 |
+
13793,
|
| 188 |
+
14157,
|
| 189 |
+
14635,
|
| 190 |
+
15265,
|
| 191 |
+
15618,
|
| 192 |
+
16553,
|
| 193 |
+
16604,
|
| 194 |
+
18362,
|
| 195 |
+
18956,
|
| 196 |
+
20075,
|
| 197 |
+
21675,
|
| 198 |
+
22520,
|
| 199 |
+
26130,
|
| 200 |
+
26161,
|
| 201 |
+
26435,
|
| 202 |
+
28279,
|
| 203 |
+
29464,
|
| 204 |
+
31650,
|
| 205 |
+
32302,
|
| 206 |
+
32470,
|
| 207 |
+
36865,
|
| 208 |
+
42863,
|
| 209 |
+
47425,
|
| 210 |
+
49870,
|
| 211 |
+
50254,
|
| 212 |
+
50258,
|
| 213 |
+
50360,
|
| 214 |
+
50361,
|
| 215 |
+
50362
|
| 216 |
+
],
|
| 217 |
+
"task_to_id": {
|
| 218 |
+
"transcribe": 50359,
|
| 219 |
+
"translate": 50358
|
| 220 |
+
},
|
| 221 |
+
"transformers_version": "4.27.0.dev0"
|
| 222 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac9176650abc6537f10b6886c4679f7d5271d4e832fea5c902fd21fec43755f
|
| 3 |
+
size 6111424583
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ada5c452383a232533b6e0e7e183fdd1dc7b4323db670c40271b54952658dcae
|
| 3 |
+
size 3055748571
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b75673f962e71673e5a5d168b28998429862022327ff481af8ed9d61c94c6ce
|
| 3 |
+
size 14503
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:682f2adab43c35de6eefe529f4d9fde92897e7bcd6925429a35513ce90331a69
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:056e6d0419c58f7183c15262f9cf4bb009b0dbf3e2ca6d5b6156af7ce3a4d99e
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 31.96095635007677,
|
| 3 |
+
"best_model_checkpoint": "./whisper-medium-bn/checkpoint-64000",
|
| 4 |
+
"epoch": 4.046023517511696,
|
| 5 |
+
"global_step": 64000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 9.936816319635089e-06,
|
| 13 |
+
"loss": 0.2519,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"eval_loss": 0.10757352411746979,
|
| 19 |
+
"eval_runtime": 1082.7593,
|
| 20 |
+
"eval_samples_per_second": 5.962,
|
| 21 |
+
"eval_steps_per_second": 0.373,
|
| 22 |
+
"eval_wer": 100.07530891277328,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.25,
|
| 27 |
+
"learning_rate": 9.852346158719434e-06,
|
| 28 |
+
"loss": 0.1112,
|
| 29 |
+
"step": 4000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.25,
|
| 33 |
+
"eval_loss": 0.08318958431482315,
|
| 34 |
+
"eval_runtime": 1158.0641,
|
| 35 |
+
"eval_samples_per_second": 5.574,
|
| 36 |
+
"eval_steps_per_second": 0.349,
|
| 37 |
+
"eval_wer": 99.66732470571031,
|
| 38 |
+
"step": 4000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.38,
|
| 42 |
+
"learning_rate": 9.767875997803777e-06,
|
| 43 |
+
"loss": 0.0909,
|
| 44 |
+
"step": 6000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.38,
|
| 48 |
+
"eval_loss": 0.0710902065038681,
|
| 49 |
+
"eval_runtime": 1331.5659,
|
| 50 |
+
"eval_samples_per_second": 4.848,
|
| 51 |
+
"eval_steps_per_second": 0.303,
|
| 52 |
+
"eval_wer": 98.73729619068509,
|
| 53 |
+
"step": 6000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.51,
|
| 57 |
+
"learning_rate": 9.683490307049036e-06,
|
| 58 |
+
"loss": 0.0824,
|
| 59 |
+
"step": 8000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.51,
|
| 63 |
+
"eval_loss": 0.06057652831077576,
|
| 64 |
+
"eval_runtime": 2277.9347,
|
| 65 |
+
"eval_samples_per_second": 2.834,
|
| 66 |
+
"eval_steps_per_second": 0.177,
|
| 67 |
+
"eval_wer": 71.25392995539957,
|
| 68 |
+
"step": 8000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.63,
|
| 72 |
+
"learning_rate": 9.599062381213838e-06,
|
| 73 |
+
"loss": 0.0766,
|
| 74 |
+
"step": 10000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.63,
|
| 78 |
+
"eval_loss": 0.054338764399290085,
|
| 79 |
+
"eval_runtime": 2259.5514,
|
| 80 |
+
"eval_samples_per_second": 2.857,
|
| 81 |
+
"eval_steps_per_second": 0.179,
|
| 82 |
+
"eval_wer": 72.27827740001462,
|
| 83 |
+
"step": 10000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.76,
|
| 87 |
+
"learning_rate": 9.51459222029818e-06,
|
| 88 |
+
"loss": 0.0697,
|
| 89 |
+
"step": 12000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.76,
|
| 93 |
+
"eval_loss": 0.05125707387924194,
|
| 94 |
+
"eval_runtime": 2175.3979,
|
| 95 |
+
"eval_samples_per_second": 2.967,
|
| 96 |
+
"eval_steps_per_second": 0.186,
|
| 97 |
+
"eval_wer": 81.96680558602033,
|
| 98 |
+
"step": 12000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.89,
|
| 102 |
+
"learning_rate": 9.43016429446298e-06,
|
| 103 |
+
"loss": 0.0628,
|
| 104 |
+
"step": 14000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.89,
|
| 108 |
+
"eval_loss": 0.04882914572954178,
|
| 109 |
+
"eval_runtime": 2201.7571,
|
| 110 |
+
"eval_samples_per_second": 2.932,
|
| 111 |
+
"eval_steps_per_second": 0.183,
|
| 112 |
+
"eval_wer": 78.58814067412445,
|
| 113 |
+
"step": 14000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.01,
|
| 117 |
+
"learning_rate": 9.345736368627784e-06,
|
| 118 |
+
"loss": 0.0584,
|
| 119 |
+
"step": 16000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.01,
|
| 123 |
+
"eval_loss": 0.045878272503614426,
|
| 124 |
+
"eval_runtime": 2300.4041,
|
| 125 |
+
"eval_samples_per_second": 2.806,
|
| 126 |
+
"eval_steps_per_second": 0.176,
|
| 127 |
+
"eval_wer": 48.36294509029758,
|
| 128 |
+
"step": 16000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.14,
|
| 132 |
+
"learning_rate": 9.261266207712126e-06,
|
| 133 |
+
"loss": 0.048,
|
| 134 |
+
"step": 18000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.14,
|
| 138 |
+
"eval_loss": 0.0436786450445652,
|
| 139 |
+
"eval_runtime": 2280.8033,
|
| 140 |
+
"eval_samples_per_second": 2.83,
|
| 141 |
+
"eval_steps_per_second": 0.177,
|
| 142 |
+
"eval_wer": 55.72201506178256,
|
| 143 |
+
"step": 18000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.26,
|
| 147 |
+
"learning_rate": 9.17679604679647e-06,
|
| 148 |
+
"loss": 0.0479,
|
| 149 |
+
"step": 20000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.26,
|
| 153 |
+
"eval_loss": 0.04214460402727127,
|
| 154 |
+
"eval_runtime": 2296.865,
|
| 155 |
+
"eval_samples_per_second": 2.81,
|
| 156 |
+
"eval_steps_per_second": 0.176,
|
| 157 |
+
"eval_wer": 49.24910433574614,
|
| 158 |
+
"step": 20000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.39,
|
| 162 |
+
"learning_rate": 9.09236812096127e-06,
|
| 163 |
+
"loss": 0.0449,
|
| 164 |
+
"step": 22000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.39,
|
| 168 |
+
"eval_loss": 0.041120000183582306,
|
| 169 |
+
"eval_runtime": 2298.4349,
|
| 170 |
+
"eval_samples_per_second": 2.808,
|
| 171 |
+
"eval_steps_per_second": 0.176,
|
| 172 |
+
"eval_wer": 49.43774219492579,
|
| 173 |
+
"step": 22000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.52,
|
| 177 |
+
"learning_rate": 9.007940195126072e-06,
|
| 178 |
+
"loss": 0.0442,
|
| 179 |
+
"step": 24000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.52,
|
| 183 |
+
"eval_loss": 0.03955331817269325,
|
| 184 |
+
"eval_runtime": 2308.5361,
|
| 185 |
+
"eval_samples_per_second": 2.796,
|
| 186 |
+
"eval_steps_per_second": 0.175,
|
| 187 |
+
"eval_wer": 42.16494845360825,
|
| 188 |
+
"step": 24000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.64,
|
| 192 |
+
"learning_rate": 8.923512269290874e-06,
|
| 193 |
+
"loss": 0.0434,
|
| 194 |
+
"step": 26000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.64,
|
| 198 |
+
"eval_loss": 0.037342339754104614,
|
| 199 |
+
"eval_runtime": 2302.7779,
|
| 200 |
+
"eval_samples_per_second": 2.803,
|
| 201 |
+
"eval_steps_per_second": 0.175,
|
| 202 |
+
"eval_wer": 45.68765080061417,
|
| 203 |
+
"step": 26000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.77,
|
| 207 |
+
"learning_rate": 8.839084343455674e-06,
|
| 208 |
+
"loss": 0.0421,
|
| 209 |
+
"step": 28000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.77,
|
| 213 |
+
"eval_loss": 0.0369366817176342,
|
| 214 |
+
"eval_runtime": 2289.7529,
|
| 215 |
+
"eval_samples_per_second": 2.819,
|
| 216 |
+
"eval_steps_per_second": 0.176,
|
| 217 |
+
"eval_wer": 56.33399137237698,
|
| 218 |
+
"step": 28000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.9,
|
| 222 |
+
"learning_rate": 8.754656417620476e-06,
|
| 223 |
+
"loss": 0.0417,
|
| 224 |
+
"step": 30000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.9,
|
| 228 |
+
"eval_loss": 0.03590318188071251,
|
| 229 |
+
"eval_runtime": 2299.447,
|
| 230 |
+
"eval_samples_per_second": 2.807,
|
| 231 |
+
"eval_steps_per_second": 0.176,
|
| 232 |
+
"eval_wer": 40.42114498793595,
|
| 233 |
+
"step": 30000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.02,
|
| 237 |
+
"learning_rate": 8.670228491785278e-06,
|
| 238 |
+
"loss": 0.0396,
|
| 239 |
+
"step": 32000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.02,
|
| 243 |
+
"eval_loss": 0.03535410389304161,
|
| 244 |
+
"eval_runtime": 2295.7712,
|
| 245 |
+
"eval_samples_per_second": 2.812,
|
| 246 |
+
"eval_steps_per_second": 0.176,
|
| 247 |
+
"eval_wer": 39.69218395847042,
|
| 248 |
+
"step": 32000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.15,
|
| 252 |
+
"learning_rate": 8.585758330869621e-06,
|
| 253 |
+
"loss": 0.0316,
|
| 254 |
+
"step": 34000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.15,
|
| 258 |
+
"eval_loss": 0.035752419382333755,
|
| 259 |
+
"eval_runtime": 2290.0476,
|
| 260 |
+
"eval_samples_per_second": 2.819,
|
| 261 |
+
"eval_steps_per_second": 0.176,
|
| 262 |
+
"eval_wer": 48.914966732470575,
|
| 263 |
+
"step": 34000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.28,
|
| 267 |
+
"learning_rate": 8.501330405034423e-06,
|
| 268 |
+
"loss": 0.0304,
|
| 269 |
+
"step": 36000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.28,
|
| 273 |
+
"eval_loss": 0.03435269743204117,
|
| 274 |
+
"eval_runtime": 2306.3737,
|
| 275 |
+
"eval_samples_per_second": 2.799,
|
| 276 |
+
"eval_steps_per_second": 0.175,
|
| 277 |
+
"eval_wer": 37.936682020911014,
|
| 278 |
+
"step": 36000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.4,
|
| 282 |
+
"learning_rate": 8.416944714279682e-06,
|
| 283 |
+
"loss": 0.0308,
|
| 284 |
+
"step": 38000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.4,
|
| 288 |
+
"eval_loss": 0.034886814653873444,
|
| 289 |
+
"eval_runtime": 2296.8318,
|
| 290 |
+
"eval_samples_per_second": 2.81,
|
| 291 |
+
"eval_steps_per_second": 0.176,
|
| 292 |
+
"eval_wer": 38.98735102727206,
|
| 293 |
+
"step": 38000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.53,
|
| 297 |
+
"learning_rate": 8.332474553364025e-06,
|
| 298 |
+
"loss": 0.031,
|
| 299 |
+
"step": 40000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.53,
|
| 303 |
+
"eval_loss": 0.03347828984260559,
|
| 304 |
+
"eval_runtime": 2306.1956,
|
| 305 |
+
"eval_samples_per_second": 2.799,
|
| 306 |
+
"eval_steps_per_second": 0.175,
|
| 307 |
+
"eval_wer": 34.57117788988813,
|
| 308 |
+
"step": 40000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.66,
|
| 312 |
+
"learning_rate": 8.24800439244837e-06,
|
| 313 |
+
"loss": 0.0299,
|
| 314 |
+
"step": 42000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.66,
|
| 318 |
+
"eval_loss": 0.03452066704630852,
|
| 319 |
+
"eval_runtime": 2295.8518,
|
| 320 |
+
"eval_samples_per_second": 2.812,
|
| 321 |
+
"eval_steps_per_second": 0.176,
|
| 322 |
+
"eval_wer": 37.69832565621115,
|
| 323 |
+
"step": 42000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.78,
|
| 327 |
+
"learning_rate": 8.16357646661317e-06,
|
| 328 |
+
"loss": 0.0304,
|
| 329 |
+
"step": 44000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.78,
|
| 333 |
+
"eval_loss": 0.03322349861264229,
|
| 334 |
+
"eval_runtime": 2305.8554,
|
| 335 |
+
"eval_samples_per_second": 2.799,
|
| 336 |
+
"eval_steps_per_second": 0.175,
|
| 337 |
+
"eval_wer": 36.211157417562326,
|
| 338 |
+
"step": 44000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.91,
|
| 342 |
+
"learning_rate": 8.079148540777972e-06,
|
| 343 |
+
"loss": 0.028,
|
| 344 |
+
"step": 46000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.91,
|
| 348 |
+
"eval_loss": 0.03227932006120682,
|
| 349 |
+
"eval_runtime": 2303.1451,
|
| 350 |
+
"eval_samples_per_second": 2.803,
|
| 351 |
+
"eval_steps_per_second": 0.175,
|
| 352 |
+
"eval_wer": 35.43905827301309,
|
| 353 |
+
"step": 46000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.03,
|
| 357 |
+
"learning_rate": 7.994678379862315e-06,
|
| 358 |
+
"loss": 0.0281,
|
| 359 |
+
"step": 48000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.03,
|
| 363 |
+
"eval_loss": 0.03418450057506561,
|
| 364 |
+
"eval_runtime": 2296.1947,
|
| 365 |
+
"eval_samples_per_second": 2.811,
|
| 366 |
+
"eval_steps_per_second": 0.176,
|
| 367 |
+
"eval_wer": 35.552387219419465,
|
| 368 |
+
"step": 48000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.16,
|
| 372 |
+
"learning_rate": 7.910250454027115e-06,
|
| 373 |
+
"loss": 0.0208,
|
| 374 |
+
"step": 50000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.16,
|
| 378 |
+
"eval_loss": 0.0337488129734993,
|
| 379 |
+
"eval_runtime": 2291.6062,
|
| 380 |
+
"eval_samples_per_second": 2.817,
|
| 381 |
+
"eval_steps_per_second": 0.176,
|
| 382 |
+
"eval_wer": 37.779483804927985,
|
| 383 |
+
"step": 50000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.29,
|
| 387 |
+
"learning_rate": 7.82578029311146e-06,
|
| 388 |
+
"loss": 0.021,
|
| 389 |
+
"step": 52000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.29,
|
| 393 |
+
"eval_loss": 0.033615775406360626,
|
| 394 |
+
"eval_runtime": 2304.2255,
|
| 395 |
+
"eval_samples_per_second": 2.801,
|
| 396 |
+
"eval_steps_per_second": 0.175,
|
| 397 |
+
"eval_wer": 33.51612195656942,
|
| 398 |
+
"step": 52000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.41,
|
| 402 |
+
"learning_rate": 7.74135236727626e-06,
|
| 403 |
+
"loss": 0.021,
|
| 404 |
+
"step": 54000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.41,
|
| 408 |
+
"eval_loss": 0.03333365172147751,
|
| 409 |
+
"eval_runtime": 2311.8192,
|
| 410 |
+
"eval_samples_per_second": 2.792,
|
| 411 |
+
"eval_steps_per_second": 0.175,
|
| 412 |
+
"eval_wer": 32.82591211522995,
|
| 413 |
+
"step": 54000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.54,
|
| 417 |
+
"learning_rate": 7.656882206360604e-06,
|
| 418 |
+
"loss": 0.0202,
|
| 419 |
+
"step": 56000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.54,
|
| 423 |
+
"eval_loss": 0.032315392047166824,
|
| 424 |
+
"eval_runtime": 2307.3986,
|
| 425 |
+
"eval_samples_per_second": 2.798,
|
| 426 |
+
"eval_steps_per_second": 0.175,
|
| 427 |
+
"eval_wer": 33.00870073846604,
|
| 428 |
+
"step": 56000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.67,
|
| 432 |
+
"learning_rate": 7.5724965156058624e-06,
|
| 433 |
+
"loss": 0.0214,
|
| 434 |
+
"step": 58000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.67,
|
| 438 |
+
"eval_loss": 0.0318850576877594,
|
| 439 |
+
"eval_runtime": 2301.2104,
|
| 440 |
+
"eval_samples_per_second": 2.805,
|
| 441 |
+
"eval_steps_per_second": 0.176,
|
| 442 |
+
"eval_wer": 32.453023323828326,
|
| 443 |
+
"step": 58000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.79,
|
| 447 |
+
"learning_rate": 7.488026354690206e-06,
|
| 448 |
+
"loss": 0.0206,
|
| 449 |
+
"step": 60000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.79,
|
| 453 |
+
"eval_loss": 0.031195413321256638,
|
| 454 |
+
"eval_runtime": 2300.0768,
|
| 455 |
+
"eval_samples_per_second": 2.806,
|
| 456 |
+
"eval_steps_per_second": 0.176,
|
| 457 |
+
"eval_wer": 32.26511661914163,
|
| 458 |
+
"step": 60000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.92,
|
| 462 |
+
"learning_rate": 7.403598428855008e-06,
|
| 463 |
+
"loss": 0.0213,
|
| 464 |
+
"step": 62000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.92,
|
| 468 |
+
"eval_loss": 0.03142615407705307,
|
| 469 |
+
"eval_runtime": 2307.3794,
|
| 470 |
+
"eval_samples_per_second": 2.798,
|
| 471 |
+
"eval_steps_per_second": 0.175,
|
| 472 |
+
"eval_wer": 32.072822987497254,
|
| 473 |
+
"step": 62000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.05,
|
| 477 |
+
"learning_rate": 7.319170503019809e-06,
|
| 478 |
+
"loss": 0.0169,
|
| 479 |
+
"step": 64000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.05,
|
| 483 |
+
"eval_loss": 0.03290534391999245,
|
| 484 |
+
"eval_runtime": 2313.6442,
|
| 485 |
+
"eval_samples_per_second": 2.79,
|
| 486 |
+
"eval_steps_per_second": 0.175,
|
| 487 |
+
"eval_wer": 31.96095635007677,
|
| 488 |
+
"step": 64000
|
| 489 |
+
}
|
| 490 |
+
],
|
| 491 |
+
"max_steps": 237270,
|
| 492 |
+
"num_train_epochs": 15,
|
| 493 |
+
"total_flos": 2.6127077390548992e+20,
|
| 494 |
+
"trial_name": null,
|
| 495 |
+
"trial_params": null
|
| 496 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65afc654b2b4016b72f7814fad9feb6c388bfa0a3c726489f8b902c085e5374
|
| 3 |
+
size 3695
|