Upload folder using huggingface_hub
Browse files- config.json +61 -0
- generation_config.json +248 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +14 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +505 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": null,
|
| 11 |
+
"bos_token_id": 50257,
|
| 12 |
+
"classifier_proj_size": 256,
|
| 13 |
+
"d_model": 1024,
|
| 14 |
+
"decoder_attention_heads": 16,
|
| 15 |
+
"decoder_ffn_dim": 4096,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 24,
|
| 18 |
+
"decoder_start_token_id": 50258,
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"encoder_attention_heads": 16,
|
| 21 |
+
"encoder_ffn_dim": 4096,
|
| 22 |
+
"encoder_layerdrop": 0.0,
|
| 23 |
+
"encoder_layers": 24,
|
| 24 |
+
"eos_token_id": 50257,
|
| 25 |
+
"forced_decoder_ids": [
|
| 26 |
+
[
|
| 27 |
+
1,
|
| 28 |
+
50269
|
| 29 |
+
],
|
| 30 |
+
[
|
| 31 |
+
2,
|
| 32 |
+
50359
|
| 33 |
+
],
|
| 34 |
+
[
|
| 35 |
+
3,
|
| 36 |
+
50363
|
| 37 |
+
]
|
| 38 |
+
],
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"mask_feature_length": 10,
|
| 42 |
+
"mask_feature_min_masks": 0,
|
| 43 |
+
"mask_feature_prob": 0.0,
|
| 44 |
+
"mask_time_length": 10,
|
| 45 |
+
"mask_time_min_masks": 2,
|
| 46 |
+
"mask_time_prob": 0.05,
|
| 47 |
+
"max_length": null,
|
| 48 |
+
"max_source_positions": 1500,
|
| 49 |
+
"max_target_positions": 448,
|
| 50 |
+
"median_filter_width": 7,
|
| 51 |
+
"model_type": "whisper",
|
| 52 |
+
"num_hidden_layers": 24,
|
| 53 |
+
"num_mel_bins": 80,
|
| 54 |
+
"pad_token_id": 50257,
|
| 55 |
+
"scale_embedding": false,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.45.2",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_weighted_layer_sum": false,
|
| 60 |
+
"vocab_size": 51865
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"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 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 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 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [
|
| 154 |
+
1,
|
| 155 |
+
2,
|
| 156 |
+
7,
|
| 157 |
+
8,
|
| 158 |
+
9,
|
| 159 |
+
10,
|
| 160 |
+
14,
|
| 161 |
+
25,
|
| 162 |
+
26,
|
| 163 |
+
27,
|
| 164 |
+
28,
|
| 165 |
+
29,
|
| 166 |
+
31,
|
| 167 |
+
58,
|
| 168 |
+
59,
|
| 169 |
+
60,
|
| 170 |
+
61,
|
| 171 |
+
62,
|
| 172 |
+
63,
|
| 173 |
+
90,
|
| 174 |
+
91,
|
| 175 |
+
92,
|
| 176 |
+
93,
|
| 177 |
+
359,
|
| 178 |
+
503,
|
| 179 |
+
522,
|
| 180 |
+
542,
|
| 181 |
+
873,
|
| 182 |
+
893,
|
| 183 |
+
902,
|
| 184 |
+
918,
|
| 185 |
+
922,
|
| 186 |
+
931,
|
| 187 |
+
1350,
|
| 188 |
+
1853,
|
| 189 |
+
1982,
|
| 190 |
+
2460,
|
| 191 |
+
2627,
|
| 192 |
+
3246,
|
| 193 |
+
3253,
|
| 194 |
+
3268,
|
| 195 |
+
3536,
|
| 196 |
+
3846,
|
| 197 |
+
3961,
|
| 198 |
+
4183,
|
| 199 |
+
4667,
|
| 200 |
+
6585,
|
| 201 |
+
6647,
|
| 202 |
+
7273,
|
| 203 |
+
9061,
|
| 204 |
+
9383,
|
| 205 |
+
10428,
|
| 206 |
+
10929,
|
| 207 |
+
11938,
|
| 208 |
+
12033,
|
| 209 |
+
12331,
|
| 210 |
+
12562,
|
| 211 |
+
13793,
|
| 212 |
+
14157,
|
| 213 |
+
14635,
|
| 214 |
+
15265,
|
| 215 |
+
15618,
|
| 216 |
+
16553,
|
| 217 |
+
16604,
|
| 218 |
+
18362,
|
| 219 |
+
18956,
|
| 220 |
+
20075,
|
| 221 |
+
21675,
|
| 222 |
+
22520,
|
| 223 |
+
26130,
|
| 224 |
+
26161,
|
| 225 |
+
26435,
|
| 226 |
+
28279,
|
| 227 |
+
29464,
|
| 228 |
+
31650,
|
| 229 |
+
32302,
|
| 230 |
+
32470,
|
| 231 |
+
36865,
|
| 232 |
+
42863,
|
| 233 |
+
47425,
|
| 234 |
+
49870,
|
| 235 |
+
50254,
|
| 236 |
+
50258,
|
| 237 |
+
50358,
|
| 238 |
+
50359,
|
| 239 |
+
50360,
|
| 240 |
+
50361,
|
| 241 |
+
50362
|
| 242 |
+
],
|
| 243 |
+
"task_to_id": {
|
| 244 |
+
"transcribe": 50359,
|
| 245 |
+
"translate": 50358
|
| 246 |
+
},
|
| 247 |
+
"transformers_version": "4.45.2"
|
| 248 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dddbec4e23fd304a856cabd5fd404a83334104d5e82f86520e78dfce51396468
|
| 3 |
+
size 3055544304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a417e901fc111123acf5d0bb0897cd0a465cda5f35d9e5af998d7fb61bf698dc
|
| 3 |
+
size 6099368783
|
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 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb9797f2a717da7201b345659d92175ed5a003888546563c3c9c54c29ae40372
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ade1c95f4829471f6f08ab8a27d7b178b8054745ff76da84224ce6a8b782a962
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15666962437148774,
|
| 3 |
+
"best_model_checkpoint": "results15/checkpoint-3000",
|
| 4 |
+
"epoch": 0.256,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0064,
|
| 13 |
+
"grad_norm": 4.8001484870910645,
|
| 14 |
+
"learning_rate": 1.9200000000000003e-06,
|
| 15 |
+
"loss": 1.3393,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0128,
|
| 20 |
+
"grad_norm": 3.706824779510498,
|
| 21 |
+
"learning_rate": 3.920000000000001e-06,
|
| 22 |
+
"loss": 0.5176,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0192,
|
| 27 |
+
"grad_norm": 3.8430540561676025,
|
| 28 |
+
"learning_rate": 5.92e-06,
|
| 29 |
+
"loss": 0.2587,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0256,
|
| 34 |
+
"grad_norm": 3.9047493934631348,
|
| 35 |
+
"learning_rate": 7.92e-06,
|
| 36 |
+
"loss": 0.2493,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.032,
|
| 41 |
+
"grad_norm": 3.7892723083496094,
|
| 42 |
+
"learning_rate": 9.920000000000002e-06,
|
| 43 |
+
"loss": 0.2446,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.032,
|
| 48 |
+
"eval_test1_cer": 0.1596436118028828,
|
| 49 |
+
"eval_test1_cer_norm": 0.14118874332848133,
|
| 50 |
+
"eval_test1_loss": 0.22201526165008545,
|
| 51 |
+
"eval_test1_runtime": 1157.1217,
|
| 52 |
+
"eval_test1_samples_per_second": 2.161,
|
| 53 |
+
"eval_test1_steps_per_second": 0.068,
|
| 54 |
+
"eval_test1_wer": 0.3501922508133688,
|
| 55 |
+
"eval_test1_wer_norm": 0.27503187357310166,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.032,
|
| 60 |
+
"eval_test2_cer": 0.34475821649329114,
|
| 61 |
+
"eval_test2_cer_norm": 0.32302360141569386,
|
| 62 |
+
"eval_test2_loss": 0.3860654830932617,
|
| 63 |
+
"eval_test2_runtime": 1327.3073,
|
| 64 |
+
"eval_test2_samples_per_second": 1.884,
|
| 65 |
+
"eval_test2_steps_per_second": 0.06,
|
| 66 |
+
"eval_test2_wer": 0.5888413010765134,
|
| 67 |
+
"eval_test2_wer_norm": 0.5090455757856894,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.0384,
|
| 72 |
+
"grad_norm": 4.102191925048828,
|
| 73 |
+
"learning_rate": 9.936528925619836e-06,
|
| 74 |
+
"loss": 0.2387,
|
| 75 |
+
"step": 600
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.0448,
|
| 79 |
+
"grad_norm": 3.395754337310791,
|
| 80 |
+
"learning_rate": 9.870413223140496e-06,
|
| 81 |
+
"loss": 0.2333,
|
| 82 |
+
"step": 700
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0512,
|
| 86 |
+
"grad_norm": 3.3210232257843018,
|
| 87 |
+
"learning_rate": 9.804297520661158e-06,
|
| 88 |
+
"loss": 0.2296,
|
| 89 |
+
"step": 800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.0576,
|
| 93 |
+
"grad_norm": 3.533163070678711,
|
| 94 |
+
"learning_rate": 9.738181818181818e-06,
|
| 95 |
+
"loss": 0.2235,
|
| 96 |
+
"step": 900
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.064,
|
| 100 |
+
"grad_norm": 3.154200315475464,
|
| 101 |
+
"learning_rate": 9.67206611570248e-06,
|
| 102 |
+
"loss": 0.2268,
|
| 103 |
+
"step": 1000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.064,
|
| 107 |
+
"eval_test1_cer": 0.06988151837597162,
|
| 108 |
+
"eval_test1_cer_norm": 0.05281416787967006,
|
| 109 |
+
"eval_test1_loss": 0.2057729810476303,
|
| 110 |
+
"eval_test1_runtime": 1040.3745,
|
| 111 |
+
"eval_test1_samples_per_second": 2.403,
|
| 112 |
+
"eval_test1_steps_per_second": 0.076,
|
| 113 |
+
"eval_test1_wer": 0.20041407867494823,
|
| 114 |
+
"eval_test1_wer_norm": 0.1341062057105583,
|
| 115 |
+
"step": 1000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.064,
|
| 119 |
+
"eval_test2_cer": 0.17753561736770693,
|
| 120 |
+
"eval_test2_cer_norm": 0.1456756809604818,
|
| 121 |
+
"eval_test2_loss": 0.35842248797416687,
|
| 122 |
+
"eval_test2_runtime": 1152.2398,
|
| 123 |
+
"eval_test2_samples_per_second": 2.17,
|
| 124 |
+
"eval_test2_steps_per_second": 0.069,
|
| 125 |
+
"eval_test2_wer": 0.36184743604583863,
|
| 126 |
+
"eval_test2_wer_norm": 0.28771889133712164,
|
| 127 |
+
"step": 1000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.0704,
|
| 131 |
+
"grad_norm": 4.132891654968262,
|
| 132 |
+
"learning_rate": 9.605950413223142e-06,
|
| 133 |
+
"loss": 0.2234,
|
| 134 |
+
"step": 1100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.0768,
|
| 138 |
+
"grad_norm": 3.4513018131256104,
|
| 139 |
+
"learning_rate": 9.539834710743802e-06,
|
| 140 |
+
"loss": 0.2218,
|
| 141 |
+
"step": 1200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.0832,
|
| 145 |
+
"grad_norm": 3.2677953243255615,
|
| 146 |
+
"learning_rate": 9.473719008264464e-06,
|
| 147 |
+
"loss": 0.2178,
|
| 148 |
+
"step": 1300
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.0896,
|
| 152 |
+
"grad_norm": 2.8952624797821045,
|
| 153 |
+
"learning_rate": 9.407603305785124e-06,
|
| 154 |
+
"loss": 0.2161,
|
| 155 |
+
"step": 1400
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.096,
|
| 159 |
+
"grad_norm": 3.3220458030700684,
|
| 160 |
+
"learning_rate": 9.341487603305786e-06,
|
| 161 |
+
"loss": 0.209,
|
| 162 |
+
"step": 1500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.096,
|
| 166 |
+
"eval_test1_cer": 0.061481208965361106,
|
| 167 |
+
"eval_test1_cer_norm": 0.04084910237748666,
|
| 168 |
+
"eval_test1_loss": 0.19823798537254333,
|
| 169 |
+
"eval_test1_runtime": 1030.8083,
|
| 170 |
+
"eval_test1_samples_per_second": 2.425,
|
| 171 |
+
"eval_test1_steps_per_second": 0.077,
|
| 172 |
+
"eval_test1_wer": 0.1774622892635315,
|
| 173 |
+
"eval_test1_wer_norm": 0.11234322649509296,
|
| 174 |
+
"step": 1500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.096,
|
| 178 |
+
"eval_test2_cer": 0.11561981757877281,
|
| 179 |
+
"eval_test2_cer_norm": 0.09326176648872725,
|
| 180 |
+
"eval_test2_loss": 0.34961584210395813,
|
| 181 |
+
"eval_test2_runtime": 1044.2589,
|
| 182 |
+
"eval_test2_samples_per_second": 2.394,
|
| 183 |
+
"eval_test2_steps_per_second": 0.076,
|
| 184 |
+
"eval_test2_wer": 0.25847899062391483,
|
| 185 |
+
"eval_test2_wer_norm": 0.18728980633190306,
|
| 186 |
+
"step": 1500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.1024,
|
| 190 |
+
"grad_norm": 3.133871555328369,
|
| 191 |
+
"learning_rate": 9.275371900826448e-06,
|
| 192 |
+
"loss": 0.2173,
|
| 193 |
+
"step": 1600
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.1088,
|
| 197 |
+
"grad_norm": 3.023627758026123,
|
| 198 |
+
"learning_rate": 9.209917355371902e-06,
|
| 199 |
+
"loss": 0.2098,
|
| 200 |
+
"step": 1700
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.1152,
|
| 204 |
+
"grad_norm": 3.384046792984009,
|
| 205 |
+
"learning_rate": 9.143801652892564e-06,
|
| 206 |
+
"loss": 0.2085,
|
| 207 |
+
"step": 1800
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.1216,
|
| 211 |
+
"grad_norm": 4.177057266235352,
|
| 212 |
+
"learning_rate": 9.077685950413224e-06,
|
| 213 |
+
"loss": 0.2057,
|
| 214 |
+
"step": 1900
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.128,
|
| 218 |
+
"grad_norm": 3.657303810119629,
|
| 219 |
+
"learning_rate": 9.011570247933886e-06,
|
| 220 |
+
"loss": 0.2073,
|
| 221 |
+
"step": 2000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.128,
|
| 225 |
+
"eval_test1_cer": 0.06908912534903026,
|
| 226 |
+
"eval_test1_cer_norm": 0.04828723920426977,
|
| 227 |
+
"eval_test1_loss": 0.18983058631420135,
|
| 228 |
+
"eval_test1_runtime": 1097.0314,
|
| 229 |
+
"eval_test1_samples_per_second": 2.279,
|
| 230 |
+
"eval_test1_steps_per_second": 0.072,
|
| 231 |
+
"eval_test1_wer": 0.1898846495119787,
|
| 232 |
+
"eval_test1_wer_norm": 0.128057639280102,
|
| 233 |
+
"step": 2000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.128,
|
| 237 |
+
"eval_test2_cer": 0.1378665385195236,
|
| 238 |
+
"eval_test2_cer_norm": 0.1097016092763145,
|
| 239 |
+
"eval_test2_loss": 0.33988869190216064,
|
| 240 |
+
"eval_test2_runtime": 1142.2555,
|
| 241 |
+
"eval_test2_samples_per_second": 2.189,
|
| 242 |
+
"eval_test2_steps_per_second": 0.069,
|
| 243 |
+
"eval_test2_wer": 0.2811957402477139,
|
| 244 |
+
"eval_test2_wer_norm": 0.21402064246781863,
|
| 245 |
+
"step": 2000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.1344,
|
| 249 |
+
"grad_norm": 2.9096293449401855,
|
| 250 |
+
"learning_rate": 8.945454545454546e-06,
|
| 251 |
+
"loss": 0.208,
|
| 252 |
+
"step": 2100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.1408,
|
| 256 |
+
"grad_norm": 3.0557897090911865,
|
| 257 |
+
"learning_rate": 8.879338842975208e-06,
|
| 258 |
+
"loss": 0.2146,
|
| 259 |
+
"step": 2200
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.1472,
|
| 263 |
+
"grad_norm": 3.3298580646514893,
|
| 264 |
+
"learning_rate": 8.81322314049587e-06,
|
| 265 |
+
"loss": 0.2035,
|
| 266 |
+
"step": 2300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.1536,
|
| 270 |
+
"grad_norm": 2.332103729248047,
|
| 271 |
+
"learning_rate": 8.74710743801653e-06,
|
| 272 |
+
"loss": 0.196,
|
| 273 |
+
"step": 2400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.16,
|
| 277 |
+
"grad_norm": 2.920443534851074,
|
| 278 |
+
"learning_rate": 8.680991735537191e-06,
|
| 279 |
+
"loss": 0.1982,
|
| 280 |
+
"step": 2500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.16,
|
| 284 |
+
"eval_test1_cer": 0.06446211606671194,
|
| 285 |
+
"eval_test1_cer_norm": 0.04428918000970403,
|
| 286 |
+
"eval_test1_loss": 0.18459410965442657,
|
| 287 |
+
"eval_test1_runtime": 1086.8024,
|
| 288 |
+
"eval_test1_samples_per_second": 2.3,
|
| 289 |
+
"eval_test1_steps_per_second": 0.073,
|
| 290 |
+
"eval_test1_wer": 0.17775805974563738,
|
| 291 |
+
"eval_test1_wer_norm": 0.11643490378628399,
|
| 292 |
+
"step": 2500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.16,
|
| 296 |
+
"eval_test2_cer": 0.11876224935926429,
|
| 297 |
+
"eval_test2_cer_norm": 0.09257249564928335,
|
| 298 |
+
"eval_test2_loss": 0.33487755060195923,
|
| 299 |
+
"eval_test2_runtime": 1110.7242,
|
| 300 |
+
"eval_test2_samples_per_second": 2.251,
|
| 301 |
+
"eval_test2_steps_per_second": 0.071,
|
| 302 |
+
"eval_test2_wer": 0.2543986572519968,
|
| 303 |
+
"eval_test2_wer_norm": 0.1844195755537516,
|
| 304 |
+
"step": 2500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1664,
|
| 308 |
+
"grad_norm": 2.761300802230835,
|
| 309 |
+
"learning_rate": 8.614876033057852e-06,
|
| 310 |
+
"loss": 0.1969,
|
| 311 |
+
"step": 2600
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.1728,
|
| 315 |
+
"grad_norm": 2.2639405727386475,
|
| 316 |
+
"learning_rate": 8.548760330578513e-06,
|
| 317 |
+
"loss": 0.2011,
|
| 318 |
+
"step": 2700
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1792,
|
| 322 |
+
"grad_norm": 2.7103681564331055,
|
| 323 |
+
"learning_rate": 8.482644628099175e-06,
|
| 324 |
+
"loss": 0.1911,
|
| 325 |
+
"step": 2800
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1856,
|
| 329 |
+
"grad_norm": 3.4355201721191406,
|
| 330 |
+
"learning_rate": 8.416528925619835e-06,
|
| 331 |
+
"loss": 0.1915,
|
| 332 |
+
"step": 2900
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.192,
|
| 336 |
+
"grad_norm": 2.784461259841919,
|
| 337 |
+
"learning_rate": 8.350413223140497e-06,
|
| 338 |
+
"loss": 0.1962,
|
| 339 |
+
"step": 3000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.192,
|
| 343 |
+
"eval_test1_cer": 0.052505471285186026,
|
| 344 |
+
"eval_test1_cer_norm": 0.03515769044153324,
|
| 345 |
+
"eval_test1_loss": 0.17998091876506805,
|
| 346 |
+
"eval_test1_runtime": 1020.463,
|
| 347 |
+
"eval_test1_samples_per_second": 2.45,
|
| 348 |
+
"eval_test1_steps_per_second": 0.077,
|
| 349 |
+
"eval_test1_wer": 0.15666962437148774,
|
| 350 |
+
"eval_test1_wer_norm": 0.09473122424170546,
|
| 351 |
+
"step": 3000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.192,
|
| 355 |
+
"eval_test2_cer": 0.11729232624755012,
|
| 356 |
+
"eval_test2_cer_norm": 0.09097886236092372,
|
| 357 |
+
"eval_test2_loss": 0.3286541700363159,
|
| 358 |
+
"eval_test2_runtime": 1052.1877,
|
| 359 |
+
"eval_test2_samples_per_second": 2.376,
|
| 360 |
+
"eval_test2_steps_per_second": 0.075,
|
| 361 |
+
"eval_test2_wer": 0.2477427943048964,
|
| 362 |
+
"eval_test2_wer_norm": 0.17702655688275543,
|
| 363 |
+
"step": 3000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.1984,
|
| 367 |
+
"grad_norm": 2.9920506477355957,
|
| 368 |
+
"learning_rate": 8.284297520661157e-06,
|
| 369 |
+
"loss": 0.1916,
|
| 370 |
+
"step": 3100
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.2048,
|
| 374 |
+
"grad_norm": 2.529097318649292,
|
| 375 |
+
"learning_rate": 8.21818181818182e-06,
|
| 376 |
+
"loss": 0.1909,
|
| 377 |
+
"step": 3200
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.2112,
|
| 381 |
+
"grad_norm": 2.646070718765259,
|
| 382 |
+
"learning_rate": 8.152066115702481e-06,
|
| 383 |
+
"loss": 0.1904,
|
| 384 |
+
"step": 3300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.2176,
|
| 388 |
+
"grad_norm": 3.047825336456299,
|
| 389 |
+
"learning_rate": 8.085950413223141e-06,
|
| 390 |
+
"loss": 0.1935,
|
| 391 |
+
"step": 3400
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.224,
|
| 395 |
+
"grad_norm": 2.928596258163452,
|
| 396 |
+
"learning_rate": 8.019834710743803e-06,
|
| 397 |
+
"loss": 0.1943,
|
| 398 |
+
"step": 3500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.224,
|
| 402 |
+
"eval_test1_cer": 0.06426873443513698,
|
| 403 |
+
"eval_test1_cer_norm": 0.041746724890829694,
|
| 404 |
+
"eval_test1_loss": 0.17650315165519714,
|
| 405 |
+
"eval_test1_runtime": 1003.7308,
|
| 406 |
+
"eval_test1_samples_per_second": 2.491,
|
| 407 |
+
"eval_test1_steps_per_second": 0.079,
|
| 408 |
+
"eval_test1_wer": 0.17329192546583852,
|
| 409 |
+
"eval_test1_wer_norm": 0.10694695644439173,
|
| 410 |
+
"step": 3500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.224,
|
| 414 |
+
"eval_test2_cer": 0.13343792401628224,
|
| 415 |
+
"eval_test2_cer_norm": 0.09719207680725836,
|
| 416 |
+
"eval_test2_loss": 0.32644087076187134,
|
| 417 |
+
"eval_test2_runtime": 1081.9218,
|
| 418 |
+
"eval_test2_samples_per_second": 2.311,
|
| 419 |
+
"eval_test2_steps_per_second": 0.073,
|
| 420 |
+
"eval_test2_wer": 0.26533742331288346,
|
| 421 |
+
"eval_test2_wer_norm": 0.1966542966484982,
|
| 422 |
+
"step": 3500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2304,
|
| 426 |
+
"grad_norm": 2.7711305618286133,
|
| 427 |
+
"learning_rate": 7.953719008264463e-06,
|
| 428 |
+
"loss": 0.196,
|
| 429 |
+
"step": 3600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2368,
|
| 433 |
+
"grad_norm": 2.9088964462280273,
|
| 434 |
+
"learning_rate": 7.888264462809919e-06,
|
| 435 |
+
"loss": 0.1899,
|
| 436 |
+
"step": 3700
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2432,
|
| 440 |
+
"grad_norm": 2.884896993637085,
|
| 441 |
+
"learning_rate": 7.822148760330579e-06,
|
| 442 |
+
"loss": 0.1938,
|
| 443 |
+
"step": 3800
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2496,
|
| 447 |
+
"grad_norm": 2.511730432510376,
|
| 448 |
+
"learning_rate": 7.75603305785124e-06,
|
| 449 |
+
"loss": 0.1872,
|
| 450 |
+
"step": 3900
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.256,
|
| 454 |
+
"grad_norm": 2.930680990219116,
|
| 455 |
+
"learning_rate": 7.689917355371903e-06,
|
| 456 |
+
"loss": 0.1894,
|
| 457 |
+
"step": 4000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.256,
|
| 461 |
+
"eval_test1_cer": 0.071758735189797,
|
| 462 |
+
"eval_test1_cer_norm": 0.047394468704512374,
|
| 463 |
+
"eval_test1_loss": 0.1755101978778839,
|
| 464 |
+
"eval_test1_runtime": 1295.9749,
|
| 465 |
+
"eval_test1_samples_per_second": 1.929,
|
| 466 |
+
"eval_test1_steps_per_second": 0.061,
|
| 467 |
+
"eval_test1_wer": 0.18352558414670217,
|
| 468 |
+
"eval_test1_wer_norm": 0.12132712663444718,
|
| 469 |
+
"step": 4000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.256,
|
| 473 |
+
"eval_test2_cer": 0.13147802653399668,
|
| 474 |
+
"eval_test2_cer_norm": 0.10113216401712911,
|
| 475 |
+
"eval_test2_loss": 0.32261422276496887,
|
| 476 |
+
"eval_test2_runtime": 1380.4258,
|
| 477 |
+
"eval_test2_samples_per_second": 1.811,
|
| 478 |
+
"eval_test2_steps_per_second": 0.057,
|
| 479 |
+
"eval_test2_wer": 0.2693888181502489,
|
| 480 |
+
"eval_test2_wer_norm": 0.19903165951524993,
|
| 481 |
+
"step": 4000
|
| 482 |
+
}
|
| 483 |
+
],
|
| 484 |
+
"logging_steps": 100,
|
| 485 |
+
"max_steps": 15625,
|
| 486 |
+
"num_input_tokens_seen": 0,
|
| 487 |
+
"num_train_epochs": 9223372036854775807,
|
| 488 |
+
"save_steps": 500,
|
| 489 |
+
"stateful_callbacks": {
|
| 490 |
+
"TrainerControl": {
|
| 491 |
+
"args": {
|
| 492 |
+
"should_epoch_stop": false,
|
| 493 |
+
"should_evaluate": false,
|
| 494 |
+
"should_log": false,
|
| 495 |
+
"should_save": true,
|
| 496 |
+
"should_training_stop": false
|
| 497 |
+
},
|
| 498 |
+
"attributes": {}
|
| 499 |
+
}
|
| 500 |
+
},
|
| 501 |
+
"total_flos": 1.3063742816256e+20,
|
| 502 |
+
"train_batch_size": 32,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11c5247ce7036864a2b251a751a9841aee3e1371b95e5607defbd0d3804d9892
|
| 3 |
+
size 4911
|