Upload 5 files
Browse files- config.json +152 -0
- generation_config.json +256 -0
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
- trainer_state.json +611 -0
config.json
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 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": 768,
|
| 17 |
+
"decoder_attention_heads": 12,
|
| 18 |
+
"decoder_ffn_dim": 3072,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 12,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 12,
|
| 24 |
+
"encoder_ffn_dim": 3072,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": [
|
| 29 |
+
[
|
| 30 |
+
1,
|
| 31 |
+
50259
|
| 32 |
+
],
|
| 33 |
+
[
|
| 34 |
+
2,
|
| 35 |
+
50359
|
| 36 |
+
],
|
| 37 |
+
[
|
| 38 |
+
3,
|
| 39 |
+
50363
|
| 40 |
+
]
|
| 41 |
+
],
|
| 42 |
+
"init_std": 0.02,
|
| 43 |
+
"is_encoder_decoder": true,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.0,
|
| 47 |
+
"mask_time_length": 10,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.05,
|
| 50 |
+
"max_length": 448,
|
| 51 |
+
"max_source_positions": 1500,
|
| 52 |
+
"max_target_positions": 448,
|
| 53 |
+
"median_filter_width": 7,
|
| 54 |
+
"model_type": "whisper",
|
| 55 |
+
"num_hidden_layers": 12,
|
| 56 |
+
"num_mel_bins": 80,
|
| 57 |
+
"pad_token_id": 50257,
|
| 58 |
+
"scale_embedding": false,
|
| 59 |
+
"suppress_tokens": [
|
| 60 |
+
1,
|
| 61 |
+
2,
|
| 62 |
+
7,
|
| 63 |
+
8,
|
| 64 |
+
9,
|
| 65 |
+
10,
|
| 66 |
+
14,
|
| 67 |
+
25,
|
| 68 |
+
26,
|
| 69 |
+
27,
|
| 70 |
+
28,
|
| 71 |
+
29,
|
| 72 |
+
31,
|
| 73 |
+
58,
|
| 74 |
+
59,
|
| 75 |
+
60,
|
| 76 |
+
61,
|
| 77 |
+
62,
|
| 78 |
+
63,
|
| 79 |
+
90,
|
| 80 |
+
91,
|
| 81 |
+
92,
|
| 82 |
+
93,
|
| 83 |
+
359,
|
| 84 |
+
503,
|
| 85 |
+
522,
|
| 86 |
+
542,
|
| 87 |
+
873,
|
| 88 |
+
893,
|
| 89 |
+
902,
|
| 90 |
+
918,
|
| 91 |
+
922,
|
| 92 |
+
931,
|
| 93 |
+
1350,
|
| 94 |
+
1853,
|
| 95 |
+
1982,
|
| 96 |
+
2460,
|
| 97 |
+
2627,
|
| 98 |
+
3246,
|
| 99 |
+
3253,
|
| 100 |
+
3268,
|
| 101 |
+
3536,
|
| 102 |
+
3846,
|
| 103 |
+
3961,
|
| 104 |
+
4183,
|
| 105 |
+
4667,
|
| 106 |
+
6585,
|
| 107 |
+
6647,
|
| 108 |
+
7273,
|
| 109 |
+
9061,
|
| 110 |
+
9383,
|
| 111 |
+
10428,
|
| 112 |
+
10929,
|
| 113 |
+
11938,
|
| 114 |
+
12033,
|
| 115 |
+
12331,
|
| 116 |
+
12562,
|
| 117 |
+
13793,
|
| 118 |
+
14157,
|
| 119 |
+
14635,
|
| 120 |
+
15265,
|
| 121 |
+
15618,
|
| 122 |
+
16553,
|
| 123 |
+
16604,
|
| 124 |
+
18362,
|
| 125 |
+
18956,
|
| 126 |
+
20075,
|
| 127 |
+
21675,
|
| 128 |
+
22520,
|
| 129 |
+
26130,
|
| 130 |
+
26161,
|
| 131 |
+
26435,
|
| 132 |
+
28279,
|
| 133 |
+
29464,
|
| 134 |
+
31650,
|
| 135 |
+
32302,
|
| 136 |
+
32470,
|
| 137 |
+
36865,
|
| 138 |
+
42863,
|
| 139 |
+
47425,
|
| 140 |
+
49870,
|
| 141 |
+
50254,
|
| 142 |
+
50258,
|
| 143 |
+
50360,
|
| 144 |
+
50361,
|
| 145 |
+
50362
|
| 146 |
+
],
|
| 147 |
+
"torch_dtype": "float32",
|
| 148 |
+
"transformers_version": "4.42.4",
|
| 149 |
+
"use_cache": true,
|
| 150 |
+
"use_weighted_layer_sum": false,
|
| 151 |
+
"vocab_size": 51865
|
| 152 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"begin_suppress_tokens": [
|
| 45 |
+
220,
|
| 46 |
+
50257
|
| 47 |
+
],
|
| 48 |
+
"bos_token_id": 50257,
|
| 49 |
+
"decoder_start_token_id": 50258,
|
| 50 |
+
"eos_token_id": 50257,
|
| 51 |
+
"is_multilingual": true,
|
| 52 |
+
"lang_to_id": {
|
| 53 |
+
"<|af|>": 50327,
|
| 54 |
+
"<|am|>": 50334,
|
| 55 |
+
"<|ar|>": 50272,
|
| 56 |
+
"<|as|>": 50350,
|
| 57 |
+
"<|az|>": 50304,
|
| 58 |
+
"<|ba|>": 50355,
|
| 59 |
+
"<|be|>": 50330,
|
| 60 |
+
"<|bg|>": 50292,
|
| 61 |
+
"<|bn|>": 50302,
|
| 62 |
+
"<|bo|>": 50347,
|
| 63 |
+
"<|br|>": 50309,
|
| 64 |
+
"<|bs|>": 50315,
|
| 65 |
+
"<|ca|>": 50270,
|
| 66 |
+
"<|cs|>": 50283,
|
| 67 |
+
"<|cy|>": 50297,
|
| 68 |
+
"<|da|>": 50285,
|
| 69 |
+
"<|de|>": 50261,
|
| 70 |
+
"<|el|>": 50281,
|
| 71 |
+
"<|en|>": 50259,
|
| 72 |
+
"<|es|>": 50262,
|
| 73 |
+
"<|et|>": 50307,
|
| 74 |
+
"<|eu|>": 50310,
|
| 75 |
+
"<|fa|>": 50300,
|
| 76 |
+
"<|fi|>": 50277,
|
| 77 |
+
"<|fo|>": 50338,
|
| 78 |
+
"<|fr|>": 50265,
|
| 79 |
+
"<|gl|>": 50319,
|
| 80 |
+
"<|gu|>": 50333,
|
| 81 |
+
"<|haw|>": 50352,
|
| 82 |
+
"<|ha|>": 50354,
|
| 83 |
+
"<|he|>": 50279,
|
| 84 |
+
"<|hi|>": 50276,
|
| 85 |
+
"<|hr|>": 50291,
|
| 86 |
+
"<|ht|>": 50339,
|
| 87 |
+
"<|hu|>": 50286,
|
| 88 |
+
"<|hy|>": 50312,
|
| 89 |
+
"<|id|>": 50275,
|
| 90 |
+
"<|is|>": 50311,
|
| 91 |
+
"<|it|>": 50274,
|
| 92 |
+
"<|ja|>": 50266,
|
| 93 |
+
"<|jw|>": 50356,
|
| 94 |
+
"<|ka|>": 50329,
|
| 95 |
+
"<|kk|>": 50316,
|
| 96 |
+
"<|km|>": 50323,
|
| 97 |
+
"<|kn|>": 50306,
|
| 98 |
+
"<|ko|>": 50264,
|
| 99 |
+
"<|la|>": 50294,
|
| 100 |
+
"<|lb|>": 50345,
|
| 101 |
+
"<|ln|>": 50353,
|
| 102 |
+
"<|lo|>": 50336,
|
| 103 |
+
"<|lt|>": 50293,
|
| 104 |
+
"<|lv|>": 50301,
|
| 105 |
+
"<|mg|>": 50349,
|
| 106 |
+
"<|mi|>": 50295,
|
| 107 |
+
"<|mk|>": 50308,
|
| 108 |
+
"<|ml|>": 50296,
|
| 109 |
+
"<|mn|>": 50314,
|
| 110 |
+
"<|mr|>": 50320,
|
| 111 |
+
"<|ms|>": 50282,
|
| 112 |
+
"<|mt|>": 50343,
|
| 113 |
+
"<|my|>": 50346,
|
| 114 |
+
"<|ne|>": 50313,
|
| 115 |
+
"<|nl|>": 50271,
|
| 116 |
+
"<|nn|>": 50342,
|
| 117 |
+
"<|no|>": 50288,
|
| 118 |
+
"<|oc|>": 50328,
|
| 119 |
+
"<|pa|>": 50321,
|
| 120 |
+
"<|pl|>": 50269,
|
| 121 |
+
"<|ps|>": 50340,
|
| 122 |
+
"<|pt|>": 50267,
|
| 123 |
+
"<|ro|>": 50284,
|
| 124 |
+
"<|ru|>": 50263,
|
| 125 |
+
"<|sa|>": 50344,
|
| 126 |
+
"<|sd|>": 50332,
|
| 127 |
+
"<|si|>": 50322,
|
| 128 |
+
"<|sk|>": 50298,
|
| 129 |
+
"<|sl|>": 50305,
|
| 130 |
+
"<|sn|>": 50324,
|
| 131 |
+
"<|so|>": 50326,
|
| 132 |
+
"<|sq|>": 50317,
|
| 133 |
+
"<|sr|>": 50303,
|
| 134 |
+
"<|su|>": 50357,
|
| 135 |
+
"<|sv|>": 50273,
|
| 136 |
+
"<|sw|>": 50318,
|
| 137 |
+
"<|ta|>": 50287,
|
| 138 |
+
"<|te|>": 50299,
|
| 139 |
+
"<|tg|>": 50331,
|
| 140 |
+
"<|th|>": 50289,
|
| 141 |
+
"<|tk|>": 50341,
|
| 142 |
+
"<|tl|>": 50348,
|
| 143 |
+
"<|tr|>": 50268,
|
| 144 |
+
"<|tt|>": 50351,
|
| 145 |
+
"<|uk|>": 50280,
|
| 146 |
+
"<|ur|>": 50290,
|
| 147 |
+
"<|uz|>": 50337,
|
| 148 |
+
"<|vi|>": 50278,
|
| 149 |
+
"<|yi|>": 50335,
|
| 150 |
+
"<|yo|>": 50325,
|
| 151 |
+
"<|zh|>": 50260
|
| 152 |
+
},
|
| 153 |
+
"language": "polish",
|
| 154 |
+
"max_initial_timestamp_index": 50,
|
| 155 |
+
"max_length": 448,
|
| 156 |
+
"no_timestamps_token_id": 50363,
|
| 157 |
+
"pad_token_id": 50257,
|
| 158 |
+
"prev_sot_token_id": 50361,
|
| 159 |
+
"return_timestamps": false,
|
| 160 |
+
"suppress_tokens": [
|
| 161 |
+
1,
|
| 162 |
+
2,
|
| 163 |
+
7,
|
| 164 |
+
8,
|
| 165 |
+
9,
|
| 166 |
+
10,
|
| 167 |
+
14,
|
| 168 |
+
25,
|
| 169 |
+
26,
|
| 170 |
+
27,
|
| 171 |
+
28,
|
| 172 |
+
29,
|
| 173 |
+
31,
|
| 174 |
+
58,
|
| 175 |
+
59,
|
| 176 |
+
60,
|
| 177 |
+
61,
|
| 178 |
+
62,
|
| 179 |
+
63,
|
| 180 |
+
90,
|
| 181 |
+
91,
|
| 182 |
+
92,
|
| 183 |
+
93,
|
| 184 |
+
359,
|
| 185 |
+
503,
|
| 186 |
+
522,
|
| 187 |
+
542,
|
| 188 |
+
873,
|
| 189 |
+
893,
|
| 190 |
+
902,
|
| 191 |
+
918,
|
| 192 |
+
922,
|
| 193 |
+
931,
|
| 194 |
+
1350,
|
| 195 |
+
1853,
|
| 196 |
+
1982,
|
| 197 |
+
2460,
|
| 198 |
+
2627,
|
| 199 |
+
3246,
|
| 200 |
+
3253,
|
| 201 |
+
3268,
|
| 202 |
+
3536,
|
| 203 |
+
3846,
|
| 204 |
+
3961,
|
| 205 |
+
4183,
|
| 206 |
+
4667,
|
| 207 |
+
6585,
|
| 208 |
+
6647,
|
| 209 |
+
7273,
|
| 210 |
+
9061,
|
| 211 |
+
9383,
|
| 212 |
+
10428,
|
| 213 |
+
10929,
|
| 214 |
+
11938,
|
| 215 |
+
12033,
|
| 216 |
+
12331,
|
| 217 |
+
12562,
|
| 218 |
+
13793,
|
| 219 |
+
14157,
|
| 220 |
+
14635,
|
| 221 |
+
15265,
|
| 222 |
+
15618,
|
| 223 |
+
16553,
|
| 224 |
+
16604,
|
| 225 |
+
18362,
|
| 226 |
+
18956,
|
| 227 |
+
20075,
|
| 228 |
+
21675,
|
| 229 |
+
22520,
|
| 230 |
+
26130,
|
| 231 |
+
26161,
|
| 232 |
+
26435,
|
| 233 |
+
28279,
|
| 234 |
+
29464,
|
| 235 |
+
31650,
|
| 236 |
+
32302,
|
| 237 |
+
32470,
|
| 238 |
+
36865,
|
| 239 |
+
42863,
|
| 240 |
+
47425,
|
| 241 |
+
49870,
|
| 242 |
+
50254,
|
| 243 |
+
50258,
|
| 244 |
+
50358,
|
| 245 |
+
50359,
|
| 246 |
+
50360,
|
| 247 |
+
50361,
|
| 248 |
+
50362
|
| 249 |
+
],
|
| 250 |
+
"task": "transcribe",
|
| 251 |
+
"task_to_id": {
|
| 252 |
+
"transcribe": 50359,
|
| 253 |
+
"translate": 50358
|
| 254 |
+
},
|
| 255 |
+
"transformers_version": "4.42.4"
|
| 256 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed970c9e53c8bdd3f0f202bff91cd4f502bca2ac499cf6032900696c12183de
|
| 3 |
+
size 966995080
|
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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,611 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 25.035120389427945,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-pl/checkpoint-2000",
|
| 4 |
+
"epoch": 1.9342359767891684,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.024177949709864602,
|
| 13 |
+
"grad_norm": 13.08698844909668,
|
| 14 |
+
"learning_rate": 4.6000000000000004e-07,
|
| 15 |
+
"loss": 0.7941,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.048355899419729204,
|
| 20 |
+
"grad_norm": 9.012430191040039,
|
| 21 |
+
"learning_rate": 9.600000000000001e-07,
|
| 22 |
+
"loss": 0.7344,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0725338491295938,
|
| 27 |
+
"grad_norm": 9.37657356262207,
|
| 28 |
+
"learning_rate": 1.46e-06,
|
| 29 |
+
"loss": 0.5611,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09671179883945841,
|
| 34 |
+
"grad_norm": 7.428127288818359,
|
| 35 |
+
"learning_rate": 1.9600000000000003e-06,
|
| 36 |
+
"loss": 0.2917,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12088974854932302,
|
| 41 |
+
"grad_norm": 7.270956039428711,
|
| 42 |
+
"learning_rate": 2.46e-06,
|
| 43 |
+
"loss": 0.2767,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1450676982591876,
|
| 48 |
+
"grad_norm": 6.277708530426025,
|
| 49 |
+
"learning_rate": 2.96e-06,
|
| 50 |
+
"loss": 0.2621,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16924564796905223,
|
| 55 |
+
"grad_norm": 7.922985553741455,
|
| 56 |
+
"learning_rate": 3.46e-06,
|
| 57 |
+
"loss": 0.2482,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.19342359767891681,
|
| 62 |
+
"grad_norm": 7.432052135467529,
|
| 63 |
+
"learning_rate": 3.96e-06,
|
| 64 |
+
"loss": 0.2468,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21760154738878143,
|
| 69 |
+
"grad_norm": 5.777613162994385,
|
| 70 |
+
"learning_rate": 4.4600000000000005e-06,
|
| 71 |
+
"loss": 0.2526,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.24177949709864605,
|
| 76 |
+
"grad_norm": 7.955958843231201,
|
| 77 |
+
"learning_rate": 4.960000000000001e-06,
|
| 78 |
+
"loss": 0.2293,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.26595744680851063,
|
| 83 |
+
"grad_norm": 8.523419380187988,
|
| 84 |
+
"learning_rate": 5.460000000000001e-06,
|
| 85 |
+
"loss": 0.2112,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2901353965183752,
|
| 90 |
+
"grad_norm": 6.596875190734863,
|
| 91 |
+
"learning_rate": 5.9600000000000005e-06,
|
| 92 |
+
"loss": 0.2224,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.31431334622823986,
|
| 97 |
+
"grad_norm": 7.191504955291748,
|
| 98 |
+
"learning_rate": 6.460000000000001e-06,
|
| 99 |
+
"loss": 0.2112,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.33849129593810445,
|
| 104 |
+
"grad_norm": 8.093416213989258,
|
| 105 |
+
"learning_rate": 6.96e-06,
|
| 106 |
+
"loss": 0.215,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.36266924564796904,
|
| 111 |
+
"grad_norm": 6.397820949554443,
|
| 112 |
+
"learning_rate": 7.4600000000000006e-06,
|
| 113 |
+
"loss": 0.2079,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.38684719535783363,
|
| 118 |
+
"grad_norm": 5.670892238616943,
|
| 119 |
+
"learning_rate": 7.960000000000002e-06,
|
| 120 |
+
"loss": 0.2377,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.41102514506769827,
|
| 125 |
+
"grad_norm": 6.631639003753662,
|
| 126 |
+
"learning_rate": 8.46e-06,
|
| 127 |
+
"loss": 0.2409,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.43520309477756286,
|
| 132 |
+
"grad_norm": 5.997097015380859,
|
| 133 |
+
"learning_rate": 8.96e-06,
|
| 134 |
+
"loss": 0.219,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.45938104448742745,
|
| 139 |
+
"grad_norm": 5.482093334197998,
|
| 140 |
+
"learning_rate": 9.460000000000001e-06,
|
| 141 |
+
"loss": 0.2004,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4835589941972921,
|
| 146 |
+
"grad_norm": 7.19942045211792,
|
| 147 |
+
"learning_rate": 9.960000000000001e-06,
|
| 148 |
+
"loss": 0.2118,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5077369439071566,
|
| 153 |
+
"grad_norm": 4.876007080078125,
|
| 154 |
+
"learning_rate": 9.846666666666668e-06,
|
| 155 |
+
"loss": 0.1984,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5319148936170213,
|
| 160 |
+
"grad_norm": 5.836966037750244,
|
| 161 |
+
"learning_rate": 9.68e-06,
|
| 162 |
+
"loss": 0.218,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5560928433268859,
|
| 167 |
+
"grad_norm": 5.95539665222168,
|
| 168 |
+
"learning_rate": 9.513333333333334e-06,
|
| 169 |
+
"loss": 0.2,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5802707930367504,
|
| 174 |
+
"grad_norm": 7.50021505355835,
|
| 175 |
+
"learning_rate": 9.346666666666666e-06,
|
| 176 |
+
"loss": 0.2087,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6044487427466151,
|
| 181 |
+
"grad_norm": 5.989735126495361,
|
| 182 |
+
"learning_rate": 9.180000000000002e-06,
|
| 183 |
+
"loss": 0.198,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6286266924564797,
|
| 188 |
+
"grad_norm": 7.257640838623047,
|
| 189 |
+
"learning_rate": 9.013333333333334e-06,
|
| 190 |
+
"loss": 0.2134,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6528046421663443,
|
| 195 |
+
"grad_norm": 7.139352798461914,
|
| 196 |
+
"learning_rate": 8.846666666666668e-06,
|
| 197 |
+
"loss": 0.1896,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6769825918762089,
|
| 202 |
+
"grad_norm": 5.189645290374756,
|
| 203 |
+
"learning_rate": 8.68e-06,
|
| 204 |
+
"loss": 0.2043,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7011605415860735,
|
| 209 |
+
"grad_norm": 6.447940349578857,
|
| 210 |
+
"learning_rate": 8.513333333333335e-06,
|
| 211 |
+
"loss": 0.2004,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7253384912959381,
|
| 216 |
+
"grad_norm": 6.197971820831299,
|
| 217 |
+
"learning_rate": 8.346666666666668e-06,
|
| 218 |
+
"loss": 0.2128,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7495164410058027,
|
| 223 |
+
"grad_norm": 6.4797186851501465,
|
| 224 |
+
"learning_rate": 8.18e-06,
|
| 225 |
+
"loss": 0.2027,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7736943907156673,
|
| 230 |
+
"grad_norm": 6.49001407623291,
|
| 231 |
+
"learning_rate": 8.013333333333333e-06,
|
| 232 |
+
"loss": 0.2039,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7978723404255319,
|
| 237 |
+
"grad_norm": 7.675256729125977,
|
| 238 |
+
"learning_rate": 7.846666666666667e-06,
|
| 239 |
+
"loss": 0.2132,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8220502901353965,
|
| 244 |
+
"grad_norm": 6.154118537902832,
|
| 245 |
+
"learning_rate": 7.680000000000001e-06,
|
| 246 |
+
"loss": 0.185,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8462282398452611,
|
| 251 |
+
"grad_norm": 4.915777206420898,
|
| 252 |
+
"learning_rate": 7.513333333333334e-06,
|
| 253 |
+
"loss": 0.1964,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8704061895551257,
|
| 258 |
+
"grad_norm": 6.114099025726318,
|
| 259 |
+
"learning_rate": 7.346666666666668e-06,
|
| 260 |
+
"loss": 0.1829,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8945841392649904,
|
| 265 |
+
"grad_norm": 4.89927339553833,
|
| 266 |
+
"learning_rate": 7.180000000000001e-06,
|
| 267 |
+
"loss": 0.1811,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9187620889748549,
|
| 272 |
+
"grad_norm": 6.713924884796143,
|
| 273 |
+
"learning_rate": 7.0133333333333345e-06,
|
| 274 |
+
"loss": 0.2002,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9429400386847195,
|
| 279 |
+
"grad_norm": 3.8542282581329346,
|
| 280 |
+
"learning_rate": 6.846666666666667e-06,
|
| 281 |
+
"loss": 0.1919,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9671179883945842,
|
| 286 |
+
"grad_norm": 5.772714138031006,
|
| 287 |
+
"learning_rate": 6.680000000000001e-06,
|
| 288 |
+
"loss": 0.1948,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9671179883945842,
|
| 293 |
+
"eval_loss": 0.3445706367492676,
|
| 294 |
+
"eval_runtime": 2461.0106,
|
| 295 |
+
"eval_samples_per_second": 3.37,
|
| 296 |
+
"eval_steps_per_second": 0.421,
|
| 297 |
+
"eval_wer": 27.341631546277238,
|
| 298 |
+
"step": 1000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.9912959381044487,
|
| 302 |
+
"grad_norm": 5.760690689086914,
|
| 303 |
+
"learning_rate": 6.513333333333333e-06,
|
| 304 |
+
"loss": 0.1792,
|
| 305 |
+
"step": 1025
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.0154738878143132,
|
| 309 |
+
"grad_norm": 2.4457898139953613,
|
| 310 |
+
"learning_rate": 6.346666666666668e-06,
|
| 311 |
+
"loss": 0.1373,
|
| 312 |
+
"step": 1050
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.039651837524178,
|
| 316 |
+
"grad_norm": 6.8382792472839355,
|
| 317 |
+
"learning_rate": 6.18e-06,
|
| 318 |
+
"loss": 0.1037,
|
| 319 |
+
"step": 1075
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.0638297872340425,
|
| 323 |
+
"grad_norm": 2.8886797428131104,
|
| 324 |
+
"learning_rate": 6.013333333333335e-06,
|
| 325 |
+
"loss": 0.0919,
|
| 326 |
+
"step": 1100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.0880077369439072,
|
| 330 |
+
"grad_norm": 3.747055768966675,
|
| 331 |
+
"learning_rate": 5.846666666666667e-06,
|
| 332 |
+
"loss": 0.0998,
|
| 333 |
+
"step": 1125
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.1121856866537718,
|
| 337 |
+
"grad_norm": 5.849277973175049,
|
| 338 |
+
"learning_rate": 5.68e-06,
|
| 339 |
+
"loss": 0.0987,
|
| 340 |
+
"step": 1150
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.1363636363636362,
|
| 344 |
+
"grad_norm": 4.248702526092529,
|
| 345 |
+
"learning_rate": 5.513333333333334e-06,
|
| 346 |
+
"loss": 0.0986,
|
| 347 |
+
"step": 1175
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.1605415860735009,
|
| 351 |
+
"grad_norm": 2.798823595046997,
|
| 352 |
+
"learning_rate": 5.346666666666667e-06,
|
| 353 |
+
"loss": 0.0984,
|
| 354 |
+
"step": 1200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.1847195357833655,
|
| 358 |
+
"grad_norm": 3.916948080062866,
|
| 359 |
+
"learning_rate": 5.18e-06,
|
| 360 |
+
"loss": 0.1046,
|
| 361 |
+
"step": 1225
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.2088974854932302,
|
| 365 |
+
"grad_norm": 4.392205238342285,
|
| 366 |
+
"learning_rate": 5.013333333333333e-06,
|
| 367 |
+
"loss": 0.1004,
|
| 368 |
+
"step": 1250
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.2330754352030948,
|
| 372 |
+
"grad_norm": 4.6209940910339355,
|
| 373 |
+
"learning_rate": 4.846666666666667e-06,
|
| 374 |
+
"loss": 0.0974,
|
| 375 |
+
"step": 1275
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.2572533849129595,
|
| 379 |
+
"grad_norm": 3.8491697311401367,
|
| 380 |
+
"learning_rate": 4.680000000000001e-06,
|
| 381 |
+
"loss": 0.0964,
|
| 382 |
+
"step": 1300
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.281431334622824,
|
| 386 |
+
"grad_norm": 3.726794958114624,
|
| 387 |
+
"learning_rate": 4.513333333333333e-06,
|
| 388 |
+
"loss": 0.1073,
|
| 389 |
+
"step": 1325
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3056092843326885,
|
| 393 |
+
"grad_norm": 2.047708511352539,
|
| 394 |
+
"learning_rate": 4.346666666666667e-06,
|
| 395 |
+
"loss": 0.0946,
|
| 396 |
+
"step": 1350
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3297872340425532,
|
| 400 |
+
"grad_norm": 3.641178846359253,
|
| 401 |
+
"learning_rate": 4.18e-06,
|
| 402 |
+
"loss": 0.1003,
|
| 403 |
+
"step": 1375
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.3539651837524178,
|
| 407 |
+
"grad_norm": 4.149508476257324,
|
| 408 |
+
"learning_rate": 4.013333333333334e-06,
|
| 409 |
+
"loss": 0.0878,
|
| 410 |
+
"step": 1400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.3781431334622825,
|
| 414 |
+
"grad_norm": 3.5799102783203125,
|
| 415 |
+
"learning_rate": 3.8466666666666665e-06,
|
| 416 |
+
"loss": 0.1025,
|
| 417 |
+
"step": 1425
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.402321083172147,
|
| 421 |
+
"grad_norm": 3.7035670280456543,
|
| 422 |
+
"learning_rate": 3.6800000000000003e-06,
|
| 423 |
+
"loss": 0.0968,
|
| 424 |
+
"step": 1450
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4264990328820115,
|
| 428 |
+
"grad_norm": 3.0954935550689697,
|
| 429 |
+
"learning_rate": 3.5133333333333337e-06,
|
| 430 |
+
"loss": 0.0914,
|
| 431 |
+
"step": 1475
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.4506769825918762,
|
| 435 |
+
"grad_norm": 5.010723114013672,
|
| 436 |
+
"learning_rate": 3.346666666666667e-06,
|
| 437 |
+
"loss": 0.096,
|
| 438 |
+
"step": 1500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.4748549323017408,
|
| 442 |
+
"grad_norm": 4.114623546600342,
|
| 443 |
+
"learning_rate": 3.1800000000000005e-06,
|
| 444 |
+
"loss": 0.0895,
|
| 445 |
+
"step": 1525
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.4990328820116054,
|
| 449 |
+
"grad_norm": 2.368100881576538,
|
| 450 |
+
"learning_rate": 3.013333333333334e-06,
|
| 451 |
+
"loss": 0.0875,
|
| 452 |
+
"step": 1550
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.52321083172147,
|
| 456 |
+
"grad_norm": 3.3124420642852783,
|
| 457 |
+
"learning_rate": 2.8466666666666672e-06,
|
| 458 |
+
"loss": 0.0901,
|
| 459 |
+
"step": 1575
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.5473887814313345,
|
| 463 |
+
"grad_norm": 2.9692959785461426,
|
| 464 |
+
"learning_rate": 2.68e-06,
|
| 465 |
+
"loss": 0.0958,
|
| 466 |
+
"step": 1600
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.5715667311411994,
|
| 470 |
+
"grad_norm": 3.253309726715088,
|
| 471 |
+
"learning_rate": 2.5133333333333336e-06,
|
| 472 |
+
"loss": 0.0844,
|
| 473 |
+
"step": 1625
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.5957446808510638,
|
| 477 |
+
"grad_norm": 4.483941078186035,
|
| 478 |
+
"learning_rate": 2.346666666666667e-06,
|
| 479 |
+
"loss": 0.0964,
|
| 480 |
+
"step": 1650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.6199226305609284,
|
| 484 |
+
"grad_norm": 3.4813811779022217,
|
| 485 |
+
"learning_rate": 2.1800000000000003e-06,
|
| 486 |
+
"loss": 0.0898,
|
| 487 |
+
"step": 1675
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.644100580270793,
|
| 491 |
+
"grad_norm": 2.9097344875335693,
|
| 492 |
+
"learning_rate": 2.0133333333333337e-06,
|
| 493 |
+
"loss": 0.0785,
|
| 494 |
+
"step": 1700
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.6682785299806575,
|
| 498 |
+
"grad_norm": 4.8369011878967285,
|
| 499 |
+
"learning_rate": 1.8466666666666668e-06,
|
| 500 |
+
"loss": 0.0858,
|
| 501 |
+
"step": 1725
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.6924564796905224,
|
| 505 |
+
"grad_norm": 3.383228302001953,
|
| 506 |
+
"learning_rate": 1.6800000000000002e-06,
|
| 507 |
+
"loss": 0.0925,
|
| 508 |
+
"step": 1750
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.7166344294003868,
|
| 512 |
+
"grad_norm": 3.398839235305786,
|
| 513 |
+
"learning_rate": 1.5133333333333334e-06,
|
| 514 |
+
"loss": 0.0966,
|
| 515 |
+
"step": 1775
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.7408123791102514,
|
| 519 |
+
"grad_norm": 4.022014617919922,
|
| 520 |
+
"learning_rate": 1.3466666666666668e-06,
|
| 521 |
+
"loss": 0.086,
|
| 522 |
+
"step": 1800
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.764990328820116,
|
| 526 |
+
"grad_norm": 4.035211086273193,
|
| 527 |
+
"learning_rate": 1.1800000000000001e-06,
|
| 528 |
+
"loss": 0.0932,
|
| 529 |
+
"step": 1825
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.7891682785299805,
|
| 533 |
+
"grad_norm": 3.886571168899536,
|
| 534 |
+
"learning_rate": 1.0133333333333333e-06,
|
| 535 |
+
"loss": 0.0823,
|
| 536 |
+
"step": 1850
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.8133462282398454,
|
| 540 |
+
"grad_norm": 3.486004590988159,
|
| 541 |
+
"learning_rate": 8.466666666666668e-07,
|
| 542 |
+
"loss": 0.0984,
|
| 543 |
+
"step": 1875
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.8375241779497098,
|
| 547 |
+
"grad_norm": 2.604168176651001,
|
| 548 |
+
"learning_rate": 6.800000000000001e-07,
|
| 549 |
+
"loss": 0.0892,
|
| 550 |
+
"step": 1900
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.8617021276595744,
|
| 554 |
+
"grad_norm": 3.2812445163726807,
|
| 555 |
+
"learning_rate": 5.133333333333334e-07,
|
| 556 |
+
"loss": 0.0817,
|
| 557 |
+
"step": 1925
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.885880077369439,
|
| 561 |
+
"grad_norm": 3.6800663471221924,
|
| 562 |
+
"learning_rate": 3.466666666666667e-07,
|
| 563 |
+
"loss": 0.0925,
|
| 564 |
+
"step": 1950
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.9100580270793037,
|
| 568 |
+
"grad_norm": 4.335522651672363,
|
| 569 |
+
"learning_rate": 1.8e-07,
|
| 570 |
+
"loss": 0.0908,
|
| 571 |
+
"step": 1975
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.9342359767891684,
|
| 575 |
+
"grad_norm": 1.6400020122528076,
|
| 576 |
+
"learning_rate": 1.3333333333333334e-08,
|
| 577 |
+
"loss": 0.0809,
|
| 578 |
+
"step": 2000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.9342359767891684,
|
| 582 |
+
"eval_loss": 0.33456456661224365,
|
| 583 |
+
"eval_runtime": 2469.2143,
|
| 584 |
+
"eval_samples_per_second": 3.359,
|
| 585 |
+
"eval_steps_per_second": 0.42,
|
| 586 |
+
"eval_wer": 25.035120389427945,
|
| 587 |
+
"step": 2000
|
| 588 |
+
}
|
| 589 |
+
],
|
| 590 |
+
"logging_steps": 25,
|
| 591 |
+
"max_steps": 2000,
|
| 592 |
+
"num_input_tokens_seen": 0,
|
| 593 |
+
"num_train_epochs": 2,
|
| 594 |
+
"save_steps": 1000,
|
| 595 |
+
"stateful_callbacks": {
|
| 596 |
+
"TrainerControl": {
|
| 597 |
+
"args": {
|
| 598 |
+
"should_epoch_stop": false,
|
| 599 |
+
"should_evaluate": false,
|
| 600 |
+
"should_log": false,
|
| 601 |
+
"should_save": true,
|
| 602 |
+
"should_training_stop": true
|
| 603 |
+
},
|
| 604 |
+
"attributes": {}
|
| 605 |
+
}
|
| 606 |
+
},
|
| 607 |
+
"total_flos": 9.2332898832384e+18,
|
| 608 |
+
"train_batch_size": 8,
|
| 609 |
+
"trial_name": null,
|
| 610 |
+
"trial_params": null
|
| 611 |
+
}
|