Upload folder
Browse files- checkpoint-2045/config.json +154 -0
- checkpoint-2045/generation_config.json +248 -0
- checkpoint-2045/model.safetensors +3 -0
- checkpoint-2045/optimizer.pt +3 -0
- checkpoint-2045/preprocessor_config.json +14 -0
- checkpoint-2045/rng_state.pth +3 -0
- checkpoint-2045/scheduler.pt +3 -0
- checkpoint-2045/trainer_state.json +650 -0
- checkpoint-2045/training_args.bin +3 -0
- config.json +1 -1
- model.safetensors +1 -1
- runs/Jun25_06-08-05_557d2a8f2caf/events.out.tfevents.1719295686.557d2a8f2caf.34.0 +3 -0
- training_args.bin +2 -2
checkpoint-2045/config.json
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "DazMashaly/new_downloads",
|
| 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": 512,
|
| 17 |
+
"decoder_attention_heads": 8,
|
| 18 |
+
"decoder_ffn_dim": 2048,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 6,
|
| 21 |
+
"decoder_start_token_id": 50257,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 8,
|
| 24 |
+
"encoder_ffn_dim": 2048,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 6,
|
| 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": 6,
|
| 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 |
+
50358,
|
| 144 |
+
50359,
|
| 145 |
+
50360,
|
| 146 |
+
50361,
|
| 147 |
+
50362
|
| 148 |
+
],
|
| 149 |
+
"torch_dtype": "float32",
|
| 150 |
+
"transformers_version": "4.41.2",
|
| 151 |
+
"use_cache": true,
|
| 152 |
+
"use_weighted_layer_sum": false,
|
| 153 |
+
"vocab_size": 51865
|
| 154 |
+
}
|
checkpoint-2045/generation_config.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
3,
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
4,
|
| 9 |
+
2
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
4,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
4,
|
| 17 |
+
7
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
5,
|
| 21 |
+
1
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
5,
|
| 25 |
+
2
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
5,
|
| 29 |
+
4
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
5,
|
| 33 |
+
6
|
| 34 |
+
]
|
| 35 |
+
],
|
| 36 |
+
"begin_suppress_tokens": [
|
| 37 |
+
220,
|
| 38 |
+
50257
|
| 39 |
+
],
|
| 40 |
+
"bos_token_id": 50257,
|
| 41 |
+
"decoder_start_token_id": 50258,
|
| 42 |
+
"eos_token_id": 50257,
|
| 43 |
+
"is_multilingual": true,
|
| 44 |
+
"lang_to_id": {
|
| 45 |
+
"<|af|>": 50327,
|
| 46 |
+
"<|am|>": 50334,
|
| 47 |
+
"<|ar|>": 50272,
|
| 48 |
+
"<|as|>": 50350,
|
| 49 |
+
"<|az|>": 50304,
|
| 50 |
+
"<|ba|>": 50355,
|
| 51 |
+
"<|be|>": 50330,
|
| 52 |
+
"<|bg|>": 50292,
|
| 53 |
+
"<|bn|>": 50302,
|
| 54 |
+
"<|bo|>": 50347,
|
| 55 |
+
"<|br|>": 50309,
|
| 56 |
+
"<|bs|>": 50315,
|
| 57 |
+
"<|ca|>": 50270,
|
| 58 |
+
"<|cs|>": 50283,
|
| 59 |
+
"<|cy|>": 50297,
|
| 60 |
+
"<|da|>": 50285,
|
| 61 |
+
"<|de|>": 50261,
|
| 62 |
+
"<|el|>": 50281,
|
| 63 |
+
"<|en|>": 50259,
|
| 64 |
+
"<|es|>": 50262,
|
| 65 |
+
"<|et|>": 50307,
|
| 66 |
+
"<|eu|>": 50310,
|
| 67 |
+
"<|fa|>": 50300,
|
| 68 |
+
"<|fi|>": 50277,
|
| 69 |
+
"<|fo|>": 50338,
|
| 70 |
+
"<|fr|>": 50265,
|
| 71 |
+
"<|gl|>": 50319,
|
| 72 |
+
"<|gu|>": 50333,
|
| 73 |
+
"<|haw|>": 50352,
|
| 74 |
+
"<|ha|>": 50354,
|
| 75 |
+
"<|he|>": 50279,
|
| 76 |
+
"<|hi|>": 50276,
|
| 77 |
+
"<|hr|>": 50291,
|
| 78 |
+
"<|ht|>": 50339,
|
| 79 |
+
"<|hu|>": 50286,
|
| 80 |
+
"<|hy|>": 50312,
|
| 81 |
+
"<|id|>": 50275,
|
| 82 |
+
"<|is|>": 50311,
|
| 83 |
+
"<|it|>": 50274,
|
| 84 |
+
"<|ja|>": 50266,
|
| 85 |
+
"<|jw|>": 50356,
|
| 86 |
+
"<|ka|>": 50329,
|
| 87 |
+
"<|kk|>": 50316,
|
| 88 |
+
"<|km|>": 50323,
|
| 89 |
+
"<|kn|>": 50306,
|
| 90 |
+
"<|ko|>": 50264,
|
| 91 |
+
"<|la|>": 50294,
|
| 92 |
+
"<|lb|>": 50345,
|
| 93 |
+
"<|ln|>": 50353,
|
| 94 |
+
"<|lo|>": 50336,
|
| 95 |
+
"<|lt|>": 50293,
|
| 96 |
+
"<|lv|>": 50301,
|
| 97 |
+
"<|mg|>": 50349,
|
| 98 |
+
"<|mi|>": 50295,
|
| 99 |
+
"<|mk|>": 50308,
|
| 100 |
+
"<|ml|>": 50296,
|
| 101 |
+
"<|mn|>": 50314,
|
| 102 |
+
"<|mr|>": 50320,
|
| 103 |
+
"<|ms|>": 50282,
|
| 104 |
+
"<|mt|>": 50343,
|
| 105 |
+
"<|my|>": 50346,
|
| 106 |
+
"<|ne|>": 50313,
|
| 107 |
+
"<|nl|>": 50271,
|
| 108 |
+
"<|nn|>": 50342,
|
| 109 |
+
"<|no|>": 50288,
|
| 110 |
+
"<|oc|>": 50328,
|
| 111 |
+
"<|pa|>": 50321,
|
| 112 |
+
"<|pl|>": 50269,
|
| 113 |
+
"<|ps|>": 50340,
|
| 114 |
+
"<|pt|>": 50267,
|
| 115 |
+
"<|ro|>": 50284,
|
| 116 |
+
"<|ru|>": 50263,
|
| 117 |
+
"<|sa|>": 50344,
|
| 118 |
+
"<|sd|>": 50332,
|
| 119 |
+
"<|si|>": 50322,
|
| 120 |
+
"<|sk|>": 50298,
|
| 121 |
+
"<|sl|>": 50305,
|
| 122 |
+
"<|sn|>": 50324,
|
| 123 |
+
"<|so|>": 50326,
|
| 124 |
+
"<|sq|>": 50317,
|
| 125 |
+
"<|sr|>": 50303,
|
| 126 |
+
"<|su|>": 50357,
|
| 127 |
+
"<|sv|>": 50273,
|
| 128 |
+
"<|sw|>": 50318,
|
| 129 |
+
"<|ta|>": 50287,
|
| 130 |
+
"<|te|>": 50299,
|
| 131 |
+
"<|tg|>": 50331,
|
| 132 |
+
"<|th|>": 50289,
|
| 133 |
+
"<|tk|>": 50341,
|
| 134 |
+
"<|tl|>": 50348,
|
| 135 |
+
"<|tr|>": 50268,
|
| 136 |
+
"<|tt|>": 50351,
|
| 137 |
+
"<|uk|>": 50280,
|
| 138 |
+
"<|ur|>": 50290,
|
| 139 |
+
"<|uz|>": 50337,
|
| 140 |
+
"<|vi|>": 50278,
|
| 141 |
+
"<|yi|>": 50335,
|
| 142 |
+
"<|yo|>": 50325,
|
| 143 |
+
"<|zh|>": 50260
|
| 144 |
+
},
|
| 145 |
+
"language": "arabic",
|
| 146 |
+
"max_initial_timestamp_index": 50,
|
| 147 |
+
"max_length": 448,
|
| 148 |
+
"no_timestamps_token_id": 50363,
|
| 149 |
+
"pad_token_id": 50257,
|
| 150 |
+
"prev_sot_token_id": 50361,
|
| 151 |
+
"return_timestamps": false,
|
| 152 |
+
"suppress_tokens": [
|
| 153 |
+
1,
|
| 154 |
+
2,
|
| 155 |
+
7,
|
| 156 |
+
8,
|
| 157 |
+
9,
|
| 158 |
+
10,
|
| 159 |
+
14,
|
| 160 |
+
25,
|
| 161 |
+
26,
|
| 162 |
+
27,
|
| 163 |
+
28,
|
| 164 |
+
29,
|
| 165 |
+
31,
|
| 166 |
+
58,
|
| 167 |
+
59,
|
| 168 |
+
60,
|
| 169 |
+
61,
|
| 170 |
+
62,
|
| 171 |
+
63,
|
| 172 |
+
90,
|
| 173 |
+
91,
|
| 174 |
+
92,
|
| 175 |
+
93,
|
| 176 |
+
359,
|
| 177 |
+
503,
|
| 178 |
+
522,
|
| 179 |
+
542,
|
| 180 |
+
873,
|
| 181 |
+
893,
|
| 182 |
+
902,
|
| 183 |
+
918,
|
| 184 |
+
922,
|
| 185 |
+
931,
|
| 186 |
+
1350,
|
| 187 |
+
1853,
|
| 188 |
+
1982,
|
| 189 |
+
2460,
|
| 190 |
+
2627,
|
| 191 |
+
3246,
|
| 192 |
+
3253,
|
| 193 |
+
3268,
|
| 194 |
+
3536,
|
| 195 |
+
3846,
|
| 196 |
+
3961,
|
| 197 |
+
4183,
|
| 198 |
+
4667,
|
| 199 |
+
6585,
|
| 200 |
+
6647,
|
| 201 |
+
7273,
|
| 202 |
+
9061,
|
| 203 |
+
9383,
|
| 204 |
+
10428,
|
| 205 |
+
10929,
|
| 206 |
+
11938,
|
| 207 |
+
12033,
|
| 208 |
+
12331,
|
| 209 |
+
12562,
|
| 210 |
+
13793,
|
| 211 |
+
14157,
|
| 212 |
+
14635,
|
| 213 |
+
15265,
|
| 214 |
+
15618,
|
| 215 |
+
16553,
|
| 216 |
+
16604,
|
| 217 |
+
18362,
|
| 218 |
+
18956,
|
| 219 |
+
20075,
|
| 220 |
+
21675,
|
| 221 |
+
22520,
|
| 222 |
+
26130,
|
| 223 |
+
26161,
|
| 224 |
+
26435,
|
| 225 |
+
28279,
|
| 226 |
+
29464,
|
| 227 |
+
31650,
|
| 228 |
+
32302,
|
| 229 |
+
32470,
|
| 230 |
+
36865,
|
| 231 |
+
42863,
|
| 232 |
+
47425,
|
| 233 |
+
49870,
|
| 234 |
+
50254,
|
| 235 |
+
50258,
|
| 236 |
+
50358,
|
| 237 |
+
50359,
|
| 238 |
+
50360,
|
| 239 |
+
50361,
|
| 240 |
+
50362
|
| 241 |
+
],
|
| 242 |
+
"task": "transcribe",
|
| 243 |
+
"task_to_id": {
|
| 244 |
+
"transcribe": 50359,
|
| 245 |
+
"translate": 50358
|
| 246 |
+
},
|
| 247 |
+
"transformers_version": "4.41.2"
|
| 248 |
+
}
|
checkpoint-2045/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc48c0adcc1e3b3c0bd007518f406e2619082456c1687e6f499e09a28926a2b2
|
| 3 |
+
size 290403936
|
checkpoint-2045/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e45493dfa7426ec72a87461be315979f4a854c336cde70dea9cc7fa7ee2e20
|
| 3 |
+
size 574811514
|
checkpoint-2045/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 |
+
}
|
checkpoint-2045/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4047c10ca9a8a573586cb56ed498443cc0e72e2b8103f581ba258d4b23bf4578
|
| 3 |
+
size 14244
|
checkpoint-2045/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf0578990f895e8b7945ea9bb7146cc84583e4003e10edc31e52b497f1672062
|
| 3 |
+
size 1064
|
checkpoint-2045/trainer_state.json
ADDED
|
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "DazMashaly/output/checkpoint-409",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2045,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.061124694376528114,
|
| 13 |
+
"grad_norm": 1.064210295677185,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 6.0673,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12224938875305623,
|
| 20 |
+
"grad_norm": 0.982063889503479,
|
| 21 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
+
"loss": 6.0659,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.18337408312958436,
|
| 27 |
+
"grad_norm": 0.9887572526931763,
|
| 28 |
+
"learning_rate": 1.5e-06,
|
| 29 |
+
"loss": 6.069,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.24449877750611246,
|
| 34 |
+
"grad_norm": 1.076440691947937,
|
| 35 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
+
"loss": 6.0588,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3056234718826406,
|
| 41 |
+
"grad_norm": 1.1176767349243164,
|
| 42 |
+
"learning_rate": 2.5e-06,
|
| 43 |
+
"loss": 6.0642,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.36674816625916873,
|
| 48 |
+
"grad_norm": 1.0234830379486084,
|
| 49 |
+
"learning_rate": 3e-06,
|
| 50 |
+
"loss": 6.0708,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4278728606356968,
|
| 55 |
+
"grad_norm": 1.090944528579712,
|
| 56 |
+
"learning_rate": 3.5e-06,
|
| 57 |
+
"loss": 6.0339,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4889975550122249,
|
| 62 |
+
"grad_norm": 1.1804206371307373,
|
| 63 |
+
"learning_rate": 4.000000000000001e-06,
|
| 64 |
+
"loss": 6.0542,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5501222493887531,
|
| 69 |
+
"grad_norm": 1.3007625341415405,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 6.0549,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6112469437652812,
|
| 76 |
+
"grad_norm": 1.2753345966339111,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 6.0535,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6723716381418093,
|
| 83 |
+
"grad_norm": 1.321979284286499,
|
| 84 |
+
"learning_rate": 5.500000000000001e-06,
|
| 85 |
+
"loss": 6.0401,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.7334963325183375,
|
| 90 |
+
"grad_norm": 1.1843823194503784,
|
| 91 |
+
"learning_rate": 6e-06,
|
| 92 |
+
"loss": 6.0463,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7946210268948656,
|
| 97 |
+
"grad_norm": 1.2534185647964478,
|
| 98 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 99 |
+
"loss": 6.0248,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8557457212713936,
|
| 104 |
+
"grad_norm": 1.2556980848312378,
|
| 105 |
+
"learning_rate": 7e-06,
|
| 106 |
+
"loss": 6.045,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.9168704156479217,
|
| 111 |
+
"grad_norm": 1.263355016708374,
|
| 112 |
+
"learning_rate": 7.500000000000001e-06,
|
| 113 |
+
"loss": 6.034,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9779951100244498,
|
| 118 |
+
"grad_norm": 1.1825202703475952,
|
| 119 |
+
"learning_rate": 8.000000000000001e-06,
|
| 120 |
+
"loss": 5.9866,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0,
|
| 125 |
+
"eval_cer": 1.0,
|
| 126 |
+
"eval_loss": 5.615485191345215,
|
| 127 |
+
"eval_runtime": 703.3832,
|
| 128 |
+
"eval_samples_per_second": 3.126,
|
| 129 |
+
"eval_steps_per_second": 0.026,
|
| 130 |
+
"eval_wer": 1.0,
|
| 131 |
+
"step": 409
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.039119804400978,
|
| 135 |
+
"grad_norm": 1.388098955154419,
|
| 136 |
+
"learning_rate": 8.5e-06,
|
| 137 |
+
"loss": 6.0005,
|
| 138 |
+
"step": 425
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.1002444987775062,
|
| 142 |
+
"grad_norm": 1.1844673156738281,
|
| 143 |
+
"learning_rate": 9e-06,
|
| 144 |
+
"loss": 5.9922,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.1613691931540342,
|
| 149 |
+
"grad_norm": 1.2709770202636719,
|
| 150 |
+
"learning_rate": 9.5e-06,
|
| 151 |
+
"loss": 5.9917,
|
| 152 |
+
"step": 475
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.2224938875305624,
|
| 156 |
+
"grad_norm": 1.331032395362854,
|
| 157 |
+
"learning_rate": 1e-05,
|
| 158 |
+
"loss": 5.9767,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.2836185819070904,
|
| 163 |
+
"grad_norm": 1.436553955078125,
|
| 164 |
+
"learning_rate": 9.967447916666668e-06,
|
| 165 |
+
"loss": 5.984,
|
| 166 |
+
"step": 525
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.3447432762836184,
|
| 170 |
+
"grad_norm": 1.2195194959640503,
|
| 171 |
+
"learning_rate": 9.934895833333335e-06,
|
| 172 |
+
"loss": 5.9959,
|
| 173 |
+
"step": 550
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.4058679706601467,
|
| 177 |
+
"grad_norm": 1.265336036682129,
|
| 178 |
+
"learning_rate": 9.902343750000001e-06,
|
| 179 |
+
"loss": 5.9657,
|
| 180 |
+
"step": 575
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.466992665036675,
|
| 184 |
+
"grad_norm": 1.2491796016693115,
|
| 185 |
+
"learning_rate": 9.869791666666667e-06,
|
| 186 |
+
"loss": 5.9545,
|
| 187 |
+
"step": 600
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.528117359413203,
|
| 191 |
+
"grad_norm": 1.5214732885360718,
|
| 192 |
+
"learning_rate": 9.837239583333335e-06,
|
| 193 |
+
"loss": 5.9556,
|
| 194 |
+
"step": 625
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.589242053789731,
|
| 198 |
+
"grad_norm": 1.478154182434082,
|
| 199 |
+
"learning_rate": 9.8046875e-06,
|
| 200 |
+
"loss": 5.9557,
|
| 201 |
+
"step": 650
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.6503667481662592,
|
| 205 |
+
"grad_norm": 1.4325579404830933,
|
| 206 |
+
"learning_rate": 9.772135416666667e-06,
|
| 207 |
+
"loss": 5.9392,
|
| 208 |
+
"step": 675
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.7114914425427874,
|
| 212 |
+
"grad_norm": 1.258053183555603,
|
| 213 |
+
"learning_rate": 9.739583333333334e-06,
|
| 214 |
+
"loss": 5.9329,
|
| 215 |
+
"step": 700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.7726161369193154,
|
| 219 |
+
"grad_norm": 1.439457893371582,
|
| 220 |
+
"learning_rate": 9.707031250000001e-06,
|
| 221 |
+
"loss": 5.9353,
|
| 222 |
+
"step": 725
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.8337408312958434,
|
| 226 |
+
"grad_norm": 2.1067497730255127,
|
| 227 |
+
"learning_rate": 9.674479166666668e-06,
|
| 228 |
+
"loss": 5.9253,
|
| 229 |
+
"step": 750
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.8948655256723717,
|
| 233 |
+
"grad_norm": 1.6002326011657715,
|
| 234 |
+
"learning_rate": 9.641927083333335e-06,
|
| 235 |
+
"loss": 5.8955,
|
| 236 |
+
"step": 775
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.9559902200488999,
|
| 240 |
+
"grad_norm": 1.249984622001648,
|
| 241 |
+
"learning_rate": 9.609375000000001e-06,
|
| 242 |
+
"loss": 5.8937,
|
| 243 |
+
"step": 800
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.0,
|
| 247 |
+
"eval_cer": 1.0,
|
| 248 |
+
"eval_loss": 5.5135722160339355,
|
| 249 |
+
"eval_runtime": 702.4432,
|
| 250 |
+
"eval_samples_per_second": 3.131,
|
| 251 |
+
"eval_steps_per_second": 0.026,
|
| 252 |
+
"eval_wer": 1.0,
|
| 253 |
+
"step": 818
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.0171149144254277,
|
| 257 |
+
"grad_norm": 1.5596375465393066,
|
| 258 |
+
"learning_rate": 9.576822916666667e-06,
|
| 259 |
+
"loss": 5.8783,
|
| 260 |
+
"step": 825
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.078239608801956,
|
| 264 |
+
"grad_norm": 1.5268152952194214,
|
| 265 |
+
"learning_rate": 9.544270833333335e-06,
|
| 266 |
+
"loss": 5.8633,
|
| 267 |
+
"step": 850
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.139364303178484,
|
| 271 |
+
"grad_norm": 1.8570572137832642,
|
| 272 |
+
"learning_rate": 9.51171875e-06,
|
| 273 |
+
"loss": 5.875,
|
| 274 |
+
"step": 875
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.2004889975550124,
|
| 278 |
+
"grad_norm": 1.7126903533935547,
|
| 279 |
+
"learning_rate": 9.479166666666667e-06,
|
| 280 |
+
"loss": 5.844,
|
| 281 |
+
"step": 900
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.26161369193154,
|
| 285 |
+
"grad_norm": 1.4625195264816284,
|
| 286 |
+
"learning_rate": 9.446614583333334e-06,
|
| 287 |
+
"loss": 5.8778,
|
| 288 |
+
"step": 925
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.3227383863080684,
|
| 292 |
+
"grad_norm": 1.4512864351272583,
|
| 293 |
+
"learning_rate": 9.414062500000001e-06,
|
| 294 |
+
"loss": 5.8592,
|
| 295 |
+
"step": 950
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.3838630806845966,
|
| 299 |
+
"grad_norm": 1.7913607358932495,
|
| 300 |
+
"learning_rate": 9.381510416666668e-06,
|
| 301 |
+
"loss": 5.8493,
|
| 302 |
+
"step": 975
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.444987775061125,
|
| 306 |
+
"grad_norm": 1.9679557085037231,
|
| 307 |
+
"learning_rate": 9.348958333333335e-06,
|
| 308 |
+
"loss": 5.8396,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.5061124694376526,
|
| 313 |
+
"grad_norm": 1.8194330930709839,
|
| 314 |
+
"learning_rate": 9.316406250000002e-06,
|
| 315 |
+
"loss": 5.8435,
|
| 316 |
+
"step": 1025
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.567237163814181,
|
| 320 |
+
"grad_norm": 1.9096548557281494,
|
| 321 |
+
"learning_rate": 9.283854166666667e-06,
|
| 322 |
+
"loss": 5.8206,
|
| 323 |
+
"step": 1050
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.628361858190709,
|
| 327 |
+
"grad_norm": 1.6974539756774902,
|
| 328 |
+
"learning_rate": 9.251302083333335e-06,
|
| 329 |
+
"loss": 5.8062,
|
| 330 |
+
"step": 1075
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.689486552567237,
|
| 334 |
+
"grad_norm": 1.7971349954605103,
|
| 335 |
+
"learning_rate": 9.21875e-06,
|
| 336 |
+
"loss": 5.8371,
|
| 337 |
+
"step": 1100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.750611246943765,
|
| 341 |
+
"grad_norm": 1.5566753149032593,
|
| 342 |
+
"learning_rate": 9.186197916666667e-06,
|
| 343 |
+
"loss": 5.8337,
|
| 344 |
+
"step": 1125
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.8117359413202934,
|
| 348 |
+
"grad_norm": 1.7522369623184204,
|
| 349 |
+
"learning_rate": 9.153645833333334e-06,
|
| 350 |
+
"loss": 5.7644,
|
| 351 |
+
"step": 1150
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.8728606356968216,
|
| 355 |
+
"grad_norm": 1.545310378074646,
|
| 356 |
+
"learning_rate": 9.121093750000001e-06,
|
| 357 |
+
"loss": 5.7901,
|
| 358 |
+
"step": 1175
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.93398533007335,
|
| 362 |
+
"grad_norm": 1.4376916885375977,
|
| 363 |
+
"learning_rate": 9.088541666666666e-06,
|
| 364 |
+
"loss": 5.7892,
|
| 365 |
+
"step": 1200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.9951100244498776,
|
| 369 |
+
"grad_norm": 1.7640162706375122,
|
| 370 |
+
"learning_rate": 9.055989583333335e-06,
|
| 371 |
+
"loss": 5.7924,
|
| 372 |
+
"step": 1225
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.0,
|
| 376 |
+
"eval_cer": 1.0,
|
| 377 |
+
"eval_loss": 5.430821895599365,
|
| 378 |
+
"eval_runtime": 955.8928,
|
| 379 |
+
"eval_samples_per_second": 2.3,
|
| 380 |
+
"eval_steps_per_second": 0.019,
|
| 381 |
+
"eval_wer": 1.0,
|
| 382 |
+
"step": 1227
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 3.056234718826406,
|
| 386 |
+
"grad_norm": 1.6651889085769653,
|
| 387 |
+
"learning_rate": 9.0234375e-06,
|
| 388 |
+
"loss": 5.778,
|
| 389 |
+
"step": 1250
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.117359413202934,
|
| 393 |
+
"grad_norm": 2.1398913860321045,
|
| 394 |
+
"learning_rate": 8.990885416666667e-06,
|
| 395 |
+
"loss": 5.75,
|
| 396 |
+
"step": 1275
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.178484107579462,
|
| 400 |
+
"grad_norm": 1.9647698402404785,
|
| 401 |
+
"learning_rate": 8.958333333333334e-06,
|
| 402 |
+
"loss": 5.7652,
|
| 403 |
+
"step": 1300
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.23960880195599,
|
| 407 |
+
"grad_norm": 1.7572517395019531,
|
| 408 |
+
"learning_rate": 8.92578125e-06,
|
| 409 |
+
"loss": 5.7267,
|
| 410 |
+
"step": 1325
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.3007334963325183,
|
| 414 |
+
"grad_norm": 2.1968727111816406,
|
| 415 |
+
"learning_rate": 8.893229166666667e-06,
|
| 416 |
+
"loss": 5.7432,
|
| 417 |
+
"step": 1350
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.3618581907090466,
|
| 421 |
+
"grad_norm": 1.857980728149414,
|
| 422 |
+
"learning_rate": 8.860677083333334e-06,
|
| 423 |
+
"loss": 5.7513,
|
| 424 |
+
"step": 1375
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.422982885085575,
|
| 428 |
+
"grad_norm": 1.9934026002883911,
|
| 429 |
+
"learning_rate": 8.828125000000001e-06,
|
| 430 |
+
"loss": 5.7348,
|
| 431 |
+
"step": 1400
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.4841075794621026,
|
| 435 |
+
"grad_norm": 2.0249619483947754,
|
| 436 |
+
"learning_rate": 8.795572916666666e-06,
|
| 437 |
+
"loss": 5.7324,
|
| 438 |
+
"step": 1425
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.545232273838631,
|
| 442 |
+
"grad_norm": 2.061025381088257,
|
| 443 |
+
"learning_rate": 8.763020833333335e-06,
|
| 444 |
+
"loss": 5.7322,
|
| 445 |
+
"step": 1450
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 3.606356968215159,
|
| 449 |
+
"grad_norm": 1.7257977724075317,
|
| 450 |
+
"learning_rate": 8.73046875e-06,
|
| 451 |
+
"loss": 5.7322,
|
| 452 |
+
"step": 1475
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.667481662591687,
|
| 456 |
+
"grad_norm": 1.7211699485778809,
|
| 457 |
+
"learning_rate": 8.697916666666667e-06,
|
| 458 |
+
"loss": 5.6969,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.728606356968215,
|
| 463 |
+
"grad_norm": 2.0788753032684326,
|
| 464 |
+
"learning_rate": 8.665364583333334e-06,
|
| 465 |
+
"loss": 5.7322,
|
| 466 |
+
"step": 1525
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 3.7897310513447433,
|
| 470 |
+
"grad_norm": 1.8665424585342407,
|
| 471 |
+
"learning_rate": 8.6328125e-06,
|
| 472 |
+
"loss": 5.7221,
|
| 473 |
+
"step": 1550
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.8508557457212715,
|
| 477 |
+
"grad_norm": 2.3112571239471436,
|
| 478 |
+
"learning_rate": 8.600260416666667e-06,
|
| 479 |
+
"loss": 5.6939,
|
| 480 |
+
"step": 1575
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.9119804400977998,
|
| 484 |
+
"grad_norm": 1.8274345397949219,
|
| 485 |
+
"learning_rate": 8.567708333333334e-06,
|
| 486 |
+
"loss": 5.6866,
|
| 487 |
+
"step": 1600
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 3.9731051344743276,
|
| 491 |
+
"grad_norm": 1.6363919973373413,
|
| 492 |
+
"learning_rate": 8.535156250000001e-06,
|
| 493 |
+
"loss": 5.7078,
|
| 494 |
+
"step": 1625
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.0,
|
| 498 |
+
"eval_cer": 1.0,
|
| 499 |
+
"eval_loss": 5.3543291091918945,
|
| 500 |
+
"eval_runtime": 973.8534,
|
| 501 |
+
"eval_samples_per_second": 2.258,
|
| 502 |
+
"eval_steps_per_second": 0.018,
|
| 503 |
+
"eval_wer": 1.0,
|
| 504 |
+
"step": 1636
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.034229828850855,
|
| 508 |
+
"grad_norm": 1.8639775514602661,
|
| 509 |
+
"learning_rate": 8.502604166666666e-06,
|
| 510 |
+
"loss": 5.684,
|
| 511 |
+
"step": 1650
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.095354523227384,
|
| 515 |
+
"grad_norm": 1.908738613128662,
|
| 516 |
+
"learning_rate": 8.470052083333335e-06,
|
| 517 |
+
"loss": 5.6709,
|
| 518 |
+
"step": 1675
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.156479217603912,
|
| 522 |
+
"grad_norm": 1.785302996635437,
|
| 523 |
+
"learning_rate": 8.4375e-06,
|
| 524 |
+
"loss": 5.6488,
|
| 525 |
+
"step": 1700
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.21760391198044,
|
| 529 |
+
"grad_norm": 2.2629177570343018,
|
| 530 |
+
"learning_rate": 8.404947916666667e-06,
|
| 531 |
+
"loss": 5.6633,
|
| 532 |
+
"step": 1725
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.278728606356968,
|
| 536 |
+
"grad_norm": 2.158043384552002,
|
| 537 |
+
"learning_rate": 8.372395833333334e-06,
|
| 538 |
+
"loss": 5.6558,
|
| 539 |
+
"step": 1750
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.3398533007334965,
|
| 543 |
+
"grad_norm": 2.032712936401367,
|
| 544 |
+
"learning_rate": 8.33984375e-06,
|
| 545 |
+
"loss": 5.661,
|
| 546 |
+
"step": 1775
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.400977995110025,
|
| 550 |
+
"grad_norm": 2.150649070739746,
|
| 551 |
+
"learning_rate": 8.307291666666668e-06,
|
| 552 |
+
"loss": 5.6587,
|
| 553 |
+
"step": 1800
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.462102689486553,
|
| 557 |
+
"grad_norm": 1.866034746170044,
|
| 558 |
+
"learning_rate": 8.274739583333334e-06,
|
| 559 |
+
"loss": 5.6306,
|
| 560 |
+
"step": 1825
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.52322738386308,
|
| 564 |
+
"grad_norm": 2.2522027492523193,
|
| 565 |
+
"learning_rate": 8.242187500000001e-06,
|
| 566 |
+
"loss": 5.6434,
|
| 567 |
+
"step": 1850
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.5843520782396086,
|
| 571 |
+
"grad_norm": 2.266977071762085,
|
| 572 |
+
"learning_rate": 8.209635416666666e-06,
|
| 573 |
+
"loss": 5.6378,
|
| 574 |
+
"step": 1875
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.645476772616137,
|
| 578 |
+
"grad_norm": 2.038745164871216,
|
| 579 |
+
"learning_rate": 8.177083333333335e-06,
|
| 580 |
+
"loss": 5.6404,
|
| 581 |
+
"step": 1900
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.706601466992665,
|
| 585 |
+
"grad_norm": 1.8621001243591309,
|
| 586 |
+
"learning_rate": 8.14453125e-06,
|
| 587 |
+
"loss": 5.651,
|
| 588 |
+
"step": 1925
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.767726161369193,
|
| 592 |
+
"grad_norm": 1.8880043029785156,
|
| 593 |
+
"learning_rate": 8.111979166666667e-06,
|
| 594 |
+
"loss": 5.6317,
|
| 595 |
+
"step": 1950
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 4.8288508557457215,
|
| 599 |
+
"grad_norm": 1.8351385593414307,
|
| 600 |
+
"learning_rate": 8.079427083333334e-06,
|
| 601 |
+
"loss": 5.5911,
|
| 602 |
+
"step": 1975
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.88997555012225,
|
| 606 |
+
"grad_norm": 1.9690709114074707,
|
| 607 |
+
"learning_rate": 8.046875e-06,
|
| 608 |
+
"loss": 5.6174,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.951100244498777,
|
| 613 |
+
"grad_norm": 1.8599187135696411,
|
| 614 |
+
"learning_rate": 8.014322916666668e-06,
|
| 615 |
+
"loss": 5.6252,
|
| 616 |
+
"step": 2025
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 5.0,
|
| 620 |
+
"eval_cer": 1.0,
|
| 621 |
+
"eval_loss": 5.2904744148254395,
|
| 622 |
+
"eval_runtime": 980.786,
|
| 623 |
+
"eval_samples_per_second": 2.242,
|
| 624 |
+
"eval_steps_per_second": 0.018,
|
| 625 |
+
"eval_wer": 1.0,
|
| 626 |
+
"step": 2045
|
| 627 |
+
}
|
| 628 |
+
],
|
| 629 |
+
"logging_steps": 25,
|
| 630 |
+
"max_steps": 8180,
|
| 631 |
+
"num_input_tokens_seen": 0,
|
| 632 |
+
"num_train_epochs": 20,
|
| 633 |
+
"save_steps": 500,
|
| 634 |
+
"stateful_callbacks": {
|
| 635 |
+
"TrainerControl": {
|
| 636 |
+
"args": {
|
| 637 |
+
"should_epoch_stop": false,
|
| 638 |
+
"should_evaluate": false,
|
| 639 |
+
"should_log": false,
|
| 640 |
+
"should_save": true,
|
| 641 |
+
"should_training_stop": false
|
| 642 |
+
},
|
| 643 |
+
"attributes": {}
|
| 644 |
+
}
|
| 645 |
+
},
|
| 646 |
+
"total_flos": 1.6446873526272e+19,
|
| 647 |
+
"train_batch_size": 124,
|
| 648 |
+
"trial_name": null,
|
| 649 |
+
"trial_params": null
|
| 650 |
+
}
|
checkpoint-2045/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f73b80aec597d06b3d2e1eea4b8902092e7ee47b50c6ace8e729e22ced3aeffe
|
| 3 |
+
size 5304
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "DazMashaly/
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "DazMashaly/new_downloads",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 290403936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc48c0adcc1e3b3c0bd007518f406e2619082456c1687e6f499e09a28926a2b2
|
| 3 |
size 290403936
|
runs/Jun25_06-08-05_557d2a8f2caf/events.out.tfevents.1719295686.557d2a8f2caf.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a38e9cab8684672c3cc746d192f713b68066ee08a46ed3f907012f1af7651469
|
| 3 |
+
size 12062
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f73b80aec597d06b3d2e1eea4b8902092e7ee47b50c6ace8e729e22ced3aeffe
|
| 3 |
+
size 5304
|