Upload 9 files
Browse filesUploading the best performing checkpoint - after 1000 steps
- config.json +52 -0
- generation_config.json +192 -0
- optimizer.pt +3 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +97 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small.en",
|
| 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 |
+
50256
|
| 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": 50257,
|
| 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": 50256,
|
| 28 |
+
"forced_decoder_ids": null,
|
| 29 |
+
"init_std": 0.02,
|
| 30 |
+
"is_encoder_decoder": true,
|
| 31 |
+
"mask_feature_length": 10,
|
| 32 |
+
"mask_feature_min_masks": 0,
|
| 33 |
+
"mask_feature_prob": 0.0,
|
| 34 |
+
"mask_time_length": 10,
|
| 35 |
+
"mask_time_min_masks": 2,
|
| 36 |
+
"mask_time_prob": 0.05,
|
| 37 |
+
"max_length": 448,
|
| 38 |
+
"max_source_positions": 1500,
|
| 39 |
+
"max_target_positions": 448,
|
| 40 |
+
"median_filter_width": 7,
|
| 41 |
+
"model_type": "whisper",
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"num_mel_bins": 80,
|
| 44 |
+
"pad_token_id": 50256,
|
| 45 |
+
"scale_embedding": false,
|
| 46 |
+
"suppress_tokens": [],
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.32.1",
|
| 49 |
+
"use_cache": false,
|
| 50 |
+
"use_weighted_layer_sum": false,
|
| 51 |
+
"vocab_size": 51864
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
6,
|
| 5 |
+
6
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
7,
|
| 9 |
+
0
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
7,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
7,
|
| 17 |
+
8
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
8,
|
| 21 |
+
2
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
8,
|
| 25 |
+
5
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
8,
|
| 29 |
+
7
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
9,
|
| 33 |
+
0
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
9,
|
| 37 |
+
4
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
9,
|
| 41 |
+
8
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
9,
|
| 45 |
+
10
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
10,
|
| 49 |
+
0
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
10,
|
| 53 |
+
1
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
10,
|
| 57 |
+
2
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
10,
|
| 61 |
+
3
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
10,
|
| 65 |
+
6
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
10,
|
| 69 |
+
11
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
11,
|
| 73 |
+
2
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
11,
|
| 77 |
+
4
|
| 78 |
+
]
|
| 79 |
+
],
|
| 80 |
+
"begin_suppress_tokens": [
|
| 81 |
+
220,
|
| 82 |
+
50256
|
| 83 |
+
],
|
| 84 |
+
"bos_token_id": 50257,
|
| 85 |
+
"decoder_start_token_id": 50257,
|
| 86 |
+
"eos_token_id": 50256,
|
| 87 |
+
"forced_decoder_ids": [
|
| 88 |
+
[
|
| 89 |
+
1,
|
| 90 |
+
50362
|
| 91 |
+
]
|
| 92 |
+
],
|
| 93 |
+
"is_multilingual": false,
|
| 94 |
+
"max_initial_timestamp_index": 1,
|
| 95 |
+
"max_length": 448,
|
| 96 |
+
"no_timestamps_token_id": 50362,
|
| 97 |
+
"pad_token_id": 50256,
|
| 98 |
+
"return_timestamps": false,
|
| 99 |
+
"suppress_tokens": [
|
| 100 |
+
1,
|
| 101 |
+
2,
|
| 102 |
+
7,
|
| 103 |
+
8,
|
| 104 |
+
9,
|
| 105 |
+
10,
|
| 106 |
+
14,
|
| 107 |
+
25,
|
| 108 |
+
26,
|
| 109 |
+
27,
|
| 110 |
+
28,
|
| 111 |
+
29,
|
| 112 |
+
31,
|
| 113 |
+
58,
|
| 114 |
+
59,
|
| 115 |
+
60,
|
| 116 |
+
61,
|
| 117 |
+
62,
|
| 118 |
+
63,
|
| 119 |
+
90,
|
| 120 |
+
91,
|
| 121 |
+
92,
|
| 122 |
+
93,
|
| 123 |
+
357,
|
| 124 |
+
366,
|
| 125 |
+
438,
|
| 126 |
+
532,
|
| 127 |
+
685,
|
| 128 |
+
705,
|
| 129 |
+
796,
|
| 130 |
+
930,
|
| 131 |
+
1058,
|
| 132 |
+
1220,
|
| 133 |
+
1267,
|
| 134 |
+
1279,
|
| 135 |
+
1303,
|
| 136 |
+
1343,
|
| 137 |
+
1377,
|
| 138 |
+
1391,
|
| 139 |
+
1635,
|
| 140 |
+
1782,
|
| 141 |
+
1875,
|
| 142 |
+
2162,
|
| 143 |
+
2361,
|
| 144 |
+
2488,
|
| 145 |
+
3467,
|
| 146 |
+
4008,
|
| 147 |
+
4211,
|
| 148 |
+
4600,
|
| 149 |
+
4808,
|
| 150 |
+
5299,
|
| 151 |
+
5855,
|
| 152 |
+
6329,
|
| 153 |
+
7203,
|
| 154 |
+
9609,
|
| 155 |
+
9959,
|
| 156 |
+
10563,
|
| 157 |
+
10786,
|
| 158 |
+
11420,
|
| 159 |
+
11709,
|
| 160 |
+
11907,
|
| 161 |
+
13163,
|
| 162 |
+
13697,
|
| 163 |
+
13700,
|
| 164 |
+
14808,
|
| 165 |
+
15306,
|
| 166 |
+
16410,
|
| 167 |
+
16791,
|
| 168 |
+
17992,
|
| 169 |
+
19203,
|
| 170 |
+
19510,
|
| 171 |
+
20724,
|
| 172 |
+
22305,
|
| 173 |
+
22935,
|
| 174 |
+
27007,
|
| 175 |
+
30109,
|
| 176 |
+
30420,
|
| 177 |
+
33409,
|
| 178 |
+
34949,
|
| 179 |
+
40283,
|
| 180 |
+
40493,
|
| 181 |
+
40549,
|
| 182 |
+
47282,
|
| 183 |
+
49146,
|
| 184 |
+
50257,
|
| 185 |
+
50357,
|
| 186 |
+
50358,
|
| 187 |
+
50359,
|
| 188 |
+
50360,
|
| 189 |
+
50361
|
| 190 |
+
],
|
| 191 |
+
"transformers_version": "4.32.1"
|
| 192 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44b7cf7354db7162afd07c305d3f5665950a5253160e86ac1d36e67bcceacf52
|
| 3 |
+
size 1934274298
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
+
"feature_size": 80,
|
| 5 |
+
"hop_length": 160,
|
| 6 |
+
"n_fft": 400,
|
| 7 |
+
"n_samples": 480000,
|
| 8 |
+
"nb_max_frames": 3000,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"padding_value": 0.0,
|
| 11 |
+
"processor_class": "WhisperProcessor",
|
| 12 |
+
"return_attention_mask": false,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58515da7fa6bc50fc2633af1cd7d840f1493f38366c6626ab23aaf75b9c261aa
|
| 3 |
+
size 967099657
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee9453d879144260ca40e3cf2f6584e6740a68d1b433953f5d5afba4db36af9
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3d860e7c43a252b8f2511effef76259d509b67e4328bc8beb563c2ae48ef1b5
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 8.508066331024994,
|
| 3 |
+
"best_model_checkpoint": "./fine-tuned-whisper/openai/whisper-small.en/lr_1e-05_warmup_500_epochs_0_batch_64_grad_acc_1_max_steps_10000/dataset_myst/2023-09-02_21-54-45/checkpoint-1000",
|
| 4 |
+
"epoch": 3.194888178913738,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"learning_rate": 1.9600000000000003e-06,
|
| 14 |
+
"loss": 1.5656,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 3.96e-06,
|
| 20 |
+
"loss": 0.7581,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 5.9600000000000005e-06,
|
| 26 |
+
"loss": 0.5573,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.28,
|
| 31 |
+
"learning_rate": 7.960000000000002e-06,
|
| 32 |
+
"loss": 0.4219,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.6,
|
| 37 |
+
"learning_rate": 9.960000000000001e-06,
|
| 38 |
+
"loss": 0.4093,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.6,
|
| 43 |
+
"eval_loss": 0.25834476947784424,
|
| 44 |
+
"eval_runtime": 526.7286,
|
| 45 |
+
"eval_samples_per_second": 5.999,
|
| 46 |
+
"eval_steps_per_second": 0.188,
|
| 47 |
+
"eval_wer": 8.59808517068215,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.92,
|
| 52 |
+
"learning_rate": 9.89684210526316e-06,
|
| 53 |
+
"loss": 0.4065,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.24,
|
| 58 |
+
"learning_rate": 9.791578947368422e-06,
|
| 59 |
+
"loss": 0.3522,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.56,
|
| 64 |
+
"learning_rate": 9.686315789473684e-06,
|
| 65 |
+
"loss": 0.3314,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.88,
|
| 70 |
+
"learning_rate": 9.581052631578947e-06,
|
| 71 |
+
"loss": 0.3269,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.19,
|
| 76 |
+
"learning_rate": 9.475789473684212e-06,
|
| 77 |
+
"loss": 0.286,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.19,
|
| 82 |
+
"eval_loss": 0.26971688866615295,
|
| 83 |
+
"eval_runtime": 523.4232,
|
| 84 |
+
"eval_samples_per_second": 6.037,
|
| 85 |
+
"eval_steps_per_second": 0.189,
|
| 86 |
+
"eval_wer": 8.508066331024994,
|
| 87 |
+
"step": 1000
|
| 88 |
+
}
|
| 89 |
+
],
|
| 90 |
+
"logging_steps": 100,
|
| 91 |
+
"max_steps": 10000,
|
| 92 |
+
"num_train_epochs": 32,
|
| 93 |
+
"save_steps": 500,
|
| 94 |
+
"total_flos": 1.84305065914368e+19,
|
| 95 |
+
"trial_name": null,
|
| 96 |
+
"trial_params": null
|
| 97 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d744b7523c8bc1cf72d71ac4227656fd4daeb821393753bf2e14cb217064cdb
|
| 3 |
+
size 4411
|