Upload folder using huggingface_hub
Browse files- checkpoint-200/config.json +47 -0
- checkpoint-200/generation_config.json +175 -0
- checkpoint-200/model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/preprocessor_config.json +15 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scaler.pt +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +113 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-400/config.json +47 -0
- checkpoint-400/generation_config.json +175 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/preprocessor_config.json +15 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/trainer_state.json +192 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-425/config.json +47 -0
- checkpoint-425/generation_config.json +175 -0
- checkpoint-425/model.safetensors +3 -0
- checkpoint-425/optimizer.pt +3 -0
- checkpoint-425/preprocessor_config.json +15 -0
- checkpoint-425/rng_state.pth +3 -0
- checkpoint-425/scaler.pt +3 -0
- checkpoint-425/scheduler.pt +3 -0
- checkpoint-425/trainer_state.json +199 -0
- checkpoint-425/training_args.bin +3 -0
- runs/May01_13-12-38_cffb3ce9e37b/events.out.tfevents.1746105160.cffb3ce9e37b.5237.1 +2 -2
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": null,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_proj_size": 256,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"decoder_attention_heads": 12,
|
| 14 |
+
"decoder_ffn_dim": 3072,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 12,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 12,
|
| 20 |
+
"encoder_ffn_dim": 3072,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 12,
|
| 23 |
+
"eos_token_id": 50257,
|
| 24 |
+
"forced_decoder_ids": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"mask_feature_length": 10,
|
| 28 |
+
"mask_feature_min_masks": 0,
|
| 29 |
+
"mask_feature_prob": 0.0,
|
| 30 |
+
"mask_time_length": 10,
|
| 31 |
+
"mask_time_min_masks": 2,
|
| 32 |
+
"mask_time_prob": 0.05,
|
| 33 |
+
"max_length": null,
|
| 34 |
+
"max_source_positions": 1500,
|
| 35 |
+
"max_target_positions": 448,
|
| 36 |
+
"median_filter_width": 7,
|
| 37 |
+
"model_type": "whisper",
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"num_mel_bins": 80,
|
| 40 |
+
"pad_token_id": 50257,
|
| 41 |
+
"scale_embedding": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_weighted_layer_sum": false,
|
| 46 |
+
"vocab_size": 51865
|
| 47 |
+
}
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"forced_decoder_ids": [
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
null
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
+
2,
|
| 58 |
+
50359
|
| 59 |
+
]
|
| 60 |
+
],
|
| 61 |
+
"is_multilingual": true,
|
| 62 |
+
"lang_to_id": {
|
| 63 |
+
"<|af|>": 50327,
|
| 64 |
+
"<|am|>": 50334,
|
| 65 |
+
"<|ar|>": 50272,
|
| 66 |
+
"<|as|>": 50350,
|
| 67 |
+
"<|az|>": 50304,
|
| 68 |
+
"<|ba|>": 50355,
|
| 69 |
+
"<|be|>": 50330,
|
| 70 |
+
"<|bg|>": 50292,
|
| 71 |
+
"<|bn|>": 50302,
|
| 72 |
+
"<|bo|>": 50347,
|
| 73 |
+
"<|br|>": 50309,
|
| 74 |
+
"<|bs|>": 50315,
|
| 75 |
+
"<|ca|>": 50270,
|
| 76 |
+
"<|cs|>": 50283,
|
| 77 |
+
"<|cy|>": 50297,
|
| 78 |
+
"<|da|>": 50285,
|
| 79 |
+
"<|de|>": 50261,
|
| 80 |
+
"<|el|>": 50281,
|
| 81 |
+
"<|en|>": 50259,
|
| 82 |
+
"<|es|>": 50262,
|
| 83 |
+
"<|et|>": 50307,
|
| 84 |
+
"<|eu|>": 50310,
|
| 85 |
+
"<|fa|>": 50300,
|
| 86 |
+
"<|fi|>": 50277,
|
| 87 |
+
"<|fo|>": 50338,
|
| 88 |
+
"<|fr|>": 50265,
|
| 89 |
+
"<|gl|>": 50319,
|
| 90 |
+
"<|gu|>": 50333,
|
| 91 |
+
"<|haw|>": 50352,
|
| 92 |
+
"<|ha|>": 50354,
|
| 93 |
+
"<|he|>": 50279,
|
| 94 |
+
"<|hi|>": 50276,
|
| 95 |
+
"<|hr|>": 50291,
|
| 96 |
+
"<|ht|>": 50339,
|
| 97 |
+
"<|hu|>": 50286,
|
| 98 |
+
"<|hy|>": 50312,
|
| 99 |
+
"<|id|>": 50275,
|
| 100 |
+
"<|is|>": 50311,
|
| 101 |
+
"<|it|>": 50274,
|
| 102 |
+
"<|ja|>": 50266,
|
| 103 |
+
"<|jw|>": 50356,
|
| 104 |
+
"<|ka|>": 50329,
|
| 105 |
+
"<|kk|>": 50316,
|
| 106 |
+
"<|km|>": 50323,
|
| 107 |
+
"<|kn|>": 50306,
|
| 108 |
+
"<|ko|>": 50264,
|
| 109 |
+
"<|la|>": 50294,
|
| 110 |
+
"<|lb|>": 50345,
|
| 111 |
+
"<|ln|>": 50353,
|
| 112 |
+
"<|lo|>": 50336,
|
| 113 |
+
"<|lt|>": 50293,
|
| 114 |
+
"<|lv|>": 50301,
|
| 115 |
+
"<|mg|>": 50349,
|
| 116 |
+
"<|mi|>": 50295,
|
| 117 |
+
"<|mk|>": 50308,
|
| 118 |
+
"<|ml|>": 50296,
|
| 119 |
+
"<|mn|>": 50314,
|
| 120 |
+
"<|mr|>": 50320,
|
| 121 |
+
"<|ms|>": 50282,
|
| 122 |
+
"<|mt|>": 50343,
|
| 123 |
+
"<|my|>": 50346,
|
| 124 |
+
"<|ne|>": 50313,
|
| 125 |
+
"<|nl|>": 50271,
|
| 126 |
+
"<|nn|>": 50342,
|
| 127 |
+
"<|no|>": 50288,
|
| 128 |
+
"<|oc|>": 50328,
|
| 129 |
+
"<|pa|>": 50321,
|
| 130 |
+
"<|pl|>": 50269,
|
| 131 |
+
"<|ps|>": 50340,
|
| 132 |
+
"<|pt|>": 50267,
|
| 133 |
+
"<|ro|>": 50284,
|
| 134 |
+
"<|ru|>": 50263,
|
| 135 |
+
"<|sa|>": 50344,
|
| 136 |
+
"<|sd|>": 50332,
|
| 137 |
+
"<|si|>": 50322,
|
| 138 |
+
"<|sk|>": 50298,
|
| 139 |
+
"<|sl|>": 50305,
|
| 140 |
+
"<|sn|>": 50324,
|
| 141 |
+
"<|so|>": 50326,
|
| 142 |
+
"<|sq|>": 50317,
|
| 143 |
+
"<|sr|>": 50303,
|
| 144 |
+
"<|su|>": 50357,
|
| 145 |
+
"<|sv|>": 50273,
|
| 146 |
+
"<|sw|>": 50318,
|
| 147 |
+
"<|ta|>": 50287,
|
| 148 |
+
"<|te|>": 50299,
|
| 149 |
+
"<|tg|>": 50331,
|
| 150 |
+
"<|th|>": 50289,
|
| 151 |
+
"<|tk|>": 50341,
|
| 152 |
+
"<|tl|>": 50348,
|
| 153 |
+
"<|tr|>": 50268,
|
| 154 |
+
"<|tt|>": 50351,
|
| 155 |
+
"<|uk|>": 50280,
|
| 156 |
+
"<|ur|>": 50290,
|
| 157 |
+
"<|uz|>": 50337,
|
| 158 |
+
"<|vi|>": 50278,
|
| 159 |
+
"<|yi|>": 50335,
|
| 160 |
+
"<|yo|>": 50325,
|
| 161 |
+
"<|zh|>": 50260
|
| 162 |
+
},
|
| 163 |
+
"max_initial_timestamp_index": 50,
|
| 164 |
+
"max_length": 448,
|
| 165 |
+
"no_timestamps_token_id": 50363,
|
| 166 |
+
"pad_token_id": 50257,
|
| 167 |
+
"prev_sot_token_id": 50361,
|
| 168 |
+
"return_timestamps": false,
|
| 169 |
+
"suppress_tokens": [],
|
| 170 |
+
"task_to_id": {
|
| 171 |
+
"transcribe": 50359,
|
| 172 |
+
"translate": 50358
|
| 173 |
+
},
|
| 174 |
+
"transformers_version": "4.51.3"
|
| 175 |
+
}
|
checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b2892e2e8a768289512d80a4527ba6a28e97b8786cb115dc57ba64fb5dd1b35
|
| 3 |
+
size 966995080
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fee27de3f002951623132d14fb9111b69495b5382d4bd6cfe5b785e99689855
|
| 3 |
+
size 1925064044
|
checkpoint-200/preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92ade350e84ed8edc73f8df3ecb0b81d4efe23f223f59b19ab9f901c5bd3f39f
|
| 3 |
+
size 14244
|
checkpoint-200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:210384cc8aac9b5f42f3d07f3f98c31fe1102ba37532cf4f431d4379f4392fbb
|
| 3 |
+
size 988
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b551e44d36a93f06118444de4d46a48d68025b941ad3f20a21f7cd1e45875cd
|
| 3 |
+
size 1064
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 200,
|
| 3 |
+
"best_metric": 41.783249393769815,
|
| 4 |
+
"best_model_checkpoint": "./JUDIC/checkpoint-200",
|
| 5 |
+
"epoch": 2.3529411764705883,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.23529411764705882,
|
| 14 |
+
"grad_norm": 39.55274200439453,
|
| 15 |
+
"learning_rate": 8.000000000000001e-07,
|
| 16 |
+
"loss": 2.8704,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 16.861303329467773,
|
| 22 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 23 |
+
"loss": 2.4422,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 10.871281623840332,
|
| 29 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 30 |
+
"loss": 1.9044,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 7.858098030090332,
|
| 36 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 37 |
+
"loss": 1.4465,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 7.4879231452941895,
|
| 43 |
+
"learning_rate": 4.800000000000001e-06,
|
| 44 |
+
"loss": 1.3179,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.4117647058823528,
|
| 49 |
+
"grad_norm": 7.5675835609436035,
|
| 50 |
+
"learning_rate": 5.8e-06,
|
| 51 |
+
"loss": 1.0743,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.6470588235294117,
|
| 56 |
+
"grad_norm": 6.898285865783691,
|
| 57 |
+
"learning_rate": 6.800000000000001e-06,
|
| 58 |
+
"loss": 1.0679,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.8823529411764706,
|
| 63 |
+
"grad_norm": 7.592809677124023,
|
| 64 |
+
"learning_rate": 7.800000000000002e-06,
|
| 65 |
+
"loss": 1.0381,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.1176470588235294,
|
| 70 |
+
"grad_norm": 8.085546493530273,
|
| 71 |
+
"learning_rate": 8.8e-06,
|
| 72 |
+
"loss": 0.8211,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.3529411764705883,
|
| 77 |
+
"grad_norm": 5.359922885894775,
|
| 78 |
+
"learning_rate": 9.800000000000001e-06,
|
| 79 |
+
"loss": 0.7182,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.3529411764705883,
|
| 84 |
+
"eval_loss": 0.6759204864501953,
|
| 85 |
+
"eval_runtime": 326.8541,
|
| 86 |
+
"eval_samples_per_second": 2.083,
|
| 87 |
+
"eval_steps_per_second": 0.263,
|
| 88 |
+
"eval_wer": 41.783249393769815,
|
| 89 |
+
"step": 200
|
| 90 |
+
}
|
| 91 |
+
],
|
| 92 |
+
"logging_steps": 20,
|
| 93 |
+
"max_steps": 425,
|
| 94 |
+
"num_input_tokens_seen": 0,
|
| 95 |
+
"num_train_epochs": 5,
|
| 96 |
+
"save_steps": 200,
|
| 97 |
+
"stateful_callbacks": {
|
| 98 |
+
"TrainerControl": {
|
| 99 |
+
"args": {
|
| 100 |
+
"should_epoch_stop": false,
|
| 101 |
+
"should_evaluate": false,
|
| 102 |
+
"should_log": false,
|
| 103 |
+
"should_save": true,
|
| 104 |
+
"should_training_stop": false
|
| 105 |
+
},
|
| 106 |
+
"attributes": {}
|
| 107 |
+
}
|
| 108 |
+
},
|
| 109 |
+
"total_flos": 1.846946562048e+18,
|
| 110 |
+
"train_batch_size": 16,
|
| 111 |
+
"trial_name": null,
|
| 112 |
+
"trial_params": null
|
| 113 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8560064d3c95b83f5ff13cbbf3f02ecfc5b06383d6bc753a071d8b592db8d83
|
| 3 |
+
size 5432
|
checkpoint-400/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": null,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_proj_size": 256,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"decoder_attention_heads": 12,
|
| 14 |
+
"decoder_ffn_dim": 3072,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 12,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 12,
|
| 20 |
+
"encoder_ffn_dim": 3072,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 12,
|
| 23 |
+
"eos_token_id": 50257,
|
| 24 |
+
"forced_decoder_ids": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"mask_feature_length": 10,
|
| 28 |
+
"mask_feature_min_masks": 0,
|
| 29 |
+
"mask_feature_prob": 0.0,
|
| 30 |
+
"mask_time_length": 10,
|
| 31 |
+
"mask_time_min_masks": 2,
|
| 32 |
+
"mask_time_prob": 0.05,
|
| 33 |
+
"max_length": null,
|
| 34 |
+
"max_source_positions": 1500,
|
| 35 |
+
"max_target_positions": 448,
|
| 36 |
+
"median_filter_width": 7,
|
| 37 |
+
"model_type": "whisper",
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"num_mel_bins": 80,
|
| 40 |
+
"pad_token_id": 50257,
|
| 41 |
+
"scale_embedding": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_weighted_layer_sum": false,
|
| 46 |
+
"vocab_size": 51865
|
| 47 |
+
}
|
checkpoint-400/generation_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"forced_decoder_ids": [
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
null
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
+
2,
|
| 58 |
+
50359
|
| 59 |
+
]
|
| 60 |
+
],
|
| 61 |
+
"is_multilingual": true,
|
| 62 |
+
"lang_to_id": {
|
| 63 |
+
"<|af|>": 50327,
|
| 64 |
+
"<|am|>": 50334,
|
| 65 |
+
"<|ar|>": 50272,
|
| 66 |
+
"<|as|>": 50350,
|
| 67 |
+
"<|az|>": 50304,
|
| 68 |
+
"<|ba|>": 50355,
|
| 69 |
+
"<|be|>": 50330,
|
| 70 |
+
"<|bg|>": 50292,
|
| 71 |
+
"<|bn|>": 50302,
|
| 72 |
+
"<|bo|>": 50347,
|
| 73 |
+
"<|br|>": 50309,
|
| 74 |
+
"<|bs|>": 50315,
|
| 75 |
+
"<|ca|>": 50270,
|
| 76 |
+
"<|cs|>": 50283,
|
| 77 |
+
"<|cy|>": 50297,
|
| 78 |
+
"<|da|>": 50285,
|
| 79 |
+
"<|de|>": 50261,
|
| 80 |
+
"<|el|>": 50281,
|
| 81 |
+
"<|en|>": 50259,
|
| 82 |
+
"<|es|>": 50262,
|
| 83 |
+
"<|et|>": 50307,
|
| 84 |
+
"<|eu|>": 50310,
|
| 85 |
+
"<|fa|>": 50300,
|
| 86 |
+
"<|fi|>": 50277,
|
| 87 |
+
"<|fo|>": 50338,
|
| 88 |
+
"<|fr|>": 50265,
|
| 89 |
+
"<|gl|>": 50319,
|
| 90 |
+
"<|gu|>": 50333,
|
| 91 |
+
"<|haw|>": 50352,
|
| 92 |
+
"<|ha|>": 50354,
|
| 93 |
+
"<|he|>": 50279,
|
| 94 |
+
"<|hi|>": 50276,
|
| 95 |
+
"<|hr|>": 50291,
|
| 96 |
+
"<|ht|>": 50339,
|
| 97 |
+
"<|hu|>": 50286,
|
| 98 |
+
"<|hy|>": 50312,
|
| 99 |
+
"<|id|>": 50275,
|
| 100 |
+
"<|is|>": 50311,
|
| 101 |
+
"<|it|>": 50274,
|
| 102 |
+
"<|ja|>": 50266,
|
| 103 |
+
"<|jw|>": 50356,
|
| 104 |
+
"<|ka|>": 50329,
|
| 105 |
+
"<|kk|>": 50316,
|
| 106 |
+
"<|km|>": 50323,
|
| 107 |
+
"<|kn|>": 50306,
|
| 108 |
+
"<|ko|>": 50264,
|
| 109 |
+
"<|la|>": 50294,
|
| 110 |
+
"<|lb|>": 50345,
|
| 111 |
+
"<|ln|>": 50353,
|
| 112 |
+
"<|lo|>": 50336,
|
| 113 |
+
"<|lt|>": 50293,
|
| 114 |
+
"<|lv|>": 50301,
|
| 115 |
+
"<|mg|>": 50349,
|
| 116 |
+
"<|mi|>": 50295,
|
| 117 |
+
"<|mk|>": 50308,
|
| 118 |
+
"<|ml|>": 50296,
|
| 119 |
+
"<|mn|>": 50314,
|
| 120 |
+
"<|mr|>": 50320,
|
| 121 |
+
"<|ms|>": 50282,
|
| 122 |
+
"<|mt|>": 50343,
|
| 123 |
+
"<|my|>": 50346,
|
| 124 |
+
"<|ne|>": 50313,
|
| 125 |
+
"<|nl|>": 50271,
|
| 126 |
+
"<|nn|>": 50342,
|
| 127 |
+
"<|no|>": 50288,
|
| 128 |
+
"<|oc|>": 50328,
|
| 129 |
+
"<|pa|>": 50321,
|
| 130 |
+
"<|pl|>": 50269,
|
| 131 |
+
"<|ps|>": 50340,
|
| 132 |
+
"<|pt|>": 50267,
|
| 133 |
+
"<|ro|>": 50284,
|
| 134 |
+
"<|ru|>": 50263,
|
| 135 |
+
"<|sa|>": 50344,
|
| 136 |
+
"<|sd|>": 50332,
|
| 137 |
+
"<|si|>": 50322,
|
| 138 |
+
"<|sk|>": 50298,
|
| 139 |
+
"<|sl|>": 50305,
|
| 140 |
+
"<|sn|>": 50324,
|
| 141 |
+
"<|so|>": 50326,
|
| 142 |
+
"<|sq|>": 50317,
|
| 143 |
+
"<|sr|>": 50303,
|
| 144 |
+
"<|su|>": 50357,
|
| 145 |
+
"<|sv|>": 50273,
|
| 146 |
+
"<|sw|>": 50318,
|
| 147 |
+
"<|ta|>": 50287,
|
| 148 |
+
"<|te|>": 50299,
|
| 149 |
+
"<|tg|>": 50331,
|
| 150 |
+
"<|th|>": 50289,
|
| 151 |
+
"<|tk|>": 50341,
|
| 152 |
+
"<|tl|>": 50348,
|
| 153 |
+
"<|tr|>": 50268,
|
| 154 |
+
"<|tt|>": 50351,
|
| 155 |
+
"<|uk|>": 50280,
|
| 156 |
+
"<|ur|>": 50290,
|
| 157 |
+
"<|uz|>": 50337,
|
| 158 |
+
"<|vi|>": 50278,
|
| 159 |
+
"<|yi|>": 50335,
|
| 160 |
+
"<|yo|>": 50325,
|
| 161 |
+
"<|zh|>": 50260
|
| 162 |
+
},
|
| 163 |
+
"max_initial_timestamp_index": 50,
|
| 164 |
+
"max_length": 448,
|
| 165 |
+
"no_timestamps_token_id": 50363,
|
| 166 |
+
"pad_token_id": 50257,
|
| 167 |
+
"prev_sot_token_id": 50361,
|
| 168 |
+
"return_timestamps": false,
|
| 169 |
+
"suppress_tokens": [],
|
| 170 |
+
"task_to_id": {
|
| 171 |
+
"transcribe": 50359,
|
| 172 |
+
"translate": 50358
|
| 173 |
+
},
|
| 174 |
+
"transformers_version": "4.51.3"
|
| 175 |
+
}
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ccf6e0b18e00966cc3aa9593f5bc67a572fe68bf2f1c193e3a9f23842ef250c
|
| 3 |
+
size 966995080
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31770e956f5864ecbeb44af1a8424c7ec91ab93053c2e7fc7840ec0c5aa72442
|
| 3 |
+
size 1925064044
|
checkpoint-400/preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3327069f4314534e1155a5e53b9e4445074a676d823a310baf6fdcb1c7c4b00a
|
| 3 |
+
size 14244
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643802dd3517303465f449d0a6e794d1e1488b20ad8fa83264855b4ced649eac
|
| 3 |
+
size 988
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98c75408be126709cd3a95cfde165c89fc584aa0301e5e1c94cc95f4373b1d92
|
| 3 |
+
size 1064
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 400,
|
| 3 |
+
"best_metric": 37.20698874588074,
|
| 4 |
+
"best_model_checkpoint": "./JUDIC/checkpoint-400",
|
| 5 |
+
"epoch": 4.705882352941177,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.23529411764705882,
|
| 14 |
+
"grad_norm": 39.55274200439453,
|
| 15 |
+
"learning_rate": 8.000000000000001e-07,
|
| 16 |
+
"loss": 2.8704,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 16.861303329467773,
|
| 22 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 23 |
+
"loss": 2.4422,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 10.871281623840332,
|
| 29 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 30 |
+
"loss": 1.9044,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 7.858098030090332,
|
| 36 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 37 |
+
"loss": 1.4465,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 7.4879231452941895,
|
| 43 |
+
"learning_rate": 4.800000000000001e-06,
|
| 44 |
+
"loss": 1.3179,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.4117647058823528,
|
| 49 |
+
"grad_norm": 7.5675835609436035,
|
| 50 |
+
"learning_rate": 5.8e-06,
|
| 51 |
+
"loss": 1.0743,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.6470588235294117,
|
| 56 |
+
"grad_norm": 6.898285865783691,
|
| 57 |
+
"learning_rate": 6.800000000000001e-06,
|
| 58 |
+
"loss": 1.0679,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.8823529411764706,
|
| 63 |
+
"grad_norm": 7.592809677124023,
|
| 64 |
+
"learning_rate": 7.800000000000002e-06,
|
| 65 |
+
"loss": 1.0381,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.1176470588235294,
|
| 70 |
+
"grad_norm": 8.085546493530273,
|
| 71 |
+
"learning_rate": 8.8e-06,
|
| 72 |
+
"loss": 0.8211,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.3529411764705883,
|
| 77 |
+
"grad_norm": 5.359922885894775,
|
| 78 |
+
"learning_rate": 9.800000000000001e-06,
|
| 79 |
+
"loss": 0.7182,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.3529411764705883,
|
| 84 |
+
"eval_loss": 0.6759204864501953,
|
| 85 |
+
"eval_runtime": 326.8541,
|
| 86 |
+
"eval_samples_per_second": 2.083,
|
| 87 |
+
"eval_steps_per_second": 0.263,
|
| 88 |
+
"eval_wer": 41.783249393769815,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.588235294117647,
|
| 93 |
+
"grad_norm": 3.346689462661743,
|
| 94 |
+
"learning_rate": 9.28888888888889e-06,
|
| 95 |
+
"loss": 0.7775,
|
| 96 |
+
"step": 220
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.8235294117647056,
|
| 100 |
+
"grad_norm": 4.038958549499512,
|
| 101 |
+
"learning_rate": 8.400000000000001e-06,
|
| 102 |
+
"loss": 0.6748,
|
| 103 |
+
"step": 240
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.0588235294117645,
|
| 107 |
+
"grad_norm": 3.325453758239746,
|
| 108 |
+
"learning_rate": 7.511111111111111e-06,
|
| 109 |
+
"loss": 0.66,
|
| 110 |
+
"step": 260
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.2941176470588234,
|
| 114 |
+
"grad_norm": 3.325045108795166,
|
| 115 |
+
"learning_rate": 6.6222222222222236e-06,
|
| 116 |
+
"loss": 0.5344,
|
| 117 |
+
"step": 280
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.5294117647058822,
|
| 121 |
+
"grad_norm": 3.9428045749664307,
|
| 122 |
+
"learning_rate": 5.733333333333334e-06,
|
| 123 |
+
"loss": 0.5228,
|
| 124 |
+
"step": 300
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.764705882352941,
|
| 128 |
+
"grad_norm": 3.552807092666626,
|
| 129 |
+
"learning_rate": 4.8444444444444446e-06,
|
| 130 |
+
"loss": 0.5771,
|
| 131 |
+
"step": 320
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.0,
|
| 135 |
+
"grad_norm": 4.557582378387451,
|
| 136 |
+
"learning_rate": 3.955555555555556e-06,
|
| 137 |
+
"loss": 0.4784,
|
| 138 |
+
"step": 340
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.235294117647059,
|
| 142 |
+
"grad_norm": 4.543866157531738,
|
| 143 |
+
"learning_rate": 3.066666666666667e-06,
|
| 144 |
+
"loss": 0.4485,
|
| 145 |
+
"step": 360
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.470588235294118,
|
| 149 |
+
"grad_norm": 3.4673140048980713,
|
| 150 |
+
"learning_rate": 2.1777777777777777e-06,
|
| 151 |
+
"loss": 0.4194,
|
| 152 |
+
"step": 380
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.705882352941177,
|
| 156 |
+
"grad_norm": 3.8203773498535156,
|
| 157 |
+
"learning_rate": 1.288888888888889e-06,
|
| 158 |
+
"loss": 0.3985,
|
| 159 |
+
"step": 400
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.705882352941177,
|
| 163 |
+
"eval_loss": 0.44990459084510803,
|
| 164 |
+
"eval_runtime": 307.4758,
|
| 165 |
+
"eval_samples_per_second": 2.215,
|
| 166 |
+
"eval_steps_per_second": 0.28,
|
| 167 |
+
"eval_wer": 37.20698874588074,
|
| 168 |
+
"step": 400
|
| 169 |
+
}
|
| 170 |
+
],
|
| 171 |
+
"logging_steps": 20,
|
| 172 |
+
"max_steps": 425,
|
| 173 |
+
"num_input_tokens_seen": 0,
|
| 174 |
+
"num_train_epochs": 5,
|
| 175 |
+
"save_steps": 200,
|
| 176 |
+
"stateful_callbacks": {
|
| 177 |
+
"TrainerControl": {
|
| 178 |
+
"args": {
|
| 179 |
+
"should_epoch_stop": false,
|
| 180 |
+
"should_evaluate": false,
|
| 181 |
+
"should_log": false,
|
| 182 |
+
"should_save": true,
|
| 183 |
+
"should_training_stop": false
|
| 184 |
+
},
|
| 185 |
+
"attributes": {}
|
| 186 |
+
}
|
| 187 |
+
},
|
| 188 |
+
"total_flos": 3.693893124096e+18,
|
| 189 |
+
"train_batch_size": 16,
|
| 190 |
+
"trial_name": null,
|
| 191 |
+
"trial_params": null
|
| 192 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8560064d3c95b83f5ff13cbbf3f02ecfc5b06383d6bc753a071d8b592db8d83
|
| 3 |
+
size 5432
|
checkpoint-425/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": null,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_proj_size": 256,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"decoder_attention_heads": 12,
|
| 14 |
+
"decoder_ffn_dim": 3072,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 12,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 12,
|
| 20 |
+
"encoder_ffn_dim": 3072,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 12,
|
| 23 |
+
"eos_token_id": 50257,
|
| 24 |
+
"forced_decoder_ids": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"mask_feature_length": 10,
|
| 28 |
+
"mask_feature_min_masks": 0,
|
| 29 |
+
"mask_feature_prob": 0.0,
|
| 30 |
+
"mask_time_length": 10,
|
| 31 |
+
"mask_time_min_masks": 2,
|
| 32 |
+
"mask_time_prob": 0.05,
|
| 33 |
+
"max_length": null,
|
| 34 |
+
"max_source_positions": 1500,
|
| 35 |
+
"max_target_positions": 448,
|
| 36 |
+
"median_filter_width": 7,
|
| 37 |
+
"model_type": "whisper",
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"num_mel_bins": 80,
|
| 40 |
+
"pad_token_id": 50257,
|
| 41 |
+
"scale_embedding": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_weighted_layer_sum": false,
|
| 46 |
+
"vocab_size": 51865
|
| 47 |
+
}
|
checkpoint-425/generation_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"forced_decoder_ids": [
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
null
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
+
2,
|
| 58 |
+
50359
|
| 59 |
+
]
|
| 60 |
+
],
|
| 61 |
+
"is_multilingual": true,
|
| 62 |
+
"lang_to_id": {
|
| 63 |
+
"<|af|>": 50327,
|
| 64 |
+
"<|am|>": 50334,
|
| 65 |
+
"<|ar|>": 50272,
|
| 66 |
+
"<|as|>": 50350,
|
| 67 |
+
"<|az|>": 50304,
|
| 68 |
+
"<|ba|>": 50355,
|
| 69 |
+
"<|be|>": 50330,
|
| 70 |
+
"<|bg|>": 50292,
|
| 71 |
+
"<|bn|>": 50302,
|
| 72 |
+
"<|bo|>": 50347,
|
| 73 |
+
"<|br|>": 50309,
|
| 74 |
+
"<|bs|>": 50315,
|
| 75 |
+
"<|ca|>": 50270,
|
| 76 |
+
"<|cs|>": 50283,
|
| 77 |
+
"<|cy|>": 50297,
|
| 78 |
+
"<|da|>": 50285,
|
| 79 |
+
"<|de|>": 50261,
|
| 80 |
+
"<|el|>": 50281,
|
| 81 |
+
"<|en|>": 50259,
|
| 82 |
+
"<|es|>": 50262,
|
| 83 |
+
"<|et|>": 50307,
|
| 84 |
+
"<|eu|>": 50310,
|
| 85 |
+
"<|fa|>": 50300,
|
| 86 |
+
"<|fi|>": 50277,
|
| 87 |
+
"<|fo|>": 50338,
|
| 88 |
+
"<|fr|>": 50265,
|
| 89 |
+
"<|gl|>": 50319,
|
| 90 |
+
"<|gu|>": 50333,
|
| 91 |
+
"<|haw|>": 50352,
|
| 92 |
+
"<|ha|>": 50354,
|
| 93 |
+
"<|he|>": 50279,
|
| 94 |
+
"<|hi|>": 50276,
|
| 95 |
+
"<|hr|>": 50291,
|
| 96 |
+
"<|ht|>": 50339,
|
| 97 |
+
"<|hu|>": 50286,
|
| 98 |
+
"<|hy|>": 50312,
|
| 99 |
+
"<|id|>": 50275,
|
| 100 |
+
"<|is|>": 50311,
|
| 101 |
+
"<|it|>": 50274,
|
| 102 |
+
"<|ja|>": 50266,
|
| 103 |
+
"<|jw|>": 50356,
|
| 104 |
+
"<|ka|>": 50329,
|
| 105 |
+
"<|kk|>": 50316,
|
| 106 |
+
"<|km|>": 50323,
|
| 107 |
+
"<|kn|>": 50306,
|
| 108 |
+
"<|ko|>": 50264,
|
| 109 |
+
"<|la|>": 50294,
|
| 110 |
+
"<|lb|>": 50345,
|
| 111 |
+
"<|ln|>": 50353,
|
| 112 |
+
"<|lo|>": 50336,
|
| 113 |
+
"<|lt|>": 50293,
|
| 114 |
+
"<|lv|>": 50301,
|
| 115 |
+
"<|mg|>": 50349,
|
| 116 |
+
"<|mi|>": 50295,
|
| 117 |
+
"<|mk|>": 50308,
|
| 118 |
+
"<|ml|>": 50296,
|
| 119 |
+
"<|mn|>": 50314,
|
| 120 |
+
"<|mr|>": 50320,
|
| 121 |
+
"<|ms|>": 50282,
|
| 122 |
+
"<|mt|>": 50343,
|
| 123 |
+
"<|my|>": 50346,
|
| 124 |
+
"<|ne|>": 50313,
|
| 125 |
+
"<|nl|>": 50271,
|
| 126 |
+
"<|nn|>": 50342,
|
| 127 |
+
"<|no|>": 50288,
|
| 128 |
+
"<|oc|>": 50328,
|
| 129 |
+
"<|pa|>": 50321,
|
| 130 |
+
"<|pl|>": 50269,
|
| 131 |
+
"<|ps|>": 50340,
|
| 132 |
+
"<|pt|>": 50267,
|
| 133 |
+
"<|ro|>": 50284,
|
| 134 |
+
"<|ru|>": 50263,
|
| 135 |
+
"<|sa|>": 50344,
|
| 136 |
+
"<|sd|>": 50332,
|
| 137 |
+
"<|si|>": 50322,
|
| 138 |
+
"<|sk|>": 50298,
|
| 139 |
+
"<|sl|>": 50305,
|
| 140 |
+
"<|sn|>": 50324,
|
| 141 |
+
"<|so|>": 50326,
|
| 142 |
+
"<|sq|>": 50317,
|
| 143 |
+
"<|sr|>": 50303,
|
| 144 |
+
"<|su|>": 50357,
|
| 145 |
+
"<|sv|>": 50273,
|
| 146 |
+
"<|sw|>": 50318,
|
| 147 |
+
"<|ta|>": 50287,
|
| 148 |
+
"<|te|>": 50299,
|
| 149 |
+
"<|tg|>": 50331,
|
| 150 |
+
"<|th|>": 50289,
|
| 151 |
+
"<|tk|>": 50341,
|
| 152 |
+
"<|tl|>": 50348,
|
| 153 |
+
"<|tr|>": 50268,
|
| 154 |
+
"<|tt|>": 50351,
|
| 155 |
+
"<|uk|>": 50280,
|
| 156 |
+
"<|ur|>": 50290,
|
| 157 |
+
"<|uz|>": 50337,
|
| 158 |
+
"<|vi|>": 50278,
|
| 159 |
+
"<|yi|>": 50335,
|
| 160 |
+
"<|yo|>": 50325,
|
| 161 |
+
"<|zh|>": 50260
|
| 162 |
+
},
|
| 163 |
+
"max_initial_timestamp_index": 50,
|
| 164 |
+
"max_length": 448,
|
| 165 |
+
"no_timestamps_token_id": 50363,
|
| 166 |
+
"pad_token_id": 50257,
|
| 167 |
+
"prev_sot_token_id": 50361,
|
| 168 |
+
"return_timestamps": false,
|
| 169 |
+
"suppress_tokens": [],
|
| 170 |
+
"task_to_id": {
|
| 171 |
+
"transcribe": 50359,
|
| 172 |
+
"translate": 50358
|
| 173 |
+
},
|
| 174 |
+
"transformers_version": "4.51.3"
|
| 175 |
+
}
|
checkpoint-425/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa0580286b2265f3e3c6fca4171d309f706b3b965875e5ec6b26415a2773d337
|
| 3 |
+
size 966995080
|
checkpoint-425/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c33a446caff0c3f938fb4f078e3ce9835bc7dd1a206d454322d7c157072a2575
|
| 3 |
+
size 1925064044
|
checkpoint-425/preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
checkpoint-425/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c56071df9f6ddfdf7711921b1c1816d748c20bacb6e7781b8852aa85b8e0a48e
|
| 3 |
+
size 14244
|
checkpoint-425/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ffebbfa87d047661b238e4e5058512285e9e08a971a086dfbc78a1c13249fe0
|
| 3 |
+
size 988
|
checkpoint-425/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe9622f19ef82ce503b99901229c61b1c7b372a9080192b99b005bd384022fda
|
| 3 |
+
size 1064
|
checkpoint-425/trainer_state.json
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 400,
|
| 3 |
+
"best_metric": 37.20698874588074,
|
| 4 |
+
"best_model_checkpoint": "./JUDIC/checkpoint-400",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 425,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.23529411764705882,
|
| 14 |
+
"grad_norm": 39.55274200439453,
|
| 15 |
+
"learning_rate": 8.000000000000001e-07,
|
| 16 |
+
"loss": 2.8704,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 16.861303329467773,
|
| 22 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 23 |
+
"loss": 2.4422,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 10.871281623840332,
|
| 29 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 30 |
+
"loss": 1.9044,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 7.858098030090332,
|
| 36 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 37 |
+
"loss": 1.4465,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 7.4879231452941895,
|
| 43 |
+
"learning_rate": 4.800000000000001e-06,
|
| 44 |
+
"loss": 1.3179,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.4117647058823528,
|
| 49 |
+
"grad_norm": 7.5675835609436035,
|
| 50 |
+
"learning_rate": 5.8e-06,
|
| 51 |
+
"loss": 1.0743,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.6470588235294117,
|
| 56 |
+
"grad_norm": 6.898285865783691,
|
| 57 |
+
"learning_rate": 6.800000000000001e-06,
|
| 58 |
+
"loss": 1.0679,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.8823529411764706,
|
| 63 |
+
"grad_norm": 7.592809677124023,
|
| 64 |
+
"learning_rate": 7.800000000000002e-06,
|
| 65 |
+
"loss": 1.0381,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.1176470588235294,
|
| 70 |
+
"grad_norm": 8.085546493530273,
|
| 71 |
+
"learning_rate": 8.8e-06,
|
| 72 |
+
"loss": 0.8211,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.3529411764705883,
|
| 77 |
+
"grad_norm": 5.359922885894775,
|
| 78 |
+
"learning_rate": 9.800000000000001e-06,
|
| 79 |
+
"loss": 0.7182,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.3529411764705883,
|
| 84 |
+
"eval_loss": 0.6759204864501953,
|
| 85 |
+
"eval_runtime": 326.8541,
|
| 86 |
+
"eval_samples_per_second": 2.083,
|
| 87 |
+
"eval_steps_per_second": 0.263,
|
| 88 |
+
"eval_wer": 41.783249393769815,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.588235294117647,
|
| 93 |
+
"grad_norm": 3.346689462661743,
|
| 94 |
+
"learning_rate": 9.28888888888889e-06,
|
| 95 |
+
"loss": 0.7775,
|
| 96 |
+
"step": 220
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.8235294117647056,
|
| 100 |
+
"grad_norm": 4.038958549499512,
|
| 101 |
+
"learning_rate": 8.400000000000001e-06,
|
| 102 |
+
"loss": 0.6748,
|
| 103 |
+
"step": 240
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.0588235294117645,
|
| 107 |
+
"grad_norm": 3.325453758239746,
|
| 108 |
+
"learning_rate": 7.511111111111111e-06,
|
| 109 |
+
"loss": 0.66,
|
| 110 |
+
"step": 260
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.2941176470588234,
|
| 114 |
+
"grad_norm": 3.325045108795166,
|
| 115 |
+
"learning_rate": 6.6222222222222236e-06,
|
| 116 |
+
"loss": 0.5344,
|
| 117 |
+
"step": 280
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.5294117647058822,
|
| 121 |
+
"grad_norm": 3.9428045749664307,
|
| 122 |
+
"learning_rate": 5.733333333333334e-06,
|
| 123 |
+
"loss": 0.5228,
|
| 124 |
+
"step": 300
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.764705882352941,
|
| 128 |
+
"grad_norm": 3.552807092666626,
|
| 129 |
+
"learning_rate": 4.8444444444444446e-06,
|
| 130 |
+
"loss": 0.5771,
|
| 131 |
+
"step": 320
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.0,
|
| 135 |
+
"grad_norm": 4.557582378387451,
|
| 136 |
+
"learning_rate": 3.955555555555556e-06,
|
| 137 |
+
"loss": 0.4784,
|
| 138 |
+
"step": 340
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.235294117647059,
|
| 142 |
+
"grad_norm": 4.543866157531738,
|
| 143 |
+
"learning_rate": 3.066666666666667e-06,
|
| 144 |
+
"loss": 0.4485,
|
| 145 |
+
"step": 360
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.470588235294118,
|
| 149 |
+
"grad_norm": 3.4673140048980713,
|
| 150 |
+
"learning_rate": 2.1777777777777777e-06,
|
| 151 |
+
"loss": 0.4194,
|
| 152 |
+
"step": 380
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.705882352941177,
|
| 156 |
+
"grad_norm": 3.8203773498535156,
|
| 157 |
+
"learning_rate": 1.288888888888889e-06,
|
| 158 |
+
"loss": 0.3985,
|
| 159 |
+
"step": 400
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.705882352941177,
|
| 163 |
+
"eval_loss": 0.44990459084510803,
|
| 164 |
+
"eval_runtime": 307.4758,
|
| 165 |
+
"eval_samples_per_second": 2.215,
|
| 166 |
+
"eval_steps_per_second": 0.28,
|
| 167 |
+
"eval_wer": 37.20698874588074,
|
| 168 |
+
"step": 400
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 4.9411764705882355,
|
| 172 |
+
"grad_norm": 3.171309471130371,
|
| 173 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 174 |
+
"loss": 0.4031,
|
| 175 |
+
"step": 420
|
| 176 |
+
}
|
| 177 |
+
],
|
| 178 |
+
"logging_steps": 20,
|
| 179 |
+
"max_steps": 425,
|
| 180 |
+
"num_input_tokens_seen": 0,
|
| 181 |
+
"num_train_epochs": 5,
|
| 182 |
+
"save_steps": 200,
|
| 183 |
+
"stateful_callbacks": {
|
| 184 |
+
"TrainerControl": {
|
| 185 |
+
"args": {
|
| 186 |
+
"should_epoch_stop": false,
|
| 187 |
+
"should_evaluate": false,
|
| 188 |
+
"should_log": false,
|
| 189 |
+
"should_save": true,
|
| 190 |
+
"should_training_stop": true
|
| 191 |
+
},
|
| 192 |
+
"attributes": {}
|
| 193 |
+
}
|
| 194 |
+
},
|
| 195 |
+
"total_flos": 3.924761444352e+18,
|
| 196 |
+
"train_batch_size": 16,
|
| 197 |
+
"trial_name": null,
|
| 198 |
+
"trial_params": null
|
| 199 |
+
}
|
checkpoint-425/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8560064d3c95b83f5ff13cbbf3f02ecfc5b06383d6bc753a071d8b592db8d83
|
| 3 |
+
size 5432
|
runs/May01_13-12-38_cffb3ce9e37b/events.out.tfevents.1746105160.cffb3ce9e37b.5237.1
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 sha256:7fce9f0379404ebcfadd0f71547ca192f92d282c29cdf235e64fcafa4cd77d92
|
| 3 |
+
size 11138
|