Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-100/config.json +47 -0
- checkpoint-100/generation_config.json +159 -0
- checkpoint-100/model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/preprocessor_config.json +15 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scaler.pt +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +78 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/config.json +47 -0
- checkpoint-200/generation_config.json +159 -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 +122 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/config.json +47 -0
- checkpoint-300/generation_config.json +159 -0
- checkpoint-300/model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/preprocessor_config.json +15 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scaler.pt +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +166 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/config.json +47 -0
- checkpoint-400/generation_config.json +159 -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 +210 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-500/config.json +47 -0
- checkpoint-500/generation_config.json +159 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/preprocessor_config.json +15 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scaler.pt +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +254 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-100/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": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 24,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 24,
|
| 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": 24,
|
| 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-100/generation_config.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [],
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3ebee1bf3b577788f44086b6870c30708ea9f1ba2b0eff15ab61dd6f507f65c
|
| 3 |
+
size 3055544304
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49465fa24f0262b8a7baa3b92f220091bb0737b6d58e7f3ea0b4be472eaaa1c0
|
| 3 |
+
size 6099375168
|
checkpoint-100/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-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206ef3b368b0d1bcf9682fc8a9634f453a8914feef8f3f6431f8b5a6d19ac754
|
| 3 |
+
size 14244
|
checkpoint-100/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58025004ffe541fca138ed57adabef0bd5bed04e11b0203f3296606a56170727
|
| 3 |
+
size 988
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343e706fe1b5301fef8ebce62d0e72a326ba6d161faefaad6659d8f462a7c19d
|
| 3 |
+
size 1064
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 100,
|
| 3 |
+
"best_metric": 74.07821923770442,
|
| 4 |
+
"best_model_checkpoint": "./JUDICM/checkpoint-100",
|
| 5 |
+
"epoch": 1.1764705882352942,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 100,
|
| 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": 9.61864185333252,
|
| 15 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 16 |
+
"loss": 2.9117,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 8.609731674194336,
|
| 22 |
+
"learning_rate": 3.7e-06,
|
| 23 |
+
"loss": 2.0419,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 7.390444278717041,
|
| 29 |
+
"learning_rate": 5.7e-06,
|
| 30 |
+
"loss": 1.5565,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 5.834730625152588,
|
| 36 |
+
"learning_rate": 7.7e-06,
|
| 37 |
+
"loss": 0.9792,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 5.353567123413086,
|
| 43 |
+
"learning_rate": 9.7e-06,
|
| 44 |
+
"loss": 0.8465,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1764705882352942,
|
| 49 |
+
"eval_loss": 0.681628942489624,
|
| 50 |
+
"eval_runtime": 544.1503,
|
| 51 |
+
"eval_samples_per_second": 1.251,
|
| 52 |
+
"eval_steps_per_second": 0.158,
|
| 53 |
+
"eval_wer": 74.07821923770442,
|
| 54 |
+
"step": 100
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"logging_steps": 20,
|
| 58 |
+
"max_steps": 850,
|
| 59 |
+
"num_input_tokens_seen": 0,
|
| 60 |
+
"num_train_epochs": 10,
|
| 61 |
+
"save_steps": 100,
|
| 62 |
+
"stateful_callbacks": {
|
| 63 |
+
"TrainerControl": {
|
| 64 |
+
"args": {
|
| 65 |
+
"should_epoch_stop": false,
|
| 66 |
+
"should_evaluate": false,
|
| 67 |
+
"should_log": false,
|
| 68 |
+
"should_save": true,
|
| 69 |
+
"should_training_stop": false
|
| 70 |
+
},
|
| 71 |
+
"attributes": {}
|
| 72 |
+
}
|
| 73 |
+
},
|
| 74 |
+
"total_flos": 3.265935704064e+18,
|
| 75 |
+
"train_batch_size": 16,
|
| 76 |
+
"trial_name": null,
|
| 77 |
+
"trial_params": null
|
| 78 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
|
| 3 |
+
size 5432
|
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": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 24,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 24,
|
| 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": 24,
|
| 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 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [],
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb80cad6e6c0bd190bad04904e728e365d0cd82e74ca67db627395d7b7b9b6ed
|
| 3 |
+
size 3055544304
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e7dce3c10f367dc9b4b882c82f2048429b26057d19ba5b338942d84cf2723c
|
| 3 |
+
size 6099375168
|
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:bd0f8fdc4bb45d077a8e9acb5eb055f681544897e03e2d5a85f869738dfad064
|
| 3 |
+
size 14244
|
checkpoint-200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098a61a2b2f4e2e2958851a7c9c3c4c247f929913aa62a8e00cca76807496a30
|
| 3 |
+
size 988
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23427674df6bb33784b590ae4aa53899078e927f5e43e1c513019f2bf257b7de
|
| 3 |
+
size 1064
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 200,
|
| 3 |
+
"best_metric": 61.49350245600945,
|
| 4 |
+
"best_model_checkpoint": "./JUDICM/checkpoint-200",
|
| 5 |
+
"epoch": 2.3529411764705883,
|
| 6 |
+
"eval_steps": 100,
|
| 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": 9.61864185333252,
|
| 15 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 16 |
+
"loss": 2.9117,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 8.609731674194336,
|
| 22 |
+
"learning_rate": 3.7e-06,
|
| 23 |
+
"loss": 2.0419,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 7.390444278717041,
|
| 29 |
+
"learning_rate": 5.7e-06,
|
| 30 |
+
"loss": 1.5565,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 5.834730625152588,
|
| 36 |
+
"learning_rate": 7.7e-06,
|
| 37 |
+
"loss": 0.9792,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 5.353567123413086,
|
| 43 |
+
"learning_rate": 9.7e-06,
|
| 44 |
+
"loss": 0.8465,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1764705882352942,
|
| 49 |
+
"eval_loss": 0.681628942489624,
|
| 50 |
+
"eval_runtime": 544.1503,
|
| 51 |
+
"eval_samples_per_second": 1.251,
|
| 52 |
+
"eval_steps_per_second": 0.158,
|
| 53 |
+
"eval_wer": 74.07821923770442,
|
| 54 |
+
"step": 100
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4117647058823528,
|
| 58 |
+
"grad_norm": 4.50194787979126,
|
| 59 |
+
"learning_rate": 9.773333333333335e-06,
|
| 60 |
+
"loss": 0.6137,
|
| 61 |
+
"step": 120
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.6470588235294117,
|
| 65 |
+
"grad_norm": 4.959797382354736,
|
| 66 |
+
"learning_rate": 9.506666666666667e-06,
|
| 67 |
+
"loss": 0.6733,
|
| 68 |
+
"step": 140
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.8823529411764706,
|
| 72 |
+
"grad_norm": 5.115293502807617,
|
| 73 |
+
"learning_rate": 9.240000000000001e-06,
|
| 74 |
+
"loss": 0.7026,
|
| 75 |
+
"step": 160
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.1176470588235294,
|
| 79 |
+
"grad_norm": 3.1620101928710938,
|
| 80 |
+
"learning_rate": 8.973333333333334e-06,
|
| 81 |
+
"loss": 0.5185,
|
| 82 |
+
"step": 180
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.3529411764705883,
|
| 86 |
+
"grad_norm": 4.74745512008667,
|
| 87 |
+
"learning_rate": 8.706666666666667e-06,
|
| 88 |
+
"loss": 0.4669,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.3529411764705883,
|
| 93 |
+
"eval_loss": 0.47813770174980164,
|
| 94 |
+
"eval_runtime": 481.7363,
|
| 95 |
+
"eval_samples_per_second": 1.414,
|
| 96 |
+
"eval_steps_per_second": 0.179,
|
| 97 |
+
"eval_wer": 61.49350245600945,
|
| 98 |
+
"step": 200
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"logging_steps": 20,
|
| 102 |
+
"max_steps": 850,
|
| 103 |
+
"num_input_tokens_seen": 0,
|
| 104 |
+
"num_train_epochs": 10,
|
| 105 |
+
"save_steps": 100,
|
| 106 |
+
"stateful_callbacks": {
|
| 107 |
+
"TrainerControl": {
|
| 108 |
+
"args": {
|
| 109 |
+
"should_epoch_stop": false,
|
| 110 |
+
"should_evaluate": false,
|
| 111 |
+
"should_log": false,
|
| 112 |
+
"should_save": true,
|
| 113 |
+
"should_training_stop": false
|
| 114 |
+
},
|
| 115 |
+
"attributes": {}
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"total_flos": 6.531871408128e+18,
|
| 119 |
+
"train_batch_size": 16,
|
| 120 |
+
"trial_name": null,
|
| 121 |
+
"trial_params": null
|
| 122 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
|
| 3 |
+
size 5432
|
checkpoint-300/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": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 24,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 24,
|
| 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": 24,
|
| 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-300/generation_config.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [],
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497c35a362547e9ba1900b0c03db786a40c943441435bf887d0bb98d248d5318
|
| 3 |
+
size 3055544304
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf6cae18b948017cfeaef4190a0ba7646f69fbe7dad08d634e1a9dbfd937969a
|
| 3 |
+
size 6099375168
|
checkpoint-300/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-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a000fee4dd7a261704c082c4dab084235fdbbde3019d4960d7076ff17338940
|
| 3 |
+
size 14244
|
checkpoint-300/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f3e185550664b35057edb47f034e1766b2ebcedc050e4c0131c34e7d23a38aa
|
| 3 |
+
size 988
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9122dc6585a724b33eebfaf95afd97b180142b91a30efe1fe1ddc84cb2148c14
|
| 3 |
+
size 1064
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 300,
|
| 3 |
+
"best_metric": 56.034321954859166,
|
| 4 |
+
"best_model_checkpoint": "./JUDICM/checkpoint-300",
|
| 5 |
+
"epoch": 3.5294117647058822,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 300,
|
| 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": 9.61864185333252,
|
| 15 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 16 |
+
"loss": 2.9117,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 8.609731674194336,
|
| 22 |
+
"learning_rate": 3.7e-06,
|
| 23 |
+
"loss": 2.0419,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 7.390444278717041,
|
| 29 |
+
"learning_rate": 5.7e-06,
|
| 30 |
+
"loss": 1.5565,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 5.834730625152588,
|
| 36 |
+
"learning_rate": 7.7e-06,
|
| 37 |
+
"loss": 0.9792,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 5.353567123413086,
|
| 43 |
+
"learning_rate": 9.7e-06,
|
| 44 |
+
"loss": 0.8465,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1764705882352942,
|
| 49 |
+
"eval_loss": 0.681628942489624,
|
| 50 |
+
"eval_runtime": 544.1503,
|
| 51 |
+
"eval_samples_per_second": 1.251,
|
| 52 |
+
"eval_steps_per_second": 0.158,
|
| 53 |
+
"eval_wer": 74.07821923770442,
|
| 54 |
+
"step": 100
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4117647058823528,
|
| 58 |
+
"grad_norm": 4.50194787979126,
|
| 59 |
+
"learning_rate": 9.773333333333335e-06,
|
| 60 |
+
"loss": 0.6137,
|
| 61 |
+
"step": 120
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.6470588235294117,
|
| 65 |
+
"grad_norm": 4.959797382354736,
|
| 66 |
+
"learning_rate": 9.506666666666667e-06,
|
| 67 |
+
"loss": 0.6733,
|
| 68 |
+
"step": 140
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.8823529411764706,
|
| 72 |
+
"grad_norm": 5.115293502807617,
|
| 73 |
+
"learning_rate": 9.240000000000001e-06,
|
| 74 |
+
"loss": 0.7026,
|
| 75 |
+
"step": 160
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.1176470588235294,
|
| 79 |
+
"grad_norm": 3.1620101928710938,
|
| 80 |
+
"learning_rate": 8.973333333333334e-06,
|
| 81 |
+
"loss": 0.5185,
|
| 82 |
+
"step": 180
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.3529411764705883,
|
| 86 |
+
"grad_norm": 4.74745512008667,
|
| 87 |
+
"learning_rate": 8.706666666666667e-06,
|
| 88 |
+
"loss": 0.4669,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.3529411764705883,
|
| 93 |
+
"eval_loss": 0.47813770174980164,
|
| 94 |
+
"eval_runtime": 481.7363,
|
| 95 |
+
"eval_samples_per_second": 1.414,
|
| 96 |
+
"eval_steps_per_second": 0.179,
|
| 97 |
+
"eval_wer": 61.49350245600945,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.588235294117647,
|
| 102 |
+
"grad_norm": 3.0848231315612793,
|
| 103 |
+
"learning_rate": 8.44e-06,
|
| 104 |
+
"loss": 0.5316,
|
| 105 |
+
"step": 220
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.8235294117647056,
|
| 109 |
+
"grad_norm": 3.566438674926758,
|
| 110 |
+
"learning_rate": 8.173333333333334e-06,
|
| 111 |
+
"loss": 0.4629,
|
| 112 |
+
"step": 240
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 3.0588235294117645,
|
| 116 |
+
"grad_norm": 2.9106101989746094,
|
| 117 |
+
"learning_rate": 7.906666666666667e-06,
|
| 118 |
+
"loss": 0.4565,
|
| 119 |
+
"step": 260
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.2941176470588234,
|
| 123 |
+
"grad_norm": 3.077847957611084,
|
| 124 |
+
"learning_rate": 7.640000000000001e-06,
|
| 125 |
+
"loss": 0.345,
|
| 126 |
+
"step": 280
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.5294117647058822,
|
| 130 |
+
"grad_norm": 3.5237925052642822,
|
| 131 |
+
"learning_rate": 7.373333333333334e-06,
|
| 132 |
+
"loss": 0.3376,
|
| 133 |
+
"step": 300
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 3.5294117647058822,
|
| 137 |
+
"eval_loss": 0.367522269487381,
|
| 138 |
+
"eval_runtime": 520.1482,
|
| 139 |
+
"eval_samples_per_second": 1.309,
|
| 140 |
+
"eval_steps_per_second": 0.165,
|
| 141 |
+
"eval_wer": 56.034321954859166,
|
| 142 |
+
"step": 300
|
| 143 |
+
}
|
| 144 |
+
],
|
| 145 |
+
"logging_steps": 20,
|
| 146 |
+
"max_steps": 850,
|
| 147 |
+
"num_input_tokens_seen": 0,
|
| 148 |
+
"num_train_epochs": 10,
|
| 149 |
+
"save_steps": 100,
|
| 150 |
+
"stateful_callbacks": {
|
| 151 |
+
"TrainerControl": {
|
| 152 |
+
"args": {
|
| 153 |
+
"should_epoch_stop": false,
|
| 154 |
+
"should_evaluate": false,
|
| 155 |
+
"should_log": false,
|
| 156 |
+
"should_save": true,
|
| 157 |
+
"should_training_stop": false
|
| 158 |
+
},
|
| 159 |
+
"attributes": {}
|
| 160 |
+
}
|
| 161 |
+
},
|
| 162 |
+
"total_flos": 9.797807112192e+18,
|
| 163 |
+
"train_batch_size": 16,
|
| 164 |
+
"trial_name": null,
|
| 165 |
+
"trial_params": null
|
| 166 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
|
| 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": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 24,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 24,
|
| 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": 24,
|
| 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 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [],
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1435db7ec114542dd0a7a7f41264db20faecb13e42bfde4dafbbc58909fdd332
|
| 3 |
+
size 3055544304
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b72a1be90d279a50cee3c99e5fd3d5a2b39107ea27dfc8fb72a3b793281ae3d
|
| 3 |
+
size 6099375168
|
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:f1c93c0d763f2f48be1002eb5f8b1862aafe7a262f77f9e6372efd5930ed91ea
|
| 3 |
+
size 14244
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d411252348daa905c30280db2bbe3da9eb26fb7a099e6886c85784755a895b83
|
| 3 |
+
size 988
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79d838619a5e73d7fb3ccfd45f48dd11a5b5251829dba401a7a2d6341f3b7f2d
|
| 3 |
+
size 1064
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 300,
|
| 3 |
+
"best_metric": 56.034321954859166,
|
| 4 |
+
"best_model_checkpoint": "./JUDICM/checkpoint-300",
|
| 5 |
+
"epoch": 4.705882352941177,
|
| 6 |
+
"eval_steps": 100,
|
| 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": 9.61864185333252,
|
| 15 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 16 |
+
"loss": 2.9117,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 8.609731674194336,
|
| 22 |
+
"learning_rate": 3.7e-06,
|
| 23 |
+
"loss": 2.0419,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 7.390444278717041,
|
| 29 |
+
"learning_rate": 5.7e-06,
|
| 30 |
+
"loss": 1.5565,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 5.834730625152588,
|
| 36 |
+
"learning_rate": 7.7e-06,
|
| 37 |
+
"loss": 0.9792,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 5.353567123413086,
|
| 43 |
+
"learning_rate": 9.7e-06,
|
| 44 |
+
"loss": 0.8465,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1764705882352942,
|
| 49 |
+
"eval_loss": 0.681628942489624,
|
| 50 |
+
"eval_runtime": 544.1503,
|
| 51 |
+
"eval_samples_per_second": 1.251,
|
| 52 |
+
"eval_steps_per_second": 0.158,
|
| 53 |
+
"eval_wer": 74.07821923770442,
|
| 54 |
+
"step": 100
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4117647058823528,
|
| 58 |
+
"grad_norm": 4.50194787979126,
|
| 59 |
+
"learning_rate": 9.773333333333335e-06,
|
| 60 |
+
"loss": 0.6137,
|
| 61 |
+
"step": 120
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.6470588235294117,
|
| 65 |
+
"grad_norm": 4.959797382354736,
|
| 66 |
+
"learning_rate": 9.506666666666667e-06,
|
| 67 |
+
"loss": 0.6733,
|
| 68 |
+
"step": 140
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.8823529411764706,
|
| 72 |
+
"grad_norm": 5.115293502807617,
|
| 73 |
+
"learning_rate": 9.240000000000001e-06,
|
| 74 |
+
"loss": 0.7026,
|
| 75 |
+
"step": 160
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.1176470588235294,
|
| 79 |
+
"grad_norm": 3.1620101928710938,
|
| 80 |
+
"learning_rate": 8.973333333333334e-06,
|
| 81 |
+
"loss": 0.5185,
|
| 82 |
+
"step": 180
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.3529411764705883,
|
| 86 |
+
"grad_norm": 4.74745512008667,
|
| 87 |
+
"learning_rate": 8.706666666666667e-06,
|
| 88 |
+
"loss": 0.4669,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.3529411764705883,
|
| 93 |
+
"eval_loss": 0.47813770174980164,
|
| 94 |
+
"eval_runtime": 481.7363,
|
| 95 |
+
"eval_samples_per_second": 1.414,
|
| 96 |
+
"eval_steps_per_second": 0.179,
|
| 97 |
+
"eval_wer": 61.49350245600945,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.588235294117647,
|
| 102 |
+
"grad_norm": 3.0848231315612793,
|
| 103 |
+
"learning_rate": 8.44e-06,
|
| 104 |
+
"loss": 0.5316,
|
| 105 |
+
"step": 220
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.8235294117647056,
|
| 109 |
+
"grad_norm": 3.566438674926758,
|
| 110 |
+
"learning_rate": 8.173333333333334e-06,
|
| 111 |
+
"loss": 0.4629,
|
| 112 |
+
"step": 240
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 3.0588235294117645,
|
| 116 |
+
"grad_norm": 2.9106101989746094,
|
| 117 |
+
"learning_rate": 7.906666666666667e-06,
|
| 118 |
+
"loss": 0.4565,
|
| 119 |
+
"step": 260
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.2941176470588234,
|
| 123 |
+
"grad_norm": 3.077847957611084,
|
| 124 |
+
"learning_rate": 7.640000000000001e-06,
|
| 125 |
+
"loss": 0.345,
|
| 126 |
+
"step": 280
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.5294117647058822,
|
| 130 |
+
"grad_norm": 3.5237925052642822,
|
| 131 |
+
"learning_rate": 7.373333333333334e-06,
|
| 132 |
+
"loss": 0.3376,
|
| 133 |
+
"step": 300
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 3.5294117647058822,
|
| 137 |
+
"eval_loss": 0.367522269487381,
|
| 138 |
+
"eval_runtime": 520.1482,
|
| 139 |
+
"eval_samples_per_second": 1.309,
|
| 140 |
+
"eval_steps_per_second": 0.165,
|
| 141 |
+
"eval_wer": 56.034321954859166,
|
| 142 |
+
"step": 300
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.764705882352941,
|
| 146 |
+
"grad_norm": 3.1221227645874023,
|
| 147 |
+
"learning_rate": 7.1066666666666675e-06,
|
| 148 |
+
"loss": 0.3879,
|
| 149 |
+
"step": 320
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"grad_norm": 3.873680353164673,
|
| 154 |
+
"learning_rate": 6.8400000000000014e-06,
|
| 155 |
+
"loss": 0.3156,
|
| 156 |
+
"step": 340
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.235294117647059,
|
| 160 |
+
"grad_norm": 5.0606160163879395,
|
| 161 |
+
"learning_rate": 6.573333333333334e-06,
|
| 162 |
+
"loss": 0.243,
|
| 163 |
+
"step": 360
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.470588235294118,
|
| 167 |
+
"grad_norm": 2.9561641216278076,
|
| 168 |
+
"learning_rate": 6.3066666666666676e-06,
|
| 169 |
+
"loss": 0.2344,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.705882352941177,
|
| 174 |
+
"grad_norm": 3.9523017406463623,
|
| 175 |
+
"learning_rate": 6.040000000000001e-06,
|
| 176 |
+
"loss": 0.2195,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.705882352941177,
|
| 181 |
+
"eval_loss": 0.2805194854736328,
|
| 182 |
+
"eval_runtime": 475.2131,
|
| 183 |
+
"eval_samples_per_second": 1.433,
|
| 184 |
+
"eval_steps_per_second": 0.181,
|
| 185 |
+
"eval_wer": 58.521420133059756,
|
| 186 |
+
"step": 400
|
| 187 |
+
}
|
| 188 |
+
],
|
| 189 |
+
"logging_steps": 20,
|
| 190 |
+
"max_steps": 850,
|
| 191 |
+
"num_input_tokens_seen": 0,
|
| 192 |
+
"num_train_epochs": 10,
|
| 193 |
+
"save_steps": 100,
|
| 194 |
+
"stateful_callbacks": {
|
| 195 |
+
"TrainerControl": {
|
| 196 |
+
"args": {
|
| 197 |
+
"should_epoch_stop": false,
|
| 198 |
+
"should_evaluate": false,
|
| 199 |
+
"should_log": false,
|
| 200 |
+
"should_save": true,
|
| 201 |
+
"should_training_stop": false
|
| 202 |
+
},
|
| 203 |
+
"attributes": {}
|
| 204 |
+
}
|
| 205 |
+
},
|
| 206 |
+
"total_flos": 1.3063742816256e+19,
|
| 207 |
+
"train_batch_size": 16,
|
| 208 |
+
"trial_name": null,
|
| 209 |
+
"trial_params": null
|
| 210 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
|
| 3 |
+
size 5432
|
checkpoint-500/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": 1024,
|
| 13 |
+
"decoder_attention_heads": 16,
|
| 14 |
+
"decoder_ffn_dim": 4096,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 24,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 24,
|
| 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": 24,
|
| 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-500/generation_config.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [],
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ffb1025b60d7771f0d45de3868862f7fa639d5b01995833309266409f45e7de
|
| 3 |
+
size 3055544304
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff7763bb0d44779104cc405fe7784b084baf7d3d20107a73feb3b806fbe7cb2a
|
| 3 |
+
size 6099375168
|
checkpoint-500/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-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a341708b6cf11886bf8cc26bc3c6f36ad48ca33355cdd25d71b56ab641b962d4
|
| 3 |
+
size 14244
|
checkpoint-500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dd0f2027b6dff8c9abeb7ff05269dab276fdd046a75d4d2cde10cb2835f2470
|
| 3 |
+
size 988
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e37d0e3abe4f26a67104e2dc03695cbf6a36428ae4534496e8677a64b279559
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,254 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 300,
|
| 3 |
+
"best_metric": 56.034321954859166,
|
| 4 |
+
"best_model_checkpoint": "./JUDICM/checkpoint-300",
|
| 5 |
+
"epoch": 5.882352941176471,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 500,
|
| 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": 9.61864185333252,
|
| 15 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 16 |
+
"loss": 2.9117,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.47058823529411764,
|
| 21 |
+
"grad_norm": 8.609731674194336,
|
| 22 |
+
"learning_rate": 3.7e-06,
|
| 23 |
+
"loss": 2.0419,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7058823529411765,
|
| 28 |
+
"grad_norm": 7.390444278717041,
|
| 29 |
+
"learning_rate": 5.7e-06,
|
| 30 |
+
"loss": 1.5565,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.9411764705882353,
|
| 35 |
+
"grad_norm": 5.834730625152588,
|
| 36 |
+
"learning_rate": 7.7e-06,
|
| 37 |
+
"loss": 0.9792,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.1764705882352942,
|
| 42 |
+
"grad_norm": 5.353567123413086,
|
| 43 |
+
"learning_rate": 9.7e-06,
|
| 44 |
+
"loss": 0.8465,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1764705882352942,
|
| 49 |
+
"eval_loss": 0.681628942489624,
|
| 50 |
+
"eval_runtime": 544.1503,
|
| 51 |
+
"eval_samples_per_second": 1.251,
|
| 52 |
+
"eval_steps_per_second": 0.158,
|
| 53 |
+
"eval_wer": 74.07821923770442,
|
| 54 |
+
"step": 100
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4117647058823528,
|
| 58 |
+
"grad_norm": 4.50194787979126,
|
| 59 |
+
"learning_rate": 9.773333333333335e-06,
|
| 60 |
+
"loss": 0.6137,
|
| 61 |
+
"step": 120
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.6470588235294117,
|
| 65 |
+
"grad_norm": 4.959797382354736,
|
| 66 |
+
"learning_rate": 9.506666666666667e-06,
|
| 67 |
+
"loss": 0.6733,
|
| 68 |
+
"step": 140
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.8823529411764706,
|
| 72 |
+
"grad_norm": 5.115293502807617,
|
| 73 |
+
"learning_rate": 9.240000000000001e-06,
|
| 74 |
+
"loss": 0.7026,
|
| 75 |
+
"step": 160
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.1176470588235294,
|
| 79 |
+
"grad_norm": 3.1620101928710938,
|
| 80 |
+
"learning_rate": 8.973333333333334e-06,
|
| 81 |
+
"loss": 0.5185,
|
| 82 |
+
"step": 180
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.3529411764705883,
|
| 86 |
+
"grad_norm": 4.74745512008667,
|
| 87 |
+
"learning_rate": 8.706666666666667e-06,
|
| 88 |
+
"loss": 0.4669,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.3529411764705883,
|
| 93 |
+
"eval_loss": 0.47813770174980164,
|
| 94 |
+
"eval_runtime": 481.7363,
|
| 95 |
+
"eval_samples_per_second": 1.414,
|
| 96 |
+
"eval_steps_per_second": 0.179,
|
| 97 |
+
"eval_wer": 61.49350245600945,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.588235294117647,
|
| 102 |
+
"grad_norm": 3.0848231315612793,
|
| 103 |
+
"learning_rate": 8.44e-06,
|
| 104 |
+
"loss": 0.5316,
|
| 105 |
+
"step": 220
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.8235294117647056,
|
| 109 |
+
"grad_norm": 3.566438674926758,
|
| 110 |
+
"learning_rate": 8.173333333333334e-06,
|
| 111 |
+
"loss": 0.4629,
|
| 112 |
+
"step": 240
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 3.0588235294117645,
|
| 116 |
+
"grad_norm": 2.9106101989746094,
|
| 117 |
+
"learning_rate": 7.906666666666667e-06,
|
| 118 |
+
"loss": 0.4565,
|
| 119 |
+
"step": 260
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.2941176470588234,
|
| 123 |
+
"grad_norm": 3.077847957611084,
|
| 124 |
+
"learning_rate": 7.640000000000001e-06,
|
| 125 |
+
"loss": 0.345,
|
| 126 |
+
"step": 280
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.5294117647058822,
|
| 130 |
+
"grad_norm": 3.5237925052642822,
|
| 131 |
+
"learning_rate": 7.373333333333334e-06,
|
| 132 |
+
"loss": 0.3376,
|
| 133 |
+
"step": 300
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 3.5294117647058822,
|
| 137 |
+
"eval_loss": 0.367522269487381,
|
| 138 |
+
"eval_runtime": 520.1482,
|
| 139 |
+
"eval_samples_per_second": 1.309,
|
| 140 |
+
"eval_steps_per_second": 0.165,
|
| 141 |
+
"eval_wer": 56.034321954859166,
|
| 142 |
+
"step": 300
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.764705882352941,
|
| 146 |
+
"grad_norm": 3.1221227645874023,
|
| 147 |
+
"learning_rate": 7.1066666666666675e-06,
|
| 148 |
+
"loss": 0.3879,
|
| 149 |
+
"step": 320
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"grad_norm": 3.873680353164673,
|
| 154 |
+
"learning_rate": 6.8400000000000014e-06,
|
| 155 |
+
"loss": 0.3156,
|
| 156 |
+
"step": 340
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.235294117647059,
|
| 160 |
+
"grad_norm": 5.0606160163879395,
|
| 161 |
+
"learning_rate": 6.573333333333334e-06,
|
| 162 |
+
"loss": 0.243,
|
| 163 |
+
"step": 360
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.470588235294118,
|
| 167 |
+
"grad_norm": 2.9561641216278076,
|
| 168 |
+
"learning_rate": 6.3066666666666676e-06,
|
| 169 |
+
"loss": 0.2344,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.705882352941177,
|
| 174 |
+
"grad_norm": 3.9523017406463623,
|
| 175 |
+
"learning_rate": 6.040000000000001e-06,
|
| 176 |
+
"loss": 0.2195,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.705882352941177,
|
| 181 |
+
"eval_loss": 0.2805194854736328,
|
| 182 |
+
"eval_runtime": 475.2131,
|
| 183 |
+
"eval_samples_per_second": 1.433,
|
| 184 |
+
"eval_steps_per_second": 0.181,
|
| 185 |
+
"eval_wer": 58.521420133059756,
|
| 186 |
+
"step": 400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 4.9411764705882355,
|
| 190 |
+
"grad_norm": 3.081202983856201,
|
| 191 |
+
"learning_rate": 5.7733333333333345e-06,
|
| 192 |
+
"loss": 0.2079,
|
| 193 |
+
"step": 420
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 5.176470588235294,
|
| 197 |
+
"grad_norm": 3.1263742446899414,
|
| 198 |
+
"learning_rate": 5.506666666666667e-06,
|
| 199 |
+
"loss": 0.1388,
|
| 200 |
+
"step": 440
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.411764705882353,
|
| 204 |
+
"grad_norm": 3.4922068119049072,
|
| 205 |
+
"learning_rate": 5.240000000000001e-06,
|
| 206 |
+
"loss": 0.1538,
|
| 207 |
+
"step": 460
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 5.647058823529412,
|
| 211 |
+
"grad_norm": 5.9641594886779785,
|
| 212 |
+
"learning_rate": 4.973333333333334e-06,
|
| 213 |
+
"loss": 0.1697,
|
| 214 |
+
"step": 480
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 5.882352941176471,
|
| 218 |
+
"grad_norm": 4.860027313232422,
|
| 219 |
+
"learning_rate": 4.706666666666667e-06,
|
| 220 |
+
"loss": 0.1284,
|
| 221 |
+
"step": 500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 5.882352941176471,
|
| 225 |
+
"eval_loss": 0.2389652281999588,
|
| 226 |
+
"eval_runtime": 524.8677,
|
| 227 |
+
"eval_samples_per_second": 1.297,
|
| 228 |
+
"eval_steps_per_second": 0.164,
|
| 229 |
+
"eval_wer": 59.46651744077598,
|
| 230 |
+
"step": 500
|
| 231 |
+
}
|
| 232 |
+
],
|
| 233 |
+
"logging_steps": 20,
|
| 234 |
+
"max_steps": 850,
|
| 235 |
+
"num_input_tokens_seen": 0,
|
| 236 |
+
"num_train_epochs": 10,
|
| 237 |
+
"save_steps": 100,
|
| 238 |
+
"stateful_callbacks": {
|
| 239 |
+
"TrainerControl": {
|
| 240 |
+
"args": {
|
| 241 |
+
"should_epoch_stop": false,
|
| 242 |
+
"should_evaluate": false,
|
| 243 |
+
"should_log": false,
|
| 244 |
+
"should_save": true,
|
| 245 |
+
"should_training_stop": false
|
| 246 |
+
},
|
| 247 |
+
"attributes": {}
|
| 248 |
+
}
|
| 249 |
+
},
|
| 250 |
+
"total_flos": 1.632967852032e+19,
|
| 251 |
+
"train_batch_size": 16,
|
| 252 |
+
"trial_name": null,
|
| 253 |
+
"trial_params": null
|
| 254 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8e554359844a47beb0c3912e9ae5b5d61f25f66591ae725d42fef0a8dfec8c1
|
| 3 |
+
size 5432
|