Upload folder using huggingface_hub
Browse files- config.json +109 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +9 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +213 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-1b",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 1024,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1280,
|
| 60 |
+
"initializer_range": 0.02,
|
| 61 |
+
"intermediate_size": 5120,
|
| 62 |
+
"layer_norm_eps": 1e-05,
|
| 63 |
+
"layerdrop": 0.1,
|
| 64 |
+
"mask_feature_length": 10,
|
| 65 |
+
"mask_feature_min_masks": 0,
|
| 66 |
+
"mask_feature_prob": 0.0,
|
| 67 |
+
"mask_time_length": 10,
|
| 68 |
+
"mask_time_min_masks": 2,
|
| 69 |
+
"mask_time_prob": 0.075,
|
| 70 |
+
"model_type": "wav2vec2",
|
| 71 |
+
"num_adapter_layers": 3,
|
| 72 |
+
"num_attention_heads": 16,
|
| 73 |
+
"num_codevector_groups": 2,
|
| 74 |
+
"num_codevectors_per_group": 320,
|
| 75 |
+
"num_conv_pos_embedding_groups": 16,
|
| 76 |
+
"num_conv_pos_embeddings": 128,
|
| 77 |
+
"num_feat_extract_layers": 7,
|
| 78 |
+
"num_hidden_layers": 48,
|
| 79 |
+
"num_negatives": 100,
|
| 80 |
+
"output_hidden_size": 1280,
|
| 81 |
+
"pad_token_id": 42,
|
| 82 |
+
"proj_codevector_dim": 1024,
|
| 83 |
+
"tdnn_dilation": [
|
| 84 |
+
1,
|
| 85 |
+
2,
|
| 86 |
+
3,
|
| 87 |
+
1,
|
| 88 |
+
1
|
| 89 |
+
],
|
| 90 |
+
"tdnn_dim": [
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
512,
|
| 95 |
+
1500
|
| 96 |
+
],
|
| 97 |
+
"tdnn_kernel": [
|
| 98 |
+
5,
|
| 99 |
+
3,
|
| 100 |
+
3,
|
| 101 |
+
1,
|
| 102 |
+
1
|
| 103 |
+
],
|
| 104 |
+
"torch_dtype": "float32",
|
| 105 |
+
"transformers_version": "4.39.3",
|
| 106 |
+
"use_weighted_layer_sum": false,
|
| 107 |
+
"vocab_size": 64,
|
| 108 |
+
"xvector_output_dim": 512
|
| 109 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98b5351d1c47878fce2ad2e0bc59debe3426c9b85877afc025ca3e9701f7f37d
|
| 3 |
+
size 3850418936
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d3a60d01b455629a1995c3c561bca7253aa20d0799c4b29988b03ac23c443a7
|
| 3 |
+
size 7667614690
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae2f37179b86cb15a864fd9a45b7ce57f632f1e336a9d02cc3f0b1070560b9b0
|
| 3 |
+
size 14308
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59aa2dbd53827a3d48120301c0684ae98deb83b3a662828bb8005dd44b824861
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 48.87983706720978,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 4.07,
|
| 13 |
+
"grad_norm": 3.8863396644592285,
|
| 14 |
+
"learning_rate": 3.936e-05,
|
| 15 |
+
"loss": 3.9012,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 4.07,
|
| 20 |
+
"eval_loss": 0.4798698425292969,
|
| 21 |
+
"eval_runtime": 164.8654,
|
| 22 |
+
"eval_samples_per_second": 19.234,
|
| 23 |
+
"eval_steps_per_second": 2.408,
|
| 24 |
+
"eval_wer": 0.46691878014085975,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 8.15,
|
| 29 |
+
"grad_norm": 1.7655788660049438,
|
| 30 |
+
"learning_rate": 7.936000000000001e-05,
|
| 31 |
+
"loss": 0.7087,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 8.15,
|
| 36 |
+
"eval_loss": 0.331632524728775,
|
| 37 |
+
"eval_runtime": 165.1487,
|
| 38 |
+
"eval_samples_per_second": 19.201,
|
| 39 |
+
"eval_steps_per_second": 2.404,
|
| 40 |
+
"eval_wer": 0.3308121985914027,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 12.22,
|
| 45 |
+
"grad_norm": 2.021256446838379,
|
| 46 |
+
"learning_rate": 7.228235294117648e-05,
|
| 47 |
+
"loss": 0.3293,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 12.22,
|
| 52 |
+
"eval_loss": 0.29065316915512085,
|
| 53 |
+
"eval_runtime": 168.1265,
|
| 54 |
+
"eval_samples_per_second": 18.861,
|
| 55 |
+
"eval_steps_per_second": 2.361,
|
| 56 |
+
"eval_wer": 0.290982895604205,
|
| 57 |
+
"step": 1500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 16.29,
|
| 61 |
+
"grad_norm": 1.2028392553329468,
|
| 62 |
+
"learning_rate": 6.443921568627452e-05,
|
| 63 |
+
"loss": 0.203,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 16.29,
|
| 68 |
+
"eval_loss": 0.29165971279144287,
|
| 69 |
+
"eval_runtime": 168.0318,
|
| 70 |
+
"eval_samples_per_second": 18.871,
|
| 71 |
+
"eval_steps_per_second": 2.363,
|
| 72 |
+
"eval_wer": 0.2812337369461888,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 20.37,
|
| 77 |
+
"grad_norm": 0.8678894639015198,
|
| 78 |
+
"learning_rate": 5.6596078431372547e-05,
|
| 79 |
+
"loss": 0.1526,
|
| 80 |
+
"step": 2500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 20.37,
|
| 84 |
+
"eval_loss": 0.2595488429069519,
|
| 85 |
+
"eval_runtime": 168.4253,
|
| 86 |
+
"eval_samples_per_second": 18.827,
|
| 87 |
+
"eval_steps_per_second": 2.357,
|
| 88 |
+
"eval_wer": 0.26881310064878744,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 24.44,
|
| 93 |
+
"grad_norm": 1.7510905265808105,
|
| 94 |
+
"learning_rate": 4.875294117647059e-05,
|
| 95 |
+
"loss": 0.1189,
|
| 96 |
+
"step": 3000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 24.44,
|
| 100 |
+
"eval_loss": 0.2896680533885956,
|
| 101 |
+
"eval_runtime": 167.8147,
|
| 102 |
+
"eval_samples_per_second": 18.896,
|
| 103 |
+
"eval_steps_per_second": 2.366,
|
| 104 |
+
"eval_wer": 0.2652395656246747,
|
| 105 |
+
"step": 3000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 28.51,
|
| 109 |
+
"grad_norm": 1.1846829652786255,
|
| 110 |
+
"learning_rate": 4.090980392156863e-05,
|
| 111 |
+
"loss": 0.0988,
|
| 112 |
+
"step": 3500
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 28.51,
|
| 116 |
+
"eval_loss": 0.30395135283470154,
|
| 117 |
+
"eval_runtime": 168.5254,
|
| 118 |
+
"eval_samples_per_second": 18.816,
|
| 119 |
+
"eval_steps_per_second": 2.356,
|
| 120 |
+
"eval_wer": 0.2631925892516393,
|
| 121 |
+
"step": 3500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 32.59,
|
| 125 |
+
"grad_norm": 1.2768597602844238,
|
| 126 |
+
"learning_rate": 3.3066666666666666e-05,
|
| 127 |
+
"loss": 0.0767,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 32.59,
|
| 132 |
+
"eval_loss": 0.2856810986995697,
|
| 133 |
+
"eval_runtime": 170.6385,
|
| 134 |
+
"eval_samples_per_second": 18.583,
|
| 135 |
+
"eval_steps_per_second": 2.327,
|
| 136 |
+
"eval_wer": 0.25576796308503624,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 36.66,
|
| 141 |
+
"grad_norm": 0.8570753931999207,
|
| 142 |
+
"learning_rate": 2.5223529411764707e-05,
|
| 143 |
+
"loss": 0.0653,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 36.66,
|
| 148 |
+
"eval_loss": 0.30118483304977417,
|
| 149 |
+
"eval_runtime": 171.6141,
|
| 150 |
+
"eval_samples_per_second": 18.478,
|
| 151 |
+
"eval_steps_per_second": 2.313,
|
| 152 |
+
"eval_wer": 0.24785761371127224,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 40.73,
|
| 157 |
+
"grad_norm": 0.5461006164550781,
|
| 158 |
+
"learning_rate": 1.7380392156862745e-05,
|
| 159 |
+
"loss": 0.0585,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 40.73,
|
| 164 |
+
"eval_loss": 0.28294435143470764,
|
| 165 |
+
"eval_runtime": 169.3236,
|
| 166 |
+
"eval_samples_per_second": 18.727,
|
| 167 |
+
"eval_steps_per_second": 2.345,
|
| 168 |
+
"eval_wer": 0.24251465843250183,
|
| 169 |
+
"step": 5000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 44.81,
|
| 173 |
+
"grad_norm": 0.47187602519989014,
|
| 174 |
+
"learning_rate": 9.537254901960786e-06,
|
| 175 |
+
"loss": 0.0467,
|
| 176 |
+
"step": 5500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 44.81,
|
| 180 |
+
"eval_loss": 0.28480401635169983,
|
| 181 |
+
"eval_runtime": 169.9442,
|
| 182 |
+
"eval_samples_per_second": 18.659,
|
| 183 |
+
"eval_steps_per_second": 2.336,
|
| 184 |
+
"eval_wer": 0.23873295631960587,
|
| 185 |
+
"step": 5500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 48.88,
|
| 189 |
+
"grad_norm": 0.4703833758831024,
|
| 190 |
+
"learning_rate": 1.6941176470588237e-06,
|
| 191 |
+
"loss": 0.0416,
|
| 192 |
+
"step": 6000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 48.88,
|
| 196 |
+
"eval_loss": 0.27989715337753296,
|
| 197 |
+
"eval_runtime": 170.4594,
|
| 198 |
+
"eval_samples_per_second": 18.603,
|
| 199 |
+
"eval_steps_per_second": 2.329,
|
| 200 |
+
"eval_wer": 0.23436144745515733,
|
| 201 |
+
"step": 6000
|
| 202 |
+
}
|
| 203 |
+
],
|
| 204 |
+
"logging_steps": 500,
|
| 205 |
+
"max_steps": 6100,
|
| 206 |
+
"num_input_tokens_seen": 0,
|
| 207 |
+
"num_train_epochs": 50,
|
| 208 |
+
"save_steps": 500,
|
| 209 |
+
"total_flos": 9.05423649471038e+19,
|
| 210 |
+
"train_batch_size": 8,
|
| 211 |
+
"trial_name": null,
|
| 212 |
+
"trial_params": null
|
| 213 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef2aea22fc3a5c26f0bab574396403ce2f94a120364ec03de87664a530be41aa
|
| 3 |
+
size 4920
|