Uploading trained model
Browse files- checkpoint-550/config.json +129 -0
- checkpoint-550/optimizer.pt +3 -0
- checkpoint-550/preprocessor_config.json +10 -0
- checkpoint-550/pytorch_model.bin +3 -0
- checkpoint-550/rng_state.pth +3 -0
- checkpoint-550/scaler.pt +3 -0
- checkpoint-550/scheduler.pt +3 -0
- checkpoint-550/trainer_state.json +472 -0
- checkpoint-550/training_args.bin +3 -0
- checkpoint-99/config.json +129 -0
- checkpoint-99/optimizer.pt +3 -0
- checkpoint-99/preprocessor_config.json +10 -0
- checkpoint-99/pytorch_model.bin +3 -0
- checkpoint-99/rng_state.pth +3 -0
- checkpoint-99/scaler.pt +3 -0
- checkpoint-99/scheduler.pt +3 -0
- checkpoint-99/trainer_state.json +97 -0
- checkpoint-99/training_args.bin +3 -0
- config.json +129 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-550/config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "slplab/wav2vec2-xls-r-300m_phone-mfa_korean",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSpeechClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_clf",
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": 0.0,
|
| 62 |
+
"1": 0.3,
|
| 63 |
+
"2": 0.7,
|
| 64 |
+
"3": 1.0,
|
| 65 |
+
"4": 1.3,
|
| 66 |
+
"5": 1.7,
|
| 67 |
+
"6": 2.0
|
| 68 |
+
},
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 4096,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"0.0": 0,
|
| 73 |
+
"0.3": 1,
|
| 74 |
+
"0.7": 2,
|
| 75 |
+
"1.0": 3,
|
| 76 |
+
"1.3": 4,
|
| 77 |
+
"1.7": 5,
|
| 78 |
+
"2.0": 6
|
| 79 |
+
},
|
| 80 |
+
"layer_norm_eps": 1e-05,
|
| 81 |
+
"layerdrop": 0.1,
|
| 82 |
+
"mask_feature_length": 10,
|
| 83 |
+
"mask_feature_min_masks": 0,
|
| 84 |
+
"mask_feature_prob": 0.0,
|
| 85 |
+
"mask_time_length": 10,
|
| 86 |
+
"mask_time_min_masks": 2,
|
| 87 |
+
"mask_time_prob": 0.075,
|
| 88 |
+
"model_type": "wav2vec2",
|
| 89 |
+
"num_adapter_layers": 3,
|
| 90 |
+
"num_attention_heads": 16,
|
| 91 |
+
"num_codevector_groups": 2,
|
| 92 |
+
"num_codevectors_per_group": 320,
|
| 93 |
+
"num_conv_pos_embedding_groups": 16,
|
| 94 |
+
"num_conv_pos_embeddings": 128,
|
| 95 |
+
"num_feat_extract_layers": 7,
|
| 96 |
+
"num_hidden_layers": 24,
|
| 97 |
+
"num_negatives": 100,
|
| 98 |
+
"output_hidden_size": 1024,
|
| 99 |
+
"pad_token_id": 42,
|
| 100 |
+
"pooling_mode": "mean",
|
| 101 |
+
"problem_type": "single_label_classification",
|
| 102 |
+
"proj_codevector_dim": 768,
|
| 103 |
+
"tdnn_dilation": [
|
| 104 |
+
1,
|
| 105 |
+
2,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"tdnn_dim": [
|
| 111 |
+
512,
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
1500
|
| 116 |
+
],
|
| 117 |
+
"tdnn_kernel": [
|
| 118 |
+
5,
|
| 119 |
+
3,
|
| 120 |
+
3,
|
| 121 |
+
1,
|
| 122 |
+
1
|
| 123 |
+
],
|
| 124 |
+
"torch_dtype": "float32",
|
| 125 |
+
"transformers_version": "4.19.3",
|
| 126 |
+
"use_weighted_layer_sum": false,
|
| 127 |
+
"vocab_size": 45,
|
| 128 |
+
"xvector_output_dim": 512
|
| 129 |
+
}
|
checkpoint-550/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08d888ddb8ecaa9ea57437700cad6b55604332d7c271e5fc895bcebb75a43539
|
| 3 |
+
size 2498514313
|
checkpoint-550/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_dir": "/data2/excalibur12/.cache/huggingface/datasets",
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 5 |
+
"feature_size": 1,
|
| 6 |
+
"padding_side": "right",
|
| 7 |
+
"padding_value": 0.0,
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-550/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b57a9b7236f81d487413bc7fee8b96a71c65a928f5415fd0974e0cd29a81340
|
| 3 |
+
size 1266126445
|
checkpoint-550/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46015840c7dc0498fdae4bd8dce131fc8fdb7beb4db6d28e7f511ed2c19d088f
|
| 3 |
+
size 14567
|
checkpoint-550/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c33378e25f610e335ddba9ca3bc1885deef22bd7de80474020b185e11026b99
|
| 3 |
+
size 559
|
checkpoint-550/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37e8d607b82b4eb73fe403c69aa9e37348793e30ec147c856a28d72e5b4d7d9b
|
| 3 |
+
size 623
|
checkpoint-550/trainer_state.json
ADDED
|
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0679948329925537,
|
| 3 |
+
"best_model_checkpoint": "asd_pronunciation_w2v_xlsr-300m/checkpoint-99",
|
| 4 |
+
"epoch": 49.977777777777774,
|
| 5 |
+
"global_step": 550,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.98,
|
| 12 |
+
"eval_accuracy": 0.33144742250442505,
|
| 13 |
+
"eval_loss": 1.5670545101165771,
|
| 14 |
+
"eval_runtime": 62.8235,
|
| 15 |
+
"eval_samples_per_second": 33.761,
|
| 16 |
+
"eval_steps_per_second": 1.066,
|
| 17 |
+
"step": 11
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.98,
|
| 21 |
+
"eval_accuracy": 0.39273926615715027,
|
| 22 |
+
"eval_loss": 1.3582004308700562,
|
| 23 |
+
"eval_runtime": 62.2914,
|
| 24 |
+
"eval_samples_per_second": 34.05,
|
| 25 |
+
"eval_steps_per_second": 1.076,
|
| 26 |
+
"step": 22
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.98,
|
| 30 |
+
"eval_accuracy": 0.380952388048172,
|
| 31 |
+
"eval_loss": 1.3765946626663208,
|
| 32 |
+
"eval_runtime": 63.9238,
|
| 33 |
+
"eval_samples_per_second": 33.18,
|
| 34 |
+
"eval_steps_per_second": 1.048,
|
| 35 |
+
"step": 33
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.98,
|
| 39 |
+
"eval_accuracy": 0.4186704456806183,
|
| 40 |
+
"eval_loss": 1.3837833404541016,
|
| 41 |
+
"eval_runtime": 63.6397,
|
| 42 |
+
"eval_samples_per_second": 33.328,
|
| 43 |
+
"eval_steps_per_second": 1.053,
|
| 44 |
+
"step": 44
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.98,
|
| 48 |
+
"eval_accuracy": 0.3663366436958313,
|
| 49 |
+
"eval_loss": 1.5986249446868896,
|
| 50 |
+
"eval_runtime": 63.7365,
|
| 51 |
+
"eval_samples_per_second": 33.278,
|
| 52 |
+
"eval_steps_per_second": 1.051,
|
| 53 |
+
"step": 55
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.98,
|
| 57 |
+
"eval_accuracy": 0.42904290556907654,
|
| 58 |
+
"eval_loss": 1.8822154998779297,
|
| 59 |
+
"eval_runtime": 63.6958,
|
| 60 |
+
"eval_samples_per_second": 33.299,
|
| 61 |
+
"eval_steps_per_second": 1.052,
|
| 62 |
+
"step": 66
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 6.98,
|
| 66 |
+
"eval_accuracy": 0.34983497858047485,
|
| 67 |
+
"eval_loss": 1.865776538848877,
|
| 68 |
+
"eval_runtime": 63.1847,
|
| 69 |
+
"eval_samples_per_second": 33.568,
|
| 70 |
+
"eval_steps_per_second": 1.06,
|
| 71 |
+
"step": 77
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 7.98,
|
| 75 |
+
"eval_accuracy": 0.4502592980861664,
|
| 76 |
+
"eval_loss": 1.966166377067566,
|
| 77 |
+
"eval_runtime": 63.6503,
|
| 78 |
+
"eval_samples_per_second": 33.323,
|
| 79 |
+
"eval_steps_per_second": 1.053,
|
| 80 |
+
"step": 88
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 8.98,
|
| 84 |
+
"eval_accuracy": 0.6855257153511047,
|
| 85 |
+
"eval_loss": 1.0679948329925537,
|
| 86 |
+
"eval_runtime": 63.1701,
|
| 87 |
+
"eval_samples_per_second": 33.576,
|
| 88 |
+
"eval_steps_per_second": 1.061,
|
| 89 |
+
"step": 99
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 9.98,
|
| 93 |
+
"eval_accuracy": 0.6539368033409119,
|
| 94 |
+
"eval_loss": 1.1463075876235962,
|
| 95 |
+
"eval_runtime": 63.3309,
|
| 96 |
+
"eval_samples_per_second": 33.491,
|
| 97 |
+
"eval_steps_per_second": 1.058,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 10.98,
|
| 102 |
+
"eval_accuracy": 0.7157001495361328,
|
| 103 |
+
"eval_loss": 1.1053473949432373,
|
| 104 |
+
"eval_runtime": 63.7039,
|
| 105 |
+
"eval_samples_per_second": 33.295,
|
| 106 |
+
"eval_steps_per_second": 1.052,
|
| 107 |
+
"step": 121
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 11.98,
|
| 111 |
+
"eval_accuracy": 0.5836869478225708,
|
| 112 |
+
"eval_loss": 1.6300278902053833,
|
| 113 |
+
"eval_runtime": 63.4359,
|
| 114 |
+
"eval_samples_per_second": 33.435,
|
| 115 |
+
"eval_steps_per_second": 1.056,
|
| 116 |
+
"step": 132
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 12.98,
|
| 120 |
+
"eval_accuracy": 0.697312593460083,
|
| 121 |
+
"eval_loss": 1.190132975578308,
|
| 122 |
+
"eval_runtime": 62.8623,
|
| 123 |
+
"eval_samples_per_second": 33.74,
|
| 124 |
+
"eval_steps_per_second": 1.066,
|
| 125 |
+
"step": 143
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 13.98,
|
| 129 |
+
"eval_accuracy": 0.5761433243751526,
|
| 130 |
+
"eval_loss": 1.677795171737671,
|
| 131 |
+
"eval_runtime": 63.1508,
|
| 132 |
+
"eval_samples_per_second": 33.586,
|
| 133 |
+
"eval_steps_per_second": 1.061,
|
| 134 |
+
"step": 154
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 14.98,
|
| 138 |
+
"eval_accuracy": 0.7072135806083679,
|
| 139 |
+
"eval_loss": 1.2646026611328125,
|
| 140 |
+
"eval_runtime": 64.2737,
|
| 141 |
+
"eval_samples_per_second": 33.0,
|
| 142 |
+
"eval_steps_per_second": 1.042,
|
| 143 |
+
"step": 165
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 15.98,
|
| 147 |
+
"eval_accuracy": 0.5535125136375427,
|
| 148 |
+
"eval_loss": 1.866857647895813,
|
| 149 |
+
"eval_runtime": 63.6272,
|
| 150 |
+
"eval_samples_per_second": 33.335,
|
| 151 |
+
"eval_steps_per_second": 1.053,
|
| 152 |
+
"step": 176
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 16.98,
|
| 156 |
+
"eval_accuracy": 0.5700141191482544,
|
| 157 |
+
"eval_loss": 1.911484956741333,
|
| 158 |
+
"eval_runtime": 63.0574,
|
| 159 |
+
"eval_samples_per_second": 33.636,
|
| 160 |
+
"eval_steps_per_second": 1.063,
|
| 161 |
+
"step": 187
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 17.98,
|
| 165 |
+
"eval_accuracy": 0.608203649520874,
|
| 166 |
+
"eval_loss": 1.748372197151184,
|
| 167 |
+
"eval_runtime": 63.9869,
|
| 168 |
+
"eval_samples_per_second": 33.147,
|
| 169 |
+
"eval_steps_per_second": 1.047,
|
| 170 |
+
"step": 198
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 18.98,
|
| 174 |
+
"eval_accuracy": 0.6209335327148438,
|
| 175 |
+
"eval_loss": 1.736160159111023,
|
| 176 |
+
"eval_runtime": 63.5615,
|
| 177 |
+
"eval_samples_per_second": 33.369,
|
| 178 |
+
"eval_steps_per_second": 1.054,
|
| 179 |
+
"step": 209
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 19.98,
|
| 183 |
+
"eval_accuracy": 0.5535125136375427,
|
| 184 |
+
"eval_loss": 2.0504212379455566,
|
| 185 |
+
"eval_runtime": 63.6231,
|
| 186 |
+
"eval_samples_per_second": 33.337,
|
| 187 |
+
"eval_steps_per_second": 1.053,
|
| 188 |
+
"step": 220
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 20.98,
|
| 192 |
+
"eval_accuracy": 0.6520509123802185,
|
| 193 |
+
"eval_loss": 1.6594103574752808,
|
| 194 |
+
"eval_runtime": 63.6587,
|
| 195 |
+
"eval_samples_per_second": 33.318,
|
| 196 |
+
"eval_steps_per_second": 1.052,
|
| 197 |
+
"step": 231
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 21.98,
|
| 201 |
+
"eval_accuracy": 0.6779820919036865,
|
| 202 |
+
"eval_loss": 1.5675663948059082,
|
| 203 |
+
"eval_runtime": 64.5637,
|
| 204 |
+
"eval_samples_per_second": 32.851,
|
| 205 |
+
"eval_steps_per_second": 1.038,
|
| 206 |
+
"step": 242
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 22.98,
|
| 210 |
+
"eval_accuracy": 0.6737387776374817,
|
| 211 |
+
"eval_loss": 1.6316275596618652,
|
| 212 |
+
"eval_runtime": 63.4257,
|
| 213 |
+
"eval_samples_per_second": 33.441,
|
| 214 |
+
"eval_steps_per_second": 1.056,
|
| 215 |
+
"step": 253
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 23.98,
|
| 219 |
+
"eval_accuracy": 0.5983026623725891,
|
| 220 |
+
"eval_loss": 1.9427396059036255,
|
| 221 |
+
"eval_runtime": 63.6629,
|
| 222 |
+
"eval_samples_per_second": 33.316,
|
| 223 |
+
"eval_steps_per_second": 1.052,
|
| 224 |
+
"step": 264
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 24.98,
|
| 228 |
+
"eval_accuracy": 0.6619518995285034,
|
| 229 |
+
"eval_loss": 1.7251100540161133,
|
| 230 |
+
"eval_runtime": 63.8986,
|
| 231 |
+
"eval_samples_per_second": 33.193,
|
| 232 |
+
"eval_steps_per_second": 1.049,
|
| 233 |
+
"step": 275
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 25.98,
|
| 237 |
+
"eval_accuracy": 0.7133427858352661,
|
| 238 |
+
"eval_loss": 1.4861173629760742,
|
| 239 |
+
"eval_runtime": 63.105,
|
| 240 |
+
"eval_samples_per_second": 33.611,
|
| 241 |
+
"eval_steps_per_second": 1.062,
|
| 242 |
+
"step": 286
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 26.98,
|
| 246 |
+
"eval_accuracy": 0.6388496160507202,
|
| 247 |
+
"eval_loss": 1.8551920652389526,
|
| 248 |
+
"eval_runtime": 63.3692,
|
| 249 |
+
"eval_samples_per_second": 33.471,
|
| 250 |
+
"eval_steps_per_second": 1.057,
|
| 251 |
+
"step": 297
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 27.98,
|
| 255 |
+
"eval_accuracy": 0.6218764781951904,
|
| 256 |
+
"eval_loss": 1.9755550622940063,
|
| 257 |
+
"eval_runtime": 63.7438,
|
| 258 |
+
"eval_samples_per_second": 33.274,
|
| 259 |
+
"eval_steps_per_second": 1.051,
|
| 260 |
+
"step": 308
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 28.98,
|
| 264 |
+
"eval_accuracy": 0.5879302024841309,
|
| 265 |
+
"eval_loss": 2.2480831146240234,
|
| 266 |
+
"eval_runtime": 62.9459,
|
| 267 |
+
"eval_samples_per_second": 33.696,
|
| 268 |
+
"eval_steps_per_second": 1.064,
|
| 269 |
+
"step": 319
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 29.98,
|
| 273 |
+
"eval_accuracy": 0.6176331639289856,
|
| 274 |
+
"eval_loss": 1.9868534803390503,
|
| 275 |
+
"eval_runtime": 63.9115,
|
| 276 |
+
"eval_samples_per_second": 33.187,
|
| 277 |
+
"eval_steps_per_second": 1.048,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 30.98,
|
| 282 |
+
"eval_accuracy": 0.6991984844207764,
|
| 283 |
+
"eval_loss": 1.6001139879226685,
|
| 284 |
+
"eval_runtime": 62.9701,
|
| 285 |
+
"eval_samples_per_second": 33.683,
|
| 286 |
+
"eval_steps_per_second": 1.064,
|
| 287 |
+
"step": 341
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 31.98,
|
| 291 |
+
"eval_accuracy": 0.6562942266464233,
|
| 292 |
+
"eval_loss": 1.80760657787323,
|
| 293 |
+
"eval_runtime": 64.5355,
|
| 294 |
+
"eval_samples_per_second": 32.866,
|
| 295 |
+
"eval_steps_per_second": 1.038,
|
| 296 |
+
"step": 352
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 32.98,
|
| 300 |
+
"eval_accuracy": 0.6539368033409119,
|
| 301 |
+
"eval_loss": 1.8803389072418213,
|
| 302 |
+
"eval_runtime": 63.8068,
|
| 303 |
+
"eval_samples_per_second": 33.241,
|
| 304 |
+
"eval_steps_per_second": 1.05,
|
| 305 |
+
"step": 363
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 33.98,
|
| 309 |
+
"eval_accuracy": 0.6308345198631287,
|
| 310 |
+
"eval_loss": 1.9857879877090454,
|
| 311 |
+
"eval_runtime": 63.5545,
|
| 312 |
+
"eval_samples_per_second": 33.373,
|
| 313 |
+
"eval_steps_per_second": 1.054,
|
| 314 |
+
"step": 374
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 34.98,
|
| 318 |
+
"eval_accuracy": 0.6228194236755371,
|
| 319 |
+
"eval_loss": 2.016218900680542,
|
| 320 |
+
"eval_runtime": 63.1093,
|
| 321 |
+
"eval_samples_per_second": 33.608,
|
| 322 |
+
"eval_steps_per_second": 1.062,
|
| 323 |
+
"step": 385
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 35.98,
|
| 327 |
+
"eval_accuracy": 0.6247053146362305,
|
| 328 |
+
"eval_loss": 1.9806338548660278,
|
| 329 |
+
"eval_runtime": 63.643,
|
| 330 |
+
"eval_samples_per_second": 33.327,
|
| 331 |
+
"eval_steps_per_second": 1.053,
|
| 332 |
+
"step": 396
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 36.98,
|
| 336 |
+
"eval_accuracy": 0.6148043274879456,
|
| 337 |
+
"eval_loss": 2.0684027671813965,
|
| 338 |
+
"eval_runtime": 63.1391,
|
| 339 |
+
"eval_samples_per_second": 33.593,
|
| 340 |
+
"eval_steps_per_second": 1.061,
|
| 341 |
+
"step": 407
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 37.98,
|
| 345 |
+
"eval_accuracy": 0.6826968193054199,
|
| 346 |
+
"eval_loss": 1.7208051681518555,
|
| 347 |
+
"eval_runtime": 63.3764,
|
| 348 |
+
"eval_samples_per_second": 33.467,
|
| 349 |
+
"eval_steps_per_second": 1.057,
|
| 350 |
+
"step": 418
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 38.98,
|
| 354 |
+
"eval_accuracy": 0.6676096320152283,
|
| 355 |
+
"eval_loss": 1.7736769914627075,
|
| 356 |
+
"eval_runtime": 63.0716,
|
| 357 |
+
"eval_samples_per_second": 33.628,
|
| 358 |
+
"eval_steps_per_second": 1.062,
|
| 359 |
+
"step": 429
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 39.98,
|
| 363 |
+
"eval_accuracy": 0.6940122842788696,
|
| 364 |
+
"eval_loss": 1.7225761413574219,
|
| 365 |
+
"eval_runtime": 64.0078,
|
| 366 |
+
"eval_samples_per_second": 33.137,
|
| 367 |
+
"eval_steps_per_second": 1.047,
|
| 368 |
+
"step": 440
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 40.98,
|
| 372 |
+
"eval_accuracy": 0.606789231300354,
|
| 373 |
+
"eval_loss": 2.0414962768554688,
|
| 374 |
+
"eval_runtime": 63.4689,
|
| 375 |
+
"eval_samples_per_second": 33.418,
|
| 376 |
+
"eval_steps_per_second": 1.056,
|
| 377 |
+
"step": 451
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 41.98,
|
| 381 |
+
"eval_accuracy": 0.6214050054550171,
|
| 382 |
+
"eval_loss": 2.019111394882202,
|
| 383 |
+
"eval_runtime": 63.5976,
|
| 384 |
+
"eval_samples_per_second": 33.35,
|
| 385 |
+
"eval_steps_per_second": 1.053,
|
| 386 |
+
"step": 462
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 42.98,
|
| 390 |
+
"eval_accuracy": 0.6379066705703735,
|
| 391 |
+
"eval_loss": 1.947460412979126,
|
| 392 |
+
"eval_runtime": 63.6957,
|
| 393 |
+
"eval_samples_per_second": 33.299,
|
| 394 |
+
"eval_steps_per_second": 1.052,
|
| 395 |
+
"step": 473
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 43.98,
|
| 399 |
+
"eval_accuracy": 0.669966995716095,
|
| 400 |
+
"eval_loss": 1.8389097452163696,
|
| 401 |
+
"eval_runtime": 64.1144,
|
| 402 |
+
"eval_samples_per_second": 33.081,
|
| 403 |
+
"eval_steps_per_second": 1.045,
|
| 404 |
+
"step": 484
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 44.98,
|
| 408 |
+
"eval_accuracy": 0.6666666865348816,
|
| 409 |
+
"eval_loss": 1.814638376235962,
|
| 410 |
+
"eval_runtime": 63.7225,
|
| 411 |
+
"eval_samples_per_second": 33.285,
|
| 412 |
+
"eval_steps_per_second": 1.051,
|
| 413 |
+
"step": 495
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 45.44,
|
| 417 |
+
"learning_rate": 3.03030303030303e-05,
|
| 418 |
+
"loss": 0.3177,
|
| 419 |
+
"step": 500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 45.98,
|
| 423 |
+
"eval_accuracy": 0.6718528866767883,
|
| 424 |
+
"eval_loss": 1.79548978805542,
|
| 425 |
+
"eval_runtime": 63.2169,
|
| 426 |
+
"eval_samples_per_second": 33.551,
|
| 427 |
+
"eval_steps_per_second": 1.06,
|
| 428 |
+
"step": 506
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 46.98,
|
| 432 |
+
"eval_accuracy": 0.65865159034729,
|
| 433 |
+
"eval_loss": 1.9061682224273682,
|
| 434 |
+
"eval_runtime": 64.47,
|
| 435 |
+
"eval_samples_per_second": 32.899,
|
| 436 |
+
"eval_steps_per_second": 1.039,
|
| 437 |
+
"step": 517
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 47.98,
|
| 441 |
+
"eval_accuracy": 0.6643092632293701,
|
| 442 |
+
"eval_loss": 1.8877029418945312,
|
| 443 |
+
"eval_runtime": 63.3351,
|
| 444 |
+
"eval_samples_per_second": 33.489,
|
| 445 |
+
"eval_steps_per_second": 1.058,
|
| 446 |
+
"step": 528
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 48.98,
|
| 450 |
+
"eval_accuracy": 0.6694955229759216,
|
| 451 |
+
"eval_loss": 1.8578468561172485,
|
| 452 |
+
"eval_runtime": 63.6561,
|
| 453 |
+
"eval_samples_per_second": 33.32,
|
| 454 |
+
"eval_steps_per_second": 1.053,
|
| 455 |
+
"step": 539
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 49.98,
|
| 459 |
+
"eval_accuracy": 0.6690240502357483,
|
| 460 |
+
"eval_loss": 1.8590630292892456,
|
| 461 |
+
"eval_runtime": 62.2809,
|
| 462 |
+
"eval_samples_per_second": 34.055,
|
| 463 |
+
"eval_steps_per_second": 1.076,
|
| 464 |
+
"step": 550
|
| 465 |
+
}
|
| 466 |
+
],
|
| 467 |
+
"max_steps": 550,
|
| 468 |
+
"num_train_epochs": 50,
|
| 469 |
+
"total_flos": 1.6031529967362595e+20,
|
| 470 |
+
"trial_name": null,
|
| 471 |
+
"trial_params": null
|
| 472 |
+
}
|
checkpoint-550/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4afb2655f3c0073e780badb5d2bfdc98d7aec81af4e009015d689aaa98fc87c7
|
| 3 |
+
size 3247
|
checkpoint-99/config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "slplab/wav2vec2-xls-r-300m_phone-mfa_korean",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSpeechClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_clf",
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": 0.0,
|
| 62 |
+
"1": 0.3,
|
| 63 |
+
"2": 0.7,
|
| 64 |
+
"3": 1.0,
|
| 65 |
+
"4": 1.3,
|
| 66 |
+
"5": 1.7,
|
| 67 |
+
"6": 2.0
|
| 68 |
+
},
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 4096,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"0.0": 0,
|
| 73 |
+
"0.3": 1,
|
| 74 |
+
"0.7": 2,
|
| 75 |
+
"1.0": 3,
|
| 76 |
+
"1.3": 4,
|
| 77 |
+
"1.7": 5,
|
| 78 |
+
"2.0": 6
|
| 79 |
+
},
|
| 80 |
+
"layer_norm_eps": 1e-05,
|
| 81 |
+
"layerdrop": 0.1,
|
| 82 |
+
"mask_feature_length": 10,
|
| 83 |
+
"mask_feature_min_masks": 0,
|
| 84 |
+
"mask_feature_prob": 0.0,
|
| 85 |
+
"mask_time_length": 10,
|
| 86 |
+
"mask_time_min_masks": 2,
|
| 87 |
+
"mask_time_prob": 0.075,
|
| 88 |
+
"model_type": "wav2vec2",
|
| 89 |
+
"num_adapter_layers": 3,
|
| 90 |
+
"num_attention_heads": 16,
|
| 91 |
+
"num_codevector_groups": 2,
|
| 92 |
+
"num_codevectors_per_group": 320,
|
| 93 |
+
"num_conv_pos_embedding_groups": 16,
|
| 94 |
+
"num_conv_pos_embeddings": 128,
|
| 95 |
+
"num_feat_extract_layers": 7,
|
| 96 |
+
"num_hidden_layers": 24,
|
| 97 |
+
"num_negatives": 100,
|
| 98 |
+
"output_hidden_size": 1024,
|
| 99 |
+
"pad_token_id": 42,
|
| 100 |
+
"pooling_mode": "mean",
|
| 101 |
+
"problem_type": "single_label_classification",
|
| 102 |
+
"proj_codevector_dim": 768,
|
| 103 |
+
"tdnn_dilation": [
|
| 104 |
+
1,
|
| 105 |
+
2,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"tdnn_dim": [
|
| 111 |
+
512,
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
1500
|
| 116 |
+
],
|
| 117 |
+
"tdnn_kernel": [
|
| 118 |
+
5,
|
| 119 |
+
3,
|
| 120 |
+
3,
|
| 121 |
+
1,
|
| 122 |
+
1
|
| 123 |
+
],
|
| 124 |
+
"torch_dtype": "float32",
|
| 125 |
+
"transformers_version": "4.19.3",
|
| 126 |
+
"use_weighted_layer_sum": false,
|
| 127 |
+
"vocab_size": 45,
|
| 128 |
+
"xvector_output_dim": 512
|
| 129 |
+
}
|
checkpoint-99/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfb12195e7135500901e00751639cdbcde56bfc2e24194958e2cfd5095def437
|
| 3 |
+
size 2498513929
|
checkpoint-99/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_dir": "/data2/excalibur12/.cache/huggingface/datasets",
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 5 |
+
"feature_size": 1,
|
| 6 |
+
"padding_side": "right",
|
| 7 |
+
"padding_value": 0.0,
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-99/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ba667b34a70f35c0d48a0d6cde1c22b16df9bebc1d00dad51070cb2e544073b
|
| 3 |
+
size 1266126445
|
checkpoint-99/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e53ff83bc5a0f7e3f45273d2de1bf2192e1300b343841603a2b096df6ad8c127
|
| 3 |
+
size 14567
|
checkpoint-99/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a083ceb88b83ff7ed1f0adf6d62580b8ceb7d9c17ad4684f511424e289c436
|
| 3 |
+
size 559
|
checkpoint-99/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0de4bd42e78a35b7fa3b4618172ba102f4f2a9be54789adf5790bde4d76e585e
|
| 3 |
+
size 623
|
checkpoint-99/trainer_state.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0679948329925537,
|
| 3 |
+
"best_model_checkpoint": "asd_pronunciation_w2v_xlsr-300m/checkpoint-99",
|
| 4 |
+
"epoch": 8.977777777777778,
|
| 5 |
+
"global_step": 99,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.98,
|
| 12 |
+
"eval_accuracy": 0.33144742250442505,
|
| 13 |
+
"eval_loss": 1.5670545101165771,
|
| 14 |
+
"eval_runtime": 62.8235,
|
| 15 |
+
"eval_samples_per_second": 33.761,
|
| 16 |
+
"eval_steps_per_second": 1.066,
|
| 17 |
+
"step": 11
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.98,
|
| 21 |
+
"eval_accuracy": 0.39273926615715027,
|
| 22 |
+
"eval_loss": 1.3582004308700562,
|
| 23 |
+
"eval_runtime": 62.2914,
|
| 24 |
+
"eval_samples_per_second": 34.05,
|
| 25 |
+
"eval_steps_per_second": 1.076,
|
| 26 |
+
"step": 22
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.98,
|
| 30 |
+
"eval_accuracy": 0.380952388048172,
|
| 31 |
+
"eval_loss": 1.3765946626663208,
|
| 32 |
+
"eval_runtime": 63.9238,
|
| 33 |
+
"eval_samples_per_second": 33.18,
|
| 34 |
+
"eval_steps_per_second": 1.048,
|
| 35 |
+
"step": 33
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.98,
|
| 39 |
+
"eval_accuracy": 0.4186704456806183,
|
| 40 |
+
"eval_loss": 1.3837833404541016,
|
| 41 |
+
"eval_runtime": 63.6397,
|
| 42 |
+
"eval_samples_per_second": 33.328,
|
| 43 |
+
"eval_steps_per_second": 1.053,
|
| 44 |
+
"step": 44
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.98,
|
| 48 |
+
"eval_accuracy": 0.3663366436958313,
|
| 49 |
+
"eval_loss": 1.5986249446868896,
|
| 50 |
+
"eval_runtime": 63.7365,
|
| 51 |
+
"eval_samples_per_second": 33.278,
|
| 52 |
+
"eval_steps_per_second": 1.051,
|
| 53 |
+
"step": 55
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.98,
|
| 57 |
+
"eval_accuracy": 0.42904290556907654,
|
| 58 |
+
"eval_loss": 1.8822154998779297,
|
| 59 |
+
"eval_runtime": 63.6958,
|
| 60 |
+
"eval_samples_per_second": 33.299,
|
| 61 |
+
"eval_steps_per_second": 1.052,
|
| 62 |
+
"step": 66
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 6.98,
|
| 66 |
+
"eval_accuracy": 0.34983497858047485,
|
| 67 |
+
"eval_loss": 1.865776538848877,
|
| 68 |
+
"eval_runtime": 63.1847,
|
| 69 |
+
"eval_samples_per_second": 33.568,
|
| 70 |
+
"eval_steps_per_second": 1.06,
|
| 71 |
+
"step": 77
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 7.98,
|
| 75 |
+
"eval_accuracy": 0.4502592980861664,
|
| 76 |
+
"eval_loss": 1.966166377067566,
|
| 77 |
+
"eval_runtime": 63.6503,
|
| 78 |
+
"eval_samples_per_second": 33.323,
|
| 79 |
+
"eval_steps_per_second": 1.053,
|
| 80 |
+
"step": 88
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 8.98,
|
| 84 |
+
"eval_accuracy": 0.6855257153511047,
|
| 85 |
+
"eval_loss": 1.0679948329925537,
|
| 86 |
+
"eval_runtime": 63.1701,
|
| 87 |
+
"eval_samples_per_second": 33.576,
|
| 88 |
+
"eval_steps_per_second": 1.061,
|
| 89 |
+
"step": 99
|
| 90 |
+
}
|
| 91 |
+
],
|
| 92 |
+
"max_steps": 550,
|
| 93 |
+
"num_train_epochs": 50,
|
| 94 |
+
"total_flos": 2.8846941106899534e+19,
|
| 95 |
+
"trial_name": null,
|
| 96 |
+
"trial_params": null
|
| 97 |
+
}
|
checkpoint-99/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4afb2655f3c0073e780badb5d2bfdc98d7aec81af4e009015d689aaa98fc87c7
|
| 3 |
+
size 3247
|
config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "slplab/wav2vec2-xls-r-300m_phone-mfa_korean",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSpeechClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_clf",
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": 0.0,
|
| 62 |
+
"1": 0.3,
|
| 63 |
+
"2": 0.7,
|
| 64 |
+
"3": 1.0,
|
| 65 |
+
"4": 1.3,
|
| 66 |
+
"5": 1.7,
|
| 67 |
+
"6": 2.0
|
| 68 |
+
},
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 4096,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"0.0": 0,
|
| 73 |
+
"0.3": 1,
|
| 74 |
+
"0.7": 2,
|
| 75 |
+
"1.0": 3,
|
| 76 |
+
"1.3": 4,
|
| 77 |
+
"1.7": 5,
|
| 78 |
+
"2.0": 6
|
| 79 |
+
},
|
| 80 |
+
"layer_norm_eps": 1e-05,
|
| 81 |
+
"layerdrop": 0.1,
|
| 82 |
+
"mask_feature_length": 10,
|
| 83 |
+
"mask_feature_min_masks": 0,
|
| 84 |
+
"mask_feature_prob": 0.0,
|
| 85 |
+
"mask_time_length": 10,
|
| 86 |
+
"mask_time_min_masks": 2,
|
| 87 |
+
"mask_time_prob": 0.075,
|
| 88 |
+
"model_type": "wav2vec2",
|
| 89 |
+
"num_adapter_layers": 3,
|
| 90 |
+
"num_attention_heads": 16,
|
| 91 |
+
"num_codevector_groups": 2,
|
| 92 |
+
"num_codevectors_per_group": 320,
|
| 93 |
+
"num_conv_pos_embedding_groups": 16,
|
| 94 |
+
"num_conv_pos_embeddings": 128,
|
| 95 |
+
"num_feat_extract_layers": 7,
|
| 96 |
+
"num_hidden_layers": 24,
|
| 97 |
+
"num_negatives": 100,
|
| 98 |
+
"output_hidden_size": 1024,
|
| 99 |
+
"pad_token_id": 42,
|
| 100 |
+
"pooling_mode": "mean",
|
| 101 |
+
"problem_type": "single_label_classification",
|
| 102 |
+
"proj_codevector_dim": 768,
|
| 103 |
+
"tdnn_dilation": [
|
| 104 |
+
1,
|
| 105 |
+
2,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"tdnn_dim": [
|
| 111 |
+
512,
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
1500
|
| 116 |
+
],
|
| 117 |
+
"tdnn_kernel": [
|
| 118 |
+
5,
|
| 119 |
+
3,
|
| 120 |
+
3,
|
| 121 |
+
1,
|
| 122 |
+
1
|
| 123 |
+
],
|
| 124 |
+
"torch_dtype": "float32",
|
| 125 |
+
"transformers_version": "4.19.3",
|
| 126 |
+
"use_weighted_layer_sum": false,
|
| 127 |
+
"vocab_size": 45,
|
| 128 |
+
"xvector_output_dim": 512
|
| 129 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_dir": "/data2/excalibur12/.cache/huggingface/datasets",
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 5 |
+
"feature_size": 1,
|
| 6 |
+
"padding_side": "right",
|
| 7 |
+
"padding_value": 0.0,
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ba667b34a70f35c0d48a0d6cde1c22b16df9bebc1d00dad51070cb2e544073b
|
| 3 |
+
size 1266126445
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4afb2655f3c0073e780badb5d2bfdc98d7aec81af4e009015d689aaa98fc87c7
|
| 3 |
+
size 3247
|