Training in progress, epoch 2, checkpoint
Browse files- checkpoint-169/config.json +96 -0
- checkpoint-169/model.safetensors +3 -0
- checkpoint-169/optimizer.pt +3 -0
- checkpoint-169/preprocessor_config.json +9 -0
- checkpoint-169/rng_state.pth +3 -0
- checkpoint-169/scheduler.pt +3 -0
- checkpoint-169/trainer_state.json +244 -0
- checkpoint-169/training_args.bin +3 -0
checkpoint-169/config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout": 0.1,
|
| 50 |
+
"hidden_size": 768,
|
| 51 |
+
"id2label": {
|
| 52 |
+
"0": "blues",
|
| 53 |
+
"1": "classical",
|
| 54 |
+
"2": "country",
|
| 55 |
+
"3": "disco",
|
| 56 |
+
"4": "hiphop",
|
| 57 |
+
"5": "jazz",
|
| 58 |
+
"6": "metal",
|
| 59 |
+
"7": "pop",
|
| 60 |
+
"8": "reggae",
|
| 61 |
+
"9": "rock"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"blues": "0",
|
| 67 |
+
"classical": "1",
|
| 68 |
+
"country": "2",
|
| 69 |
+
"disco": "3",
|
| 70 |
+
"hiphop": "4",
|
| 71 |
+
"jazz": "5",
|
| 72 |
+
"metal": "6",
|
| 73 |
+
"pop": "7",
|
| 74 |
+
"reggae": "8",
|
| 75 |
+
"rock": "9"
|
| 76 |
+
},
|
| 77 |
+
"layer_norm_eps": 1e-05,
|
| 78 |
+
"layerdrop": 0.0,
|
| 79 |
+
"mask_feature_length": 10,
|
| 80 |
+
"mask_feature_min_masks": 0,
|
| 81 |
+
"mask_feature_prob": 0.0,
|
| 82 |
+
"mask_time_length": 10,
|
| 83 |
+
"mask_time_min_masks": 2,
|
| 84 |
+
"mask_time_prob": 0.05,
|
| 85 |
+
"model_type": "hubert",
|
| 86 |
+
"num_attention_heads": 12,
|
| 87 |
+
"num_conv_pos_embedding_groups": 16,
|
| 88 |
+
"num_conv_pos_embeddings": 128,
|
| 89 |
+
"num_feat_extract_layers": 7,
|
| 90 |
+
"num_hidden_layers": 2,
|
| 91 |
+
"pad_token_id": 0,
|
| 92 |
+
"torch_dtype": "float32",
|
| 93 |
+
"transformers_version": "4.35.2",
|
| 94 |
+
"use_weighted_layer_sum": false,
|
| 95 |
+
"vocab_size": 32
|
| 96 |
+
}
|
checkpoint-169/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b681b4308f7d25e4bdf9a893b9fabfab122e8ed6dd929b2e1dd742789bd597d1
|
| 3 |
+
size 94771728
|
checkpoint-169/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5941eda0d0e6aad4282c198be6da229f71509ee54ed705ed9a452664fd2cc69
|
| 3 |
+
size 189575930
|
checkpoint-169/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,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
checkpoint-169/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:327ffa16e04a18d6cf6fc20109cf07704071d784619bc9d12d9c1dd6a7410d3a
|
| 3 |
+
size 14244
|
checkpoint-169/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ee09a6145636e67ae0e8f9871a8688305dce6cb1cf920af0129bd52647c40f4
|
| 3 |
+
size 1064
|
checkpoint-169/trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.61,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-113",
|
| 4 |
+
"epoch": 2.991150442477876,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 169,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"learning_rate": 4.464285714285714e-05,
|
| 14 |
+
"loss": 2.2976,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.18,
|
| 19 |
+
"learning_rate": 8.928571428571429e-05,
|
| 20 |
+
"loss": 2.2855,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.27,
|
| 25 |
+
"learning_rate": 0.00013392857142857144,
|
| 26 |
+
"loss": 2.2307,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.35,
|
| 31 |
+
"learning_rate": 0.00017857142857142857,
|
| 32 |
+
"loss": 2.1327,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.44,
|
| 37 |
+
"learning_rate": 0.00022321428571428573,
|
| 38 |
+
"loss": 2.0339,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.53,
|
| 43 |
+
"learning_rate": 0.00026785714285714287,
|
| 44 |
+
"loss": 1.9633,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.62,
|
| 49 |
+
"learning_rate": 0.0003125,
|
| 50 |
+
"loss": 1.8021,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.71,
|
| 55 |
+
"learning_rate": 0.00035714285714285714,
|
| 56 |
+
"loss": 1.6938,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 0.00040178571428571433,
|
| 62 |
+
"loss": 1.5271,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.88,
|
| 67 |
+
"learning_rate": 0.00044642857142857147,
|
| 68 |
+
"loss": 1.4038,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.97,
|
| 73 |
+
"learning_rate": 0.0004910714285714286,
|
| 74 |
+
"loss": 1.496,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.99,
|
| 79 |
+
"eval_accuracy": 0.27,
|
| 80 |
+
"eval_loss": 1.8467493057250977,
|
| 81 |
+
"eval_runtime": 72.5718,
|
| 82 |
+
"eval_samples_per_second": 1.378,
|
| 83 |
+
"eval_steps_per_second": 0.179,
|
| 84 |
+
"step": 56
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.06,
|
| 88 |
+
"learning_rate": 0.000496031746031746,
|
| 89 |
+
"loss": 1.3528,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.15,
|
| 94 |
+
"learning_rate": 0.0004910714285714286,
|
| 95 |
+
"loss": 1.507,
|
| 96 |
+
"step": 65
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.24,
|
| 100 |
+
"learning_rate": 0.0004861111111111111,
|
| 101 |
+
"loss": 1.504,
|
| 102 |
+
"step": 70
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.33,
|
| 106 |
+
"learning_rate": 0.0004811507936507937,
|
| 107 |
+
"loss": 1.3719,
|
| 108 |
+
"step": 75
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.42,
|
| 112 |
+
"learning_rate": 0.0004761904761904762,
|
| 113 |
+
"loss": 1.2284,
|
| 114 |
+
"step": 80
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.5,
|
| 118 |
+
"learning_rate": 0.00047123015873015874,
|
| 119 |
+
"loss": 1.2997,
|
| 120 |
+
"step": 85
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.59,
|
| 124 |
+
"learning_rate": 0.0004662698412698413,
|
| 125 |
+
"loss": 1.2284,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.68,
|
| 130 |
+
"learning_rate": 0.00046130952380952383,
|
| 131 |
+
"loss": 1.3332,
|
| 132 |
+
"step": 95
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.77,
|
| 136 |
+
"learning_rate": 0.0004563492063492063,
|
| 137 |
+
"loss": 1.1091,
|
| 138 |
+
"step": 100
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.86,
|
| 142 |
+
"learning_rate": 0.0004513888888888889,
|
| 143 |
+
"loss": 1.1335,
|
| 144 |
+
"step": 105
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.95,
|
| 148 |
+
"learning_rate": 0.00044642857142857147,
|
| 149 |
+
"loss": 1.1313,
|
| 150 |
+
"step": 110
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.0,
|
| 154 |
+
"eval_accuracy": 0.61,
|
| 155 |
+
"eval_loss": 1.175675868988037,
|
| 156 |
+
"eval_runtime": 71.9077,
|
| 157 |
+
"eval_samples_per_second": 1.391,
|
| 158 |
+
"eval_steps_per_second": 0.181,
|
| 159 |
+
"step": 113
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.04,
|
| 163 |
+
"learning_rate": 0.00044146825396825396,
|
| 164 |
+
"loss": 1.1765,
|
| 165 |
+
"step": 115
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.12,
|
| 169 |
+
"learning_rate": 0.0004365079365079365,
|
| 170 |
+
"loss": 1.0945,
|
| 171 |
+
"step": 120
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.21,
|
| 175 |
+
"learning_rate": 0.00043154761904761905,
|
| 176 |
+
"loss": 0.9198,
|
| 177 |
+
"step": 125
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.3,
|
| 181 |
+
"learning_rate": 0.0004265873015873016,
|
| 182 |
+
"loss": 1.1504,
|
| 183 |
+
"step": 130
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.39,
|
| 187 |
+
"learning_rate": 0.00042162698412698415,
|
| 188 |
+
"loss": 1.03,
|
| 189 |
+
"step": 135
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.48,
|
| 193 |
+
"learning_rate": 0.0004166666666666667,
|
| 194 |
+
"loss": 1.294,
|
| 195 |
+
"step": 140
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.57,
|
| 199 |
+
"learning_rate": 0.0004117063492063492,
|
| 200 |
+
"loss": 0.918,
|
| 201 |
+
"step": 145
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.65,
|
| 205 |
+
"learning_rate": 0.00040674603174603173,
|
| 206 |
+
"loss": 0.9529,
|
| 207 |
+
"step": 150
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.74,
|
| 211 |
+
"learning_rate": 0.00040178571428571433,
|
| 212 |
+
"loss": 0.9366,
|
| 213 |
+
"step": 155
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.83,
|
| 217 |
+
"learning_rate": 0.0003968253968253968,
|
| 218 |
+
"loss": 0.9388,
|
| 219 |
+
"step": 160
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.92,
|
| 223 |
+
"learning_rate": 0.00039186507936507937,
|
| 224 |
+
"loss": 1.2432,
|
| 225 |
+
"step": 165
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.99,
|
| 229 |
+
"eval_accuracy": 0.58,
|
| 230 |
+
"eval_loss": 1.3774330615997314,
|
| 231 |
+
"eval_runtime": 72.0805,
|
| 232 |
+
"eval_samples_per_second": 1.387,
|
| 233 |
+
"eval_steps_per_second": 0.18,
|
| 234 |
+
"step": 169
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 5,
|
| 238 |
+
"max_steps": 560,
|
| 239 |
+
"num_train_epochs": 10,
|
| 240 |
+
"save_steps": 500,
|
| 241 |
+
"total_flos": 1.8401964823872e+17,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|
checkpoint-169/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbef9bdfa53985d2dd1361cb595119941d5a4b9581e158c102613a779ed26711
|
| 3 |
+
size 4600
|