Training in progress, epoch 4, checkpoint
Browse files- checkpoint-140/config.json +96 -0
- checkpoint-140/model.safetensors +3 -0
- checkpoint-140/optimizer.pt +3 -0
- checkpoint-140/preprocessor_config.json +9 -0
- checkpoint-140/rng_state.pth +3 -0
- checkpoint-140/scheduler.pt +3 -0
- checkpoint-140/trainer_state.json +232 -0
- checkpoint-140/training_args.bin +3 -0
checkpoint-140/config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "arshsin/distilhubert-finetuned-gtzan",
|
| 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-140/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:affbc15cd1f575f8c1998b67d5b2e1abbcb18bf883a540878256aa623dd96e62
|
| 3 |
+
size 94771728
|
checkpoint-140/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfaa89f0e9d9ffa4be5cacbee0f636b0186ce0e3ad4fed66469edd3e29de0d49
|
| 3 |
+
size 189575930
|
checkpoint-140/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-140/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab20d289feb087d6488313442f1d6ff75f95c7e146db6611ee9f3a7d4a0e8cd
|
| 3 |
+
size 14244
|
checkpoint-140/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27747f7be8645ac5f9bcbb520b00ed96f136dbf530506d26beadb39d65256bd1
|
| 3 |
+
size 1064
|
checkpoint-140/trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.83,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
|
| 4 |
+
"epoch": 4.95575221238938,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 14 |
+
"loss": 0.0338,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.35,
|
| 19 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 20 |
+
"loss": 0.0053,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.53,
|
| 25 |
+
"learning_rate": 9.920634920634922e-06,
|
| 26 |
+
"loss": 0.0056,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.71,
|
| 31 |
+
"learning_rate": 9.523809523809525e-06,
|
| 32 |
+
"loss": 0.0437,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.88,
|
| 37 |
+
"learning_rate": 9.126984126984127e-06,
|
| 38 |
+
"loss": 0.0017,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.99,
|
| 43 |
+
"eval_accuracy": 0.82,
|
| 44 |
+
"eval_loss": 1.0909959077835083,
|
| 45 |
+
"eval_runtime": 72.1207,
|
| 46 |
+
"eval_samples_per_second": 1.387,
|
| 47 |
+
"eval_steps_per_second": 0.18,
|
| 48 |
+
"step": 28
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.06,
|
| 52 |
+
"learning_rate": 8.730158730158731e-06,
|
| 53 |
+
"loss": 0.0013,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.24,
|
| 58 |
+
"learning_rate": 8.333333333333334e-06,
|
| 59 |
+
"loss": 0.0373,
|
| 60 |
+
"step": 35
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.42,
|
| 64 |
+
"learning_rate": 7.936507936507936e-06,
|
| 65 |
+
"loss": 0.0041,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.59,
|
| 70 |
+
"learning_rate": 7.53968253968254e-06,
|
| 71 |
+
"loss": 0.0012,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.77,
|
| 76 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 77 |
+
"loss": 0.0338,
|
| 78 |
+
"step": 50
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.95,
|
| 82 |
+
"learning_rate": 6.746031746031747e-06,
|
| 83 |
+
"loss": 0.0143,
|
| 84 |
+
"step": 55
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.98,
|
| 88 |
+
"eval_accuracy": 0.83,
|
| 89 |
+
"eval_loss": 1.1379410028457642,
|
| 90 |
+
"eval_runtime": 71.5138,
|
| 91 |
+
"eval_samples_per_second": 1.398,
|
| 92 |
+
"eval_steps_per_second": 0.182,
|
| 93 |
+
"step": 56
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.12,
|
| 97 |
+
"learning_rate": 6.349206349206349e-06,
|
| 98 |
+
"loss": 0.036,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3,
|
| 103 |
+
"learning_rate": 5.9523809523809525e-06,
|
| 104 |
+
"loss": 0.001,
|
| 105 |
+
"step": 65
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.48,
|
| 109 |
+
"learning_rate": 5.555555555555557e-06,
|
| 110 |
+
"loss": 0.0412,
|
| 111 |
+
"step": 70
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.65,
|
| 115 |
+
"learning_rate": 5.15873015873016e-06,
|
| 116 |
+
"loss": 0.001,
|
| 117 |
+
"step": 75
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.83,
|
| 121 |
+
"learning_rate": 4.761904761904762e-06,
|
| 122 |
+
"loss": 0.01,
|
| 123 |
+
"step": 80
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.97,
|
| 127 |
+
"eval_accuracy": 0.82,
|
| 128 |
+
"eval_loss": 1.1369585990905762,
|
| 129 |
+
"eval_runtime": 71.7929,
|
| 130 |
+
"eval_samples_per_second": 1.393,
|
| 131 |
+
"eval_steps_per_second": 0.181,
|
| 132 |
+
"step": 84
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.01,
|
| 136 |
+
"learning_rate": 4.365079365079366e-06,
|
| 137 |
+
"loss": 0.001,
|
| 138 |
+
"step": 85
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.19,
|
| 142 |
+
"learning_rate": 3.968253968253968e-06,
|
| 143 |
+
"loss": 0.0476,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.36,
|
| 148 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 149 |
+
"loss": 0.0009,
|
| 150 |
+
"step": 95
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.54,
|
| 154 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 155 |
+
"loss": 0.0009,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.72,
|
| 160 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 161 |
+
"loss": 0.001,
|
| 162 |
+
"step": 105
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.89,
|
| 166 |
+
"learning_rate": 2.380952380952381e-06,
|
| 167 |
+
"loss": 0.0377,
|
| 168 |
+
"step": 110
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 4.0,
|
| 172 |
+
"eval_accuracy": 0.82,
|
| 173 |
+
"eval_loss": 1.142837643623352,
|
| 174 |
+
"eval_runtime": 71.2388,
|
| 175 |
+
"eval_samples_per_second": 1.404,
|
| 176 |
+
"eval_steps_per_second": 0.182,
|
| 177 |
+
"step": 113
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.07,
|
| 181 |
+
"learning_rate": 1.984126984126984e-06,
|
| 182 |
+
"loss": 0.0358,
|
| 183 |
+
"step": 115
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.25,
|
| 187 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 188 |
+
"loss": 0.0028,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.42,
|
| 193 |
+
"learning_rate": 1.1904761904761906e-06,
|
| 194 |
+
"loss": 0.0008,
|
| 195 |
+
"step": 125
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.6,
|
| 199 |
+
"learning_rate": 7.936507936507937e-07,
|
| 200 |
+
"loss": 0.0077,
|
| 201 |
+
"step": 130
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.78,
|
| 205 |
+
"learning_rate": 3.9682539682539683e-07,
|
| 206 |
+
"loss": 0.0008,
|
| 207 |
+
"step": 135
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.96,
|
| 211 |
+
"learning_rate": 0.0,
|
| 212 |
+
"loss": 0.0318,
|
| 213 |
+
"step": 140
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.96,
|
| 217 |
+
"eval_accuracy": 0.83,
|
| 218 |
+
"eval_loss": 1.1521978378295898,
|
| 219 |
+
"eval_runtime": 71.6822,
|
| 220 |
+
"eval_samples_per_second": 1.395,
|
| 221 |
+
"eval_steps_per_second": 0.181,
|
| 222 |
+
"step": 140
|
| 223 |
+
}
|
| 224 |
+
],
|
| 225 |
+
"logging_steps": 5,
|
| 226 |
+
"max_steps": 140,
|
| 227 |
+
"num_train_epochs": 5,
|
| 228 |
+
"save_steps": 500,
|
| 229 |
+
"total_flos": 3.043113204096e+17,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|
checkpoint-140/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c8327b62c2d89df2d87b86e12181649733dbdfae7f66da82435847a359e69a
|
| 3 |
+
size 4600
|