Training in progress, epoch 0, checkpoint

checkpoint-56/config.json

@@ -0,0 +1,96 @@
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoint-56/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79260246d365035f9707e2ebe4f56571ebbf8991f8149a4077a2a601171c30ac
+size 94771728

checkpoint-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9082cd06dd579e3271d0105b56f0d8e846c9e545c7a06e61cb41e5a2ccc840c1
+size 189575930

checkpoint-56/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d80c482adc0bf69fb6533d98998b0f610c663026a7d2d3e262919fe827b14b0
+size 14244

checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a41d9d94f50ff1436cbdabc7e4624705b1da0b0f8d7c8ca0a9d41940a9f16e
+size 1064

checkpoint-56/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.27,
+  "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
+  "epoch": 0.9911504424778761,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.464285714285714e-05,
+      "loss": 2.2976,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.928571428571429e-05,
+      "loss": 2.2855,
+      "step": 10
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00013392857142857144,
+      "loss": 2.2307,
+      "step": 15
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00017857142857142857,
+      "loss": 2.1327,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00022321428571428573,
+      "loss": 2.0339,
+      "step": 25
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00026785714285714287,
+      "loss": 1.9633,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003125,
+      "loss": 1.8021,
+      "step": 35
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00035714285714285714,
+      "loss": 1.6938,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00040178571428571433,
+      "loss": 1.5271,
+      "step": 45
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00044642857142857147,
+      "loss": 1.4038,
+      "step": 50
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0004910714285714286,
+      "loss": 1.496,
+      "step": 55
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.27,
+      "eval_loss": 1.8467493057250977,
+      "eval_runtime": 72.5718,
+      "eval_samples_per_second": 1.378,
+      "eval_steps_per_second": 0.179,
+      "step": 56
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 560,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.133988274624e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-56/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbef9bdfa53985d2dd1361cb595119941d5a4b9581e158c102613a779ed26711
+size 4600