Training in progress, epoch 2, checkpoint

checkpoint-84/config.json

@@ -0,0 +1,96 @@
+{
+  "_name_or_path": "arshsin/distilhubert-finetuned-gtzan",
+  "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-84/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b274b4c0e6c8625909c2b25c338552edfd6a19c16f9da6263e2867aafaff72
+size 94771728

checkpoint-84/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b58f100be412ba2bef69185d7cda47d826a1113f6f3a84c1bf6076ec025e51
+size 189575930

checkpoint-84/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-84/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327ffa16e04a18d6cf6fc20109cf07704071d784619bc9d12d9c1dd6a7410d3a
+size 14244

checkpoint-84/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bbe5fa64984a394f535799459e89b80b6fde64026917648b3c3f0f3149e2a0
+size 1064

checkpoint-84/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": 0.83,
+  "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
+  "epoch": 2.9734513274336285,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.0338,
+      "step": 5
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0053,
+      "step": 10
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.920634920634922e-06,
+      "loss": 0.0056,
+      "step": 15
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.0437,
+      "step": 20
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.126984126984127e-06,
+      "loss": 0.0017,
+      "step": 25
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.82,
+      "eval_loss": 1.0909959077835083,
+      "eval_runtime": 72.1207,
+      "eval_samples_per_second": 1.387,
+      "eval_steps_per_second": 0.18,
+      "step": 28
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.730158730158731e-06,
+      "loss": 0.0013,
+      "step": 30
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0373,
+      "step": 35
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.0041,
+      "step": 40
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 7.53968253968254e-06,
+      "loss": 0.0012,
+      "step": 45
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0338,
+      "step": 50
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.746031746031747e-06,
+      "loss": 0.0143,
+      "step": 55
+    },
+    {
+      "epoch": 1.98,
+      "eval_accuracy": 0.83,
+      "eval_loss": 1.1379410028457642,
+      "eval_runtime": 71.5138,
+      "eval_samples_per_second": 1.398,
+      "eval_steps_per_second": 0.182,
+      "step": 56
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 0.036,
+      "step": 60
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 0.001,
+      "step": 65
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.0412,
+      "step": 70
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.15873015873016e-06,
+      "loss": 0.001,
+      "step": 75
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.01,
+      "step": 80
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.82,
+      "eval_loss": 1.1369585990905762,
+      "eval_runtime": 71.7929,
+      "eval_samples_per_second": 1.393,
+      "eval_steps_per_second": 0.181,
+      "step": 84
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 140,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.8401964823872e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-84/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c8327b62c2d89df2d87b86e12181649733dbdfae7f66da82435847a359e69a
+size 4600