Training in progress, epoch 1, checkpoint

checkpoint-42/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-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4252e23666fa5e5cd26e0773b843a1e56ca80790026c247befe64e9c5153a631
+size 94771728

checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701caae72efe414fdf5a76bafcb4d73d99766494f49a249eafe7ede30cc221ec
+size 189575930

checkpoint-42/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-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6badfb232c6e781d8722f91e29d3ff9d2f222ba4eadfdff1aea46ce3a48ff41
+size 14244

checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373736c4b7a529bcd7e342f31bcd224ca3acce1c2be3bd194fb4a60614d1660a
+size 1064

checkpoint-42/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.84,
+  "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-21",
+  "epoch": 1.96,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.0321,
+      "step": 5
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.0077,
+      "step": 10
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8571428571428574e-05,
+      "loss": 0.0345,
+      "step": 15
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.80952380952381e-05,
+      "loss": 0.0009,
+      "step": 20
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.84,
+      "eval_loss": 1.215333342552185,
+      "eval_runtime": 71.621,
+      "eval_samples_per_second": 1.396,
+      "eval_steps_per_second": 0.237,
+      "step": 21
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.9153439153439155e-05,
+      "loss": 0.0094,
+      "step": 25
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.80952380952381e-05,
+      "loss": 0.0319,
+      "step": 30
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.703703703703704e-05,
+      "loss": 0.0006,
+      "step": 35
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.597883597883598e-05,
+      "loss": 0.0122,
+      "step": 40
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.82,
+      "eval_loss": 1.2078099250793457,
+      "eval_runtime": 72.4494,
+      "eval_samples_per_second": 1.38,
+      "eval_steps_per_second": 0.235,
+      "step": 42
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 210,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.2267976549248e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993ac23386c550d4dd26922cb1cbafc1a8195ab1902207d39addd6b52e321d14
+size 4600