Upload folder using huggingface_hub

config.json

@@ -0,0 +1,48 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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,
+  "max_source_positions": 50,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf450316310bd2dfaec62f0f4fa8125234a80696ad45991074548715e60e99a
+size 2541820056

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4340bad1ecad21aff8080fabc3ba2525fe0b4809ea0899766db3a4d3be838779
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad29f50bd0008e7400dd1fe22125f0edd923eb4d04e3097158b9279e11ec725
+size 1465

trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_global_step": 115,
+  "best_metric": 0.995475113122172,
+  "best_model_checkpoint": "wav2vec2_frog_classifier_sew_d/checkpoint-115",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 10.85987377166748,
+      "learning_rate": 4.891304347826088e-07,
+      "loss": 0.6973,
+      "step": 10
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 13.688446998596191,
+      "learning_rate": 1.032608695652174e-06,
+      "loss": 0.4829,
+      "step": 20
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 30.344524383544922,
+      "learning_rate": 1.5760869565217394e-06,
+      "loss": 0.304,
+      "step": 30
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4.452210426330566,
+      "learning_rate": 2.1195652173913046e-06,
+      "loss": 0.2746,
+      "step": 40
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 98.70622253417969,
+      "learning_rate": 2.6630434782608698e-06,
+      "loss": 0.2312,
+      "step": 50
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 2.581968069076538,
+      "learning_rate": 3.206521739130435e-06,
+      "loss": 0.1619,
+      "step": 60
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 13.092533111572266,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.1114,
+      "step": 70
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.7139033675193787,
+      "learning_rate": 4.293478260869566e-06,
+      "loss": 0.0281,
+      "step": 80
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.22714175283908844,
+      "learning_rate": 4.836956521739131e-06,
+      "loss": 0.0137,
+      "step": 90
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.6208930015563965,
+      "learning_rate": 5.380434782608695e-06,
+      "loss": 0.07,
+      "step": 100
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.2036219835281372,
+      "learning_rate": 5.923913043478261e-06,
+      "loss": 0.1044,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.995475113122172,
+      "eval_fbeta": 0.9981850375328207,
+      "eval_loss": 0.021344376727938652,
+      "eval_precision": 1.0,
+      "eval_recall": 0.990990990990991,
+      "eval_runtime": 12.0249,
+      "eval_samples_per_second": 65.614,
+      "eval_steps_per_second": 8.233,
+      "step": 115
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.9737655576832e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9efb29a5b904dbccd1e1647929f5abf459953533c48c2467ca871dae8496a9
+size 5777