Upload folder using huggingface_hub

checkpoint-1164/config.json

@@ -0,0 +1,47 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "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_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-1164/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "pad_token_id": 50257,
+  "suppress_tokens": [],
+  "transformers_version": "4.52.4",
+  "use_cache": false
+}

checkpoint-1164/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc0dd3713ca1fe3a5898c6d99b3f98fa468879f401331578f9dfb2d6c2e4e4b
+size 966995080

checkpoint-1164/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2d4e589058cd51f313e1914273e898aa600a18958dc5cd5db0c09674a8d0f9
+size 1925064044

checkpoint-1164/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}

checkpoint-1164/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ee6d1fa1e906d3a168a00ea76c602f7376b652736afa03acbc3fb1aee7b72c
+size 14244

checkpoint-1164/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc8422fe5087e9de012c63ae503b55efb9eff33fca88c14997ba0afd718c4a3
+size 988

checkpoint-1164/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45373ddaa9fd2ce860307ef6fe2c7f7941c18c340727eac7ac5cc3b871cf008f
+size 1064

checkpoint-1164/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 29.237737985703166,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1164,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34393809114359414,
+      "grad_norm": 4.264090538024902,
+      "learning_rate": 9.950000000000001e-06,
+      "loss": 0.3063,
+      "step": 200
+    },
+    {
+      "epoch": 0.6878761822871883,
+      "grad_norm": 4.479090690612793,
+      "learning_rate": 7.935684647302904e-06,
+      "loss": 0.27,
+      "step": 400
+    },
+    {
+      "epoch": 0.8598452278589854,
+      "eval_loss": 0.42083939909935,
+      "eval_runtime": 3551.6805,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.164,
+      "eval_wer": 30.74999410196523,
+      "step": 500
+    },
+    {
+      "epoch": 1.0309544282029235,
+      "grad_norm": 3.53800368309021,
+      "learning_rate": 5.860995850622408e-06,
+      "loss": 0.2493,
+      "step": 600
+    },
+    {
+      "epoch": 1.3748925193465176,
+      "grad_norm": 3.7234232425689697,
+      "learning_rate": 3.786307053941909e-06,
+      "loss": 0.1682,
+      "step": 800
+    },
+    {
+      "epoch": 1.7188306104901119,
+      "grad_norm": 3.9923925399780273,
+      "learning_rate": 1.711618257261411e-06,
+      "loss": 0.1779,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7188306104901119,
+      "eval_loss": 0.4090772867202759,
+      "eval_runtime": 3535.4367,
+      "eval_samples_per_second": 1.315,
+      "eval_steps_per_second": 0.165,
+      "eval_wer": 29.237737985703166,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 1164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.073364537950208e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1164/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669ce0265b300c16f5d56d8a1ebe99c865163f36a78f2831f29e322c8307c933
+size 5432