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 sha256:1fdf1a1570fce8cb8a511cc2680db42f6a86daade195e32b0f0d6e6020e2ecd2
+size 966995080

checkpoint-1164/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0c1edbe9e927926cedb6d7123818953fdb598574349923d52d3d71dcccf2fb
+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 sha256:3daf01d3476e111f35c616b0afb4b7ab2bf92b985b92dce6585cb39e81e48909
+size 988

checkpoint-1164/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feedc884630318a5a88102665484edeec4b02f24462a5f54e6ab53281d686b2e
+size 1064

checkpoint-1164/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_global_step": 800,
+  "best_metric": 7.272170821856534,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 400,
+  "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": 4.169175624847412,
+      "learning_rate": 9.950000000000001e-06,
+      "loss": 0.1094,
+      "step": 200
+    },
+    {
+      "epoch": 0.6878761822871883,
+      "grad_norm": 3.851189613342285,
+      "learning_rate": 7.946058091286308e-06,
+      "loss": 0.1075,
+      "step": 400
+    },
+    {
+      "epoch": 0.6878761822871883,
+      "eval_loss": 0.10680446028709412,
+      "eval_runtime": 3328.993,
+      "eval_samples_per_second": 1.397,
+      "eval_steps_per_second": 0.175,
+      "eval_wer": 8.390423052475457,
+      "step": 400
+    },
+    {
+      "epoch": 1.0309544282029235,
+      "grad_norm": 2.2491328716278076,
+      "learning_rate": 5.87136929460581e-06,
+      "loss": 0.0919,
+      "step": 600
+    },
+    {
+      "epoch": 1.3748925193465176,
+      "grad_norm": 1.6838488578796387,
+      "learning_rate": 3.7966804979253114e-06,
+      "loss": 0.0335,
+      "step": 800
+    },
+    {
+      "epoch": 1.3748925193465176,
+      "eval_loss": 0.10098689794540405,
+      "eval_runtime": 2901.1453,
+      "eval_samples_per_second": 1.603,
+      "eval_steps_per_second": 0.201,
+      "eval_wer": 7.272170821856534,
+      "step": 800
+    },
+    {
+      "epoch": 1.7188306104901119,
+      "grad_norm": 3.0112545490264893,
+      "learning_rate": 1.7219917012448133e-06,
+      "loss": 0.0339,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 1164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1200,
+  "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:c8d9dde94d2021ed6939900b1cbe80ab1eeddcf09b80bc21b6e82b311b313545
+size 5432