End of training

check-500/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Martha-987/whisper-small-Arabic-aar",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "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,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51865
+}

check-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f71e37c76d17d37b6c49bb6a06e88743c3d4d0dd59c914c9ca0ab4201476e4
+size 1934161093

check-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23b42f5b3ab491865863fb24d42677e6befbc7b433819cd00967ec7a3d0b440
+size 967102601

check-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532443d81ef4fb524dc55aadfa88d56a742d906f97342a48a45079087affca6c
+size 14575

check-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e3020d2b05d1d52f5d7b6ff366145852484245f7f1a72fd8585891d54324d5
+size 557

check-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ab431eb947e595f4e748c0a429e67e01e4635f6b3bc217bdbe189bb67412fa
+size 627

check-500/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 54.78835735928749,
+  "best_model_checkpoint": "./whisper-small-Arabic-aar11/checkpoint-500",
+  "epoch": 0.20781379883624274,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 0.4095,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 0.367,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.46e-06,
+      "loss": 0.3891,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 0.3948,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.46e-06,
+      "loss": 0.392,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.96e-06,
+      "loss": 0.3581,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.46e-06,
+      "loss": 0.3859,
+      "step": 175
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.96e-06,
+      "loss": 0.3538,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.4600000000000005e-06,
+      "loss": 0.3655,
+      "step": 225
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.960000000000001e-06,
+      "loss": 0.3524,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.460000000000001e-06,
+      "loss": 0.3462,
+      "step": 275
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.94e-06,
+      "loss": 0.3635,
+      "step": 300
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 0.3448,
+      "step": 325
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 0.3565,
+      "step": 350
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 0.3398,
+      "step": 375
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.94e-06,
+      "loss": 0.3582,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.44e-06,
+      "loss": 0.3824,
+      "step": 425
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.94e-06,
+      "loss": 0.3858,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.3145,
+      "step": 475
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.3256,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4237127900123596,
+      "eval_runtime": 4883.7495,
+      "eval_samples_per_second": 2.138,
+      "eval_steps_per_second": 0.267,
+      "eval_wer": 54.78835735928749,
+      "step": 500
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 1,
+  "total_flos": 2.30868320256e+18,
+  "trial_name": null,
+  "trial_params": null
+}

check-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c9b4273b92e769ca0ed0bf95124af0ee366f4bc6706fbb1368bb9beff2810f
+size 3643