Upload checkpoint-1000 with huggingface_hub

checkpoint-1000/config (5).json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "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
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ae001d56fc22cf99b14d892a4bb166f1e30174e851cc3934d271753beb540c
+size 1934161093

checkpoint-1000/pytorch_model (3).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325219cdd0a28326de2172bd3df6924b2f4b2e7a6a59e35fb2070a0fecf5e0a3
+size 967102601

checkpoint-1000/rng_state (2).pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f0089eb47760f9be550d5a46ecb3cef5953026a997e1a02e6301f4086d5ec3
+size 14511

checkpoint-1000/scaler (2).pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95b5e63a2de24f8c8c9db56d650764aad12cf45e225f186d23cfc18a4c7a34a
+size 557

checkpoint-1000/scheduler (2).pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6adcde01329da1c49a2d134cbe54a6b362ab48eeb83973a53b8bbb28a1e83f
+size 627

checkpoint-1000/trainer_state (2).json

@@ -0,0 +1,265 @@
+{
+  "best_metric": 51.185382425856204,
+  "best_model_checkpoint": "./whisper-small-Arabicc1/checkpoint-1000",
+  "epoch": 0.41562759767248547,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 3.262,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.200000000000001e-07,
+      "loss": 2.5218,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.42e-06,
+      "loss": 1.7958,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.2313,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.42e-06,
+      "loss": 1.0969,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.92e-06,
+      "loss": 0.9609,
+      "step": 150
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.4200000000000007e-06,
+      "loss": 0.9173,
+      "step": 175
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.8191,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.42e-06,
+      "loss": 0.7742,
+      "step": 225
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.92e-06,
+      "loss": 0.6781,
+      "step": 250
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.420000000000001e-06,
+      "loss": 0.5776,
+      "step": 275
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.92e-06,
+      "loss": 0.4557,
+      "step": 300
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.42e-06,
+      "loss": 0.4113,
+      "step": 325
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.92e-06,
+      "loss": 0.4198,
+      "step": 350
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.420000000000001e-06,
+      "loss": 0.393,
+      "step": 375
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.92e-06,
+      "loss": 0.4105,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.42e-06,
+      "loss": 0.4266,
+      "step": 425
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.920000000000001e-06,
+      "loss": 0.4303,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.42e-06,
+      "loss": 0.3524,
+      "step": 475
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.920000000000002e-06,
+      "loss": 0.3636,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.58e-06,
+      "loss": 0.3609,
+      "step": 525
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 0.3359,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 0.3273,
+      "step": 575
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.08e-06,
+      "loss": 0.3641,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 7.58e-06,
+      "loss": 0.3759,
+      "step": 625
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 7.08e-06,
+      "loss": 0.3445,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 0.3277,
+      "step": 675
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.08e-06,
+      "loss": 0.3411,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 0.3377,
+      "step": 725
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.0800000000000005e-06,
+      "loss": 0.3398,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.58e-06,
+      "loss": 0.3125,
+      "step": 775
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.08e-06,
+      "loss": 0.3291,
+      "step": 800
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.58e-06,
+      "loss": 0.3104,
+      "step": 825
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.08e-06,
+      "loss": 0.299,
+      "step": 850
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 0.2963,
+      "step": 875
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.08e-06,
+      "loss": 0.3068,
+      "step": 900
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 0.3393,
+      "step": 925
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.08e-06,
+      "loss": 0.3138,
+      "step": 950
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 0.3214,
+      "step": 975
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8e-08,
+      "loss": 0.2726,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.38373443484306335,
+      "eval_runtime": 4844.9923,
+      "eval_samples_per_second": 2.155,
+      "eval_steps_per_second": 0.269,
+      "eval_wer": 51.185382425856204,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 1,
+  "total_flos": 4.61736640512e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args (5).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554771e2c89811c21892a38338011221c19fff7d10fb3b6aeeaa38f7349a930a
+size 3643