lade till checkpoint

checkpoint-1000/config.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/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bc2c82a0c7ebb3e6cd0d1f54250daece0b4fabc6756649e495edcf07213cb1
+size 14503

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6f5a26544d77b7a9117cf0f491edbac06fba0acbfff578e5ef1a9715ef1d5a
+size 559

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309511db1ddf7147c73ec796441878bda2593bb3c9c2a7c34fac9c91aa858337
+size 623

checkpoint-1000/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_metric": 21.513269339356295,
+  "best_model_checkpoint": "./whisper-small-sv-SE/checkpoint-1000",
+  "epoch": 1.2936610608020698,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 4.1985,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.200000000000001e-07,
+      "loss": 3.3699,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.42e-06,
+      "loss": 2.4858,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.4969,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.42e-06,
+      "loss": 1.1419,
+      "step": 125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.92e-06,
+      "loss": 1.0148,
+      "step": 150
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.4200000000000007e-06,
+      "loss": 0.9295,
+      "step": 175
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.8613,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.42e-06,
+      "loss": 0.7114,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.92e-06,
+      "loss": 0.6183,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.420000000000001e-06,
+      "loss": 0.4704,
+      "step": 275
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.92e-06,
+      "loss": 0.3114,
+      "step": 300
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.42e-06,
+      "loss": 0.338,
+      "step": 325
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.92e-06,
+      "loss": 0.2958,
+      "step": 350
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.420000000000001e-06,
+      "loss": 0.3174,
+      "step": 375
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 7.92e-06,
+      "loss": 0.3205,
+      "step": 400
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.42e-06,
+      "loss": 0.3135,
+      "step": 425
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.920000000000001e-06,
+      "loss": 0.3043,
+      "step": 450
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.42e-06,
+      "loss": 0.2761,
+      "step": 475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.920000000000002e-06,
+      "loss": 0.3105,
+      "step": 500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 0.2965,
+      "step": 525
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.86857142857143e-06,
+      "loss": 0.2924,
+      "step": 550
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.797142857142858e-06,
+      "loss": 0.3032,
+      "step": 575
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.725714285714287e-06,
+      "loss": 0.31,
+      "step": 600
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.654285714285716e-06,
+      "loss": 0.2935,
+      "step": 625
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.582857142857143e-06,
+      "loss": 0.3066,
+      "step": 650
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.511428571428572e-06,
+      "loss": 0.2755,
+      "step": 675
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 0.2881,
+      "step": 700
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.368571428571428e-06,
+      "loss": 0.2916,
+      "step": 725
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.297142857142857e-06,
+      "loss": 0.2859,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.225714285714286e-06,
+      "loss": 0.2802,
+      "step": 775
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.154285714285715e-06,
+      "loss": 0.1393,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.082857142857143e-06,
+      "loss": 0.1485,
+      "step": 825
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.011428571428572e-06,
+      "loss": 0.1489,
+      "step": 850
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.94e-06,
+      "loss": 0.1303,
+      "step": 875
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.86857142857143e-06,
+      "loss": 0.1503,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.797142857142857e-06,
+      "loss": 0.1574,
+      "step": 925
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.725714285714286e-06,
+      "loss": 0.1526,
+      "step": 950
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.654285714285715e-06,
+      "loss": 0.1497,
+      "step": 975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 8.582857142857144e-06,
+      "loss": 0.1375,
+      "step": 1000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.2958570122718811,
+      "eval_runtime": 2113.6861,
+      "eval_samples_per_second": 2.398,
+      "eval_steps_per_second": 0.3,
+      "eval_wer": 21.513269339356295,
+      "step": 1000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 6,
+  "total_flos": 4.61505772191744e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2086aa9952f52d5f3b83b20eb6b34ff8af093010381c864c36f14dd768432483
+size 3567