Training in progress, step 300, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,52 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperEncoderOnlyForClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "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_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper_encoder_classifier",
+  "n_code": 1965,
+  "n_fam": 11,
+  "n_super": 68,
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.56.2",
+  "unsloth_version": "2025.12.8",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389139e8293cf0265bd0dd8a65a2482d21cc51a5fa821642143b7daf82f108b0
+size 2558403928

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7507fef582f26fa6dd26593efcff1fe00c92de5de40a9e14d4bcfae3d4660cf5
+size 1313044361

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bfeac7f2161ffd59c7dec4e192c42f83cdf28d8494d04d02013314243750b1
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30af866df24edce708e1eb20700878b402fa05707fa9bc5f332496baf440dbbb
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7f847589ff5ebc49461e971738b280435583eb06a67d9e67099912165ff9ed
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004,
+      "grad_norm": 8.119571685791016,
+      "learning_rate": 0.0,
+      "loss": 3.4677,
+      "step": 1
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 8.098031997680664,
+      "learning_rate": 9e-06,
+      "loss": 4.4682,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 8.463135719299316,
+      "learning_rate": 1.9e-05,
+      "loss": 4.6132,
+      "step": 20
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 7.452148914337158,
+      "learning_rate": 2.9e-05,
+      "loss": 4.223,
+      "step": 30
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 5.572236061096191,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 4.4111,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 7.39447021484375,
+      "learning_rate": 4.9e-05,
+      "loss": 4.0543,
+      "step": 50
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 9.954078674316406,
+      "learning_rate": 4.999833521640187e-05,
+      "loss": 4.5007,
+      "step": 60
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 5.994736194610596,
+      "learning_rate": 4.9992580693557054e-05,
+      "loss": 4.6204,
+      "step": 70
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 7.18951940536499,
+      "learning_rate": 4.998271682453017e-05,
+      "loss": 4.2467,
+      "step": 80
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 9.591761589050293,
+      "learning_rate": 4.996874523116464e-05,
+      "loss": 4.4063,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.566534519195557,
+      "learning_rate": 4.995066821070679e-05,
+      "loss": 4.0773,
+      "step": 100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 5.793056488037109,
+      "learning_rate": 4.9928488735428105e-05,
+      "loss": 4.063,
+      "step": 110
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 7.917051792144775,
+      "learning_rate": 4.990221045213652e-05,
+      "loss": 4.2533,
+      "step": 120
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 7.804363250732422,
+      "learning_rate": 4.987183768157686e-05,
+      "loss": 4.0497,
+      "step": 130
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 7.605108261108398,
+      "learning_rate": 4.983737541772033e-05,
+      "loss": 4.4334,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.323838233947754,
+      "learning_rate": 4.979882932694346e-05,
+      "loss": 4.0412,
+      "step": 150
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 9.219818115234375,
+      "learning_rate": 4.9756205747096385e-05,
+      "loss": 3.9774,
+      "step": 160
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 8.375937461853027,
+      "learning_rate": 4.9709511686460775e-05,
+      "loss": 4.0021,
+      "step": 170
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 8.215436935424805,
+      "learning_rate": 4.96587548225975e-05,
+      "loss": 4.4227,
+      "step": 180
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 9.561295509338379,
+      "learning_rate": 4.960394350108429e-05,
+      "loss": 4.1091,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.014528274536133,
+      "learning_rate": 4.954508673414351e-05,
+      "loss": 3.9428,
+      "step": 200
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 7.69431209564209,
+      "learning_rate": 4.948219419916037e-05,
+      "loss": 4.368,
+      "step": 210
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 11.925583839416504,
+      "learning_rate": 4.941527623709172e-05,
+      "loss": 3.6757,
+      "step": 220
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 8.191117286682129,
+      "learning_rate": 4.934434385076576e-05,
+      "loss": 4.1905,
+      "step": 230
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 7.863613128662109,
+      "learning_rate": 4.926940870307296e-05,
+      "loss": 4.0099,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 10.665002822875977,
+      "learning_rate": 4.9190483115048375e-05,
+      "loss": 3.9059,
+      "step": 250
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 10.385906219482422,
+      "learning_rate": 4.910758006384583e-05,
+      "loss": 3.9221,
+      "step": 260
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 8.544922828674316,
+      "learning_rate": 4.9020713180604126e-05,
+      "loss": 3.9398,
+      "step": 270
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 7.989080429077148,
+      "learning_rate": 4.892989674820585e-05,
+      "loss": 3.7757,
+      "step": 280
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 6.576107025146484,
+      "learning_rate": 4.8835145698928856e-05,
+      "loss": 3.5309,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.80089282989502,
+      "learning_rate": 4.873647561199115e-05,
+      "loss": 4.1776,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.41041809391616e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96555ac3c0979f5dce122c8f700ea90690bfa57f9771c6c52bfcefa74d7b8abe
+size 5841