Upload folder using huggingface_hub

log/log-train-2026-01-13-17-17-08-1

@@ -0,0 +1,95 @@
+2026-01-13 17:17:08,223 INFO [train.py:967] (1/2) Training started
+2026-01-13 17:17:08,223 INFO [train.py:977] (1/2) Device: cuda:1
+2026-01-13 17:17:08,225 INFO [train.py:986] (1/2) {
+  "am_scale": 0.0,
+  "attention_dims": "192,192,192,192,192",
+  "average_period": 200,
+  "base_lr": 0.05,
+  "batch_idx_train": 0,
+  "best_train_epoch": -1,
+  "best_train_loss": Infinity,
+  "best_valid_epoch": -1,
+  "best_valid_loss": Infinity,
+  "blank_id": 0,
+  "bpe_model": "/kaggle/working/amharic_training/bpe/bpe.model",
+  "bucketing_sampler": true,
+  "cnn_module_kernels": "31,31,31,31,31",
+  "concatenate_cuts": false,
+  "context_size": 2,
+  "decode_chunk_len": 32,
+  "decoder_dim": 512,
+  "drop_last": true,
+  "duration_factor": 1.0,
+  "enable_musan": false,
+  "enable_spec_aug": true,
+  "encoder_dims": "384,384,384,384,384",
+  "encoder_unmasked_dims": "256,256,256,256,256",
+  "env_info": {
+    "IP address": "172.19.2.2",
+    "hostname": "6ec37ec2ba95",
+    "icefall-git-branch": "master",
+    "icefall-git-date": "Fri Nov 28 03:42:20 2025",
+    "icefall-git-sha1": "0904e490-clean",
+    "icefall-path": "/kaggle/working/icefall",
+    "k2-build-type": "Release",
+    "k2-git-date": "Thu Jul 25 03:34:26 2024",
+    "k2-git-sha1": "40e8d1676f6062e46458dc32ad21229c93cc9c50",
+    "k2-path": "/usr/local/lib/python3.12/dist-packages/k2/__init__.py",
+    "k2-version": "1.24.4",
+    "k2-with-cuda": true,
+    "lhotse-path": "/usr/local/lib/python3.12/dist-packages/lhotse/__init__.py",
+    "lhotse-version": "1.32.1",
+    "python-version": "3.12",
+    "torch-cuda-available": true,
+    "torch-cuda-version": "12.1",
+    "torch-version": "2.4.0+cu121"
+  },
+  "exp_dir": "/kaggle/working/amharic_training/exp_amharic_streaming",
+  "feature_dim": 80,
+  "feedforward_dims": "1024,1024,2048,2048,1024",
+  "full_libri": false,
+  "gap": 1.0,
+  "inf_check": false,
+  "input_strategy": "PrecomputedFeatures",
+  "joiner_dim": 512,
+  "keep_last_k": 5,
+  "lm_scale": 0.25,
+  "log_interval": 50,
+  "lr_batches": 5000,
+  "lr_epochs": 3.5,
+  "manifest_dir": "/kaggle/working/amharic_training/manifests",
+  "master_port": 12354,
+  "max_duration": 120,
+  "mini_libri": false,
+  "nhead": "8,8,8,8,8",
+  "num_buckets": 30,
+  "num_encoder_layers": "2,4,3,2,4",
+  "num_epochs": 50,
+  "num_left_chunks": 4,
+  "num_workers": 2,
+  "on_the_fly_feats": false,
+  "print_diagnostics": false,
+  "prune_range": 5,
+  "reset_interval": 200,
+  "return_cuts": true,
+  "save_every_n": 1000,
+  "seed": 42,
+  "short_chunk_size": 50,
+  "shuffle": true,
+  "simple_loss_scale": 0.5,
+  "spec_aug_time_warp_factor": 80,
+  "start_batch": 0,
+  "start_epoch": 1,
+  "subsampling_factor": 4,
+  "tensorboard": true,
+  "use_fp16": true,
+  "valid_interval": 1600,
+  "vocab_size": 1000,
+  "warm_step": 2000,
+  "world_size": 2,
+  "zipformer_downsampling_factors": "1,2,4,8,2"
+}
+2026-01-13 17:17:08,226 INFO [train.py:988] (1/2) About to create model
+2026-01-13 17:17:08,848 INFO [zipformer.py:405] (1/2) At encoder stack 4, which has downsampling_factor=2, we will combine the outputs of layers 1 and 3, with downsampling_factors=2 and 8.
+2026-01-13 17:17:08,866 INFO [train.py:992] (1/2) Number of model parameters: 71330891
+2026-01-13 17:17:08,973 INFO [train.py:1007] (1/2) Using DDP