Update latest checkpoint

log/log-train-2026-01-13-11-24-40

@@ -0,0 +1,123 @@
+2026-01-13 11:24:40,921 INFO [train.py:967] Training started
+2026-01-13 11:24:40,922 INFO [train.py:977] Device: cuda:0
+2026-01-13 11:24:40,925 INFO [train.py:986] {
+  "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": "8e64ffbd666a",
+    "icefall-git-branch": "master",
+    "icefall-git-date": "Fri Nov 28 03:42:20 2025",
+    "icefall-git-sha1": "0904e490-dirty",
+    "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": 1,
+  "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": 60,
+  "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": 1,
+  "zipformer_downsampling_factors": "1,2,4,8,2"
+}
+2026-01-13 11:24:40,925 INFO [train.py:988] About to create model
+2026-01-13 11:24:41,536 INFO [zipformer.py:405] 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 11:24:41,554 INFO [train.py:992] Number of model parameters: 71330891
+2026-01-13 11:24:43,824 INFO [asr_datamodule.py:422] About to get train-clean-100 cuts
+2026-01-13 11:24:43,825 INFO [asr_datamodule.py:239] Disable MUSAN
+2026-01-13 11:24:43,825 INFO [asr_datamodule.py:257] Enable SpecAugment
+2026-01-13 11:24:43,825 INFO [asr_datamodule.py:258] Time warp factor: 80
+2026-01-13 11:24:43,826 INFO [asr_datamodule.py:268] Num frame mask: 10
+2026-01-13 11:24:43,826 INFO [asr_datamodule.py:281] About to create train dataset
+2026-01-13 11:24:43,826 INFO [asr_datamodule.py:308] Using DynamicBucketingSampler.
+2026-01-13 11:24:44,140 INFO [asr_datamodule.py:324] About to create train dataloader
+2026-01-13 11:24:44,140 INFO [asr_datamodule.py:460] About to get dev-clean cuts
+2026-01-13 11:24:44,141 INFO [asr_datamodule.py:467] About to get dev-other cuts
+2026-01-13 11:24:44,141 INFO [asr_datamodule.py:355] About to create dev dataset
+2026-01-13 11:24:44,334 INFO [asr_datamodule.py:372] About to create dev dataloader
+2026-01-13 11:24:47,893 INFO [train.py:895] Epoch 1, batch 0, loss[loss=8.347, simple_loss=7.594, pruned_loss=7.506, over 1138.00 frames. ], tot_loss[loss=8.347, simple_loss=7.594, pruned_loss=7.506, over 1138.00 frames. ], batch size: 3, lr: 2.50e-02, grad_scale: 2.0
+2026-01-13 11:24:47,894 INFO [train.py:920] Computing validation loss
+2026-01-13 11:25:49,674 INFO [zipformer.py:2441] attn_weights_entropy = tensor([2.9199, 2.9204, 2.9209, 2.9167, 2.9196, 2.9205, 2.9204, 2.9204],
+       device='cuda:0'), covar=tensor([0.0048, 0.0085, 0.0084, 0.0041, 0.0051, 0.0054, 0.0087, 0.0047],
+       device='cuda:0'), in_proj_covar=tensor([0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009],
+       device='cuda:0'), out_proj_covar=tensor([8.5571e-06, 8.6460e-06, 8.6548e-06, 8.5692e-06, 8.8457e-06, 8.6909e-06,
+        8.7530e-06, 8.7241e-06], device='cuda:0')
+2026-01-13 11:26:30,538 INFO [zipformer.py:2441] attn_weights_entropy = tensor([4.2729, 4.2729, 4.2729, 4.2729, 4.2729, 4.2729, 4.2729, 4.2729],
+       device='cuda:0'), covar=tensor([0.0003, 0.0002, 0.0003, 0.0002, 0.0002, 0.0003, 0.0001, 0.0003],
+       device='cuda:0'), in_proj_covar=tensor([0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0008],
+       device='cuda:0'), out_proj_covar=tensor([8.8449e-06, 8.8559e-06, 8.7936e-06, 8.6492e-06, 8.7990e-06, 8.7099e-06,
+        8.5965e-06, 8.7138e-06], device='cuda:0')
+2026-01-13 11:26:45,813 INFO [zipformer.py:2441] attn_weights_entropy = tensor([3.5795, 3.5857, 3.5854, 3.5868, 3.5840, 3.5854, 3.5849, 3.5870],
+       device='cuda:0'), covar=tensor([0.0071, 0.0040, 0.0091, 0.0069, 0.0067, 0.0080, 0.0082, 0.0090],
+       device='cuda:0'), in_proj_covar=tensor([0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009, 0.0009],
+       device='cuda:0'), out_proj_covar=tensor([8.7006e-06, 8.7710e-06, 8.6193e-06, 8.7975e-06, 8.6463e-06, 8.7048e-06,
+        8.7000e-06, 8.8221e-06], device='cuda:0')

tensorboard/events.out.tfevents.1768303480.8e64ffbd666a.84129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f145c404960eccd40673635221acc99443610080542ee3d3d1f0f0bc8e34fcc9
+size 598

tensorboard/events.out.tfevents.1768303480.8e64ffbd666a.84130.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2c6a2446e890bbd3264a5e2bf1f87a91751443ad5639f3fab09e821cea2713
+size 598