Model save

README.md

@@ -0,0 +1,84 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: openai/whisper-base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: exp_002_base_lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# exp_002_base_lora
+
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5781
+- Wer: 54.5829
+- Wer Ortho: 57.7728
+- Cer: 17.2107
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer     | Wer Ortho | Cer     |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:---------:|:-------:|
+| 2.364         | 0.05  | 500   | 1.3775          | 89.3018 | 90.4210   | 30.2665 |
+| 1.9822        | 0.1   | 1000  | 1.0647          | 79.1535 | 81.1369   | 25.7959 |
+| 1.773         | 0.15  | 1500  | 0.8929          | 71.8646 | 74.4727   | 22.9622 |
+| 1.6612        | 1.044 | 2000  | 0.8104          | 68.2874 | 70.8852   | 20.9447 |
+| 1.5587        | 1.094 | 2500  | 0.7594          | 65.4784 | 68.2362   | 20.1626 |
+| 1.5063        | 1.144 | 3000  | 0.7234          | 63.3287 | 66.1393   | 19.5334 |
+| 1.4318        | 2.038 | 3500  | 0.6917          | 61.0404 | 64.1920   | 19.0537 |
+| 1.3879        | 2.088 | 4000  | 0.6697          | 59.6591 | 62.7346   | 18.5726 |
+| 1.3831        | 2.138 | 4500  | 0.6524          | 58.5128 | 61.6924   | 17.9122 |
+| 1.3231        | 3.032 | 5000  | 0.6385          | 59.3316 | 62.5270   | 19.6542 |
+| 1.3064        | 3.082 | 5500  | 0.6270          | 58.2777 | 61.2398   | 18.6335 |
+| 1.2766        | 3.132 | 6000  | 0.6143          | 56.9425 | 60.0897   | 18.0292 |
+| 1.255         | 4.026 | 6500  | 0.6063          | 57.1315 | 60.3056   | 18.3886 |
+| 1.2481        | 4.076 | 7000  | 0.5986          | 56.2203 | 59.3298   | 17.9156 |
+| 1.2161        | 4.126 | 7500  | 0.5905          | 55.6115 | 58.8274   | 17.8844 |
+| 1.2109        | 5.02  | 8000  | 0.5860          | 55.6535 | 58.8233   | 17.7709 |
+| 1.2183        | 5.07  | 8500  | 0.5834          | 55.3218 | 58.5202   | 17.4484 |
+| 1.1953        | 5.12  | 9000  | 0.5781          | 54.5829 | 57.7728   | 17.2107 |
+| 1.1721        | 6.014 | 9500  | 0.5760          | 54.8012 | 57.9347   | 17.4963 |
+| 1.1816        | 6.064 | 10000 | 0.5753          | 54.7718 | 57.8641   | 17.3142 |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.48.3
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d69242bd2d685d78862e6f8e3882b6daf3aed4297326f59d5602a506d1297d
+oid sha256:b53ff3848589132b36bcfce67569abe3dcf48bcd428b6ba293254c461c55484e
 size 9447288

experiment_log.txt

@@ -3821,3 +3821,292 @@ The attention mask is not set and cannot be inferred from input because pad toke
 
 
                                                 
                                                       
 
+
+Running final evaluation...
+
  0%|          | 0/176 [00:00<?, ?it/s]
  1%|          | 2/176 [00:00<01:03,  2.73it/s]
  2%|▏         | 3/176 [00:01<01:29,  1.93it/s]
  2%|▏         | 4/176 [00:02<01:45,  1.63it/s]
  3%|▎         | 5/176 [00:02<01:53,  1.51it/s]
  3%|▎         | 6/176 [00:03<01:59,  1.43it/s]
  4%|▍         | 7/176 [00:04<02:03,  1.37it/s]
  5%|▍         | 8/176 [00:05<02:03,  1.36it/s]
  5%|▌         | 9/176 [00:06<02:04,  1.34it/s]
  6%|▌         | 10/176 [00:06<02:06,  1.32it/s]
  6%|▋         | 11/176 [00:07<02:05,  1.32it/s]
  7%|▋         | 12/176 [00:08<02:05,  1.31it/s]
  7%|▋         | 13/176 [00:09<02:04,  1.31it/s]
  8%|▊         | 14/176 [00:09<02:01,  1.34it/s]
  9%|▊         | 15/176 [00:10<02:01,  1.32it/s]
  9%|▉         | 16/176 [00:11<01:59,  1.34it/s]
 10%|▉         | 17/176 [00:12<02:00,  1.32it/s]
 10%|█         | 18/176 [00:12<02:02,  1.29it/s]
 11%|█         | 19/176 [00:13<02:02,  1.28it/s]
 11%|█▏        | 20/176 [00:14<01:59,  1.30it/s]
 12%|█▏        | 21/176 [00:15<01:59,  1.30it/s]
 12%|█▎        | 22/176 [00:16<01:59,  1.29it/s]
 13%|█▎        | 23/176 [00:16<01:57,  1.30it/s]
 14%|█▎        | 24/176 [00:17<01:56,  1.31it/s]
 14%|█▍        | 25/176 [00:18<01:56,  1.30it/s]
 15%|█▍        | 26/176 [00:19<01:56,  1.29it/s]
 15%|█▌        | 27/176 [00:19<01:55,  1.29it/s]
 16%|█▌        | 28/176 [00:20<01:52,  1.31it/s]
 16%|█▋        | 29/176 [00:21<01:54,  1.28it/s]
 17%|█▋        | 30/176 [00:22<01:53,  1.29it/s]
 18%|█▊        | 31/176 [00:23<01:51,  1.30it/s]
 18%|█▊        | 32/176 [00:23<01:50,  1.31it/s]
 19%|█▉        | 33/176 [00:24<01:49,  1.31it/s]
 19%|█▉        | 34/176 [00:25<01:49,  1.29it/s]
 20%|█▉        | 35/176 [00:26<01:47,  1.31it/s]
 20%|██        | 36/176 [00:26<01:46,  1.32it/s]
 21%|██        | 37/176 [00:27<01:46,  1.30it/s]
 22%|██▏       | 38/176 [00:28<01:44,  1.32it/s]
 22%|██▏       | 39/176 [00:29<01:44,  1.31it/s]
 23%|██▎       | 40/176 [00:29<01:43,  1.32it/s]
 23%|██▎       | 41/176 [00:30<01:42,  1.31it/s]
 24%|██▍       | 42/176 [00:31<01:42,  1.30it/s]
 24%|██▍       | 43/176 [00:32<01:42,  1.30it/s]
 25%|██▌       | 44/176 [00:32<01:41,  1.30it/s]
 26%|██▌       | 45/176 [00:33<01:39,  1.32it/s]
 26%|██▌       | 46/176 [00:34<01:39,  1.30it/s]
 27%|██▋       | 47/176 [00:35<01:37,  1.32it/s]
 27%|██▋       | 48/176 [00:35<01:37,  1.32it/s]
 28%|██▊       | 49/176 [00:36<01:37,  1.30it/s]
 28%|██▊       | 50/176 [00:37<01:33,  1.34it/s]
 29%|██▉       | 51/176 [00:38<01:32,  1.35it/s]
 30%|██▉       | 52/176 [00:38<01:34,  1.32it/s]
 30%|███       | 53/176 [00:39<01:37,  1.26it/s]
 31%|███       | 54/176 [00:40<01:35,  1.27it/s]
 31%|███▏      | 55/176 [00:41<01:35,  1.27it/s]
 32%|███▏      | 56/176 [00:42<01:33,  1.28it/s]
 32%|███▏      | 57/176 [00:42<01:31,  1.30it/s]
 33%|███▎      | 58/176 [00:43<01:29,  1.32it/s]
 34%|███▎      | 59/176 [00:44<01:29,  1.31it/s]
 34%|███▍      | 60/176 [00:45<01:28,  1.31it/s]
 35%|███▍      | 61/176 [00:46<01:36,  1.19it/s]
 35%|███▌      | 62/176 [00:46<01:32,  1.23it/s]
 36%|███▌      | 63/176 [00:47<01:30,  1.25it/s]
 36%|███▋      | 64/176 [00:48<01:27,  1.27it/s]
 37%|███▋      | 65/176 [00:49<01:26,  1.29it/s]
 38%|███▊      | 66/176 [00:49<01:23,  1.32it/s]
 38%|███▊      | 67/176 [00:50<01:23,  1.30it/s]
 39%|███▊      | 68/176 [00:51<01:23,  1.29it/s]
 39%|███▉      | 69/176 [00:52<01:22,  1.29it/s]
 40%|███▉      | 70/176 [00:53<01:19,  1.33it/s]
 40%|████      | 71/176 [00:53<01:19,  1.32it/s]
 41%|████      | 72/176 [00:54<01:18,  1.32it/s]
 41%|████▏     | 73/176 [00:55<01:18,  1.31it/s]
 42%|████▏     | 74/176 [00:56<01:16,  1.33it/s]
 43%|████▎     | 75/176 [00:56<01:15,  1.33it/s]
 43%|████▎     | 76/176 [00:57<01:15,  1.32it/s]
 44%|████▍     | 77/176 [00:58<01:15,  1.31it/s]
 44%|████▍     | 78/176 [00:59<01:13,  1.33it/s]
 45%|████▍     | 79/176 [00:59<01:13,  1.32it/s]
 45%|████▌     | 80/176 [01:00<01:12,  1.32it/s]
 46%|████▌     | 81/176 [01:01<01:11,  1.33it/s]
 47%|████▋     | 82/176 [01:02<01:09,  1.34it/s]
 47%|████▋     | 83/176 [01:02<01:10,  1.32it/s]
 48%|████▊     | 84/176 [01:03<01:10,  1.31it/s]
 48%|████▊     | 85/176 [01:04<01:08,  1.33it/s]
 49%|████▉     | 86/176 [01:05<01:05,  1.36it/s]
 49%|████▉     | 87/176 [01:05<01:06,  1.34it/s]
 50%|█████     | 88/176 [01:06<01:06,  1.33it/s]
 51%|█████     | 89/176 [01:07<01:05,  1.33it/s]
 51%|█████     | 90/176 [01:08<01:04,  1.33it/s]
 52%|█████▏    | 91/176 [01:08<01:02,  1.35it/s]
 52%|█████▏    | 92/176 [01:09<01:01,  1.36it/s]
 53%|█████▎    | 93/176 [01:10<01:07,  1.22it/s]
 53%|█████▎    | 94/176 [01:11<01:05,  1.26it/s]
 54%|█████▍    | 95/176 [01:13<01:28,  1.09s/it]
 55%|█████▍    | 96/176 [01:13<01:17,  1.03it/s]
 55%|█████▌    | 97/176 [01:14<01:12,  1.08it/s]
 56%|█████▌    | 98/176 [01:15<01:08,  1.15it/s]
 56%|█████▋    | 99/176 [01:16<01:05,  1.17it/s]
 57%|█████▋    | 100/176 [01:16<01:02,  1.23it/s]
 57%|█████▋    | 101/176 [01:17<01:00,  1.25it/s]
 58%|█████▊    | 102/176 [01:18<00:58,  1.27it/s]
 59%|█████▊    | 103/176 [01:19<00:56,  1.30it/s]
 59%|█████▉    | 104/176 [01:19<00:55,  1.30it/s]
 60%|█████▉    | 105/176 [01:20<00:54,  1.30it/s]
 60%|██████    | 106/176 [01:21<00:55,  1.26it/s]
 61%|██████    | 107/176 [01:22<00:53,  1.29it/s]
 61%|██████▏   | 108/176 [01:22<00:52,  1.30it/s]
 62%|██████▏   | 109/176 [01:23<00:50,  1.32it/s]
 62%|██████▎   | 110/176 [01:24<00:49,  1.33it/s]
 63%|██████▎   | 111/176 [01:25<00:48,  1.34it/s]
 64%|██████▎   | 112/176 [01:25<00:47,  1.35it/s]
 64%|██████▍   | 113/176 [01:26<00:46,  1.35it/s]
 65%|██████▍   | 114/176 [01:27<00:46,  1.32it/s]
 65%|██████▌   | 115/176 [01:28<00:46,  1.32it/s]
 66%|██████▌   | 116/176 [01:28<00:45,  1.33it/s]
 66%|██████▋   | 117/176 [01:29<00:44,  1.32it/s]
 67%|██████▋   | 118/176 [01:30<00:44,  1.30it/s]
 68%|██████▊   | 119/176 [01:31<00:43,  1.30it/s]
 68%|██████▊   | 120/176 [01:32<00:43,  1.28it/s]
 69%|██████▉   | 121/176 [01:32<00:43,  1.28it/s]
 69%|██████▉   | 122/176 [01:33<00:41,  1.29it/s]
 70%|██████▉   | 123/176 [01:34<00:40,  1.30it/s]
 70%|███████   | 124/176 [01:35<00:40,  1.29it/s]
 71%|███████   | 125/176 [01:35<00:39,  1.30it/s]
 72%|███████▏  | 126/176 [01:36<00:38,  1.30it/s]
 72%|███████▏  | 127/176 [01:37<00:37,  1.31it/s]
 73%|███████▎  | 128/176 [01:38<00:36,  1.31it/s]
 73%|███████▎  | 129/176 [01:38<00:35,  1.31it/s]
 74%|███████▍  | 130/176 [01:39<00:35,  1.30it/s]
 74%|███████▍  | 131/176 [01:40<00:33,  1.32it/s]
 75%|███████▌  | 132/176 [01:41<00:33,  1.31it/s]
 76%|███████▌  | 133/176 [01:41<00:32,  1.32it/s]
 76%|███████▌  | 134/176 [01:42<00:31,  1.31it/s]
 77%|███████▋  | 135/176 [01:43<00:31,  1.30it/s]
 77%|███████▋  | 136/176 [01:44<00:30,  1.30it/s]
 78%|███████▊  | 137/176 [01:45<00:29,  1.32it/s]
 78%|███████▊  | 138/176 [01:45<00:28,  1.31it/s]
 79%|███████▉  | 139/176 [01:46<00:27,  1.33it/s]
 80%|███████▉  | 140/176 [01:47<00:27,  1.33it/s]
 80%|████████  | 141/176 [01:48<00:26,  1.31it/s]
 81%|████████  | 142/176 [01:48<00:25,  1.32it/s]
 81%|████████▏ | 143/176 [01:49<00:24,  1.34it/s]
 82%|████████▏ | 144/176 [01:50<00:23,  1.34it/s]
 82%|████████▏ | 145/176 [01:51<00:23,  1.34it/s]
 83%|████████▎ | 146/176 [01:51<00:22,  1.32it/s]
 84%|████████▎ | 147/176 [01:52<00:22,  1.31it/s]
 84%|████████▍ | 148/176 [01:53<00:21,  1.31it/s]
 85%|████████▍ | 149/176 [01:54<00:20,  1.30it/s]
 85%|████████▌ | 150/176 [01:54<00:19,  1.30it/s]
 86%|████████▌ | 151/176 [01:55<00:19,  1.31it/s]
 86%|████████▋ | 152/176 [01:56<00:18,  1.30it/s]
 87%|████████▋ | 153/176 [01:57<00:17,  1.29it/s]
 88%|████████▊ | 154/176 [01:57<00:16,  1.32it/s]
 88%|████████▊ | 155/176 [01:58<00:16,  1.31it/s]
 89%|████████▊ | 156/176 [01:59<00:15,  1.31it/s]
 89%|████████▉ | 157/176 [02:00<00:14,  1.35it/s]
 90%|████████▉ | 158/176 [02:00<00:13,  1.33it/s]
 90%|█████████ | 159/176 [02:01<00:12,  1.31it/s]
 91%|█████████ | 160/176 [02:02<00:12,  1.32it/s]
 91%|█████████▏| 161/176 [02:03<00:11,  1.30it/s]
 92%|█████████▏| 162/176 [02:04<00:10,  1.31it/s]
 93%|��████████▎| 163/176 [02:04<00:09,  1.32it/s]
 93%|█████████▎| 164/176 [02:05<00:08,  1.34it/s]
 94%|█████████▍| 165/176 [02:06<00:08,  1.30it/s]
 94%|█████████▍| 166/176 [02:07<00:07,  1.27it/s]
 95%|█████████▍| 167/176 [02:07<00:07,  1.28it/s]
 95%|█████████▌| 168/176 [02:08<00:06,  1.29it/s]
 96%|█████████▌| 169/176 [02:09<00:05,  1.32it/s]
 97%|█████████▋| 170/176 [02:10<00:04,  1.31it/s]
 97%|█████████▋| 171/176 [02:10<00:03,  1.32it/s]
 98%|█████████▊| 172/176 [02:11<00:03,  1.32it/s]
 98%|█████████▊| 173/176 [02:12<00:02,  1.31it/s]
 99%|█████████▉| 174/176 [02:13<00:01,  1.27it/s]
 99%|█████████▉| 175/176 [02:14<00:00,  1.27it/s]
+
+Final Evaluation Results:
+  eval_loss: 0.5781
+  eval_wer: 54.5829
+  eval_wer_ortho: 57.7728
+  eval_cer: 17.2107
+  eval_runtime: 194.9835
+  eval_samples_per_second: 14.3650
+  eval_steps_per_second: 0.9030
+  epoch: 6.0640
+
+Saving final model to /workspace/experiments/exp_002_base_lora...
+
+
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            

nohup.log

@@ -3828,3 +3828,292 @@ The attention mask is not set and cannot be inferred from input because pad toke
 
 
                                                 
                                                       
 
+
+Running final evaluation...
+
  0%|          | 0/176 [00:00<?, ?it/s]
  1%|          | 2/176 [00:00<01:03,  2.73it/s]
  2%|▏         | 3/176 [00:01<01:29,  1.93it/s]
  2%|▏         | 4/176 [00:02<01:45,  1.63it/s]
  3%|▎         | 5/176 [00:02<01:53,  1.51it/s]
  3%|▎         | 6/176 [00:03<01:59,  1.43it/s]
  4%|▍         | 7/176 [00:04<02:03,  1.37it/s]
  5%|▍         | 8/176 [00:05<02:03,  1.36it/s]
  5%|▌         | 9/176 [00:06<02:04,  1.34it/s]
  6%|▌         | 10/176 [00:06<02:06,  1.32it/s]
  6%|▋         | 11/176 [00:07<02:05,  1.32it/s]
  7%|▋         | 12/176 [00:08<02:05,  1.31it/s]
  7%|▋         | 13/176 [00:09<02:04,  1.31it/s]
  8%|▊         | 14/176 [00:09<02:01,  1.34it/s]
  9%|▊         | 15/176 [00:10<02:01,  1.32it/s]
  9%|▉         | 16/176 [00:11<01:59,  1.34it/s]
 10%|▉         | 17/176 [00:12<02:00,  1.32it/s]
 10%|█         | 18/176 [00:12<02:02,  1.29it/s]
 11%|█         | 19/176 [00:13<02:02,  1.28it/s]
 11%|█▏        | 20/176 [00:14<01:59,  1.30it/s]
 12%|█▏        | 21/176 [00:15<01:59,  1.30it/s]
 12%|█▎        | 22/176 [00:16<01:59,  1.29it/s]
 13%|█▎        | 23/176 [00:16<01:57,  1.30it/s]
 14%|█▎        | 24/176 [00:17<01:56,  1.31it/s]
 14%|█▍        | 25/176 [00:18<01:56,  1.30it/s]
 15%|█▍        | 26/176 [00:19<01:56,  1.29it/s]
 15%|█▌        | 27/176 [00:19<01:55,  1.29it/s]
 16%|█▌        | 28/176 [00:20<01:52,  1.31it/s]
 16%|█▋        | 29/176 [00:21<01:54,  1.28it/s]
 17%|█▋        | 30/176 [00:22<01:53,  1.29it/s]
 18%|█▊        | 31/176 [00:23<01:51,  1.30it/s]
 18%|█▊        | 32/176 [00:23<01:50,  1.31it/s]
 19%|█▉        | 33/176 [00:24<01:49,  1.31it/s]
 19%|█▉        | 34/176 [00:25<01:49,  1.29it/s]
 20%|█▉        | 35/176 [00:26<01:47,  1.31it/s]
 20%|██        | 36/176 [00:26<01:46,  1.32it/s]
 21%|██        | 37/176 [00:27<01:46,  1.30it/s]
 22%|██▏       | 38/176 [00:28<01:44,  1.32it/s]
 22%|██▏       | 39/176 [00:29<01:44,  1.31it/s]
 23%|██▎       | 40/176 [00:29<01:43,  1.32it/s]
 23%|██▎       | 41/176 [00:30<01:42,  1.31it/s]
 24%|██▍       | 42/176 [00:31<01:42,  1.30it/s]
 24%|██▍       | 43/176 [00:32<01:42,  1.30it/s]
 25%|██▌       | 44/176 [00:32<01:41,  1.30it/s]
 26%|██▌       | 45/176 [00:33<01:39,  1.32it/s]
 26%|██▌       | 46/176 [00:34<01:39,  1.30it/s]
 27%|██▋       | 47/176 [00:35<01:37,  1.32it/s]
 27%|██▋       | 48/176 [00:35<01:37,  1.32it/s]
 28%|██▊       | 49/176 [00:36<01:37,  1.30it/s]
 28%|██▊       | 50/176 [00:37<01:33,  1.34it/s]
 29%|██▉       | 51/176 [00:38<01:32,  1.35it/s]
 30%|██▉       | 52/176 [00:38<01:34,  1.32it/s]
 30%|███       | 53/176 [00:39<01:37,  1.26it/s]
 31%|███       | 54/176 [00:40<01:35,  1.27it/s]
 31%|███▏      | 55/176 [00:41<01:35,  1.27it/s]
 32%|███▏      | 56/176 [00:42<01:33,  1.28it/s]
 32%|███▏      | 57/176 [00:42<01:31,  1.30it/s]
 33%|███▎      | 58/176 [00:43<01:29,  1.32it/s]
 34%|███▎      | 59/176 [00:44<01:29,  1.31it/s]
 34%|███▍      | 60/176 [00:45<01:28,  1.31it/s]
 35%|███▍      | 61/176 [00:46<01:36,  1.19it/s]
 35%|███▌      | 62/176 [00:46<01:32,  1.23it/s]
 36%|███▌      | 63/176 [00:47<01:30,  1.25it/s]
 36%|███▋      | 64/176 [00:48<01:27,  1.27it/s]
 37%|███▋      | 65/176 [00:49<01:26,  1.29it/s]
 38%|███▊      | 66/176 [00:49<01:23,  1.32it/s]
 38%|███▊      | 67/176 [00:50<01:23,  1.30it/s]
 39%|███▊      | 68/176 [00:51<01:23,  1.29it/s]
 39%|███▉      | 69/176 [00:52<01:22,  1.29it/s]
 40%|███▉      | 70/176 [00:53<01:19,  1.33it/s]
 40%|████      | 71/176 [00:53<01:19,  1.32it/s]
 41%|████      | 72/176 [00:54<01:18,  1.32it/s]
 41%|████▏     | 73/176 [00:55<01:18,  1.31it/s]
 42%|████▏     | 74/176 [00:56<01:16,  1.33it/s]
 43%|████▎     | 75/176 [00:56<01:15,  1.33it/s]
 43%|████▎     | 76/176 [00:57<01:15,  1.32it/s]
 44%|████▍     | 77/176 [00:58<01:15,  1.31it/s]
 44%|████▍     | 78/176 [00:59<01:13,  1.33it/s]
 45%|████▍     | 79/176 [00:59<01:13,  1.32it/s]
 45%|████▌     | 80/176 [01:00<01:12,  1.32it/s]
 46%|████▌     | 81/176 [01:01<01:11,  1.33it/s]
 47%|████▋     | 82/176 [01:02<01:09,  1.34it/s]
 47%|████▋     | 83/176 [01:02<01:10,  1.32it/s]
 48%|████▊     | 84/176 [01:03<01:10,  1.31it/s]
 48%|████▊     | 85/176 [01:04<01:08,  1.33it/s]
 49%|████▉     | 86/176 [01:05<01:05,  1.36it/s]
 49%|████▉     | 87/176 [01:05<01:06,  1.34it/s]
 50%|█████     | 88/176 [01:06<01:06,  1.33it/s]
 51%|█████     | 89/176 [01:07<01:05,  1.33it/s]
 51%|█████     | 90/176 [01:08<01:04,  1.33it/s]
 52%|█████▏    | 91/176 [01:08<01:02,  1.35it/s]
 52%|█████▏    | 92/176 [01:09<01:01,  1.36it/s]
 53%|█████▎    | 93/176 [01:10<01:07,  1.22it/s]
 53%|█████▎    | 94/176 [01:11<01:05,  1.26it/s]
 54%|█████▍    | 95/176 [01:13<01:28,  1.09s/it]
 55%|█████▍    | 96/176 [01:13<01:17,  1.03it/s]
 55%|█████▌    | 97/176 [01:14<01:12,  1.08it/s]
 56%|█████▌    | 98/176 [01:15<01:08,  1.15it/s]
 56%|█████▋    | 99/176 [01:16<01:05,  1.17it/s]
 57%|█████▋    | 100/176 [01:16<01:02,  1.23it/s]
 57%|█████▋    | 101/176 [01:17<01:00,  1.25it/s]
 58%|█████▊    | 102/176 [01:18<00:58,  1.27it/s]
 59%|█████▊    | 103/176 [01:19<00:56,  1.30it/s]
 59%|█████▉    | 104/176 [01:19<00:55,  1.30it/s]
 60%|█████▉    | 105/176 [01:20<00:54,  1.30it/s]
 60%|██████    | 106/176 [01:21<00:55,  1.26it/s]
 61%|██████    | 107/176 [01:22<00:53,  1.29it/s]
 61%|██████▏   | 108/176 [01:22<00:52,  1.30it/s]
 62%|██████▏   | 109/176 [01:23<00:50,  1.32it/s]
 62%|██████▎   | 110/176 [01:24<00:49,  1.33it/s]
 63%|██████▎   | 111/176 [01:25<00:48,  1.34it/s]
 64%|██████▎   | 112/176 [01:25<00:47,  1.35it/s]
 64%|██████▍   | 113/176 [01:26<00:46,  1.35it/s]
 65%|██████▍   | 114/176 [01:27<00:46,  1.32it/s]
 65%|██████▌   | 115/176 [01:28<00:46,  1.32it/s]
 66%|██████▌   | 116/176 [01:28<00:45,  1.33it/s]
 66%|██████▋   | 117/176 [01:29<00:44,  1.32it/s]
 67%|██████▋   | 118/176 [01:30<00:44,  1.30it/s]
 68%|██████▊   | 119/176 [01:31<00:43,  1.30it/s]
 68%|██████▊   | 120/176 [01:32<00:43,  1.28it/s]
 69%|██████▉   | 121/176 [01:32<00:43,  1.28it/s]
 69%|██████▉   | 122/176 [01:33<00:41,  1.29it/s]
 70%|██████▉   | 123/176 [01:34<00:40,  1.30it/s]
 70%|███████   | 124/176 [01:35<00:40,  1.29it/s]
 71%|███████   | 125/176 [01:35<00:39,  1.30it/s]
 72%|███████▏  | 126/176 [01:36<00:38,  1.30it/s]
 72%|███████▏  | 127/176 [01:37<00:37,  1.31it/s]
 73%|███████▎  | 128/176 [01:38<00:36,  1.31it/s]
 73%|███████▎  | 129/176 [01:38<00:35,  1.31it/s]
 74%|███████▍  | 130/176 [01:39<00:35,  1.30it/s]
 74%|███████▍  | 131/176 [01:40<00:33,  1.32it/s]
 75%|███████▌  | 132/176 [01:41<00:33,  1.31it/s]
 76%|███████▌  | 133/176 [01:41<00:32,  1.32it/s]
 76%|███████▌  | 134/176 [01:42<00:31,  1.31it/s]
 77%|███████▋  | 135/176 [01:43<00:31,  1.30it/s]
 77%|███████▋  | 136/176 [01:44<00:30,  1.30it/s]
 78%|███████▊  | 137/176 [01:45<00:29,  1.32it/s]
 78%|███████▊  | 138/176 [01:45<00:28,  1.31it/s]
 79%|███████▉  | 139/176 [01:46<00:27,  1.33it/s]
 80%|███████▉  | 140/176 [01:47<00:27,  1.33it/s]
 80%|████████  | 141/176 [01:48<00:26,  1.31it/s]
 81%|████████  | 142/176 [01:48<00:25,  1.32it/s]
 81%|████████▏ | 143/176 [01:49<00:24,  1.34it/s]
 82%|████████▏ | 144/176 [01:50<00:23,  1.34it/s]
 82%|████████▏ | 145/176 [01:51<00:23,  1.34it/s]
 83%|████████▎ | 146/176 [01:51<00:22,  1.32it/s]
 84%|████████▎ | 147/176 [01:52<00:22,  1.31it/s]
 84%|████████▍ | 148/176 [01:53<00:21,  1.31it/s]
 85%|████████▍ | 149/176 [01:54<00:20,  1.30it/s]
 85%|████████▌ | 150/176 [01:54<00:19,  1.30it/s]
 86%|████████▌ | 151/176 [01:55<00:19,  1.31it/s]
 86%|████████▋ | 152/176 [01:56<00:18,  1.30it/s]
 87%|████████▋ | 153/176 [01:57<00:17,  1.29it/s]
 88%|████████▊ | 154/176 [01:57<00:16,  1.32it/s]
 88%|████████▊ | 155/176 [01:58<00:16,  1.31it/s]
 89%|████████▊ | 156/176 [01:59<00:15,  1.31it/s]
 89%|████████▉ | 157/176 [02:00<00:14,  1.35it/s]
 90%|████████▉ | 158/176 [02:00<00:13,  1.33it/s]
 90%|█████████ | 159/176 [02:01<00:12,  1.31it/s]
 91%|█████████ | 160/176 [02:02<00:12,  1.32it/s]
 91%|█████████▏| 161/176 [02:03<00:11,  1.30it/s]
 92%|█████████▏| 162/176 [02:04<00:10,  1.31it/s]
 93%|��████████▎| 163/176 [02:04<00:09,  1.32it/s]
 93%|█████████▎| 164/176 [02:05<00:08,  1.34it/s]
 94%|█████████▍| 165/176 [02:06<00:08,  1.30it/s]
 94%|█████████▍| 166/176 [02:07<00:07,  1.27it/s]
 95%|█████████▍| 167/176 [02:07<00:07,  1.28it/s]
 95%|█████████▌| 168/176 [02:08<00:06,  1.29it/s]
 96%|█████████▌| 169/176 [02:09<00:05,  1.32it/s]
 97%|█████████▋| 170/176 [02:10<00:04,  1.31it/s]
 97%|█████████▋| 171/176 [02:10<00:03,  1.32it/s]
 98%|█████████▊| 172/176 [02:11<00:03,  1.32it/s]
 98%|█████████▊| 173/176 [02:12<00:02,  1.31it/s]
 99%|█████████▉| 174/176 [02:13<00:01,  1.27it/s]
 99%|█████████▉| 175/176 [02:14<00:00,  1.27it/s]
+
+Final Evaluation Results:
+  eval_loss: 0.5781
+  eval_wer: 54.5829
+  eval_wer_ortho: 57.7728
+  eval_cer: 17.2107
+  eval_runtime: 194.9835
+  eval_samples_per_second: 14.3650
+  eval_steps_per_second: 0.9030
+  epoch: 6.0640
+
+Saving final model to /workspace/experiments/exp_002_base_lora...
+
+
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
+
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
+
+
+
+
+
+
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
+
+
+
+
+
+
+
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
+
+
+
+
+
+
+
+
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
+
+
+
+
+
+
+
+
+
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            
+
+
  ...se_lora/training_args.bin: 100%|██████████| 5.91kB / 5.91kB            
+
  ...4567.65d8b3854c39.93630.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...9876.65d8b3854c39.94606.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...9767.65d8b3854c39.92682.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...4970.65d8b3854c39.93828.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...0403.65d8b3854c39.94930.0: 100%|██████████| 36.7kB / 36.7kB            
+
  ...4234.65d8b3854c39.93425.0: 100%|██████████| 6.04kB / 6.04kB            
+
  ...8288.65d8b3854c39.94241.0: 100%|██████████| 6.90kB / 6.90kB            
+
  ...adapter_model.safetensors: 100%|██████████| 9.45MB / 9.45MB            
+
  ...9051.65d8b3854c39.94930.1: 100%|██████████|   506B /   506B            

runs/Mar29_21-40-02_65d8b3854c39/events.out.tfevents.1774829051.65d8b3854c39.94930.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b038aac50dbde232cbd38fdac6e3a54bdb6fa57b9134081732ea57c63b8a5af
+size 506