End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 49.98,
+    "eval_loss": 2.8934524059295654,
+    "eval_runtime": 13.0771,
+    "eval_samples": 341,
+    "eval_samples_per_second": 26.076,
+    "eval_steps_per_second": 3.288,
+    "eval_wer": 0.9874538745387453,
+    "train_loss": 5.6772947265625,
+    "train_runtime": 2084.0288,
+    "train_samples": 810,
+    "train_samples_per_second": 19.434,
+    "train_steps_per_second": 0.6
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 49.98,
+    "eval_loss": 2.8934524059295654,
+    "eval_runtime": 13.0771,
+    "eval_samples": 341,
+    "eval_samples_per_second": 26.076,
+    "eval_steps_per_second": 3.288,
+    "eval_wer": 0.9874538745387453
+}

nohup.out

@@ -635,3 +635,26 @@ Configuration saved in ./preprocessor_config.json
 
 Dropping the following result as it does not have all the necessary fields:
 {'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'ur'}}
+To https://huggingface.co/HarrisDePerceptron/xls-r-300m-ur
+   4e1557d..ab3e230  main -> main
+
+02/02/2022 18:41:43 - WARNING - huggingface_hub.repository - To https://huggingface.co/HarrisDePerceptron/xls-r-300m-ur
+   4e1557d..ab3e230  main -> main
+
+***** train metrics *****
+  epoch                    =      49.98
+  train_loss               =     5.6773
+  train_runtime            = 0:34:44.02
+  train_samples            =        810
+  train_samples_per_second =     19.434
+  train_steps_per_second   =        0.6
+02/02/2022 18:41:45 - INFO - __main__ - *** Evaluate ***
+The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 341
+  Batch size = 8
+
  0%|          | 0/43 [00:00<?, ?it/s]
  5%|▍         | 2/43 [00:00<00:04,  9.60it/s]
  7%|▋         | 3/43 [00:00<00:06,  5.79it/s]
  9%|▉         | 4/43 [00:00<00:08,  4.35it/s]
 12%|█▏        | 5/43 [00:01<00:09,  4.11it/s]
 14%|█▍        | 6/43 [00:01<00:09,  3.90it/s]
 16%|█▋        | 7/43 [00:01<00:09,  3.85it/s]
 19%|█▊        | 8/43 [00:01<00:09,  3.80it/s]
 21%|██        | 9/43 [00:02<00:09,  3.52it/s]
 23%|██▎       | 10/43 [00:02<00:08,  3.78it/s]
 26%|██▌       | 11/43 [00:02<00:08,  3.78it/s]
 28%|██▊       | 12/43 [00:02<00:08,  3.83it/s]
 30%|███       | 13/43 [00:03<00:07,  3.85it/s]
 33%|███▎      | 14/43 [00:03<00:08,  3.31it/s]
 35%|███▍      | 15/43 [00:04<00:09,  2.96it/s]
 37%|███▋      | 16/43 [00:04<00:08,  3.02it/s]
 40%|███▉      | 17/43 [00:04<00:08,  3.10it/s]
 42%|████▏     | 18/43 [00:05<00:08,  3.02it/s]
 44%|████▍     | 19/43 [00:05<00:08,  2.83it/s]
 47%|████▋     | 20/43 [00:05<00:08,  2.56it/s]
 49%|████▉     | 21/43 [00:06<00:08,  2.64it/s]
 51%|█████     | 22/43 [00:06<00:07,  2.69it/s]
 53%|█████▎    | 23/43 [00:06<00:07,  2.81it/s]
 56%|█████▌    | 24/43 [00:07<00:06,  3.08it/s]
 58%|█████▊    | 25/43 [00:07<00:05,  3.22it/s]
 60%|██████    | 26/43 [00:07<00:05,  3.28it/s]
 63%|██████▎   | 27/43 [00:07<00:04,  3.67it/s]
 65%|██████▌   | 28/43 [00:08<00:04,  3.66it/s]
 67%|██████▋   | 29/43 [00:08<00:03,  3.71it/s]
 70%|██████▉   | 30/43 [00:08<00:03,  3.81it/s]
 72%|███████▏  | 31/43 [00:08<00:03,  3.77it/s]
 74%|███████▍  | 32/43 [00:09<00:02,  3.81it/s]
 77%|███████▋  | 33/43 [00:09<00:02,  3.53it/s]
 79%|███████▉  | 34/43 [00:09<00:02,  3.49it/s]
 81%|████████▏ | 35/43 [00:10<00:02,  3.47it/s]
 84%|████████▎ | 36/43 [00:10<00:02,  3.38it/s]
 86%|████████▌ | 37/43 [00:10<00:01,  3.53it/s]
 88%|████████▊ | 38/43 [00:11<00:01,  3.27it/s]
 91%|█████████ | 39/43 [00:11<00:01,  3.34it/s]
 93%|█████████▎| 40/43 [00:11<00:00,  3.17it/s]
 95%|█████████▌| 41/43 [00:12<00:00,  3.28it/s]
 98%|█████████▊| 42/43 [00:12<00:00,  3.18it/s]
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./pytorch_model.bin
+Configuration saved in ./preprocessor_config.json

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 49.98,
+    "train_loss": 5.6772947265625,
+    "train_runtime": 2084.0288,
+    "train_samples": 810,
+    "train_samples_per_second": 19.434,
+    "train_steps_per_second": 0.6
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 49.98039215686274,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.675e-06,
+      "loss": 20.0794,
+      "step": 100
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 7.425e-06,
+      "loss": 10.5776,
+      "step": 200
+    },
+    {
+      "epoch": 11.98,
+      "learning_rate": 1.1174999999999999e-05,
+      "loss": 6.6033,
+      "step": 300
+    },
+    {
+      "epoch": 15.98,
+      "learning_rate": 1.4925e-05,
+      "loss": 5.3857,
+      "step": 400
+    },
+    {
+      "epoch": 19.98,
+      "learning_rate": 1.8675e-05,
+      "loss": 4.4431,
+      "step": 500
+    },
+    {
+      "epoch": 19.98,
+      "eval_loss": 4.144110202789307,
+      "eval_runtime": 12.9526,
+      "eval_samples_per_second": 26.327,
+      "eval_steps_per_second": 3.32,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 23.98,
+      "learning_rate": 2.2424999999999996e-05,
+      "loss": 3.7383,
+      "step": 600
+    },
+    {
+      "epoch": 27.98,
+      "learning_rate": 2.6174999999999996e-05,
+      "loss": 3.361,
+      "step": 700
+    },
+    {
+      "epoch": 31.98,
+      "learning_rate": 2.9925e-05,
+      "loss": 3.2219,
+      "step": 800
+    },
+    {
+      "epoch": 35.98,
+      "learning_rate": 3.3675e-05,
+      "loss": 3.104,
+      "step": 900
+    },
+    {
+      "epoch": 39.98,
+      "learning_rate": 3.7424999999999995e-05,
+      "loss": 3.0399,
+      "step": 1000
+    },
+    {
+      "epoch": 39.98,
+      "eval_loss": 2.9768528938293457,
+      "eval_runtime": 12.8843,
+      "eval_samples_per_second": 26.466,
+      "eval_steps_per_second": 3.337,
+      "eval_wer": 0.9988929889298893,
+      "step": 1000
+    },
+    {
+      "epoch": 43.98,
+      "learning_rate": 4.1175e-05,
+      "loss": 2.9893,
+      "step": 1100
+    },
+    {
+      "epoch": 47.98,
+      "learning_rate": 4.4924999999999994e-05,
+      "loss": 2.953,
+      "step": 1200
+    },
+    {
+      "epoch": 49.98,
+      "step": 1250,
+      "total_flos": 4.919672600088422e+18,
+      "train_loss": 5.6772947265625,
+      "train_runtime": 2084.0288,
+      "train_samples_per_second": 19.434,
+      "train_steps_per_second": 0.6
+    }
+  ],
+  "max_steps": 1250,
+  "num_train_epochs": 50,
+  "total_flos": 4.919672600088422e+18,
+  "trial_name": null,
+  "trial_params": null
+}