End of training

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.0,
-    "train_runtime": 9.8813,
+    "train_runtime": 8.0061,
     "train_samples": 207374,
-    "train_samples_per_second": 62959.375,
-    "train_steps_per_second": 983.674
+    "train_samples_per_second": 77706.136,
+    "train_steps_per_second": 1214.076
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.0,
-    "train_runtime": 9.8813,
+    "train_runtime": 8.0061,
     "train_samples": 207374,
-    "train_samples_per_second": 62959.375,
-    "train_steps_per_second": 983.674
+    "train_samples_per_second": 77706.136,
+    "train_steps_per_second": 1214.076
 }

trainer_state.json

@@ -58533,6 +58533,15 @@
       "train_runtime": 9.8813,
       "train_samples_per_second": 62959.375,
       "train_steps_per_second": 983.674
+    },
+    {
+      "epoch": 3.0,
+      "step": 9720,
+      "total_flos": 0.0,
+      "train_loss": 0.0,
+      "train_runtime": 8.0061,
+      "train_samples_per_second": 77706.136,
+      "train_steps_per_second": 1214.076
     }
   ],
   "max_steps": 9720,

wandb/run-20220505_170634-s79deysf/files/output.log

@@ -36,3 +36,18 @@ Upload file runs/May05_17-05-42_sanchit--v100/events.out.tfevents.1651770393.san
 Upload file runs/May05_17-05-42_sanchit--v100/1651770393.8000064/events.out.tfevents.1651770393.sanchit--v100.71806.1: 1
 Upload file training_args.bin: 100%|███████████████████████████████████████████████████████| 3.17k/3.17k [00:01<?, ?B/s]
 
+{'dataset': {'name': 'xtreme_s', 'type': 'xtreme_s', 'args': 'covost2.fr.en'}, 'metrics': [{'name': 'Bleu', 'type': 'bleu', 'value': 2.691896075803751e-15}]}
+05/05/2022 17:07:46 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en_2
+   1003015..44a61c0  main -> main
+To https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en_2
+   1003015..44a61c0  main -> main
+***** train metrics *****
+  epoch                    =        3.0
+  train_loss               =        0.0
+  train_runtime            = 0:00:08.00
+  train_samples            =     207374
+  train_samples_per_second =  77706.136
+  train_steps_per_second   =   1214.076
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./pytorch_model.bin

wandb/run-20220505_170634-s79deysf/logs/debug-internal.log

@@ -59,3 +59,13 @@
 2022-05-05 17:07:38,170 DEBUG   HandlerThread:71918 [handler.py:handle_request():131] handle_request: stop_status
 2022-05-05 17:07:38,171 DEBUG   SenderThread:71918 [sender.py:send_request():249] send_request: stop_status
 2022-05-05 17:07:38,328 INFO    Thread-8  :71918 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_170634-s79deysf/files/output.log
+2022-05-05 17:07:48,333 INFO    Thread-8  :71918 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_170634-s79deysf/files/output.log
+2022-05-05 17:07:52,334 INFO    Thread-8  :71918 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_170634-s79deysf/files/output.log
+2022-05-05 17:07:53,206 DEBUG   HandlerThread:71918 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 17:07:53,207 DEBUG   SenderThread:71918 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 17:08:04,339 INFO    Thread-8  :71918 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_170634-s79deysf/files/output.log
+2022-05-05 17:08:06,629 DEBUG   SenderThread:71918 [sender.py:send():235] send: stats
+2022-05-05 17:08:08,243 DEBUG   HandlerThread:71918 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 17:08:08,243 DEBUG   SenderThread:71918 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 17:08:23,356 DEBUG   HandlerThread:71918 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 17:08:23,357 DEBUG   SenderThread:71918 [sender.py:send_request():249] send_request: stop_status