End of training

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 1.7970677693255643,
-    "train_runtime": 95217.2299,
+    "train_loss": 0.0,
+    "train_runtime": 7.9737,
     "train_samples": 207374,
-    "train_samples_per_second": 6.534,
-    "train_steps_per_second": 0.102
+    "train_samples_per_second": 78021.8,
+    "train_steps_per_second": 1219.008
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 1.7970677693255643,
-    "train_runtime": 95217.2299,
+    "train_loss": 0.0,
+    "train_runtime": 7.9737,
     "train_samples": 207374,
-    "train_samples_per_second": 6.534,
-    "train_steps_per_second": 0.102
+    "train_samples_per_second": 78021.8,
+    "train_steps_per_second": 1219.008
 }

trainer_state.json

@@ -58506,6 +58506,15 @@
       "train_runtime": 95217.2299,
       "train_samples_per_second": 6.534,
       "train_steps_per_second": 0.102
+    },
+    {
+      "epoch": 3.0,
+      "step": 9720,
+      "total_flos": 0.0,
+      "train_loss": 0.0,
+      "train_runtime": 7.9737,
+      "train_samples_per_second": 78021.8,
+      "train_steps_per_second": 1219.008
     }
   ],
   "max_steps": 9720,

wandb/run-20220505_165612-npwlqyuz/files/output.log

@@ -42,3 +42,16 @@ Upload file training_args.bin: 100%|██████████████
 Upload file wandb/run-20220504_142129-w4rlzz90/files/output.log: 100%|██████████████| 10.7M/10.7M [00:54<00:00, 206kB/s]
 Upload file runs/May05_16-55-19_sanchit--v100/1651769771.7857685/events.out.tfevents.1651769771.sanchit--v100.69604.1: 1
 Upload file training_args.bin: 100%|███████████████████████████████████████████████████████| 3.17k/3.17k [00:54<?, ?B/s]
+Upload file wandb/run-20220504_142129-w4rlzz90/files/output.log: 100%|██████████████| 10.7M/10.7M [00:54<00:00, 159kB/s]
+05/05/2022 16:58:25 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en_2
+   c81eede..30cf64e  main -> main
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+***** train metrics *****
+  epoch                    =        3.0
+  train_loss               =        0.0
+  train_runtime            = 0:00:07.97
+  train_samples            =     207374
+  train_samples_per_second =    78021.8
+  train_steps_per_second   =   1219.008
+Model weights saved in ./pytorch_model.bin

wandb/run-20220505_165612-npwlqyuz/logs/debug-internal.log

@@ -70,3 +70,13 @@
 2022-05-05 16:58:14,989 DEBUG   SenderThread:69718 [sender.py:send():235] send: stats
 2022-05-05 16:58:16,646 DEBUG   HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
 2022-05-05 16:58:16,646 DEBUG   SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:58:26,353 INFO    Thread-8  :69718 [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_165612-npwlqyuz/files/output.log
+2022-05-05 16:58:30,355 INFO    Thread-8  :69718 [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_165612-npwlqyuz/files/output.log
+2022-05-05 16:58:32,203 DEBUG   HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:58:32,204 DEBUG   SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:58:42,360 INFO    Thread-8  :69718 [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_165612-npwlqyuz/files/output.log
+2022-05-05 16:58:45,337 DEBUG   SenderThread:69718 [sender.py:send():235] send: stats
+2022-05-05 16:58:47,246 DEBUG   HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:58:47,246 DEBUG   SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:59:02,294 DEBUG   HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:59:02,295 DEBUG   SenderThread:69718 [sender.py:send_request():249] send_request: stop_status