Training in progress, step 2500

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff528df7b0871bfbd364a59fc4b47422efc008d827e88a7ec4f8a3ba10da6e3
+oid sha256:af488077ce2b8a6c7d9d8fd3c1ef2cc57be5f648c35c44c32b080c2ff3679d8e
 size 2353867057

runs/May05_17-37-22_sanchit--v100/events.out.tfevents.1651772294.sanchit--v100.74467.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557ddf3888c01e6d85e963f79e5b2d070cc09c907c6ec446c8c6cd234305ee73
-size 324717
+oid sha256:b039ffce36206ba55d9b926890c968c0b6ddfa4f2ac350b257b6d4c01e44bde0
+size 403536

wandb/debug-cli.log

@@ -186,3 +186,5 @@
 	warmup_steps: 500
 2022-05-05 17:37:19 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=16 --greater_is_better=True --hidden_dropout=0.2 --language=fr.en --learning_rate=0.0003 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./ --per_device_eval_batch_size=8 --per_device_train_batch_size=8 --save_steps=500 --task=covost2 --warmup_steps=500
 2022-05-05 17:37:24 INFO Running runs: ['i9acyhfo']
+2022-05-06 01:57:37 ERROR 500 response executing GraphQL.
+2022-05-06 01:57:37 ERROR {"error":"driver: bad connection"}

wandb/run-20220505_173818-i9acyhfo/run-i9acyhfo.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330bb09f94077055590df43db89108ec7adfe8ca66b6c4080190d148a1193f53
-size 434944795
+oid sha256:7bf41c56d0a562b6c4a0aeee9f47a664a256264a4ca48fe160d226e132147d99
+size 542239167