test submit

config.json

@@ -34,7 +34,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.0.dev0",
+  "transformers_version": "4.11.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin → events.out.tfevents.1634552807.t1v-n-f6f5b6cc-w-0.1083016.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269d12af9cbd67b0a184d01059c26b9c096debf65b24ea8e87dc33b6e2656087
-size 510404491
+oid sha256:cc1a55582d739e19cf42476e987acab254639a592baf341caefe47ce1422f38a
+size 367914

events.out.tfevents.1634745538.t1v-n-f6f5b6cc-w-0.1277181.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae21f21ad44c444ca8e63b9a232eb05cbdd77331533f5a949ed9f5f98197884
+size 40

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38486582be28002574744c576acd719c845aae584aed1d4337b936f29e591ce1
+oid sha256:bcc8d7b05a5fd7c3d6ce4a92afc95f1c393d0e579907379f45a3e3a596c68606
 size 497764120

run.sh

@@ -1,10 +1,12 @@
 python run_clm_flax.py \
     --output_dir="./" \
     --model_type="gpt2" \
+    --model_name_or_path="." \
     --config_name="./" \
     --tokenizer_name="./" \
     --train_file="/mnt/disks/flaxdisk/corpus/train.json" \
     --validation_file="/mnt/disks/flaxdisk/corpus/validation.json" \
+    --cache_dir="/mnt/disks/flaxdisk/cache/" \
     --do_train --do_eval \
     --block_size="512" \
     --per_device_train_batch_size="64" \

run_clm_flax.py

@@ -669,7 +669,7 @@ def main():
                     model.save_pretrained(training_args.output_dir, params=params)
                     tokenizer.save_pretrained(training_args.output_dir)
                     if training_args.push_to_hub:
-                        repo.push_to_hub(commit_message=f"Saving weights and logs of step {cur_step}", blocking=False)
+                        repo.push_to_hub(commit_message=f"Saving weights and logs of step {cur_step}")
 
 
 if __name__ == "__main__":

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "norwegian-gpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "GPT2Tokenizer"}