test submit
Browse files
config.json
CHANGED
@@ -34,7 +34,7 @@
|
|
34 |
}
|
35 |
},
|
36 |
"torch_dtype": "float32",
|
37 |
-
"transformers_version": "4.
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 50257
|
40 |
}
|
|
|
34 |
}
|
35 |
},
|
36 |
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.11.0.dev0",
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 50257
|
40 |
}
|
pytorch_model.bin → events.out.tfevents.1634552807.t1v-n-f6f5b6cc-w-0.1083016.0.v2
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc1a55582d739e19cf42476e987acab254639a592baf341caefe47ce1422f38a
|
3 |
+
size 367914
|
events.out.tfevents.1634745538.t1v-n-f6f5b6cc-w-0.1277181.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae21f21ad44c444ca8e63b9a232eb05cbdd77331533f5a949ed9f5f98197884
|
3 |
+
size 40
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497764120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcc8d7b05a5fd7c3d6ce4a92afc95f1c393d0e579907379f45a3e3a596c68606
|
3 |
size 497764120
|
run.sh
CHANGED
@@ -1,10 +1,12 @@
|
|
1 |
python run_clm_flax.py \
|
2 |
--output_dir="./" \
|
3 |
--model_type="gpt2" \
|
|
|
4 |
--config_name="./" \
|
5 |
--tokenizer_name="./" \
|
6 |
--train_file="/mnt/disks/flaxdisk/corpus/train.json" \
|
7 |
--validation_file="/mnt/disks/flaxdisk/corpus/validation.json" \
|
|
|
8 |
--do_train --do_eval \
|
9 |
--block_size="512" \
|
10 |
--per_device_train_batch_size="64" \
|
|
|
1 |
python run_clm_flax.py \
|
2 |
--output_dir="./" \
|
3 |
--model_type="gpt2" \
|
4 |
+
--model_name_or_path="." \
|
5 |
--config_name="./" \
|
6 |
--tokenizer_name="./" \
|
7 |
--train_file="/mnt/disks/flaxdisk/corpus/train.json" \
|
8 |
--validation_file="/mnt/disks/flaxdisk/corpus/validation.json" \
|
9 |
+
--cache_dir="/mnt/disks/flaxdisk/cache/" \
|
10 |
--do_train --do_eval \
|
11 |
--block_size="512" \
|
12 |
--per_device_train_batch_size="64" \
|
run_clm_flax.py
CHANGED
@@ -669,7 +669,7 @@ def main():
|
|
669 |
model.save_pretrained(training_args.output_dir, params=params)
|
670 |
tokenizer.save_pretrained(training_args.output_dir)
|
671 |
if training_args.push_to_hub:
|
672 |
-
repo.push_to_hub(commit_message=f"Saving weights and logs of step {cur_step}"
|
673 |
|
674 |
|
675 |
if __name__ == "__main__":
|
|
|
669 |
model.save_pretrained(training_args.output_dir, params=params)
|
670 |
tokenizer.save_pretrained(training_args.output_dir)
|
671 |
if training_args.push_to_hub:
|
672 |
+
repo.push_to_hub(commit_message=f"Saving weights and logs of step {cur_step}")
|
673 |
|
674 |
|
675 |
if __name__ == "__main__":
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "GPT2Tokenizer"}
|