993 MB

Ctrl+K

1 contributor

History: 10 commits

LoveJesus

Retrain with flan-t5-base (248M): difficulty accuracy 93.8%, eval_loss 2.228 (upgrade from flan-t5-small 80M)

9206908 verified about 2 months ago

.gitattributes

1.52 kB
initial commit about 2 months ago
README.md

13.8 kB
Upgrade to flan-t5-base (248M): difficulty_accuracy=94.8%, eval_loss=2.228 about 2 months ago
config.json

1.57 kB
Upgrade to flan-t5-base (248M): difficulty_accuracy=94.8%, eval_loss=2.228 about 2 months ago
generation_config.json

907 Bytes
Upload Flan-T5-small passage difficulty scorer & simplifier about 2 months ago
model.safetensors

990 MB
xet

Upgrade to flan-t5-base (248M): difficulty_accuracy=94.8%, eval_loss=2.228 about 2 months ago
special_tokens_map.json

2.2 kB
Add special_tokens_map.json about 2 months ago
spiece.model

792 kB
xet

Add SentencePiece model for T5Tokenizer compatibility about 2 months ago
tokenizer.json

2.11 MB
Upload Flan-T5-small passage difficulty scorer & simplifier about 2 months ago
tokenizer_config.json

2.35 kB
Upload Flan-T5-small passage difficulty scorer & simplifier about 2 months ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.state.PartialState",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
4.92 kB
xet

Retrain with flan-t5-base (248M): difficulty accuracy 93.8%, eval_loss 2.228 (upgrade from flan-t5-small 80M) about 2 months ago

Detected Pickle imports (10)