Graphlet-AI
/

eridu

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:2130621

loss:ContrastiveLoss

text-embeddings-inference

Model card Files Files and versions

eridu

Ctrl+K

Ctrl+K

1 contributor

History: 9 commits

rjurney's picture

Updated README from latest run

ccc1d6b unverified 3 months ago

1_Pooling
Upload folder using huggingface_hub 4 months ago
checkpoint-1000
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
checkpoint-1100
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
checkpoint-1200
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
checkpoint-1300
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
checkpoint-900
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
eval
Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
.gitattributes

2.47 kB

Track all the big files I'm about to upload 4 months ago
README.md

20.8 kB

Updated README from latest run 3 months ago
config.json

619 Bytes

Upload folder using huggingface_hub 4 months ago
config_sentence_transformers.json

205 Bytes

Upload folder using huggingface_hub 4 months ago
model.safetensors

471 MB
xet

Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
modules.json

229 Bytes

Upload folder using huggingface_hub 4 months ago
sentence_bert_config.json

53 Bytes

Upload folder using huggingface_hub 4 months ago
special_tokens_map.json

964 Bytes

Upload folder using huggingface_hub 4 months ago
tokenizer.json

17.1 MB
xet

Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
tokenizer_config.json

1.45 kB

Upload folder using huggingface_hub 4 months ago
training_args.bin
Detected Pickle imports (12)
- "transformers.trainer_utils.SchedulerType",
- "sentence_transformers.training_args.BatchSamplers",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "sentence_transformers.training_args.SentenceTransformerTrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "sentence_transformers.training_args.MultiDatasetBatchSamplers",
- "accelerate.state.PartialState"
How to fix it?
6.03 kB
xet

Disabled a lot of training optimizations I had introduced in this run: eridu train --use-gpu --batch-size 1000 --epochs 8 --patience 1 --resampling --weight-decay 0.01 --random-seed 31337 --warmup-ratio 0.1 --learning-rate 3e-5 --save-strategy steps --eval-strategy steps --sample-fraction 0.1 4 months ago
unigram.json

14.8 MB
xet

Upload folder using huggingface_hub 4 months ago