13.3 GB

1 contributor

History: 34 commits

advy

Add comprehensive evaluation metrics.

b7c2f0d verified 5 days ago

last-checkpoint
Training in progress, step 1800, checkpoint 2 months ago
.gitattributes
1.64 kB

Training in progress, step 200, checkpoint 2 months ago
COMPLETEevaluation_metrics.json
424 kB

Add comprehensive evaluation metrics. 5 days ago
COMPLETEtest_set_predictions.json
414 kB

Add test set predictions with evaluation metrics (first 100 examples). 5 days ago
HOPEFULevaluation_metrics.json
445 kB

Add comprehensive evaluation metrics. 5 days ago
HOPEFULtest_set_predictions.json
432 kB

Add test set predictions with evaluation metrics (first 100 examples). 5 days ago
README.md
2.92 kB

Update README.md about 2 months ago
adapter_config.json
1.06 kB

Training in progress, step 200 2 months ago
adapter_model.safetensors
3.31 GB
xet

Model save 2 months ago
chat_template.jinja
4.61 kB

Training in progress, step 200 2 months ago
cleaned_evaluation_metrics.json
563 kB

Add recalculated evaluation metrics (with cleaned responses) 5 days ago
cleaned_test_set_predictions.json
553 kB

Add cleaned test set predictions (stripped <|assistant|> prefix) 5 days ago
predictions_with_scores.json
629 kB

Add evaluation metrics: ROUGE and BLEU scores for predictions_with_scores.json 2 months ago
special_tokens_map.json
325 Bytes

Training in progress, step 200 2 months ago
test_set_predictions.json
280 kB

Add test set predictions and ROUGE/BLEU scores. 6 days ago
tokenizer.json
17.2 MB
xet

Training in progress, step 200 2 months ago
tokenizer_config.json
50.6 kB

Training in progress, step 200 2 months ago
training_args.bin
5.43 kB
xet

Training in progress, step 200 2 months ago
training_metrics.json
1.03 kB

Finetune on MentalChat16K - eval_loss: 0.6693 2 months ago