Instructions to use duyphu/76b2d76f-2806-4468-b061-b77a8dad386a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use duyphu/76b2d76f-2806-4468-b061-b77a8dad386a with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0") model = PeftModel.from_pretrained(base_model, "duyphu/76b2d76f-2806-4468-b061-b77a8dad386a") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from duyphu/76b2d76f-2806-4468-b061-b77a8dad386a: direct link, hf CLI and curl.
- Browser
- Download file 964 Bytes
-
https://huggingface.co/duyphu/76b2d76f-2806-4468-b061-b77a8dad386a/resolve/08d7fc703385d8f7b833520cf8cbda523652a146/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://duyphu/76b2d76f-2806-4468-b061-b77a8dad386a@08d7fc703385d8f7b833520cf8cbda523652a146/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/duyphu/76b2d76f-2806-4468-b061-b77a8dad386a/resolve/08d7fc703385d8f7b833520cf8cbda523652a146/last-checkpoint/trainer_state.json
964 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005614035087719298, | |
| "eval_steps": 1, | |
| "global_step": 1, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005614035087719298, | |
| "eval_loss": 7.9864583015441895, | |
| "eval_runtime": 75.6694, | |
| "eval_samples_per_second": 9.912, | |
| "eval_steps_per_second": 4.956, | |
| "step": 1 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 184956424814592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |