Instructions to use VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("fxmarty/tiny-random-GemmaForCausalLM") model = PeftModel.from_pretrained(base_model, "VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30: direct link, hf CLI and curl.
- Browser
- Download file 2.06 kB
-
https://huggingface.co/VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/VERSIL91/7a7fdacb-4032-4374-8e61-2b930a6bbd30/resolve/main/last-checkpoint/trainer_state.json
2.06 kB
Invalid JSON:Unexpected token 'N', ..."ad_norm": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007186166629238716, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014372333258477432, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014372333258477432, | |
| "eval_loss": NaN, | |
| "eval_runtime": 57.7415, | |
| "eval_samples_per_second": 202.956, | |
| "eval_steps_per_second": 101.487, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028744666516954863, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00028744666516954863, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.64, | |
| "eval_samples_per_second": 328.816, | |
| "eval_steps_per_second": 164.422, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004311699977543229, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005748933303390973, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005748933303390973, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6553, | |
| "eval_samples_per_second": 328.675, | |
| "eval_steps_per_second": 164.352, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007186166629238716, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3357573120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |