Instructions to use dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("OpenBuddy/openbuddy-llama2-13b-v8.1-fp16") model = PeftModel.from_pretrained(base_model, "dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037: direct link, hf CLI and curl.
- Browser
- Download file 2.06 kB
-
https://huggingface.co/dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/dimasik87/4e28cde6-8ba7-4064-8ab0-0b6c6ee61037/resolve/main/last-checkpoint/trainer_state.json
2.06 kB
Invalid JSON:Unexpected token 'N', ..."_metric": NaN,
"be"... is not valid JSON
| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0008699812954021488, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.699812954021488e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 855.9891, | |
| "eval_samples_per_second": 11.309, | |
| "eval_steps_per_second": 2.827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026099438862064463, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004349906477010744, | |
| "eval_loss": NaN, | |
| "eval_runtime": 853.9639, | |
| "eval_samples_per_second": 11.335, | |
| "eval_steps_per_second": 2.834, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005219887772412893, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000782983165861934, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008699812954021488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 854.4296, | |
| "eval_samples_per_second": 11.329, | |
| "eval_steps_per_second": 2.832, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.74953984950272e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |