Instructions to use dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/SmolLM2-1.7B") model = PeftModel.from_pretrained(base_model, "dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916: direct link, hf CLI and curl.
- Browser
- Download file 2.05 kB
-
https://huggingface.co/dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/dimasik87/789db1f9-602a-4277-932a-b2aecaa0c916/resolve/main/last-checkpoint/trainer_state.json
2.05 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": 0.006394884092725819, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000639488409272582, | |
| "eval_loss": NaN, | |
| "eval_runtime": 27.3152, | |
| "eval_samples_per_second": 24.126, | |
| "eval_steps_per_second": 12.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019184652278177458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0031974420463629096, | |
| "eval_loss": NaN, | |
| "eval_runtime": 26.7751, | |
| "eval_samples_per_second": 24.612, | |
| "eval_steps_per_second": 12.325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038369304556354917, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0057553956834532375, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006394884092725819, | |
| "eval_loss": NaN, | |
| "eval_runtime": 26.7332, | |
| "eval_samples_per_second": 24.651, | |
| "eval_steps_per_second": 12.344, | |
| "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": 1180867711991808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |