Download trainer_state.json from jeromex1/Lyra-Mistral7B-irrigation-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 2.6 kB
-
https://huggingface.co/jeromex1/Lyra-Mistral7B-irrigation-LoRA/resolve/main/trainer_state.json
- Command line
-
hf download hf://jeromex1/Lyra-Mistral7B-irrigation-LoRA/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/jeromex1/Lyra-Mistral7B-irrigation-LoRA/resolve/main/trainer_state.json
2.6 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 114, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 8.119163513183594, | |
| "learning_rate": 1.989821441880933e-05, | |
| "loss": 3.3845, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 6.9536356925964355, | |
| "learning_rate": 1.9096319953545186e-05, | |
| "loss": 2.2109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.116115570068359, | |
| "learning_rate": 1.7557495743542586e-05, | |
| "loss": 1.2643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0533333333333332, | |
| "grad_norm": 6.118326663970947, | |
| "learning_rate": 1.5406408174555978e-05, | |
| "loss": 0.7636, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 4.654087543487549, | |
| "learning_rate": 1.2817325568414299e-05, | |
| "loss": 0.5695, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5866666666666667, | |
| "grad_norm": 6.207446575164795, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4991, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8533333333333335, | |
| "grad_norm": 5.133678913116455, | |
| "learning_rate": 7.182674431585703e-06, | |
| "loss": 0.388, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.1066666666666665, | |
| "grad_norm": 6.848987579345703, | |
| "learning_rate": 4.593591825444028e-06, | |
| "loss": 0.339, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.3733333333333335, | |
| "grad_norm": 4.636077880859375, | |
| "learning_rate": 2.4425042564574186e-06, | |
| "loss": 0.3037, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 6.074122428894043, | |
| "learning_rate": 9.036800464548157e-07, | |
| "loss": 0.286, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.9066666666666667, | |
| "grad_norm": 5.441417217254639, | |
| "learning_rate": 1.0178558119067316e-07, | |
| "loss": 0.2766, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 114, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2543582070374400.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |