| { | |
| "best_metric": 0.19839094579219818, | |
| "best_model_checkpoint": "llama_sequence_classification/checkpoint-412", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1030, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.22537800669670105, | |
| "eval_pearson": 0.947674606760879, | |
| "eval_runtime": 15.5763, | |
| "eval_samples_per_second": 59.834, | |
| "eval_steps_per_second": 7.511, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.19839094579219818, | |
| "eval_pearson": 0.9675925115418463, | |
| "eval_runtime": 15.7578, | |
| "eval_samples_per_second": 59.145, | |
| "eval_steps_per_second": 7.425, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 2.4271844660194173, | |
| "grad_norm": 1.8121649026870728, | |
| "learning_rate": 5.145631067961165e-05, | |
| "loss": 0.3158, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.22435146570205688, | |
| "eval_pearson": 0.9659566264389162, | |
| "eval_runtime": 15.6441, | |
| "eval_samples_per_second": 59.575, | |
| "eval_steps_per_second": 7.479, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.34289389848709106, | |
| "eval_pearson": 0.9622523400900753, | |
| "eval_runtime": 15.57, | |
| "eval_samples_per_second": 59.859, | |
| "eval_steps_per_second": 7.514, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 4.854368932038835, | |
| "grad_norm": 0.002268544165417552, | |
| "learning_rate": 2.912621359223301e-06, | |
| "loss": 0.0338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.3283066749572754, | |
| "eval_pearson": 0.9640273620816536, | |
| "eval_runtime": 15.3573, | |
| "eval_samples_per_second": 60.688, | |
| "eval_steps_per_second": 7.619, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1030, | |
| "total_flos": 5.610584124311962e+16, | |
| "train_loss": 0.1697609151198158, | |
| "train_runtime": 1118.1223, | |
| "train_samples_per_second": 29.357, | |
| "train_steps_per_second": 0.921 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1030, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 5.610584124311962e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |