| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.830188679245283, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9056603773584906, | |
| "eval_loss": 0.8220317959785461, | |
| "eval_runtime": 5.1278, | |
| "eval_samples_per_second": 34.322, | |
| "eval_steps_per_second": 0.585, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.5660377358490565, | |
| "grad_norm": 17.537668739316466, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8679245283018868, | |
| "eval_loss": 0.6778215765953064, | |
| "eval_runtime": 4.9221, | |
| "eval_samples_per_second": 35.757, | |
| "eval_steps_per_second": 0.609, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.830188679245283, | |
| "eval_loss": 0.6227314472198486, | |
| "eval_runtime": 4.2484, | |
| "eval_samples_per_second": 41.428, | |
| "eval_steps_per_second": 0.706, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.830188679245283, | |
| "step": 18, | |
| "total_flos": 29941290762240.0, | |
| "train_loss": 0.933154477013482, | |
| "train_runtime": 809.6925, | |
| "train_samples_per_second": 12.368, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 18, | |
| "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": 29941290762240.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |