| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04250797024442083, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004250797024442083, | |
| "grad_norm": 0.7029209136962891, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004250797024442083, | |
| "eval_loss": 1.5603886842727661, | |
| "eval_runtime": 2.3017, | |
| "eval_samples_per_second": 43.447, | |
| "eval_steps_per_second": 21.723, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008501594048884165, | |
| "grad_norm": 0.9273056983947754, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5879, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012752391073326248, | |
| "grad_norm": 0.6883237361907959, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012752391073326248, | |
| "eval_loss": 1.5593794584274292, | |
| "eval_runtime": 1.7995, | |
| "eval_samples_per_second": 55.572, | |
| "eval_steps_per_second": 27.786, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01700318809776833, | |
| "grad_norm": 0.708982527256012, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5621, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021253985122210415, | |
| "grad_norm": 0.8289952874183655, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5821, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025504782146652496, | |
| "grad_norm": 0.7642757296562195, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025504782146652496, | |
| "eval_loss": 1.5391772985458374, | |
| "eval_runtime": 1.8384, | |
| "eval_samples_per_second": 54.395, | |
| "eval_steps_per_second": 27.198, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02975557917109458, | |
| "grad_norm": 0.7512064576148987, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6038, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03400637619553666, | |
| "grad_norm": 0.6701497435569763, | |
| "learning_rate": 0.00016, | |
| "loss": 1.365, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03825717321997875, | |
| "grad_norm": 0.6807700991630554, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4079, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03825717321997875, | |
| "eval_loss": 1.4845983982086182, | |
| "eval_runtime": 1.84, | |
| "eval_samples_per_second": 54.349, | |
| "eval_steps_per_second": 27.175, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04250797024442083, | |
| "grad_norm": 0.8113316297531128, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4687, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 255791978250240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |