| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00914703864623828, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000914703864623828, | |
| "grad_norm": 3.900874614715576, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2092, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000914703864623828, | |
| "eval_loss": 2.992326259613037, | |
| "eval_runtime": 16.5375, | |
| "eval_samples_per_second": 27.876, | |
| "eval_steps_per_second": 13.968, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001829407729247656, | |
| "grad_norm": 3.652104616165161, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9802, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002744111593871484, | |
| "grad_norm": 3.8684983253479004, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1291, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002744111593871484, | |
| "eval_loss": 2.951554298400879, | |
| "eval_runtime": 16.4945, | |
| "eval_samples_per_second": 27.949, | |
| "eval_steps_per_second": 14.005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003658815458495312, | |
| "grad_norm": 3.71295166015625, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9264, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00457351932311914, | |
| "grad_norm": 3.8728957176208496, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8292, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005488223187742968, | |
| "grad_norm": 3.653064250946045, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7049, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005488223187742968, | |
| "eval_loss": 2.4208076000213623, | |
| "eval_runtime": 16.5085, | |
| "eval_samples_per_second": 27.925, | |
| "eval_steps_per_second": 13.993, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006402927052366796, | |
| "grad_norm": 3.2386770248413086, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3247, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007317630916990624, | |
| "grad_norm": 3.0688631534576416, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1412, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008232334781614453, | |
| "grad_norm": 2.363431930541992, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8799, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008232334781614453, | |
| "eval_loss": 1.7819440364837646, | |
| "eval_runtime": 16.514, | |
| "eval_samples_per_second": 27.916, | |
| "eval_steps_per_second": 13.988, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00914703864623828, | |
| "grad_norm": 2.161442279815674, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5952, | |
| "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": 489477793382400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |