| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02544529262086514, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 2.986571788787842, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "eval_loss": 1.6131161451339722, | |
| "eval_runtime": 4.6505, | |
| "eval_samples_per_second": 35.695, | |
| "eval_steps_per_second": 17.847, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 3.493028163909912, | |
| "learning_rate": 4e-05, | |
| "loss": 1.447, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 2.8425791263580322, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1766, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "eval_loss": 1.5416483879089355, | |
| "eval_runtime": 4.6071, | |
| "eval_samples_per_second": 36.031, | |
| "eval_steps_per_second": 18.016, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 2.444763422012329, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8453, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 2.6551995277404785, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 2.749918222427368, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9995, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "eval_loss": 0.9632787108421326, | |
| "eval_runtime": 4.7548, | |
| "eval_samples_per_second": 34.912, | |
| "eval_steps_per_second": 17.456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 2.5555613040924072, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8248, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 2.661283254623413, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6196, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": 2.314343214035034, | |
| "learning_rate": 0.00018, | |
| "loss": 0.434, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "eval_loss": 0.38469672203063965, | |
| "eval_runtime": 4.7243, | |
| "eval_samples_per_second": 35.138, | |
| "eval_steps_per_second": 17.569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 2.4576034545898438, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3559, | |
| "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": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |