| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029607698001480384, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009869232667160128, | |
| "eval_loss": 1.1808140277862549, | |
| "eval_runtime": 47.629, | |
| "eval_samples_per_second": 8.965, | |
| "eval_steps_per_second": 4.493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029607698001480384, | |
| "grad_norm": 3.3512725830078125, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7998, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005921539600296077, | |
| "grad_norm": 4.269518852233887, | |
| "learning_rate": 0.00012, | |
| "loss": 4.8916, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007895386133728102, | |
| "eval_loss": 0.9780867099761963, | |
| "eval_runtime": 48.086, | |
| "eval_samples_per_second": 8.88, | |
| "eval_steps_per_second": 4.45, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008882309400444115, | |
| "grad_norm": 5.373497486114502, | |
| "learning_rate": 0.00018, | |
| "loss": 4.2661, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011843079200592153, | |
| "grad_norm": 4.902787685394287, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.7163, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014803849000740192, | |
| "grad_norm": 4.044931411743164, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015790772267456205, | |
| "eval_loss": 0.642095685005188, | |
| "eval_runtime": 48.5408, | |
| "eval_samples_per_second": 8.797, | |
| "eval_steps_per_second": 4.409, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01776461880088823, | |
| "grad_norm": 5.7240214347839355, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 3.553171157836914, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.8476, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023686158401184307, | |
| "grad_norm": 7.226178169250488, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.0504, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023686158401184307, | |
| "eval_loss": 0.5628054738044739, | |
| "eval_runtime": 48.9279, | |
| "eval_samples_per_second": 8.727, | |
| "eval_steps_per_second": 4.374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026646928201332347, | |
| "grad_norm": 5.056282043457031, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0441, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029607698001480384, | |
| "grad_norm": 3.949553966522217, | |
| "learning_rate": 0.0, | |
| "loss": 2.3592, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801873028546560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |