| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03461205653302567, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011537352177675222, | |
| "eval_loss": 0.7028021216392517, | |
| "eval_runtime": 76.9363, | |
| "eval_samples_per_second": 4.744, | |
| "eval_steps_per_second": 2.379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003461205653302567, | |
| "grad_norm": 0.8147540092468262, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006922411306605134, | |
| "grad_norm": 0.5138474106788635, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009229881742140178, | |
| "eval_loss": 0.4824580252170563, | |
| "eval_runtime": 76.3565, | |
| "eval_samples_per_second": 4.78, | |
| "eval_steps_per_second": 2.397, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010383616959907702, | |
| "grad_norm": 0.5344618558883667, | |
| "learning_rate": 0.00018, | |
| "loss": 0.519, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013844822613210269, | |
| "grad_norm": 0.4261031150817871, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.4124, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017306028266512834, | |
| "grad_norm": 0.2541234493255615, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.3079, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018459763484280356, | |
| "eval_loss": 0.3048578202724457, | |
| "eval_runtime": 76.5039, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020767233919815404, | |
| "grad_norm": 0.2141341120004654, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.32, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02422843957311797, | |
| "grad_norm": 0.23161785304546356, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.2829, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027689645226420537, | |
| "grad_norm": 0.2098318636417389, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.2869, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027689645226420537, | |
| "eval_loss": 0.2817035913467407, | |
| "eval_runtime": 76.4839, | |
| "eval_samples_per_second": 4.772, | |
| "eval_steps_per_second": 2.393, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031150850879723104, | |
| "grad_norm": 0.17820662260055542, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.2789, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03461205653302567, | |
| "grad_norm": 0.20811568200588226, | |
| "learning_rate": 0.0, | |
| "loss": 0.2953, | |
| "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": 2.542649764478976e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |