| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02990877822640945, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000598175564528189, | |
| "eval_loss": 1.5591797828674316, | |
| "eval_runtime": 48.3156, | |
| "eval_samples_per_second": 14.571, | |
| "eval_steps_per_second": 7.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029908778226409452, | |
| "grad_norm": 1.9048610925674438, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0059817556452818905, | |
| "grad_norm": 2.2331185340881348, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0059817556452818905, | |
| "eval_loss": 0.9609334468841553, | |
| "eval_runtime": 48.5419, | |
| "eval_samples_per_second": 14.503, | |
| "eval_steps_per_second": 7.251, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008972633467922835, | |
| "grad_norm": 2.0670902729034424, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7016, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011963511290563781, | |
| "grad_norm": 2.2514219284057617, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5159, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011963511290563781, | |
| "eval_loss": 0.4601607620716095, | |
| "eval_runtime": 48.6121, | |
| "eval_samples_per_second": 14.482, | |
| "eval_steps_per_second": 7.241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014954389113204725, | |
| "grad_norm": 1.524185299873352, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01794526693584567, | |
| "grad_norm": 2.1629364490509033, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01794526693584567, | |
| "eval_loss": 0.3503962755203247, | |
| "eval_runtime": 49.216, | |
| "eval_samples_per_second": 14.304, | |
| "eval_steps_per_second": 7.152, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020936144758486618, | |
| "grad_norm": 1.596753716468811, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3254, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023927022581127562, | |
| "grad_norm": 1.4296098947525024, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023927022581127562, | |
| "eval_loss": 0.3147238790988922, | |
| "eval_runtime": 48.9583, | |
| "eval_samples_per_second": 14.38, | |
| "eval_steps_per_second": 7.19, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026917900403768506, | |
| "grad_norm": 1.4859087467193604, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2939, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02990877822640945, | |
| "grad_norm": 1.7117029428482056, | |
| "learning_rate": 0.0, | |
| "loss": 0.3142, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02990877822640945, | |
| "eval_loss": 0.3085658550262451, | |
| "eval_runtime": 49.3897, | |
| "eval_samples_per_second": 14.254, | |
| "eval_steps_per_second": 7.127, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2537993953345536.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |