| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04193751310547285, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000838750262109457, | |
| "eval_loss": 1.2205588817596436, | |
| "eval_runtime": 33.6875, | |
| "eval_samples_per_second": 14.902, | |
| "eval_steps_per_second": 7.451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "grad_norm": 0.7135269641876221, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1479, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "grad_norm": 1.156472086906433, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "eval_loss": 1.0230368375778198, | |
| "eval_runtime": 33.9518, | |
| "eval_samples_per_second": 14.786, | |
| "eval_steps_per_second": 7.393, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012581253931641853, | |
| "grad_norm": 0.8804078698158264, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "grad_norm": 0.9397221207618713, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8737, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "eval_loss": 0.8285709619522095, | |
| "eval_runtime": 34.0574, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 7.37, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020968756552736424, | |
| "grad_norm": 0.714771032333374, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025162507863283706, | |
| "grad_norm": 0.6851562261581421, | |
| "learning_rate": 5e-05, | |
| "loss": 0.76, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025162507863283706, | |
| "eval_loss": 0.7844892740249634, | |
| "eval_runtime": 34.0815, | |
| "eval_samples_per_second": 14.729, | |
| "eval_steps_per_second": 7.365, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02935625917383099, | |
| "grad_norm": 0.6834311485290527, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7816, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03355001048437828, | |
| "grad_norm": 0.7540104985237122, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7359, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03355001048437828, | |
| "eval_loss": 0.7644742131233215, | |
| "eval_runtime": 34.1728, | |
| "eval_samples_per_second": 14.69, | |
| "eval_steps_per_second": 7.345, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.037743761794925564, | |
| "grad_norm": 0.6550795435905457, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7887, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04193751310547285, | |
| "grad_norm": 0.7117176651954651, | |
| "learning_rate": 0.0, | |
| "loss": 0.8369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04193751310547285, | |
| "eval_loss": 0.7608298659324646, | |
| "eval_runtime": 34.1496, | |
| "eval_samples_per_second": 14.7, | |
| "eval_steps_per_second": 7.35, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |