| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06134969325153374, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001226993865030675, | |
| "eval_loss": 0.8833416700363159, | |
| "eval_runtime": 23.9331, | |
| "eval_samples_per_second": 14.373, | |
| "eval_steps_per_second": 7.187, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006134969325153374, | |
| "grad_norm": 2.763533592224121, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7847, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012269938650306749, | |
| "grad_norm": 2.2924604415893555, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012269938650306749, | |
| "eval_loss": 0.4092090427875519, | |
| "eval_runtime": 24.1287, | |
| "eval_samples_per_second": 14.257, | |
| "eval_steps_per_second": 7.128, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018404907975460124, | |
| "grad_norm": 0.5873926877975464, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3618, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024539877300613498, | |
| "grad_norm": 0.660757303237915, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024539877300613498, | |
| "eval_loss": 0.17818772792816162, | |
| "eval_runtime": 24.0156, | |
| "eval_samples_per_second": 14.324, | |
| "eval_steps_per_second": 7.162, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03067484662576687, | |
| "grad_norm": 0.5385717153549194, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1674, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03680981595092025, | |
| "grad_norm": 0.5803773999214172, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03680981595092025, | |
| "eval_loss": 0.13921323418617249, | |
| "eval_runtime": 24.0696, | |
| "eval_samples_per_second": 14.292, | |
| "eval_steps_per_second": 7.146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04294478527607362, | |
| "grad_norm": 0.8570263981819153, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1425, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "grad_norm": 0.47639739513397217, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "eval_loss": 0.12366819381713867, | |
| "eval_runtime": 24.1511, | |
| "eval_samples_per_second": 14.244, | |
| "eval_steps_per_second": 7.122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05521472392638037, | |
| "grad_norm": 0.6678445339202881, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.136, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06134969325153374, | |
| "grad_norm": 0.6876235008239746, | |
| "learning_rate": 0.0, | |
| "loss": 0.1143, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06134969325153374, | |
| "eval_loss": 0.12126629799604416, | |
| "eval_runtime": 24.1173, | |
| "eval_samples_per_second": 14.264, | |
| "eval_steps_per_second": 7.132, | |
| "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": 4025783512203264.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |