| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008655510675129832, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028851702250432774, | |
| "eval_loss": 2.297414779663086, | |
| "eval_runtime": 189.2798, | |
| "eval_samples_per_second": 7.713, | |
| "eval_steps_per_second": 3.857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008655510675129833, | |
| "grad_norm": 0.6467211842536926, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017311021350259665, | |
| "grad_norm": 0.6794170141220093, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2392, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002308136180034622, | |
| "eval_loss": 2.2213892936706543, | |
| "eval_runtime": 190.7475, | |
| "eval_samples_per_second": 7.654, | |
| "eval_steps_per_second": 3.827, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00259665320253895, | |
| "grad_norm": 0.9082630276679993, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003462204270051933, | |
| "grad_norm": 1.0810120105743408, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1552, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004327755337564916, | |
| "grad_norm": 1.2081598043441772, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004616272360069244, | |
| "eval_loss": 2.1524407863616943, | |
| "eval_runtime": 190.7466, | |
| "eval_samples_per_second": 7.654, | |
| "eval_steps_per_second": 3.827, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0051933064050779, | |
| "grad_norm": 0.8614229559898376, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1244, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006058857472590883, | |
| "grad_norm": 1.121108055114746, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.034, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006924408540103866, | |
| "grad_norm": 0.8655470609664917, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.9888, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006924408540103866, | |
| "eval_loss": 2.138546943664551, | |
| "eval_runtime": 190.7546, | |
| "eval_samples_per_second": 7.654, | |
| "eval_steps_per_second": 3.827, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007789959607616849, | |
| "grad_norm": 0.78122478723526, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0581, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008655510675129832, | |
| "grad_norm": 0.7370070815086365, | |
| "learning_rate": 0.0, | |
| "loss": 2.0802, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.109738548887552e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |