| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007667535654040792, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015335071308081582, | |
| "eval_loss": 10.366971015930176, | |
| "eval_runtime": 12.0125, | |
| "eval_samples_per_second": 228.595, | |
| "eval_steps_per_second": 114.298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007667535654040791, | |
| "grad_norm": 0.06585351377725601, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3697, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015335071308081583, | |
| "grad_norm": 0.05857785418629646, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015335071308081583, | |
| "eval_loss": 10.366765022277832, | |
| "eval_runtime": 12.0286, | |
| "eval_samples_per_second": 228.29, | |
| "eval_steps_per_second": 114.145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023002606962122373, | |
| "grad_norm": 0.08557874709367752, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3689, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030670142616163166, | |
| "grad_norm": 0.06665366142988205, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3697, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030670142616163166, | |
| "eval_loss": 10.36631965637207, | |
| "eval_runtime": 12.2892, | |
| "eval_samples_per_second": 223.448, | |
| "eval_steps_per_second": 111.724, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003833767827020396, | |
| "grad_norm": 0.059420373290777206, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004600521392424475, | |
| "grad_norm": 0.05777762457728386, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3674, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004600521392424475, | |
| "eval_loss": 10.36599063873291, | |
| "eval_runtime": 12.239, | |
| "eval_samples_per_second": 224.365, | |
| "eval_steps_per_second": 112.182, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005367274957828554, | |
| "grad_norm": 0.07109667360782623, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3656, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006134028523232633, | |
| "grad_norm": 0.07906866073608398, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3739, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006134028523232633, | |
| "eval_loss": 10.365830421447754, | |
| "eval_runtime": 12.2379, | |
| "eval_samples_per_second": 224.386, | |
| "eval_steps_per_second": 112.193, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006900782088636712, | |
| "grad_norm": 0.055559780448675156, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3649, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007667535654040792, | |
| "grad_norm": 0.06306865811347961, | |
| "learning_rate": 0.0, | |
| "loss": 10.3684, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007667535654040792, | |
| "eval_loss": 10.365800857543945, | |
| "eval_runtime": 12.1527, | |
| "eval_samples_per_second": 225.958, | |
| "eval_steps_per_second": 112.979, | |
| "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": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |