| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10482180293501048, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020964360587002098, | |
| "eval_loss": 1.5222282409667969, | |
| "eval_runtime": 32.5184, | |
| "eval_samples_per_second": 6.181, | |
| "eval_steps_per_second": 3.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "grad_norm": 0.5405535101890564, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4549, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "grad_norm": 0.4634641110897064, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "eval_loss": 1.4549593925476074, | |
| "eval_runtime": 34.9095, | |
| "eval_samples_per_second": 5.758, | |
| "eval_steps_per_second": 2.893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "grad_norm": 0.5414504408836365, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "grad_norm": 0.4143407642841339, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "eval_loss": 1.4077080488204956, | |
| "eval_runtime": 35.6083, | |
| "eval_samples_per_second": 5.645, | |
| "eval_steps_per_second": 2.836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "grad_norm": 0.41828131675720215, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "grad_norm": 0.4165772795677185, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4209, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "eval_loss": 1.3841878175735474, | |
| "eval_runtime": 35.7038, | |
| "eval_samples_per_second": 5.63, | |
| "eval_steps_per_second": 2.829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07337526205450734, | |
| "grad_norm": 0.4540785253047943, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4054, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08385744234800839, | |
| "grad_norm": 0.40710872411727905, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4665, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08385744234800839, | |
| "eval_loss": 1.3742934465408325, | |
| "eval_runtime": 35.7187, | |
| "eval_samples_per_second": 5.627, | |
| "eval_steps_per_second": 2.828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09433962264150944, | |
| "grad_norm": 0.3978058397769928, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10482180293501048, | |
| "grad_norm": 0.4136011302471161, | |
| "learning_rate": 0.0, | |
| "loss": 1.3557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10482180293501048, | |
| "eval_loss": 1.3728853464126587, | |
| "eval_runtime": 35.784, | |
| "eval_samples_per_second": 5.617, | |
| "eval_steps_per_second": 2.822, | |
| "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": 1.780205588840448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |