| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06291286568103177, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012582573136206354, | |
| "eval_loss": 1.9066376686096191, | |
| "eval_runtime": 22.9604, | |
| "eval_samples_per_second": 14.59, | |
| "eval_steps_per_second": 7.317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0062912865681031774, | |
| "grad_norm": 0.43031996488571167, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012582573136206355, | |
| "grad_norm": 0.5575742721557617, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012582573136206355, | |
| "eval_loss": 1.8137931823730469, | |
| "eval_runtime": 22.0854, | |
| "eval_samples_per_second": 15.168, | |
| "eval_steps_per_second": 7.607, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01887385970430953, | |
| "grad_norm": 0.5651086568832397, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7105, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02516514627241271, | |
| "grad_norm": 0.7812576293945312, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5921, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02516514627241271, | |
| "eval_loss": 1.5587526559829712, | |
| "eval_runtime": 21.8663, | |
| "eval_samples_per_second": 15.32, | |
| "eval_steps_per_second": 7.683, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.031456432840515886, | |
| "grad_norm": 0.7038311958312988, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03774771940861906, | |
| "grad_norm": 0.698702871799469, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5517, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03774771940861906, | |
| "eval_loss": 1.422050952911377, | |
| "eval_runtime": 21.9579, | |
| "eval_samples_per_second": 15.256, | |
| "eval_steps_per_second": 7.651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04403900597672224, | |
| "grad_norm": 0.7089139819145203, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.461, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05033029254482542, | |
| "grad_norm": 0.7941172122955322, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05033029254482542, | |
| "eval_loss": 1.3716589212417603, | |
| "eval_runtime": 22.0355, | |
| "eval_samples_per_second": 15.203, | |
| "eval_steps_per_second": 7.624, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056621579112928595, | |
| "grad_norm": 0.5609609484672546, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06291286568103177, | |
| "grad_norm": 0.6352398991584778, | |
| "learning_rate": 0.0, | |
| "loss": 1.3598, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06291286568103177, | |
| "eval_loss": 1.3645598888397217, | |
| "eval_runtime": 21.8758, | |
| "eval_samples_per_second": 15.314, | |
| "eval_steps_per_second": 7.68, | |
| "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": 8077479350108160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |