| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0221483942414175, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00044296788482834997, | |
| "eval_loss": 1.6710176467895508, | |
| "eval_runtime": 54.8379, | |
| "eval_samples_per_second": 17.342, | |
| "eval_steps_per_second": 8.68, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022148394241417496, | |
| "grad_norm": 1.1933499574661255, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0533, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004429678848283499, | |
| "grad_norm": 1.8788539171218872, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004429678848283499, | |
| "eval_loss": 1.621188759803772, | |
| "eval_runtime": 53.4644, | |
| "eval_samples_per_second": 17.788, | |
| "eval_steps_per_second": 8.903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006644518272425249, | |
| "grad_norm": 4.6856303215026855, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.1143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "grad_norm": 5.204329967498779, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.3266, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "eval_loss": 1.481325626373291, | |
| "eval_runtime": 53.5878, | |
| "eval_samples_per_second": 17.747, | |
| "eval_steps_per_second": 8.883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01107419712070875, | |
| "grad_norm": 4.367620468139648, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.9044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "grad_norm": 4.27791166305542, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "eval_loss": 1.4420503377914429, | |
| "eval_runtime": 53.7104, | |
| "eval_samples_per_second": 17.706, | |
| "eval_steps_per_second": 8.862, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015503875968992248, | |
| "grad_norm": 4.789373397827148, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.7568, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 4.606958866119385, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.7293, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "eval_loss": 1.4199910163879395, | |
| "eval_runtime": 53.7595, | |
| "eval_samples_per_second": 17.69, | |
| "eval_steps_per_second": 8.854, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019933554817275746, | |
| "grad_norm": 4.549298286437988, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.4629, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0221483942414175, | |
| "grad_norm": 3.8235421180725098, | |
| "learning_rate": 0.0, | |
| "loss": 6.0671, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0221483942414175, | |
| "eval_loss": 1.4167218208312988, | |
| "eval_runtime": 53.6504, | |
| "eval_samples_per_second": 17.726, | |
| "eval_steps_per_second": 8.872, | |
| "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": 8162390153625600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |