| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021324234993069624, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042648469986139245, | |
| "eval_loss": 11.933326721191406, | |
| "eval_runtime": 9.0029, | |
| "eval_samples_per_second": 109.742, | |
| "eval_steps_per_second": 54.871, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021324234993069626, | |
| "grad_norm": 0.009308514185249805, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9336, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "grad_norm": 0.012845045886933804, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "eval_loss": 11.933305740356445, | |
| "eval_runtime": 9.1755, | |
| "eval_samples_per_second": 107.678, | |
| "eval_steps_per_second": 53.839, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006397270497920887, | |
| "grad_norm": 0.010501927696168423, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9345, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "grad_norm": 0.010710126720368862, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9335, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "eval_loss": 11.933269500732422, | |
| "eval_runtime": 9.2734, | |
| "eval_samples_per_second": 106.541, | |
| "eval_steps_per_second": 53.271, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010662117496534812, | |
| "grad_norm": 0.016991719603538513, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012794540995841774, | |
| "grad_norm": 0.011298740282654762, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012794540995841774, | |
| "eval_loss": 11.933237075805664, | |
| "eval_runtime": 9.3204, | |
| "eval_samples_per_second": 106.004, | |
| "eval_steps_per_second": 53.002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014926964495148737, | |
| "grad_norm": 0.016434844583272934, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0170593879944557, | |
| "grad_norm": 0.014193267561495304, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9328, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0170593879944557, | |
| "eval_loss": 11.933220863342285, | |
| "eval_runtime": 9.3191, | |
| "eval_samples_per_second": 106.018, | |
| "eval_steps_per_second": 53.009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019191811493762662, | |
| "grad_norm": 0.010223680175840855, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9346, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021324234993069624, | |
| "grad_norm": 0.013457508757710457, | |
| "learning_rate": 0.0, | |
| "loss": 11.9313, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021324234993069624, | |
| "eval_loss": 11.933218002319336, | |
| "eval_runtime": 9.0369, | |
| "eval_samples_per_second": 109.329, | |
| "eval_steps_per_second": 54.665, | |
| "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": 5996691456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |