| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5115089514066496, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010230179028132993, | |
| "eval_loss": 1.7183011770248413, | |
| "eval_runtime": 2.8418, | |
| "eval_samples_per_second": 14.78, | |
| "eval_steps_per_second": 7.39, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "grad_norm": 31.760643005371094, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9221, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "grad_norm": 24.04104995727539, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6407, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "eval_loss": 1.2962255477905273, | |
| "eval_runtime": 2.8947, | |
| "eval_samples_per_second": 14.509, | |
| "eval_steps_per_second": 7.255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1534526854219949, | |
| "grad_norm": 20.22098731994629, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.9557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "grad_norm": 18.268779754638672, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "eval_loss": 1.1078734397888184, | |
| "eval_runtime": 2.8826, | |
| "eval_samples_per_second": 14.57, | |
| "eval_steps_per_second": 7.285, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2557544757033248, | |
| "grad_norm": 14.397125244140625, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.6283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3069053708439898, | |
| "grad_norm": 17.547170639038086, | |
| "learning_rate": 5e-05, | |
| "loss": 4.674, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3069053708439898, | |
| "eval_loss": 1.0804661512374878, | |
| "eval_runtime": 2.9408, | |
| "eval_samples_per_second": 14.282, | |
| "eval_steps_per_second": 7.141, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35805626598465473, | |
| "grad_norm": 14.113393783569336, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.3909, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4092071611253197, | |
| "grad_norm": 16.109891891479492, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.4447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4092071611253197, | |
| "eval_loss": 1.0631228685379028, | |
| "eval_runtime": 2.9579, | |
| "eval_samples_per_second": 14.199, | |
| "eval_steps_per_second": 7.1, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46035805626598464, | |
| "grad_norm": 15.316681861877441, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.1716, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5115089514066496, | |
| "grad_norm": 15.52376651763916, | |
| "learning_rate": 0.0, | |
| "loss": 4.4364, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5115089514066496, | |
| "eval_loss": 1.0604280233383179, | |
| "eval_runtime": 2.9415, | |
| "eval_samples_per_second": 14.278, | |
| "eval_steps_per_second": 7.139, | |
| "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": 8763509991014400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |