| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1784121320249777, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003568242640499554, | |
| "eval_loss": 7.846585750579834, | |
| "eval_runtime": 31.965, | |
| "eval_samples_per_second": 3.692, | |
| "eval_steps_per_second": 1.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01784121320249777, | |
| "grad_norm": 36.881221771240234, | |
| "learning_rate": 5e-05, | |
| "loss": 30.8244, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03568242640499554, | |
| "grad_norm": 57.29407501220703, | |
| "learning_rate": 0.0001, | |
| "loss": 27.1875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03568242640499554, | |
| "eval_loss": 3.8446438312530518, | |
| "eval_runtime": 32.0307, | |
| "eval_samples_per_second": 3.684, | |
| "eval_steps_per_second": 1.842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05352363960749331, | |
| "grad_norm": 22.045700073242188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.0607, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07136485280999108, | |
| "grad_norm": 18.30545425415039, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.428, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07136485280999108, | |
| "eval_loss": 0.7446629405021667, | |
| "eval_runtime": 32.0151, | |
| "eval_samples_per_second": 3.686, | |
| "eval_steps_per_second": 1.843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08920606601248884, | |
| "grad_norm": 5.891457557678223, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10704727921498662, | |
| "grad_norm": 13.18043041229248, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10704727921498662, | |
| "eval_loss": 0.7936036586761475, | |
| "eval_runtime": 31.9756, | |
| "eval_samples_per_second": 3.69, | |
| "eval_steps_per_second": 1.845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12488849241748438, | |
| "grad_norm": 5.53622579574585, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.9656, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14272970561998216, | |
| "grad_norm": 7.1533732414245605, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6927, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14272970561998216, | |
| "eval_loss": 0.7167017459869385, | |
| "eval_runtime": 31.9979, | |
| "eval_samples_per_second": 3.688, | |
| "eval_steps_per_second": 1.844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16057091882247992, | |
| "grad_norm": 11.087233543395996, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1784121320249777, | |
| "grad_norm": 8.07785415649414, | |
| "learning_rate": 0.0, | |
| "loss": 2.8839, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1784121320249777, | |
| "eval_loss": 0.7074518799781799, | |
| "eval_runtime": 32.0819, | |
| "eval_samples_per_second": 3.678, | |
| "eval_steps_per_second": 1.839, | |
| "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": 8143665679564800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |