| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033873043831718717, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.774608766343743e-05, | |
| "eval_loss": 2.3887646198272705, | |
| "eval_runtime": 475.4421, | |
| "eval_samples_per_second": 13.074, | |
| "eval_steps_per_second": 6.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033873043831718716, | |
| "grad_norm": 1.6730268001556396, | |
| "learning_rate": 5e-05, | |
| "loss": 2.353, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006774608766343743, | |
| "grad_norm": 1.3446134328842163, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3565, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006774608766343743, | |
| "eval_loss": 2.1640970706939697, | |
| "eval_runtime": 476.4049, | |
| "eval_samples_per_second": 13.048, | |
| "eval_steps_per_second": 6.524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010161913149515616, | |
| "grad_norm": 1.2943826913833618, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2338, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013549217532687486, | |
| "grad_norm": 1.197544813156128, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013549217532687486, | |
| "eval_loss": 1.9895895719528198, | |
| "eval_runtime": 478.3139, | |
| "eval_samples_per_second": 12.996, | |
| "eval_steps_per_second": 6.498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016936521915859358, | |
| "grad_norm": 0.9158143401145935, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.017, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0020323826299031233, | |
| "grad_norm": 0.8368361592292786, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020323826299031233, | |
| "eval_loss": 1.953887939453125, | |
| "eval_runtime": 477.6252, | |
| "eval_samples_per_second": 13.014, | |
| "eval_steps_per_second": 6.507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023711130682203103, | |
| "grad_norm": 0.9590093493461609, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.833, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0027098435065374973, | |
| "grad_norm": 0.7888218760490417, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0027098435065374973, | |
| "eval_loss": 1.938575267791748, | |
| "eval_runtime": 479.4053, | |
| "eval_samples_per_second": 12.966, | |
| "eval_steps_per_second": 6.483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030485739448546847, | |
| "grad_norm": 0.7486097812652588, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1037, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0033873043831718717, | |
| "grad_norm": 0.8270931839942932, | |
| "learning_rate": 0.0, | |
| "loss": 1.9445, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0033873043831718717, | |
| "eval_loss": 1.9363861083984375, | |
| "eval_runtime": 475.5221, | |
| "eval_samples_per_second": 13.072, | |
| "eval_steps_per_second": 6.536, | |
| "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": 1.0496277108228096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |