| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0490075961774075, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00098015192354815, | |
| "eval_loss": 2.4223687648773193, | |
| "eval_runtime": 7.5327, | |
| "eval_samples_per_second": 57.084, | |
| "eval_steps_per_second": 28.542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "grad_norm": 0.6046074628829956, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2393, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "grad_norm": 0.5879426598548889, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "eval_loss": 2.399517774581909, | |
| "eval_runtime": 7.6193, | |
| "eval_samples_per_second": 56.435, | |
| "eval_steps_per_second": 28.218, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014702278853222249, | |
| "grad_norm": 0.5461297035217285, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2989, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "grad_norm": 0.7177299857139587, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.279, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "eval_loss": 2.260446548461914, | |
| "eval_runtime": 7.5302, | |
| "eval_samples_per_second": 57.103, | |
| "eval_steps_per_second": 28.552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02450379808870375, | |
| "grad_norm": 0.7443307638168335, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029404557706444498, | |
| "grad_norm": 0.5858839750289917, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.029404557706444498, | |
| "eval_loss": 2.1607236862182617, | |
| "eval_runtime": 7.7464, | |
| "eval_samples_per_second": 55.51, | |
| "eval_steps_per_second": 27.755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03430531732418525, | |
| "grad_norm": 0.620461642742157, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.094, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "grad_norm": 0.6441255211830139, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "eval_loss": 2.119108200073242, | |
| "eval_runtime": 7.7335, | |
| "eval_samples_per_second": 55.602, | |
| "eval_steps_per_second": 27.801, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04410683655966675, | |
| "grad_norm": 0.7288550734519958, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0913, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0490075961774075, | |
| "grad_norm": 0.7713973522186279, | |
| "learning_rate": 0.0, | |
| "loss": 2.0359, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0490075961774075, | |
| "eval_loss": 2.1122353076934814, | |
| "eval_runtime": 7.5703, | |
| "eval_samples_per_second": 56.801, | |
| "eval_steps_per_second": 28.4, | |
| "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": 171463252377600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |