| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012525050100200401, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000250501002004008, | |
| "eval_loss": 3.7049801349639893, | |
| "eval_runtime": 29.0877, | |
| "eval_samples_per_second": 57.791, | |
| "eval_steps_per_second": 28.913, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00125250501002004, | |
| "grad_norm": 0.952879011631012, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6862, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00250501002004008, | |
| "grad_norm": 1.4141132831573486, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00250501002004008, | |
| "eval_loss": 3.6573493480682373, | |
| "eval_runtime": 29.0311, | |
| "eval_samples_per_second": 57.903, | |
| "eval_steps_per_second": 28.969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00375751503006012, | |
| "grad_norm": 1.0935112237930298, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6685, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00501002004008016, | |
| "grad_norm": 1.1594758033752441, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.4933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00501002004008016, | |
| "eval_loss": 3.4188053607940674, | |
| "eval_runtime": 29.0052, | |
| "eval_samples_per_second": 57.955, | |
| "eval_steps_per_second": 28.995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006262525050100201, | |
| "grad_norm": 1.1321828365325928, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2123, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00751503006012024, | |
| "grad_norm": 1.285302758216858, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2524, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00751503006012024, | |
| "eval_loss": 3.2013771533966064, | |
| "eval_runtime": 29.1936, | |
| "eval_samples_per_second": 57.581, | |
| "eval_steps_per_second": 28.808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00876753507014028, | |
| "grad_norm": 1.2490662336349487, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.2394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01002004008016032, | |
| "grad_norm": 1.3431196212768555, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1295, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01002004008016032, | |
| "eval_loss": 3.0911781787872314, | |
| "eval_runtime": 29.0494, | |
| "eval_samples_per_second": 57.867, | |
| "eval_steps_per_second": 28.951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011272545090180362, | |
| "grad_norm": 1.597110390663147, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.0723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012525050100200401, | |
| "grad_norm": 1.3041186332702637, | |
| "learning_rate": 0.0, | |
| "loss": 3.0719, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012525050100200401, | |
| "eval_loss": 3.071542739868164, | |
| "eval_runtime": 28.9036, | |
| "eval_samples_per_second": 58.159, | |
| "eval_steps_per_second": 29.097, | |
| "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 | |
| } | |