| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.053212717839563654, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005321271783956366, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.6644, | |
| "eval_samples_per_second": 10.191, | |
| "eval_steps_per_second": 1.275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002660635891978183, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004789144605560729, | |
| "eval_loss": NaN, | |
| "eval_runtime": 654.9766, | |
| "eval_samples_per_second": 10.202, | |
| "eval_steps_per_second": 1.276, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005321271783956366, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007981907675934548, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009578289211121457, | |
| "eval_loss": NaN, | |
| "eval_runtime": 654.9211, | |
| "eval_samples_per_second": 10.203, | |
| "eval_steps_per_second": 1.276, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010642543567912732, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013303179459890914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014855889603024227, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014367433816682188, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.079, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.276, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015963815351869096, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001442909649383465, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01862445124384728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001373602209226909, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019156578422242915, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.1074, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.276, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021285087135825463, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012803300858899104, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023945723027803643, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011666776747647015, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.023945723027803643, | |
| "eval_loss": NaN, | |
| "eval_runtime": 654.8988, | |
| "eval_samples_per_second": 10.203, | |
| "eval_steps_per_second": 1.277, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026606358919781827, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010370125742738173, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028734867633364376, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.1097, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.276, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02926699481176001, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.963177415120962e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03192763070373819, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0335240122389251, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.0838, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.276, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03458826659571638, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.036822584879038e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03724890248769456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6298742572618266e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03831315684448583, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.1807, | |
| "eval_samples_per_second": 10.199, | |
| "eval_steps_per_second": 1.276, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03990953837967274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.333223252352985e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.042570174271650926, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1966991411008938e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04310230145004656, | |
| "eval_loss": NaN, | |
| "eval_runtime": 654.9321, | |
| "eval_samples_per_second": 10.203, | |
| "eval_steps_per_second": 1.276, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04523081016362911, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2639779077309098e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04789144605560729, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.709035061653494e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04789144605560729, | |
| "eval_loss": NaN, | |
| "eval_runtime": 655.1163, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 1.276, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.050552081947585474, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4411039697577175e-06, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05268059066116802, | |
| "eval_loss": NaN, | |
| "eval_runtime": 654.963, | |
| "eval_samples_per_second": 10.202, | |
| "eval_steps_per_second": 1.276, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.053212717839563654, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8360055280422093e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |