| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1392405063291138, | |
| "eval_steps": 50, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06751054852320675, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06751054852320675, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3109, | |
| "eval_samples_per_second": 13.678, | |
| "eval_steps_per_second": 1.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1350210970464135, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.270042194092827, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47257383966244726, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.540084388185654, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7426160337552743, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.989935734988098e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.959823971496575e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8776371308016878, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.909907151739634e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9451476793248945, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8405871765993435e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0464135021097047, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.646121984004666e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1814345991561181, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.248945147679325, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.382678665009028e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.227656622467162e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3839662447257384, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.058724504646834e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4514767932489452, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8772424536302565e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.684671656182497e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5864978902953588, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4825625791348093e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6540084388185654, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.056302334890786e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7890295358649788, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.835583164544139e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8565400843881856, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6121620758762877e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3878379241237136e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1644168354558623e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0928270042194095, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9436976651092143e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.160337552742616, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5174374208651913e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.2953586497890295, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3153283438175036e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.3628691983122363, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.122757546369744e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.412754953531664e-07, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.49789029535865, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.723433775328385e-07, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.5654008438818563, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.17321334990973e-07, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.70042194092827, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.538780159953348e-07, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.7679324894514767, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4757783024395244e-07, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.59412823400657e-07, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9029535864978904, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.00928482603669e-08, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0042194092827006, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.017602850342584e-08, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.071729957805907, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.006426501190233e-08, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.1392405063291138, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5312661952528384e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |