| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.42903047800064087, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.2337, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.4659309387207031, | |
| "learning_rate": 4.999557652060729e-05, | |
| "loss": 1.1471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.730895459651947, | |
| "learning_rate": 4.946665048328287e-05, | |
| "loss": 1.0505, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.6177507638931274, | |
| "learning_rate": 4.807442755497524e-05, | |
| "loss": 1.054, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0368133783340454, | |
| "learning_rate": 4.586803181690609e-05, | |
| "loss": 1.0488, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.5574620962142944, | |
| "learning_rate": 4.292531514268008e-05, | |
| "loss": 1.0591, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.6061655282974243, | |
| "learning_rate": 3.9350110223152844e-05, | |
| "loss": 0.8107, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.3221992254257202, | |
| "learning_rate": 3.526856686758269e-05, | |
| "loss": 0.7167, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.6188404560089111, | |
| "learning_rate": 3.082470085335133e-05, | |
| "loss": 0.6753, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.9393795728683472, | |
| "learning_rate": 2.6175312381477442e-05, | |
| "loss": 0.6811, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.7857360243797302, | |
| "learning_rate": 2.148445343837755e-05, | |
| "loss": 0.7164, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.43257200717926025, | |
| "learning_rate": 1.69176392810087e-05, | |
| "loss": 0.7362, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.616813600063324, | |
| "learning_rate": 1.2636008291040618e-05, | |
| "loss": 0.7095, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.0762410163879395, | |
| "learning_rate": 8.790636265485334e-06, | |
| "loss": 0.4147, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.7847151160240173, | |
| "learning_rate": 5.51720576197794e-06, | |
| "loss": 0.4341, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.9602726101875305, | |
| "learning_rate": 2.931218588927315e-06, | |
| "loss": 0.4104, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.5409191846847534, | |
| "learning_rate": 1.1239203660860648e-06, | |
| "loss": 0.4513, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.8361196517944336, | |
| "learning_rate": 1.5908095594207583e-07, | |
| "loss": 0.3921, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6182242199207936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |