| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 10.01574420928955, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 1.545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 5.001451015472412, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.6012, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.802138566970825, | |
| "learning_rate": 1.9991228300988586e-05, | |
| "loss": 0.3138, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 5.7909345626831055, | |
| "learning_rate": 1.983571470813386e-05, | |
| "loss": 0.2683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.0869674682617188, | |
| "learning_rate": 1.9488760116444966e-05, | |
| "loss": 0.0889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.8485150337219238, | |
| "learning_rate": 1.895711760239413e-05, | |
| "loss": 0.202, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.812760353088379, | |
| "learning_rate": 1.8251134982782952e-05, | |
| "loss": 0.1592, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 7.189540863037109, | |
| "learning_rate": 1.7384553406258842e-05, | |
| "loss": 0.1, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 2.625497579574585, | |
| "learning_rate": 1.63742398974869e-05, | |
| "loss": 0.1889, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.10543157905340195, | |
| "learning_rate": 1.5239859059700794e-05, | |
| "loss": 0.1133, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 4.1977386474609375, | |
| "learning_rate": 1.4003490325568953e-05, | |
| "loss": 0.0466, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.047037750482559204, | |
| "learning_rate": 1.2689198206152657e-05, | |
| "loss": 0.1327, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 1.9393171072006226, | |
| "learning_rate": 1.1322563902571227e-05, | |
| "loss": 0.0181, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 3.4030303955078125, | |
| "learning_rate": 9.930187397020385e-06, | |
| "loss": 0.0681, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.11634967476129532, | |
| "learning_rate": 8.539169714375885e-06, | |
| "loss": 0.0355, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.0528508424758911, | |
| "learning_rate": 7.176585431571235e-06, | |
| "loss": 0.1156, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.18656061589717865, | |
| "learning_rate": 5.868955701754584e-06, | |
| "loss": 0.0125, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.2206106185913086, | |
| "learning_rate": 4.641732050210032e-06, | |
| "loss": 0.0465, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.03330332040786743, | |
| "learning_rate": 3.5188009893686916e-06, | |
| "loss": 0.0085, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.2540493309497833, | |
| "learning_rate": 2.522019095014683e-06, | |
| "loss": 0.0382, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.01842614635825157, | |
| "learning_rate": 1.6707875928990059e-06, | |
| "loss": 0.0105, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.4763164520263672, | |
| "learning_rate": 9.816747359488632e-07, | |
| "loss": 0.0363, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.038556963205337524, | |
| "learning_rate": 4.6809332207053083e-07, | |
| "loss": 0.0317, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 6.009864330291748, | |
| "learning_rate": 1.400396292949513e-07, | |
| "loss": 0.0262, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.019221752882003784, | |
| "learning_rate": 3.898849596456477e-09, | |
| "loss": 0.0135, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 250, | |
| "total_flos": 1.5362943036162048e+16, | |
| "train_loss": 0.16884834933280946, | |
| "train_runtime": 1433.2088, | |
| "train_samples_per_second": 0.698, | |
| "train_steps_per_second": 0.174 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5362943036162048e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |