| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 14064, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.035551763367463025, | |
| "grad_norm": 8.486759185791016, | |
| "learning_rate": 2.8937713310580205e-06, | |
| "loss": 1.3328, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07110352673492605, | |
| "grad_norm": 9.923312187194824, | |
| "learning_rate": 2.7873293515358363e-06, | |
| "loss": 1.0132, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "grad_norm": 8.329161643981934, | |
| "learning_rate": 2.6806740614334473e-06, | |
| "loss": 0.9106, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1422070534698521, | |
| "grad_norm": 9.29595947265625, | |
| "learning_rate": 2.5740187713310584e-06, | |
| "loss": 0.8662, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17775881683731512, | |
| "grad_norm": 8.718080520629883, | |
| "learning_rate": 2.4673634812286687e-06, | |
| "loss": 0.835, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "grad_norm": 7.578711032867432, | |
| "learning_rate": 2.360921501706485e-06, | |
| "loss": 0.7989, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.24886234357224118, | |
| "grad_norm": 7.699925422668457, | |
| "learning_rate": 2.2542662116040955e-06, | |
| "loss": 0.7699, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2844141069397042, | |
| "grad_norm": 9.358419418334961, | |
| "learning_rate": 2.1476109215017066e-06, | |
| "loss": 0.7482, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "grad_norm": 10.0253324508667, | |
| "learning_rate": 2.0409556313993177e-06, | |
| "loss": 0.7231, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.35551763367463024, | |
| "grad_norm": 7.296217918395996, | |
| "learning_rate": 1.9343003412969284e-06, | |
| "loss": 0.7141, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3910693970420933, | |
| "grad_norm": 8.735479354858398, | |
| "learning_rate": 1.8278583617747441e-06, | |
| "loss": 0.6845, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.42662116040955633, | |
| "grad_norm": 8.95112133026123, | |
| "learning_rate": 1.7212030716723552e-06, | |
| "loss": 0.673, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.46217292377701935, | |
| "grad_norm": 6.7044291496276855, | |
| "learning_rate": 1.614547781569966e-06, | |
| "loss": 0.6734, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.49772468714448237, | |
| "grad_norm": 8.28055477142334, | |
| "learning_rate": 1.5078924914675768e-06, | |
| "loss": 0.6547, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.5332764505119454, | |
| "grad_norm": 8.512009620666504, | |
| "learning_rate": 1.4014505119453925e-06, | |
| "loss": 0.6486, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.5688282138794084, | |
| "grad_norm": 7.365358352661133, | |
| "learning_rate": 1.2947952218430034e-06, | |
| "loss": 0.6417, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.6043799772468714, | |
| "grad_norm": 11.026593208312988, | |
| "learning_rate": 1.1881399317406143e-06, | |
| "loss": 0.629, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.6399317406143344, | |
| "grad_norm": 8.76122760772705, | |
| "learning_rate": 1.0814846416382254e-06, | |
| "loss": 0.6171, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.6754835039817975, | |
| "grad_norm": 9.334900856018066, | |
| "learning_rate": 9.75042662116041e-07, | |
| "loss": 0.6168, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.7110352673492605, | |
| "grad_norm": 9.215682029724121, | |
| "learning_rate": 8.683873720136519e-07, | |
| "loss": 0.6164, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.7465870307167235, | |
| "grad_norm": 7.827558994293213, | |
| "learning_rate": 7.617320819112628e-07, | |
| "loss": 0.6137, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.7821387940841866, | |
| "grad_norm": 7.96988582611084, | |
| "learning_rate": 6.550767918088738e-07, | |
| "loss": 0.607, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.8176905574516496, | |
| "grad_norm": 8.489790916442871, | |
| "learning_rate": 5.486348122866894e-07, | |
| "loss": 0.5998, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.8532423208191127, | |
| "grad_norm": 7.611661434173584, | |
| "learning_rate": 4.4197952218430034e-07, | |
| "loss": 0.5966, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.8887940841865757, | |
| "grad_norm": 9.416797637939453, | |
| "learning_rate": 3.353242320819113e-07, | |
| "loss": 0.5989, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.9243458475540387, | |
| "grad_norm": 7.783421516418457, | |
| "learning_rate": 2.286689419795222e-07, | |
| "loss": 0.593, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.9598976109215017, | |
| "grad_norm": 8.348119735717773, | |
| "learning_rate": 1.2222696245733788e-07, | |
| "loss": 0.5993, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.9954493742889647, | |
| "grad_norm": 9.241561889648438, | |
| "learning_rate": 1.5571672354948806e-08, | |
| "loss": 0.584, | |
| "step": 14000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 14064, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |