| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 96, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010471204188481676, |
| "grad_norm": 47.982173919677734, |
| "learning_rate": 1e-07, |
| "loss": 1.7413017749786377, |
| "step": 1, |
| "token_acc": 0.7888167748377434 |
| }, |
| { |
| "epoch": 0.05235602094240838, |
| "grad_norm": 50.94432067871094, |
| "learning_rate": 5e-07, |
| "loss": 1.879357933998108, |
| "step": 5, |
| "token_acc": 0.776773720845036 |
| }, |
| { |
| "epoch": 0.10471204188481675, |
| "grad_norm": 48.849647521972656, |
| "learning_rate": 4.962847472542185e-07, |
| "loss": 1.821310043334961, |
| "step": 10, |
| "token_acc": 0.7765751836103595 |
| }, |
| { |
| "epoch": 0.15706806282722513, |
| "grad_norm": 39.60130310058594, |
| "learning_rate": 4.852494138405941e-07, |
| "loss": 1.4696194648742675, |
| "step": 15, |
| "token_acc": 0.7860804416403786 |
| }, |
| { |
| "epoch": 0.2094240837696335, |
| "grad_norm": 20.00335693359375, |
| "learning_rate": 4.6722199218125165e-07, |
| "loss": 1.3047430992126465, |
| "step": 20, |
| "token_acc": 0.7964089775561097 |
| }, |
| { |
| "epoch": 0.2617801047120419, |
| "grad_norm": 15.745766639709473, |
| "learning_rate": 4.4273829369874486e-07, |
| "loss": 1.0165138244628906, |
| "step": 25, |
| "token_acc": 0.8169903377020951 |
| }, |
| { |
| "epoch": 0.31413612565445026, |
| "grad_norm": 11.822181701660156, |
| "learning_rate": 4.12526023417186e-07, |
| "loss": 0.9544364929199218, |
| "step": 30, |
| "token_acc": 0.8224739374498797 |
| }, |
| { |
| "epoch": 0.36649214659685864, |
| "grad_norm": 10.846026420593262, |
| "learning_rate": 3.77483151097534e-07, |
| "loss": 0.8972492218017578, |
| "step": 35, |
| "token_acc": 0.8303642121931908 |
| }, |
| { |
| "epoch": 0.418848167539267, |
| "grad_norm": 9.654153823852539, |
| "learning_rate": 3.3865122176063385e-07, |
| "loss": 0.7362692832946778, |
| "step": 40, |
| "token_acc": 0.8384876393601551 |
| }, |
| { |
| "epoch": 0.4712041884816754, |
| "grad_norm": 8.551219940185547, |
| "learning_rate": 2.9718439886322915e-07, |
| "loss": 0.6027413368225097, |
| "step": 45, |
| "token_acc": 0.8445121951219512 |
| }, |
| { |
| "epoch": 0.5235602094240838, |
| "grad_norm": 8.043594360351562, |
| "learning_rate": 2.5431516022634714e-07, |
| "loss": 0.5235415935516358, |
| "step": 50, |
| "token_acc": 0.8558808933002482 |
| }, |
| { |
| "epoch": 0.5759162303664922, |
| "grad_norm": 6.330442428588867, |
| "learning_rate": 2.1131766630242964e-07, |
| "loss": 0.5125304222106933, |
| "step": 55, |
| "token_acc": 0.8577164120642381 |
| }, |
| { |
| "epoch": 0.6282722513089005, |
| "grad_norm": 5.42710018157959, |
| "learning_rate": 1.6946988955037738e-07, |
| "loss": 0.47348899841308595, |
| "step": 60, |
| "token_acc": 0.8619181809347974 |
| }, |
| { |
| "epoch": 0.680628272251309, |
| "grad_norm": 4.45565128326416, |
| "learning_rate": 1.3001563051005346e-07, |
| "loss": 0.40836124420166015, |
| "step": 65, |
| "token_acc": 0.8791852955787381 |
| }, |
| { |
| "epoch": 0.7329842931937173, |
| "grad_norm": 4.402743339538574, |
| "learning_rate": 9.412754953531663e-08, |
| "loss": 0.37663998603820803, |
| "step": 70, |
| "token_acc": 0.8872172960047823 |
| }, |
| { |
| "epoch": 0.7853403141361257, |
| "grad_norm": 4.535104751586914, |
| "learning_rate": 6.28723129572247e-08, |
| "loss": 0.40417027473449707, |
| "step": 75, |
| "token_acc": 0.8783559504051548 |
| }, |
| { |
| "epoch": 0.837696335078534, |
| "grad_norm": 4.095034122467041, |
| "learning_rate": 3.7178889603912216e-08, |
| "loss": 0.4013843059539795, |
| "step": 80, |
| "token_acc": 0.8795386158475427 |
| }, |
| { |
| "epoch": 0.8900523560209425, |
| "grad_norm": 4.874212741851807, |
| "learning_rate": 1.7810939968674416e-08, |
| "loss": 0.42403125762939453, |
| "step": 85, |
| "token_acc": 0.8744140625 |
| }, |
| { |
| "epoch": 0.9424083769633508, |
| "grad_norm": 4.154896259307861, |
| "learning_rate": 5.344118676011172e-09, |
| "loss": 0.41933584213256836, |
| "step": 90, |
| "token_acc": 0.8789355687688859 |
| }, |
| { |
| "epoch": 0.9947643979057592, |
| "grad_norm": 4.3949971199035645, |
| "learning_rate": 1.4896486223239802e-10, |
| "loss": 0.4075876235961914, |
| "step": 95, |
| "token_acc": 0.8777237354085603 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 96, |
| "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": 5.0101394588513075e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
