| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 21249, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023530519083250975, | |
| "grad_norm": 1.6875, | |
| "learning_rate": 4.882347404583745e-05, | |
| "loss": 0.9427, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04706103816650195, | |
| "grad_norm": 1.75, | |
| "learning_rate": 4.76469480916749e-05, | |
| "loss": 0.8108, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07059155724975293, | |
| "grad_norm": 1.8671875, | |
| "learning_rate": 4.647042213751235e-05, | |
| "loss": 0.7777, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.0941220763330039, | |
| "grad_norm": 1.6171875, | |
| "learning_rate": 4.52938961833498e-05, | |
| "loss": 0.7551, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11765259541625488, | |
| "grad_norm": 1.4765625, | |
| "learning_rate": 4.411737022918726e-05, | |
| "loss": 0.7373, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.14118311449950585, | |
| "grad_norm": 1.6328125, | |
| "learning_rate": 4.294084427502471e-05, | |
| "loss": 0.727, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16471363358275684, | |
| "grad_norm": 1.84375, | |
| "learning_rate": 4.1764318320862164e-05, | |
| "loss": 0.718, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.1882441526660078, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 4.0587792366699614e-05, | |
| "loss": 0.7153, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2117746717492588, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 3.9411266412537063e-05, | |
| "loss": 0.7067, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.23530519083250975, | |
| "grad_norm": 1.6796875, | |
| "learning_rate": 3.823474045837451e-05, | |
| "loss": 0.7037, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.2588357099157607, | |
| "grad_norm": 1.8203125, | |
| "learning_rate": 3.705821450421196e-05, | |
| "loss": 0.6984, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2823662289990117, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 3.588168855004941e-05, | |
| "loss": 0.6954, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3058967480822627, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 3.470516259588686e-05, | |
| "loss": 0.6948, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.3294272671655137, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 3.352863664172432e-05, | |
| "loss": 0.6908, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.35295778624876467, | |
| "grad_norm": 1.6796875, | |
| "learning_rate": 3.235211068756177e-05, | |
| "loss": 0.6873, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.3764883053320156, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 3.117558473339922e-05, | |
| "loss": 0.6876, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4000188244152666, | |
| "grad_norm": 1.5703125, | |
| "learning_rate": 2.999905877923667e-05, | |
| "loss": 0.6879, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.4235493434985176, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 2.882253282507412e-05, | |
| "loss": 0.6862, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4470798625817686, | |
| "grad_norm": 1.8359375, | |
| "learning_rate": 2.7646006870911574e-05, | |
| "loss": 0.6829, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.4706103816650195, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 2.6469480916749024e-05, | |
| "loss": 0.6852, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.4941409007482705, | |
| "grad_norm": 1.5, | |
| "learning_rate": 2.5292954962586474e-05, | |
| "loss": 0.681, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.5176714198315214, | |
| "grad_norm": 1.59375, | |
| "learning_rate": 2.4116429008423927e-05, | |
| "loss": 0.6798, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.5412019389147724, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 2.2939903054261376e-05, | |
| "loss": 0.6803, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.5647324579980234, | |
| "grad_norm": 1.6875, | |
| "learning_rate": 2.176337710009883e-05, | |
| "loss": 0.6799, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.5882629770812744, | |
| "grad_norm": 1.875, | |
| "learning_rate": 2.0586851145936283e-05, | |
| "loss": 0.6761, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.6117934961645254, | |
| "grad_norm": 1.578125, | |
| "learning_rate": 1.9410325191773732e-05, | |
| "loss": 0.675, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.6353240152477764, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 1.8233799237611182e-05, | |
| "loss": 0.6785, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.6588545343310274, | |
| "grad_norm": 1.8515625, | |
| "learning_rate": 1.7057273283448632e-05, | |
| "loss": 0.6782, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.6823850534142784, | |
| "grad_norm": 1.5390625, | |
| "learning_rate": 1.5880747329286085e-05, | |
| "loss": 0.6761, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.7059155724975293, | |
| "grad_norm": 1.6015625, | |
| "learning_rate": 1.4704221375123536e-05, | |
| "loss": 0.6795, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.7294460915807802, | |
| "grad_norm": 1.8125, | |
| "learning_rate": 1.3527695420960988e-05, | |
| "loss": 0.6774, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.7529766106640312, | |
| "grad_norm": 1.5546875, | |
| "learning_rate": 1.2351169466798439e-05, | |
| "loss": 0.6777, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.7765071297472822, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 1.1174643512635889e-05, | |
| "loss": 0.6746, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.8000376488305332, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 9.998117558473342e-06, | |
| "loss": 0.6782, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.8235681679137842, | |
| "grad_norm": 1.5546875, | |
| "learning_rate": 8.821591604310792e-06, | |
| "loss": 0.6776, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.8470986869970352, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 7.645065650148241e-06, | |
| "loss": 0.6782, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.8706292060802862, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 6.468539695985694e-06, | |
| "loss": 0.6754, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.8941597251635371, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 5.292013741823145e-06, | |
| "loss": 0.6757, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.9176902442467881, | |
| "grad_norm": 1.6015625, | |
| "learning_rate": 4.1154877876605964e-06, | |
| "loss": 0.6765, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.941220763330039, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 2.938961833498047e-06, | |
| "loss": 0.6747, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.96475128241329, | |
| "grad_norm": 1.6171875, | |
| "learning_rate": 1.7624358793354984e-06, | |
| "loss": 0.677, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.988281801496541, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 5.859099251729494e-07, | |
| "loss": 0.6804, | |
| "step": 21000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21249, | |
| "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": 9.787078596423629e+17, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |