| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990574929311969, | |
| "eval_steps": 500, | |
| "global_step": 265, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03770028275212064, | |
| "grad_norm": 2.4303722381591797, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 8.4241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07540056550424128, | |
| "grad_norm": 1.5850571393966675, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 6.725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11310084825636192, | |
| "grad_norm": 2.031186103820801, | |
| "learning_rate": 9.873949579831935e-06, | |
| "loss": 4.9838, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15080113100848255, | |
| "grad_norm": 0.5165069103240967, | |
| "learning_rate": 9.453781512605043e-06, | |
| "loss": 4.7893, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1885014137606032, | |
| "grad_norm": 0.34778788685798645, | |
| "learning_rate": 9.033613445378152e-06, | |
| "loss": 4.4361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22620169651272384, | |
| "grad_norm": 0.3592067360877991, | |
| "learning_rate": 8.613445378151262e-06, | |
| "loss": 4.6479, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2639019792648445, | |
| "grad_norm": 0.354877769947052, | |
| "learning_rate": 8.19327731092437e-06, | |
| "loss": 4.2872, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3016022620169651, | |
| "grad_norm": 0.37858325242996216, | |
| "learning_rate": 7.773109243697479e-06, | |
| "loss": 4.2712, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3393025447690858, | |
| "grad_norm": 0.3336992859840393, | |
| "learning_rate": 7.352941176470589e-06, | |
| "loss": 4.3702, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3770028275212064, | |
| "grad_norm": 0.4017847180366516, | |
| "learning_rate": 6.932773109243698e-06, | |
| "loss": 4.3529, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41470311027332707, | |
| "grad_norm": 0.3004876375198364, | |
| "learning_rate": 6.512605042016807e-06, | |
| "loss": 4.3133, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4524033930254477, | |
| "grad_norm": 0.3605199158191681, | |
| "learning_rate": 6.092436974789916e-06, | |
| "loss": 4.2671, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49010367577756836, | |
| "grad_norm": 0.3112640082836151, | |
| "learning_rate": 5.672268907563025e-06, | |
| "loss": 4.1964, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.527803958529689, | |
| "grad_norm": 0.3452892005443573, | |
| "learning_rate": 5.2521008403361354e-06, | |
| "loss": 4.2662, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5655042412818096, | |
| "grad_norm": 0.30530408024787903, | |
| "learning_rate": 4.831932773109244e-06, | |
| "loss": 4.2261, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6032045240339302, | |
| "grad_norm": 0.2973043620586395, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 4.1622, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6409048067860509, | |
| "grad_norm": 0.3218187391757965, | |
| "learning_rate": 3.991596638655463e-06, | |
| "loss": 4.1368, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6786050895381716, | |
| "grad_norm": 0.30618816614151, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 4.2388, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7163053722902922, | |
| "grad_norm": 0.29443860054016113, | |
| "learning_rate": 3.1512605042016808e-06, | |
| "loss": 4.2325, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7540056550424128, | |
| "grad_norm": 0.3374607264995575, | |
| "learning_rate": 2.7310924369747897e-06, | |
| "loss": 4.1112, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7917059377945335, | |
| "grad_norm": 0.26396605372428894, | |
| "learning_rate": 2.3109243697478996e-06, | |
| "loss": 4.1212, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8294062205466541, | |
| "grad_norm": 0.27625221014022827, | |
| "learning_rate": 1.8907563025210085e-06, | |
| "loss": 4.0515, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8671065032987747, | |
| "grad_norm": 0.29995009303092957, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 4.1482, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9048067860508954, | |
| "grad_norm": 0.31163692474365234, | |
| "learning_rate": 1.050420168067227e-06, | |
| "loss": 4.0789, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.942507068803016, | |
| "grad_norm": 0.3115774989128113, | |
| "learning_rate": 6.302521008403362e-07, | |
| "loss": 4.1159, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9802073515551367, | |
| "grad_norm": 0.3227115869522095, | |
| "learning_rate": 2.100840336134454e-07, | |
| "loss": 4.1402, | |
| "step": 260 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 265, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5504880085143388e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |