| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3759, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07980845969672785, | |
| "grad_norm": 2.9029064178466797, | |
| "learning_rate": 4.8683160415003995e-05, | |
| "loss": 3.2032, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1596169193934557, | |
| "grad_norm": 2.4378926753997803, | |
| "learning_rate": 4.735301942005853e-05, | |
| "loss": 2.9781, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23942537909018355, | |
| "grad_norm": 2.5962343215942383, | |
| "learning_rate": 4.6022878425113066e-05, | |
| "loss": 2.9045, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3192338387869114, | |
| "grad_norm": 2.1558268070220947, | |
| "learning_rate": 4.4692737430167594e-05, | |
| "loss": 2.8645, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.39904229848363926, | |
| "grad_norm": 2.267333745956421, | |
| "learning_rate": 4.3362596435222136e-05, | |
| "loss": 2.8252, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4788507581803671, | |
| "grad_norm": 2.024164915084839, | |
| "learning_rate": 4.203245544027667e-05, | |
| "loss": 2.79, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5586592178770949, | |
| "grad_norm": 1.860116720199585, | |
| "learning_rate": 4.070231444533121e-05, | |
| "loss": 2.7855, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6384676775738228, | |
| "grad_norm": 2.0862903594970703, | |
| "learning_rate": 3.937217345038574e-05, | |
| "loss": 2.7215, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7182761372705507, | |
| "grad_norm": 2.151069402694702, | |
| "learning_rate": 3.804203245544028e-05, | |
| "loss": 2.7195, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7980845969672785, | |
| "grad_norm": 1.970441222190857, | |
| "learning_rate": 3.6711891460494814e-05, | |
| "loss": 2.706, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8778930566640064, | |
| "grad_norm": 1.7801231145858765, | |
| "learning_rate": 3.538175046554935e-05, | |
| "loss": 2.6971, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9577015163607342, | |
| "grad_norm": 1.7904406785964966, | |
| "learning_rate": 3.4051609470603885e-05, | |
| "loss": 2.6741, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.037509976057462, | |
| "grad_norm": 1.7989133596420288, | |
| "learning_rate": 3.272146847565842e-05, | |
| "loss": 2.6514, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.1173184357541899, | |
| "grad_norm": 1.7113661766052246, | |
| "learning_rate": 3.1391327480712955e-05, | |
| "loss": 2.597, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.1971268954509178, | |
| "grad_norm": 1.9461297988891602, | |
| "learning_rate": 3.0061186485767494e-05, | |
| "loss": 2.5942, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.2769353551476457, | |
| "grad_norm": 1.8421082496643066, | |
| "learning_rate": 2.873104549082203e-05, | |
| "loss": 2.5904, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.3567438148443736, | |
| "grad_norm": 1.7004835605621338, | |
| "learning_rate": 2.7400904495876562e-05, | |
| "loss": 2.5747, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.4365522745411012, | |
| "grad_norm": 1.8660473823547363, | |
| "learning_rate": 2.60707635009311e-05, | |
| "loss": 2.5633, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.5163607342378294, | |
| "grad_norm": 1.8421789407730103, | |
| "learning_rate": 2.4740622505985636e-05, | |
| "loss": 2.5749, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.596169193934557, | |
| "grad_norm": 1.8543329238891602, | |
| "learning_rate": 2.341048151104017e-05, | |
| "loss": 2.5855, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.675977653631285, | |
| "grad_norm": 2.2453484535217285, | |
| "learning_rate": 2.2080340516094707e-05, | |
| "loss": 2.5443, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.7557861133280128, | |
| "grad_norm": 1.8024177551269531, | |
| "learning_rate": 2.0750199521149242e-05, | |
| "loss": 2.563, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.8355945730247405, | |
| "grad_norm": 1.9053102731704712, | |
| "learning_rate": 1.942005852620378e-05, | |
| "loss": 2.5487, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.9154030327214686, | |
| "grad_norm": 1.6689891815185547, | |
| "learning_rate": 1.8089917531258313e-05, | |
| "loss": 2.5362, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.9952114924181963, | |
| "grad_norm": 1.7452094554901123, | |
| "learning_rate": 1.675977653631285e-05, | |
| "loss": 2.5411, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.075019952114924, | |
| "grad_norm": 1.710633635520935, | |
| "learning_rate": 1.5429635541367384e-05, | |
| "loss": 2.5067, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.154828411811652, | |
| "grad_norm": 1.9094699621200562, | |
| "learning_rate": 1.4099494546421921e-05, | |
| "loss": 2.5081, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.2346368715083798, | |
| "grad_norm": 1.9917291402816772, | |
| "learning_rate": 1.2769353551476457e-05, | |
| "loss": 2.4967, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.314445331205108, | |
| "grad_norm": 1.9159190654754639, | |
| "learning_rate": 1.1439212556530992e-05, | |
| "loss": 2.5066, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.3942537909018355, | |
| "grad_norm": 2.1151177883148193, | |
| "learning_rate": 1.010907156158553e-05, | |
| "loss": 2.5014, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.474062250598563, | |
| "grad_norm": 2.0249733924865723, | |
| "learning_rate": 8.778930566640065e-06, | |
| "loss": 2.4907, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.5538707102952913, | |
| "grad_norm": 1.8712220191955566, | |
| "learning_rate": 7.4487895716946e-06, | |
| "loss": 2.4914, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.633679169992019, | |
| "grad_norm": 1.951600432395935, | |
| "learning_rate": 6.118648576749136e-06, | |
| "loss": 2.492, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.713487629688747, | |
| "grad_norm": 1.969313621520996, | |
| "learning_rate": 4.788507581803672e-06, | |
| "loss": 2.4801, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.793296089385475, | |
| "grad_norm": 1.8563135862350464, | |
| "learning_rate": 3.458366586858207e-06, | |
| "loss": 2.4624, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.8731045490822025, | |
| "grad_norm": 1.7384971380233765, | |
| "learning_rate": 2.1282255919127428e-06, | |
| "loss": 2.4944, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.9529130087789306, | |
| "grad_norm": 1.8513154983520508, | |
| "learning_rate": 7.980845969672785e-07, | |
| "loss": 2.4769, | |
| "step": 3700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3759, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7185895497728e+16, | |
| "train_batch_size": 70, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |