| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 309, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032362459546925564, | |
| "grad_norm": 3.9236679077148438, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 0.598, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": 1.8179429769515991, | |
| "learning_rate": 1.2258064516129034e-05, | |
| "loss": 0.2223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0970873786407767, | |
| "grad_norm": 1.024856686592102, | |
| "learning_rate": 1.870967741935484e-05, | |
| "loss": 0.1167, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.9101268649101257, | |
| "learning_rate": 1.9959162014075553e-05, | |
| "loss": 0.0923, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16181229773462782, | |
| "grad_norm": 0.5613371729850769, | |
| "learning_rate": 1.9793829188147406e-05, | |
| "loss": 0.078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1941747572815534, | |
| "grad_norm": 0.9140991568565369, | |
| "learning_rate": 1.9503556665478066e-05, | |
| "loss": 0.0795, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22653721682847897, | |
| "grad_norm": 0.5968174338340759, | |
| "learning_rate": 1.9092047447238775e-05, | |
| "loss": 0.0635, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.4374071955680847, | |
| "learning_rate": 1.856455114887056e-05, | |
| "loss": 0.0583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2912621359223301, | |
| "grad_norm": 0.4676224887371063, | |
| "learning_rate": 1.792779703083777e-05, | |
| "loss": 0.0662, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32362459546925565, | |
| "grad_norm": 0.5119790434837341, | |
| "learning_rate": 1.7189908153577473e-05, | |
| "loss": 0.0589, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3559870550161812, | |
| "grad_norm": 0.543942391872406, | |
| "learning_rate": 1.636029775176862e-05, | |
| "loss": 0.0586, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.4500238001346588, | |
| "learning_rate": 1.544954914987238e-05, | |
| "loss": 0.0568, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.42071197411003236, | |
| "grad_norm": 0.3425617516040802, | |
| "learning_rate": 1.4469280750858854e-05, | |
| "loss": 0.0524, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.45307443365695793, | |
| "grad_norm": 0.3619914650917053, | |
| "learning_rate": 1.3431997820456592e-05, | |
| "loss": 0.0486, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4854368932038835, | |
| "grad_norm": 1.788984775543213, | |
| "learning_rate": 1.2350932957710322e-05, | |
| "loss": 0.0472, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.44366371631622314, | |
| "learning_rate": 1.1239877286961123e-05, | |
| "loss": 0.0467, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5501618122977346, | |
| "grad_norm": 0.378680557012558, | |
| "learning_rate": 1.01130045247298e-05, | |
| "loss": 0.0503, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5825242718446602, | |
| "grad_norm": 0.48776954412460327, | |
| "learning_rate": 8.98469016587892e-06, | |
| "loss": 0.0441, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6148867313915858, | |
| "grad_norm": 0.37561851739883423, | |
| "learning_rate": 7.869328095692313e-06, | |
| "loss": 0.0431, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "grad_norm": 0.35846513509750366, | |
| "learning_rate": 6.781146967348283e-06, | |
| "loss": 0.0433, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6796116504854369, | |
| "grad_norm": 0.34934285283088684, | |
| "learning_rate": 5.7340286872557515e-06, | |
| "loss": 0.0367, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7119741100323624, | |
| "grad_norm": 0.3203984498977661, | |
| "learning_rate": 4.7413313238324556e-06, | |
| "loss": 0.0425, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7443365695792881, | |
| "grad_norm": 0.399088591337204, | |
| "learning_rate": 3.815718698874672e-06, | |
| "loss": 0.0424, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 0.3292689621448517, | |
| "learning_rate": 2.9689988354181742e-06, | |
| "loss": 0.0383, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8090614886731392, | |
| "grad_norm": 0.2965834140777588, | |
| "learning_rate": 2.211973323008041e-06, | |
| "loss": 0.0423, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8414239482200647, | |
| "grad_norm": 0.4333046078681946, | |
| "learning_rate": 1.5542995220217961e-06, | |
| "loss": 0.0417, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8737864077669902, | |
| "grad_norm": 0.36212387681007385, | |
| "learning_rate": 1.0043673649027519e-06, | |
| "loss": 0.0381, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9061488673139159, | |
| "grad_norm": 0.2634587585926056, | |
| "learning_rate": 5.691923259479093e-07, | |
| "loss": 0.0379, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9385113268608414, | |
| "grad_norm": 0.27783694863319397, | |
| "learning_rate": 2.5432592503288e-07, | |
| "loss": 0.0384, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.970873786407767, | |
| "grad_norm": 0.33753329515457153, | |
| "learning_rate": 6.378490697611761e-08, | |
| "loss": 0.0407, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 309, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.151751154761728e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |