| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 454, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022050716648291068, | |
| "grad_norm": 74.42448425292969, | |
| "learning_rate": 9.782608695652175e-07, | |
| "loss": 4.3982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044101433296582136, | |
| "grad_norm": 18.701778411865234, | |
| "learning_rate": 2.065217391304348e-06, | |
| "loss": 2.2692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06615214994487321, | |
| "grad_norm": 3.115069627761841, | |
| "learning_rate": 3.152173913043479e-06, | |
| "loss": 0.2818, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08820286659316427, | |
| "grad_norm": 2.7221839427948, | |
| "learning_rate": 4.239130434782609e-06, | |
| "loss": 0.1031, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11025358324145534, | |
| "grad_norm": 2.3491132259368896, | |
| "learning_rate": 4.999333020279094e-06, | |
| "loss": 0.0683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13230429988974643, | |
| "grad_norm": 1.5490330457687378, | |
| "learning_rate": 4.987485500883267e-06, | |
| "loss": 0.0425, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1543550165380375, | |
| "grad_norm": 2.8108344078063965, | |
| "learning_rate": 4.960897034310215e-06, | |
| "loss": 0.0435, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17640573318632854, | |
| "grad_norm": 2.1171176433563232, | |
| "learning_rate": 4.919725184968307e-06, | |
| "loss": 0.0276, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19845644983461963, | |
| "grad_norm": 1.415331244468689, | |
| "learning_rate": 4.864213939025955e-06, | |
| "loss": 0.0325, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2205071664829107, | |
| "grad_norm": 1.9612994194030762, | |
| "learning_rate": 4.794692258538973e-06, | |
| "loss": 0.0313, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24255788313120177, | |
| "grad_norm": 0.8341349959373474, | |
| "learning_rate": 4.711572132007139e-06, | |
| "loss": 0.0301, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26460859977949286, | |
| "grad_norm": 1.501145839691162, | |
| "learning_rate": 4.615346132912444e-06, | |
| "loss": 0.0262, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2866593164277839, | |
| "grad_norm": 0.9406419396400452, | |
| "learning_rate": 4.506584500707229e-06, | |
| "loss": 0.0301, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.308710033076075, | |
| "grad_norm": 0.7606803774833679, | |
| "learning_rate": 4.385931761550411e-06, | |
| "loss": 0.0282, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33076074972436603, | |
| "grad_norm": 0.7711995840072632, | |
| "learning_rate": 4.254102908817454e-06, | |
| "loss": 0.0232, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3528114663726571, | |
| "grad_norm": 1.4802823066711426, | |
| "learning_rate": 4.111879166018561e-06, | |
| "loss": 0.0185, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3748621830209482, | |
| "grad_norm": 0.3809826076030731, | |
| "learning_rate": 3.960103357234192e-06, | |
| "loss": 0.0185, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.39691289966923926, | |
| "grad_norm": 0.5903116464614868, | |
| "learning_rate": 3.799674912502946e-06, | |
| "loss": 0.0265, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4189636163175303, | |
| "grad_norm": 1.0342077016830444, | |
| "learning_rate": 3.63154453776006e-06, | |
| "loss": 0.0164, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4410143329658214, | |
| "grad_norm": 1.5857564210891724, | |
| "learning_rate": 3.4567085809127247e-06, | |
| "loss": 0.0224, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.46306504961411243, | |
| "grad_norm": 0.3297180235385895, | |
| "learning_rate": 3.2762031274390876e-06, | |
| "loss": 0.0161, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.48511576626240355, | |
| "grad_norm": 0.37393227219581604, | |
| "learning_rate": 3.091097860500683e-06, | |
| "loss": 0.0172, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5071664829106945, | |
| "grad_norm": 0.4254159927368164, | |
| "learning_rate": 2.9024897219535326e-06, | |
| "loss": 0.0153, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5292171995589857, | |
| "grad_norm": 0.67938631772995, | |
| "learning_rate": 2.7114964118230352e-06, | |
| "loss": 0.0161, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5512679162072768, | |
| "grad_norm": 0.30472537875175476, | |
| "learning_rate": 2.519249764765047e-06, | |
| "loss": 0.0142, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5733186328555678, | |
| "grad_norm": 0.802527904510498, | |
| "learning_rate": 2.3268890427645213e-06, | |
| "loss": 0.0121, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5953693495038589, | |
| "grad_norm": 0.73816978931427, | |
| "learning_rate": 2.1355541838194797e-06, | |
| "loss": 0.0126, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.61742006615215, | |
| "grad_norm": 0.8889350295066833, | |
| "learning_rate": 1.946379046618894e-06, | |
| "loss": 0.0106, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.639470782800441, | |
| "grad_norm": 0.47817710041999817, | |
| "learning_rate": 1.7604846912468243e-06, | |
| "loss": 0.0104, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6615214994487321, | |
| "grad_norm": 0.7351515293121338, | |
| "learning_rate": 1.5789727357316426e-06, | |
| "loss": 0.0139, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6835722160970231, | |
| "grad_norm": 1.1249067783355713, | |
| "learning_rate": 1.40291882780972e-06, | |
| "loss": 0.009, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7056229327453142, | |
| "grad_norm": 0.6196808218955994, | |
| "learning_rate": 1.233366270590202e-06, | |
| "loss": 0.0086, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7276736493936052, | |
| "grad_norm": 0.353678435087204, | |
| "learning_rate": 1.0713198398954382e-06, | |
| "loss": 0.0104, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7497243660418964, | |
| "grad_norm": 0.240644171833992, | |
| "learning_rate": 9.177398299157989e-07, | |
| "loss": 0.009, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7717750826901875, | |
| "grad_norm": 0.38582557439804077, | |
| "learning_rate": 7.735363624645712e-07, | |
| "loss": 0.0095, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7938257993384785, | |
| "grad_norm": 0.3422253429889679, | |
| "learning_rate": 6.395639935565412e-07, | |
| "loss": 0.0142, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8158765159867696, | |
| "grad_norm": 0.5278216600418091, | |
| "learning_rate": 5.166166492719124e-07, | |
| "loss": 0.0108, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8379272326350606, | |
| "grad_norm": 0.8732016086578369, | |
| "learning_rate": 4.0542292091585447e-07, | |
| "loss": 0.0103, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8599779492833517, | |
| "grad_norm": 1.2882901430130005, | |
| "learning_rate": 3.066417473547667e-07, | |
| "loss": 0.0092, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8820286659316428, | |
| "grad_norm": 0.3473157286643982, | |
| "learning_rate": 2.2085851011591831e-07, | |
| "loss": 0.0078, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9040793825799338, | |
| "grad_norm": 0.7660663723945618, | |
| "learning_rate": 1.4858156439108097e-07, | |
| "loss": 0.01, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9261300992282249, | |
| "grad_norm": 0.18714870512485504, | |
| "learning_rate": 9.023922650156863e-08, | |
| "loss": 0.0093, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.948180815876516, | |
| "grad_norm": 0.3012760281562805, | |
| "learning_rate": 4.6177235677105634e-08, | |
| "loss": 0.0075, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9702315325248071, | |
| "grad_norm": 0.23213928937911987, | |
| "learning_rate": 1.6656705190125078e-08, | |
| "loss": 0.0103, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9922822491730982, | |
| "grad_norm": 0.67380291223526, | |
| "learning_rate": 1.852574987171174e-09, | |
| "loss": 0.0061, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 454, | |
| "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": 2.2520258148643635e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |