| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004, | |
| "grad_norm": 0.14456839859485626, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 0.12785384058952332, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012, | |
| "grad_norm": 0.13556812703609467, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 0.16702307760715485, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2516, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3053046464920044, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1036, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 0.22266729176044464, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3971, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.028, | |
| "grad_norm": 0.14757753908634186, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3272, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.1445876806974411, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3242, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.036, | |
| "grad_norm": 0.1639222800731659, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0874, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.30435118079185486, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9193, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.044, | |
| "grad_norm": 0.19899794459342957, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3188, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 0.171605184674263, | |
| "learning_rate": 0.0002, | |
| "loss": 2.285, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.052, | |
| "grad_norm": 0.18728512525558472, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2458, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 0.21194487810134888, | |
| "learning_rate": 0.0002, | |
| "loss": 2.038, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3907397985458374, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.2305271327495575, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2758, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.068, | |
| "grad_norm": 0.1841125786304474, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2169, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 0.18488088250160217, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1981, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.076, | |
| "grad_norm": 0.22125467658042908, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0181, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.36263903975486755, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7492, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.084, | |
| "grad_norm": 0.23995819687843323, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2287, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 0.18997274339199066, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2265, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.092, | |
| "grad_norm": 0.19529950618743896, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2107, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.23907797038555145, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9434, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.3128001093864441, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7463, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 0.22716236114501953, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2284, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.108, | |
| "grad_norm": 0.19475902616977692, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1706, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.19292621314525604, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1211, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.116, | |
| "grad_norm": 0.27429261803627014, | |
| "learning_rate": 0.0002, | |
| "loss": 1.916, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.35040974617004395, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6903, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.124, | |
| "grad_norm": 0.25687935948371887, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1812, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.20279887318611145, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2005, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.132, | |
| "grad_norm": 0.22153416275978088, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1195, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 0.2411063015460968, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8694, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3698059320449829, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6522, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 0.263630211353302, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1644, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.148, | |
| "grad_norm": 0.22328948974609375, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1753, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 0.21132981777191162, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1191, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.156, | |
| "grad_norm": 0.2776873707771301, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8539, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.34315550327301025, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6447, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.164, | |
| "grad_norm": 0.2831268906593323, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1451, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 0.2178158015012741, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1368, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.172, | |
| "grad_norm": 0.22629423439502716, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1039, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 0.2540661096572876, | |
| "learning_rate": 0.0002, | |
| "loss": 1.856, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3525744676589966, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6286, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 0.24233509600162506, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1296, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.188, | |
| "grad_norm": 0.20195922255516052, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1321, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.25681406259536743, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0255, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.196, | |
| "grad_norm": 0.2791021764278412, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8141, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3304845690727234, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6042, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1000, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7342773566308352e+16, | |
| "train_batch_size": 12, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |