| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.461607677094324, | |
| "eval_steps": 500, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001461607677094324, | |
| "grad_norm": 6.625, | |
| "learning_rate": 4.8721071863581e-08, | |
| "loss": 1.8813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05846430708377296, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 1.94884287454324e-05, | |
| "loss": 1.2825, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11692861416754592, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 3.89768574908648e-05, | |
| "loss": 1.1339, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.17539292125131886, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 5.84652862362972e-05, | |
| "loss": 1.0996, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23385722833509184, | |
| "grad_norm": 0.2177734375, | |
| "learning_rate": 7.79537149817296e-05, | |
| "loss": 1.0737, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.2923215354188648, | |
| "grad_norm": 0.2294921875, | |
| "learning_rate": 9.7442143727162e-05, | |
| "loss": 1.054, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3507858425026377, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 0.0001169305724725944, | |
| "loss": 1.0348, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.4092501495864107, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 0.0001364190012180268, | |
| "loss": 1.0185, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.4677144566701837, | |
| "grad_norm": 0.2275390625, | |
| "learning_rate": 0.0001559074299634592, | |
| "loss": 1.0078, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5261787637539567, | |
| "grad_norm": 0.2314453125, | |
| "learning_rate": 0.0001753958587088916, | |
| "loss": 0.9962, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5846430708377296, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 0.000194884287454324, | |
| "loss": 0.9884, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6431073779215025, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 0.00019996853166916095, | |
| "loss": 0.9802, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7015716850052754, | |
| "grad_norm": 0.232421875, | |
| "learning_rate": 0.00019982537933878626, | |
| "loss": 0.9697, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.7600359920890485, | |
| "grad_norm": 0.236328125, | |
| "learning_rate": 0.0001995667218123705, | |
| "loss": 0.9594, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.8185002991728214, | |
| "grad_norm": 0.244140625, | |
| "learning_rate": 0.00019919285837541084, | |
| "loss": 0.9493, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.8769646062565943, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.00019870422161498958, | |
| "loss": 0.9399, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9354289133403674, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.00019810137691923923, | |
| "loss": 0.9322, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.9938932204241403, | |
| "grad_norm": 0.24609375, | |
| "learning_rate": 0.00019738502182314765, | |
| "loss": 0.9238, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.0523575275079133, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 0.00019655598520145953, | |
| "loss": 0.8823, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.1108218345916863, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 0.00019561522630960813, | |
| "loss": 0.8803, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.1692861416754592, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 0.00019456383367378742, | |
| "loss": 0.8727, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.2277504487592321, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 0.00019340302383144832, | |
| "loss": 0.8737, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.286214755843005, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 0.00019213413992367673, | |
| "loss": 0.8672, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.344679062926778, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 0.00019075865014108194, | |
| "loss": 0.8652, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.4031433700105511, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 0.00018927814602499394, | |
| "loss": 0.8605, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.461607677094324, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 0.00018769434062593454, | |
| "loss": 0.8569, | |
| "step": 10000 | |
| } | |
| ], | |
| "logging_steps": 400, | |
| "max_steps": 41046, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 5000, | |
| "total_flos": 2.2714013468356038e+20, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |