| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.987755102040816, | |
| "eval_steps": 500, | |
| "global_step": 366, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.4708639085292816, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.5385, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.4191964268684387, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 0.4991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.40369561314582825, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 0.3058, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.6080173850059509, | |
| "learning_rate": 9.997948550797227e-05, | |
| "loss": 0.223, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.3516406714916229, | |
| "learning_rate": 9.961525153583327e-05, | |
| "loss": 0.1966, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.3611922264099121, | |
| "learning_rate": 9.879896064123961e-05, | |
| "loss": 0.1635, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.3673703372478485, | |
| "learning_rate": 9.753805025397779e-05, | |
| "loss": 0.1547, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.31258246302604675, | |
| "learning_rate": 9.584400884284545e-05, | |
| "loss": 0.141, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 0.40288954973220825, | |
| "learning_rate": 9.373227124134888e-05, | |
| "loss": 0.1343, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.36042073369026184, | |
| "learning_rate": 9.122207801708802e-05, | |
| "loss": 0.1552, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 0.33795708417892456, | |
| "learning_rate": 8.833630016614976e-05, | |
| "loss": 0.1341, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.2802504003047943, | |
| "learning_rate": 8.510123072976239e-05, | |
| "loss": 0.1361, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0612244897959184, | |
| "grad_norm": 0.3562999367713928, | |
| "learning_rate": 8.154634523184388e-05, | |
| "loss": 0.1554, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.3551533818244934, | |
| "learning_rate": 7.770403312015721e-05, | |
| "loss": 0.1222, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.3744591474533081, | |
| "learning_rate": 7.360930265797935e-05, | |
| "loss": 0.1268, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 0.3726373016834259, | |
| "learning_rate": 6.929946195508932e-05, | |
| "loss": 0.0923, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3877551020408163, | |
| "grad_norm": 0.45406657457351685, | |
| "learning_rate": 6.481377904428171e-05, | |
| "loss": 0.1236, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 0.26440876722335815, | |
| "learning_rate": 6.019312410053286e-05, | |
| "loss": 0.1059, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5510204081632653, | |
| "grad_norm": 0.3584797978401184, | |
| "learning_rate": 5.547959706265068e-05, | |
| "loss": 0.13, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 0.2686370611190796, | |
| "learning_rate": 5.0716144050239375e-05, | |
| "loss": 0.1132, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.29573601484298706, | |
| "learning_rate": 4.594616607090028e-05, | |
| "loss": 0.1093, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 0.33462539315223694, | |
| "learning_rate": 4.121312358283463e-05, | |
| "loss": 0.1014, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8775510204081631, | |
| "grad_norm": 0.40894749760627747, | |
| "learning_rate": 3.656014051577713e-05, | |
| "loss": 0.1038, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 0.30836549401283264, | |
| "learning_rate": 3.202961135812437e-05, | |
| "loss": 0.1088, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0408163265306123, | |
| "grad_norm": 0.3176974654197693, | |
| "learning_rate": 2.7662814890184818e-05, | |
| "loss": 0.1055, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.122448979591837, | |
| "grad_norm": 0.2630854845046997, | |
| "learning_rate": 2.3499538082923606e-05, | |
| "loss": 0.0942, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 0.3280630111694336, | |
| "learning_rate": 1.9577713588953795e-05, | |
| "loss": 0.0954, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.2787545621395111, | |
| "learning_rate": 1.5933074128684332e-05, | |
| "loss": 0.0855, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.36734693877551, | |
| "grad_norm": 0.3742433190345764, | |
| "learning_rate": 1.2598826920598772e-05, | |
| "loss": 0.1161, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": 0.2906797528266907, | |
| "learning_rate": 9.605351122011309e-06, | |
| "loss": 0.0914, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.5306122448979593, | |
| "grad_norm": 0.3414059579372406, | |
| "learning_rate": 6.979921036993042e-06, | |
| "loss": 0.0971, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "grad_norm": 0.2982410490512848, | |
| "learning_rate": 4.746457613389904e-06, | |
| "loss": 0.0855, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.693877551020408, | |
| "grad_norm": 0.3430004417896271, | |
| "learning_rate": 2.925310493105099e-06, | |
| "loss": 0.0928, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7755102040816326, | |
| "grad_norm": 0.4764673709869385, | |
| "learning_rate": 1.5330726014397668e-06, | |
| "loss": 0.1081, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.3845561742782593, | |
| "learning_rate": 5.824289648152126e-07, | |
| "loss": 0.0895, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 0.3539472818374634, | |
| "learning_rate": 8.204113433559201e-08, | |
| "loss": 0.0974, | |
| "step": 360 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 366, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9841219894640640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |