| { | |
| "best_metric": 0.9555453658103943, | |
| "best_model_checkpoint": "./ec-model/checkpoint-500", | |
| "epoch": 0.10704345964461572, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.3479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.997500535599515e-05, | |
| "loss": 2.1638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9939298721702496e-05, | |
| "loss": 1.7877, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.990716275083911e-05, | |
| "loss": 1.5925, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.987145611654645e-05, | |
| "loss": 1.6327, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9835749482253806e-05, | |
| "loss": 1.4538, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.980004284796115e-05, | |
| "loss": 1.523, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.97643362136685e-05, | |
| "loss": 1.4908, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.972862957937585e-05, | |
| "loss": 1.4713, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.96929229450832e-05, | |
| "loss": 1.4672, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.965721631079055e-05, | |
| "loss": 1.2186, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.96215096764979e-05, | |
| "loss": 1.2957, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.958580304220524e-05, | |
| "loss": 1.2997, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9550096407912596e-05, | |
| "loss": 1.4143, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.951438977361994e-05, | |
| "loss": 1.3641, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.947868313932729e-05, | |
| "loss": 1.2587, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.944297650503464e-05, | |
| "loss": 1.2986, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.940726987074199e-05, | |
| "loss": 1.2285, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9371563236449334e-05, | |
| "loss": 1.2279, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.933585660215668e-05, | |
| "loss": 1.2148, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.930014996786403e-05, | |
| "loss": 1.149, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.926444333357138e-05, | |
| "loss": 1.1807, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9228736699278726e-05, | |
| "loss": 1.2904, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.919303006498608e-05, | |
| "loss": 1.2082, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9157323430693425e-05, | |
| "loss": 1.1615, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.912161679640077e-05, | |
| "loss": 1.2131, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9085910162108124e-05, | |
| "loss": 1.1906, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.905020352781547e-05, | |
| "loss": 1.2294, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9014496893522824e-05, | |
| "loss": 1.1824, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.897879025923017e-05, | |
| "loss": 1.1318, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8943083624937516e-05, | |
| "loss": 1.1093, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.890737699064486e-05, | |
| "loss": 1.204, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.887167035635221e-05, | |
| "loss": 1.1846, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.883596372205956e-05, | |
| "loss": 1.2242, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.880025708776691e-05, | |
| "loss": 1.1337, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8764550453474254e-05, | |
| "loss": 1.1435, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.872884381918161e-05, | |
| "loss": 1.242, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.869313718488895e-05, | |
| "loss": 1.1702, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8657430550596306e-05, | |
| "loss": 1.1043, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.862172391630365e-05, | |
| "loss": 1.1109, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8586017282011e-05, | |
| "loss": 1.1437, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.855031064771835e-05, | |
| "loss": 0.9969, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.851817467685496e-05, | |
| "loss": 1.2689, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.848246804256231e-05, | |
| "loss": 1.1224, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8446761408269655e-05, | |
| "loss": 1.1185, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8411054773977e-05, | |
| "loss": 1.1684, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8375348139684355e-05, | |
| "loss": 1.163, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8343212168820965e-05, | |
| "loss": 1.1046, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.830750553452832e-05, | |
| "loss": 1.0975, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8271798900235665e-05, | |
| "loss": 0.9991, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.9555453658103943, | |
| "eval_runtime": 12.0489, | |
| "eval_samples_per_second": 775.259, | |
| "eval_steps_per_second": 48.469, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 14013, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 275019724062720.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |