| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.34375, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.996988640512931e-05, | |
| "loss": 0.7489, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.987961816680492e-05, | |
| "loss": 0.5822, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.972941274911953e-05, | |
| "loss": 0.5713, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 0.5457, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.9250781329863606e-05, | |
| "loss": 0.5473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.892350839330522e-05, | |
| "loss": 0.5339, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.853860162957552e-05, | |
| "loss": 0.5368, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.5598, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.759973232808609e-05, | |
| "loss": 0.517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.7048031608708876e-05, | |
| "loss": 0.5279, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.6443215250006806e-05, | |
| "loss": 0.5079, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 0.5045, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.508018828701612e-05, | |
| "loss": 0.5158, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.4325261334068426e-05, | |
| "loss": 0.5064, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.352377813387398e-05, | |
| "loss": 0.5072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.5087, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.178897387117546e-05, | |
| "loss": 0.3132, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.085983210409114e-05, | |
| "loss": 0.2972, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.9892482612310836e-05, | |
| "loss": 0.2747, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 0.2399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.785256860483054e-05, | |
| "loss": 0.2741, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.678491842064995e-05, | |
| "loss": 0.2622, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.624028324136517e-05, | |
| "loss": 0.258, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.513103285012475e-05, | |
| "loss": 0.2574, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.399737591337471e-05, | |
| "loss": 0.2551, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.284204350997229e-05, | |
| "loss": 0.265, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.1667818936872465e-05, | |
| "loss": 0.2641, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.0477531003921745e-05, | |
| "loss": 0.2588, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.9274047219007534e-05, | |
| "loss": 0.2366, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.8060266879980408e-05, | |
| "loss": 0.2581, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.683911408999169e-05, | |
| "loss": 0.2658, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.561353071307281e-05, | |
| "loss": 0.2474, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.4386469286927196e-05, | |
| "loss": 0.1347, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.3160885910008318e-05, | |
| "loss": 0.135, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.1939733120019598e-05, | |
| "loss": 0.1242, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.0725952780992468e-05, | |
| "loss": 0.1286, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.9522468996078258e-05, | |
| "loss": 0.1252, | |
| "step": 74 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 128, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "total_flos": 8.20785473084457e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |