| { | |
| "best_metric": 2.0682475566864014, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2840909090909091, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011363636363636364, | |
| "grad_norm": 2.7021124362945557, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "eval_loss": 4.739462375640869, | |
| "eval_runtime": 16.6811, | |
| "eval_samples_per_second": 35.549, | |
| "eval_steps_per_second": 4.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 3.2683639526367188, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5775, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03409090909090909, | |
| "grad_norm": 3.1707563400268555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 3.4560506343841553, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056818181818181816, | |
| "grad_norm": 3.3004863262176514, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3656, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 2.737147092819214, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07954545454545454, | |
| "grad_norm": 3.0929532051086426, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9262, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 2.786226987838745, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0848, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10227272727272728, | |
| "grad_norm": 2.3751325607299805, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 1.8524545431137085, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5988, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.6459931135177612, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5756, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 1.4236981868743896, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5151, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14772727272727273, | |
| "grad_norm": 0.9423320889472961, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1590909090909091, | |
| "grad_norm": 1.0780678987503052, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7815, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17045454545454544, | |
| "grad_norm": 1.0836559534072876, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0837, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.9846199750900269, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19318181818181818, | |
| "grad_norm": 1.0413646697998047, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8915, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20454545454545456, | |
| "grad_norm": 1.038799524307251, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9604, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2159090909090909, | |
| "grad_norm": 1.0064616203308105, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1818, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 0.9710341095924377, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23863636363636365, | |
| "grad_norm": 0.9461048245429993, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0471, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.106583595275879, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26136363636363635, | |
| "grad_norm": 1.0309126377105713, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.1852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 1.174065113067627, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3848, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "grad_norm": 1.564176082611084, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4425, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "eval_loss": 2.0682475566864014, | |
| "eval_runtime": 16.7837, | |
| "eval_samples_per_second": 35.332, | |
| "eval_steps_per_second": 4.469, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.16708196040704e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |