| { | |
| "best_metric": 1.2866495847702026, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1350438892640108, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027008777852802163, | |
| "grad_norm": 0.3624476194381714, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027008777852802163, | |
| "eval_loss": 1.4606833457946777, | |
| "eval_runtime": 15.6141, | |
| "eval_samples_per_second": 39.964, | |
| "eval_steps_per_second": 9.991, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054017555705604325, | |
| "grad_norm": 0.3938450813293457, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3709, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008102633355840648, | |
| "grad_norm": 0.39943069219589233, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4067, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010803511141120865, | |
| "grad_norm": 0.40101104974746704, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4221, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01350438892640108, | |
| "grad_norm": 0.36832377314567566, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4441, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016205266711681297, | |
| "grad_norm": 0.41918250918388367, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4905, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018906144496961513, | |
| "grad_norm": 0.4318130612373352, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3951, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02160702228224173, | |
| "grad_norm": 0.524061381816864, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3791, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024307900067521943, | |
| "grad_norm": 0.5278139710426331, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3826, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02700877785280216, | |
| "grad_norm": 0.5666940808296204, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3379, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029709655638082377, | |
| "grad_norm": 0.5191312432289124, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.1892, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03241053342336259, | |
| "grad_norm": 0.430105596780777, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1462, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.035111411208642807, | |
| "grad_norm": 0.4412747621536255, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.2241, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03781228899392303, | |
| "grad_norm": 0.4131179451942444, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.2011, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04051316677920324, | |
| "grad_norm": 0.4340050518512726, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.1766, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04321404456448346, | |
| "grad_norm": 0.42998600006103516, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2414, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04591492234976367, | |
| "grad_norm": 0.42034226655960083, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.0788, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.048615800135043886, | |
| "grad_norm": 0.5337233543395996, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.1981, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05131667792032411, | |
| "grad_norm": 0.4583562910556793, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.2196, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05401755570560432, | |
| "grad_norm": 0.49332761764526367, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.1968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05671843349088454, | |
| "grad_norm": 0.48594799637794495, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.1309, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05941931127616475, | |
| "grad_norm": 0.5126538276672363, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1186, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.062120189061444966, | |
| "grad_norm": 0.47921475768089294, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.0795, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06482106684672519, | |
| "grad_norm": 0.4876593053340912, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.0949, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0675219446320054, | |
| "grad_norm": 0.536691427230835, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.0373, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07022282241728561, | |
| "grad_norm": 0.6566392779350281, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2434, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07292370020256583, | |
| "grad_norm": 0.5158787369728088, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.1554, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07562457798784605, | |
| "grad_norm": 0.5759814977645874, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.3289, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07832545577312626, | |
| "grad_norm": 0.5752044320106506, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.1889, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08102633355840648, | |
| "grad_norm": 0.6152178645133972, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1266, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0837272113436867, | |
| "grad_norm": 0.6457420587539673, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.1839, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08642808912896692, | |
| "grad_norm": 0.6329084038734436, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.234, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08912896691424713, | |
| "grad_norm": 0.6863877773284912, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2342, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09182984469952735, | |
| "grad_norm": 0.6431719660758972, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.177, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09453072248480757, | |
| "grad_norm": 0.6808779835700989, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.3163, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09723160027008777, | |
| "grad_norm": 0.7064206600189209, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.3071, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.099932478055368, | |
| "grad_norm": 0.7828763723373413, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.3091, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10263335584064821, | |
| "grad_norm": 0.8526866436004639, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.2666, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10533423362592843, | |
| "grad_norm": 0.7964354157447815, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.4333, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10803511141120864, | |
| "grad_norm": 0.8185365796089172, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.3689, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11073598919648886, | |
| "grad_norm": 0.8150967955589294, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.3536, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11343686698176908, | |
| "grad_norm": 0.8503111004829407, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.3862, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11613774476704929, | |
| "grad_norm": 0.8694619536399841, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.3512, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1188386225523295, | |
| "grad_norm": 1.0029643774032593, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.2742, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12153950033760973, | |
| "grad_norm": 1.017909049987793, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.4303, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12424037812288993, | |
| "grad_norm": 1.519902229309082, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.4151, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12694125590817015, | |
| "grad_norm": 1.4137510061264038, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.4488, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12964213369345037, | |
| "grad_norm": 1.4305354356765747, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.3568, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1323430114787306, | |
| "grad_norm": 1.5225553512573242, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.2391, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1350438892640108, | |
| "grad_norm": 2.4049932956695557, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.4481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1350438892640108, | |
| "eval_loss": 1.2866495847702026, | |
| "eval_runtime": 15.5441, | |
| "eval_samples_per_second": 40.144, | |
| "eval_steps_per_second": 10.036, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.435563454365696e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |