| { | |
| "best_metric": 8.2882661819458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05884083553986467, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011768167107972932, | |
| "grad_norm": 2.250781774520874, | |
| "learning_rate": 1e-05, | |
| "loss": 10.5718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011768167107972932, | |
| "eval_loss": 10.56332015991211, | |
| "eval_runtime": 7.3108, | |
| "eval_samples_per_second": 195.876, | |
| "eval_steps_per_second": 48.969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023536334215945864, | |
| "grad_norm": 2.218484401702881, | |
| "learning_rate": 2e-05, | |
| "loss": 10.5492, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00353045013239188, | |
| "grad_norm": 2.1045329570770264, | |
| "learning_rate": 3e-05, | |
| "loss": 10.5497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004707266843189173, | |
| "grad_norm": 2.0767016410827637, | |
| "learning_rate": 4e-05, | |
| "loss": 10.5244, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005884083553986467, | |
| "grad_norm": 2.1876964569091797, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4896, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00706090026478376, | |
| "grad_norm": 2.141082763671875, | |
| "learning_rate": 6e-05, | |
| "loss": 10.4088, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008237716975581053, | |
| "grad_norm": 2.3473763465881348, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3121, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009414533686378346, | |
| "grad_norm": 2.2916038036346436, | |
| "learning_rate": 8e-05, | |
| "loss": 10.2014, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01059135039717564, | |
| "grad_norm": 2.4516515731811523, | |
| "learning_rate": 9e-05, | |
| "loss": 10.0419, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011768167107972934, | |
| "grad_norm": 2.3366496562957764, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": 2.252690076828003, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 9.6978, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01412180052956752, | |
| "grad_norm": 1.9645477533340454, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 9.5021, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015298617240364814, | |
| "grad_norm": 1.5823044776916504, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 9.4268, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016475433951162105, | |
| "grad_norm": 1.3489216566085815, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 9.2688, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0176522506619594, | |
| "grad_norm": 1.923361897468567, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 9.261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01882906737275669, | |
| "grad_norm": 2.564469575881958, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 9.214, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020005884083553988, | |
| "grad_norm": 2.759812831878662, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 9.2043, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02118270079435128, | |
| "grad_norm": 2.0286946296691895, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 9.1102, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022359517505148575, | |
| "grad_norm": 1.2676193714141846, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 9.0072, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023536334215945868, | |
| "grad_norm": 1.081269383430481, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 8.9628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02471315092674316, | |
| "grad_norm": 1.2348231077194214, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 8.9455, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025889967637540454, | |
| "grad_norm": 1.3263475894927979, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 8.9155, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027066784348337748, | |
| "grad_norm": 1.2577069997787476, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 8.862, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02824360105913504, | |
| "grad_norm": 1.1871044635772705, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 8.8077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029420417769932334, | |
| "grad_norm": 0.9002571105957031, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 8.7518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030597234480729627, | |
| "grad_norm": 0.7622474431991577, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 8.7224, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03177405119152692, | |
| "grad_norm": 0.8151483535766602, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 8.6442, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03295086790232421, | |
| "grad_norm": 0.8028168082237244, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 8.7066, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0341276846131215, | |
| "grad_norm": 0.711188554763794, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 8.6383, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "grad_norm": 0.5626480579376221, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 8.5483, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03648131803471609, | |
| "grad_norm": 0.6713583469390869, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 8.5006, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03765813474551338, | |
| "grad_norm": 0.740278959274292, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 8.5123, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "grad_norm": 0.6808012127876282, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 8.5074, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.040011768167107976, | |
| "grad_norm": 0.6216472387313843, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 8.424, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04118858487790527, | |
| "grad_norm": 0.4640122354030609, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 8.4627, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04236540158870256, | |
| "grad_norm": 0.4743383228778839, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 8.4582, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.043542218299499856, | |
| "grad_norm": 0.5901423096656799, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 8.3762, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04471903501029715, | |
| "grad_norm": 0.42769405245780945, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 8.42, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04589585172109444, | |
| "grad_norm": 0.4135448932647705, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 8.3939, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.047072668431891736, | |
| "grad_norm": 0.42513877153396606, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 8.4425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04824948514268903, | |
| "grad_norm": 0.5020366907119751, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 8.4066, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04942630185348632, | |
| "grad_norm": 0.4465470314025879, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 8.3729, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.050603118564283615, | |
| "grad_norm": 0.4423791468143463, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 8.3358, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05177993527508091, | |
| "grad_norm": 0.48596006631851196, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 8.2235, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0529567519858782, | |
| "grad_norm": 0.46758389472961426, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 8.3427, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.054133568696675495, | |
| "grad_norm": 0.4585881531238556, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 8.2957, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05531038540747279, | |
| "grad_norm": 0.5031861662864685, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 8.2837, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05648720211827008, | |
| "grad_norm": 0.44892722368240356, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 8.3556, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.057664018829067375, | |
| "grad_norm": 0.574077844619751, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 8.384, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "grad_norm": 0.6736589074134827, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 8.2858, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "eval_loss": 8.2882661819458, | |
| "eval_runtime": 7.2085, | |
| "eval_samples_per_second": 198.655, | |
| "eval_steps_per_second": 49.664, | |
| "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": 2276979395002368.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |