| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.911147011308563, | |
| "eval_steps": 500, | |
| "global_step": 95, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.1306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 4.2147, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5581, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001999417022366174, | |
| "loss": 3.3437, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019976687691905393, | |
| "loss": 2.2555, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019947572788580947, | |
| "loss": 2.3575, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019906859460363307, | |
| "loss": 2.0886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019854595177171968, | |
| "loss": 2.0926, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019790840876823232, | |
| "loss": 1.774, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00019715670893979414, | |
| "loss": 1.7544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00019629172873477995, | |
| "loss": 2.0039, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00019531447668141608, | |
| "loss": 1.6882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00019422609221188207, | |
| "loss": 1.7233, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001930278443337833, | |
| "loss": 1.6797, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00019172113015054532, | |
| "loss": 1.6446, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00019030747323245327, | |
| "loss": 1.8725, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001887885218402375, | |
| "loss": 1.8063, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00018716604700327514, | |
| "loss": 1.8655, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00018544194045464886, | |
| "loss": 1.7658, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001836182124254711, | |
| "loss": 1.3927, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001816969893010442, | |
| "loss": 1.4465, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00017968051114159047, | |
| "loss": 1.2664, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.000177571129070442, | |
| "loss": 1.5249, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017537130253273613, | |
| "loss": 1.2534, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017308359642781242, | |
| "loss": 1.2423, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.087, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016825531432186543, | |
| "loss": 1.3184, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00016572036788179727, | |
| "loss": 1.211, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00016310879443260528, | |
| "loss": 1.2384, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00016042363895210946, | |
| "loss": 1.2669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00015766803221148673, | |
| "loss": 1.1047, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00015484518712493187, | |
| "loss": 0.9884, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00015195839500354335, | |
| "loss": 1.1934, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00014901102171780174, | |
| "loss": 1.1506, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00014600650377311522, | |
| "loss": 1.1682, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0001429483443030082, | |
| "loss": 1.3578, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00013984010898462416, | |
| "loss": 1.1693, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00013668542188130566, | |
| "loss": 1.0341, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00013348796121709862, | |
| "loss": 1.1559, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001302514550881076, | |
| "loss": 0.7115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00012697967711570242, | |
| "loss": 0.694, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00012367644204664468, | |
| "loss": 0.5978, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001203456013052634, | |
| "loss": 0.6932, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00011699103850286669, | |
| "loss": 0.6343, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00011361666490962468, | |
| "loss": 0.5644, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00011022641489420342, | |
| "loss": 0.5203, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0001068242413364671, | |
| "loss": 0.7057, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00010341411101859679, | |
| "loss": 0.4707, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6605, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.658588898140322e-05, | |
| "loss": 0.6644, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.317575866353292e-05, | |
| "loss": 0.6467, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 8.977358510579657e-05, | |
| "loss": 0.6245, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 8.638333509037536e-05, | |
| "loss": 0.6898, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.300896149713334e-05, | |
| "loss": 0.5144, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.965439869473664e-05, | |
| "loss": 0.7721, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.632355795335533e-05, | |
| "loss": 0.721, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.302032288429756e-05, | |
| "loss": 0.731, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.974854491189243e-05, | |
| "loss": 0.652, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 6.651203878290139e-05, | |
| "loss": 0.4655, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 6.331457811869437e-05, | |
| "loss": 0.4752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 6.015989101537586e-05, | |
| "loss": 0.4497, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 5.7051655696991826e-05, | |
| "loss": 0.2536, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 5.399349622688479e-05, | |
| "loss": 0.3301, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 5.0988978282198305e-05, | |
| "loss": 0.3794, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.804160499645667e-05, | |
| "loss": 0.346, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 4.515481287506811e-05, | |
| "loss": 0.3531, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 4.2331967788513295e-05, | |
| "loss": 0.3091, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.9576361047890554e-05, | |
| "loss": 0.2856, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.689120556739475e-05, | |
| "loss": 0.2759, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.427963211820274e-05, | |
| "loss": 0.3152, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.174468567813461e-05, | |
| "loss": 0.2649, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.2846, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2.691640357218759e-05, | |
| "loss": 0.2286, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 2.4628697467263918e-05, | |
| "loss": 0.2379, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 2.242887092955801e-05, | |
| "loss": 0.278, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 2.0319488858409553e-05, | |
| "loss": 0.3274, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.8303010698955804e-05, | |
| "loss": 0.2248, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.638178757452894e-05, | |
| "loss": 0.3272, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.4558059545351143e-05, | |
| "loss": 0.1396, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1.2833952996724863e-05, | |
| "loss": 0.1572, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.1211478159762478e-05, | |
| "loss": 0.1203, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 9.692526767546729e-06, | |
| "loss": 0.1403, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 8.278869849454718e-06, | |
| "loss": 0.1242, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.972155666216684e-06, | |
| "loss": 0.1309, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 5.77390778811796e-06, | |
| "loss": 0.135, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.685523318583918e-06, | |
| "loss": 0.1654, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.7082712652200867e-06, | |
| "loss": 0.1342, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.843291060205855e-06, | |
| "loss": 0.2433, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.091591231767709e-06, | |
| "loss": 0.1835, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 1.4540482282803137e-06, | |
| "loss": 0.1553, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 9.314053963669245e-07, | |
| "loss": 0.1333, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 5.24272114190516e-07, | |
| "loss": 0.132, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.3312308094607382e-07, | |
| "loss": 0.1226, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.8297763382597626e-08, | |
| "loss": 0.147, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.1178, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "step": 95, | |
| "total_flos": 5041018556416.0, | |
| "train_loss": 0.9510736925037284, | |
| "train_runtime": 3904.6534, | |
| "train_samples_per_second": 0.793, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50000, | |
| "total_flos": 5041018556416.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |