| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 171, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03549639489739324, | |
| "grad_norm": 127.17037963867188, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 3.1202, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07099278979478647, | |
| "grad_norm": 127.35641479492188, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 3.1169, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1064891846921797, | |
| "grad_norm": 94.25624084472656, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 2.8233, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14198557958957295, | |
| "grad_norm": 17.775108337402344, | |
| "learning_rate": 3.88888888888889e-06, | |
| "loss": 1.8356, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.17748197448696618, | |
| "grad_norm": 10.735865592956543, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5481, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2129783693843594, | |
| "grad_norm": 7.582458972930908, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 1.2527, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24847476428175264, | |
| "grad_norm": 5.5655999183654785, | |
| "learning_rate": 7.222222222222223e-06, | |
| "loss": 1.0648, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2839711591791459, | |
| "grad_norm": 4.178959369659424, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.8722, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3194675540765391, | |
| "grad_norm": 2.8051388263702393, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.6238, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.35496394897393235, | |
| "grad_norm": 2.487281322479248, | |
| "learning_rate": 9.998945997517957e-06, | |
| "loss": 0.493, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39046034387132555, | |
| "grad_norm": 2.143423557281494, | |
| "learning_rate": 9.990516643685222e-06, | |
| "loss": 0.4248, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4259567387687188, | |
| "grad_norm": 1.8732106685638428, | |
| "learning_rate": 9.973672149817232e-06, | |
| "loss": 0.2676, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.461453133666112, | |
| "grad_norm": 1.6402384042739868, | |
| "learning_rate": 9.948440919541277e-06, | |
| "loss": 0.2245, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.49694952856350527, | |
| "grad_norm": 1.3924551010131836, | |
| "learning_rate": 9.91486549841951e-06, | |
| "loss": 0.1811, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5324459234608985, | |
| "grad_norm": 2.457998037338257, | |
| "learning_rate": 9.873002502207502e-06, | |
| "loss": 0.1166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5679423183582918, | |
| "grad_norm": 1.0437461137771606, | |
| "learning_rate": 9.822922521387277e-06, | |
| "loss": 0.1204, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.603438713255685, | |
| "grad_norm": 3.6355228424072266, | |
| "learning_rate": 9.764710002135784e-06, | |
| "loss": 0.1161, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6389351081530782, | |
| "grad_norm": 1.3620433807373047, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.1179, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6744315030504714, | |
| "grad_norm": 0.5827310681343079, | |
| "learning_rate": 9.62429353402556e-06, | |
| "loss": 0.0806, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7099278979478647, | |
| "grad_norm": 0.9769260883331299, | |
| "learning_rate": 9.542326359097619e-06, | |
| "loss": 0.0941, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7454242928452579, | |
| "grad_norm": 0.6220430731773376, | |
| "learning_rate": 9.452699794345583e-06, | |
| "loss": 0.0761, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7809206877426511, | |
| "grad_norm": 0.5837266445159912, | |
| "learning_rate": 9.355564970433288e-06, | |
| "loss": 0.068, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8164170826400444, | |
| "grad_norm": 0.445272296667099, | |
| "learning_rate": 9.251085678648072e-06, | |
| "loss": 0.0642, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8519134775374376, | |
| "grad_norm": 0.4069404900074005, | |
| "learning_rate": 9.13943809471159e-06, | |
| "loss": 0.0526, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8874098724348308, | |
| "grad_norm": 0.47115278244018555, | |
| "learning_rate": 9.020810481707709e-06, | |
| "loss": 0.049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.922906267332224, | |
| "grad_norm": 0.9125522375106812, | |
| "learning_rate": 8.895402872628352e-06, | |
| "loss": 0.0547, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9584026622296173, | |
| "grad_norm": 0.3842329978942871, | |
| "learning_rate": 8.763426733072624e-06, | |
| "loss": 0.0449, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9938990571270105, | |
| "grad_norm": 0.7765663266181946, | |
| "learning_rate": 8.625104604667965e-06, | |
| "loss": 0.0618, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0177481974486966, | |
| "grad_norm": 0.39780569076538086, | |
| "learning_rate": 8.480669729814635e-06, | |
| "loss": 0.0477, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.0532445923460898, | |
| "grad_norm": 0.3841244578361511, | |
| "learning_rate": 8.330365658386252e-06, | |
| "loss": 0.0412, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.088740987243483, | |
| "grad_norm": 0.39046695828437805, | |
| "learning_rate": 8.174445837049614e-06, | |
| "loss": 0.0366, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.1242373821408762, | |
| "grad_norm": 0.35411760210990906, | |
| "learning_rate": 8.013173181896283e-06, | |
| "loss": 0.0381, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.1597337770382696, | |
| "grad_norm": 0.37250956892967224, | |
| "learning_rate": 7.846819635106569e-06, | |
| "loss": 0.0379, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1952301719356628, | |
| "grad_norm": 0.4131050407886505, | |
| "learning_rate": 7.675665706393502e-06, | |
| "loss": 0.0381, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.230726566833056, | |
| "grad_norm": 0.4184521734714508, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0348, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2662229617304492, | |
| "grad_norm": 0.3667065501213074, | |
| "learning_rate": 7.320118728046818e-06, | |
| "loss": 0.0357, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.3017193566278424, | |
| "grad_norm": 0.307443231344223, | |
| "learning_rate": 7.136325211051905e-06, | |
| "loss": 0.0344, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.3372157515252356, | |
| "grad_norm": 0.3104756474494934, | |
| "learning_rate": 6.948929366463397e-06, | |
| "loss": 0.037, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.372712146422629, | |
| "grad_norm": 0.4366794228553772, | |
| "learning_rate": 6.758247186068684e-06, | |
| "loss": 0.0387, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.4082085413200223, | |
| "grad_norm": 0.32028865814208984, | |
| "learning_rate": 6.5646002031607726e-06, | |
| "loss": 0.0313, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.4437049362174155, | |
| "grad_norm": 0.2846560776233673, | |
| "learning_rate": 6.368314950360416e-06, | |
| "loss": 0.0348, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.4792013311148087, | |
| "grad_norm": 0.47968789935112, | |
| "learning_rate": 6.169722409008244e-06, | |
| "loss": 0.0302, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.5146977260122019, | |
| "grad_norm": 0.6367243528366089, | |
| "learning_rate": 5.9691574510553505e-06, | |
| "loss": 0.0335, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.550194120909595, | |
| "grad_norm": 0.25928691029548645, | |
| "learning_rate": 5.766958274393428e-06, | |
| "loss": 0.0334, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.5856905158069883, | |
| "grad_norm": 4.997822284698486, | |
| "learning_rate": 5.5634658325766066e-06, | |
| "loss": 0.0272, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6211869107043815, | |
| "grad_norm": 0.2188279628753662, | |
| "learning_rate": 5.359023259896638e-06, | |
| "loss": 0.0269, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.6566833056017747, | |
| "grad_norm": 0.35858553647994995, | |
| "learning_rate": 5.153975292780852e-06, | |
| "loss": 0.0352, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.692179700499168, | |
| "grad_norm": 0.308819979429245, | |
| "learning_rate": 4.948667688488552e-06, | |
| "loss": 0.0327, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.7276760953965613, | |
| "grad_norm": 0.5604074001312256, | |
| "learning_rate": 4.7434466420860515e-06, | |
| "loss": 0.033, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.7631724902939545, | |
| "grad_norm": 0.31649985909461975, | |
| "learning_rate": 4.53865820268349e-06, | |
| "loss": 0.0292, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7986688851913477, | |
| "grad_norm": 0.2754175662994385, | |
| "learning_rate": 4.334647689917734e-06, | |
| "loss": 0.0379, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.8341652800887411, | |
| "grad_norm": 0.3243215084075928, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.0315, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.8696616749861343, | |
| "grad_norm": 0.2798413336277008, | |
| "learning_rate": 3.930334583967514e-06, | |
| "loss": 0.0345, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.9051580698835275, | |
| "grad_norm": 0.2298552244901657, | |
| "learning_rate": 3.730713754144961e-06, | |
| "loss": 0.0277, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.9406544647809207, | |
| "grad_norm": 0.44037896394729614, | |
| "learning_rate": 3.5332332280757706e-06, | |
| "loss": 0.0276, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.976150859678314, | |
| "grad_norm": 0.41545015573501587, | |
| "learning_rate": 3.3382260026017027e-06, | |
| "loss": 0.0383, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3469395339488983, | |
| "learning_rate": 3.1460209040201967e-06, | |
| "loss": 0.0258, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.035496394897393, | |
| "grad_norm": 0.30031341314315796, | |
| "learning_rate": 2.956942033608843e-06, | |
| "loss": 0.0221, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.0709927897947864, | |
| "grad_norm": 0.23123888671398163, | |
| "learning_rate": 2.771308221117309e-06, | |
| "loss": 0.027, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.1064891846921796, | |
| "grad_norm": 0.2226598858833313, | |
| "learning_rate": 2.5894324871482557e-06, | |
| "loss": 0.0188, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.141985579589573, | |
| "grad_norm": 0.24335065484046936, | |
| "learning_rate": 2.411621515333788e-06, | |
| "loss": 0.0226, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.177481974486966, | |
| "grad_norm": 0.4972982108592987, | |
| "learning_rate": 2.238175135197471e-06, | |
| "loss": 0.0221, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.212978369384359, | |
| "grad_norm": 0.199220210313797, | |
| "learning_rate": 2.069385816573928e-06, | |
| "loss": 0.0182, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.2484747642817524, | |
| "grad_norm": 0.2942477762699127, | |
| "learning_rate": 1.9055381764385272e-06, | |
| "loss": 0.0257, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.283971159179146, | |
| "grad_norm": 0.2242165505886078, | |
| "learning_rate": 1.746908498978791e-06, | |
| "loss": 0.0217, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.3194675540765393, | |
| "grad_norm": 0.19704177975654602, | |
| "learning_rate": 1.5937642697167288e-06, | |
| "loss": 0.0201, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.3549639489739325, | |
| "grad_norm": 0.3458758592605591, | |
| "learning_rate": 1.4463637244677648e-06, | |
| "loss": 0.0214, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.3904603438713257, | |
| "grad_norm": 0.20692254602909088, | |
| "learning_rate": 1.3049554138967052e-06, | |
| "loss": 0.0173, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.425956738768719, | |
| "grad_norm": 0.23293040692806244, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.0217, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.461453133666112, | |
| "grad_norm": 0.24933604896068573, | |
| "learning_rate": 1.0410587760567104e-06, | |
| "loss": 0.0174, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4969495285635053, | |
| "grad_norm": 0.24881727993488312, | |
| "learning_rate": 9.190154382188921e-07, | |
| "loss": 0.0201, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.5324459234608985, | |
| "grad_norm": 0.22158710658550262, | |
| "learning_rate": 8.03853563568367e-07, | |
| "loss": 0.0194, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.5679423183582917, | |
| "grad_norm": 0.2617812156677246, | |
| "learning_rate": 6.957673410781617e-07, | |
| "loss": 0.0238, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.603438713255685, | |
| "grad_norm": 0.23341882228851318, | |
| "learning_rate": 5.949390285710777e-07, | |
| "loss": 0.0207, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.638935108153078, | |
| "grad_norm": 0.20265567302703857, | |
| "learning_rate": 5.015386453917742e-07, | |
| "loss": 0.0195, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.6744315030504713, | |
| "grad_norm": 0.24993731081485748, | |
| "learning_rate": 4.15723685715686e-07, | |
| "loss": 0.0219, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.709927897947865, | |
| "grad_norm": 0.20348049700260162, | |
| "learning_rate": 3.3763885297822153e-07, | |
| "loss": 0.0172, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.745424292845258, | |
| "grad_norm": 0.43210646510124207, | |
| "learning_rate": 2.6741581587202747e-07, | |
| "loss": 0.0228, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.7809206877426513, | |
| "grad_norm": 0.2683945298194885, | |
| "learning_rate": 2.0517298632379445e-07, | |
| "loss": 0.0194, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.8164170826400445, | |
| "grad_norm": 0.2853659689426422, | |
| "learning_rate": 1.510153198249531e-07, | |
| "loss": 0.0214, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.8519134775374377, | |
| "grad_norm": 0.28844180703163147, | |
| "learning_rate": 1.0503413845297739e-07, | |
| "loss": 0.0217, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.887409872434831, | |
| "grad_norm": 0.38325849175453186, | |
| "learning_rate": 6.730697688170251e-08, | |
| "loss": 0.0246, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.922906267332224, | |
| "grad_norm": 0.4123646020889282, | |
| "learning_rate": 3.7897451640321326e-08, | |
| "loss": 0.0239, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.9584026622296173, | |
| "grad_norm": 0.2761909067630768, | |
| "learning_rate": 1.6855153841527915e-08, | |
| "loss": 0.0198, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.9938990571270105, | |
| "grad_norm": 0.28191664814949036, | |
| "learning_rate": 4.2155655596809455e-09, | |
| "loss": 0.0218, | |
| "step": 170 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 171, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 208500261126144.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |