| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9956331877729258, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 0.12968653440475464, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.3378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 0.1782296746969223, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 0.1216743066906929, | |
| "learning_rate": 3e-06, | |
| "loss": 1.2269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 0.13824662566184998, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2621, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "grad_norm": 0.15446175634860992, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10480349344978165, | |
| "grad_norm": 0.13843178749084473, | |
| "learning_rate": 6e-06, | |
| "loss": 1.2438, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1222707423580786, | |
| "grad_norm": 0.15130339562892914, | |
| "learning_rate": 7e-06, | |
| "loss": 1.2331, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 0.15838982164859772, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.2703, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "grad_norm": 0.15755866467952728, | |
| "learning_rate": 9e-06, | |
| "loss": 1.2603, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "grad_norm": 0.16667789220809937, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2428, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19213973799126638, | |
| "grad_norm": 0.1794327050447464, | |
| "learning_rate": 9.988834393115768e-06, | |
| "loss": 1.2442, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2096069868995633, | |
| "grad_norm": 0.18840420246124268, | |
| "learning_rate": 9.955387440773902e-06, | |
| "loss": 1.2562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22707423580786026, | |
| "grad_norm": 0.24771647155284882, | |
| "learning_rate": 9.899808525182935e-06, | |
| "loss": 1.2056, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2445414847161572, | |
| "grad_norm": 0.2212584763765335, | |
| "learning_rate": 9.822345875271884e-06, | |
| "loss": 1.2462, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26200873362445415, | |
| "grad_norm": 0.2274945080280304, | |
| "learning_rate": 9.723345458039595e-06, | |
| "loss": 1.262, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2794759825327511, | |
| "grad_norm": 0.22981807589530945, | |
| "learning_rate": 9.603249433382145e-06, | |
| "loss": 1.2918, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29694323144104806, | |
| "grad_norm": 0.27434590458869934, | |
| "learning_rate": 9.462594179299408e-06, | |
| "loss": 1.2858, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.314410480349345, | |
| "grad_norm": 0.23107963800430298, | |
| "learning_rate": 9.302007896300697e-06, | |
| "loss": 1.1679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3318777292576419, | |
| "grad_norm": 0.23975740373134613, | |
| "learning_rate": 9.122207801708802e-06, | |
| "loss": 1.2119, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "grad_norm": 0.21921472251415253, | |
| "learning_rate": 8.923996926393306e-06, | |
| "loss": 1.1735, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36681222707423583, | |
| "grad_norm": 0.22271591424942017, | |
| "learning_rate": 8.708260528239788e-06, | |
| "loss": 1.2749, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38427947598253276, | |
| "grad_norm": 0.20965439081192017, | |
| "learning_rate": 8.475962138373212e-06, | |
| "loss": 1.25, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4017467248908297, | |
| "grad_norm": 0.17370395362377167, | |
| "learning_rate": 8.228139257794012e-06, | |
| "loss": 1.1968, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4192139737991266, | |
| "grad_norm": 0.19179144501686096, | |
| "learning_rate": 7.965898723646777e-06, | |
| "loss": 1.169, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4366812227074236, | |
| "grad_norm": 0.1869051307439804, | |
| "learning_rate": 7.690411765816864e-06, | |
| "loss": 1.199, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45414847161572053, | |
| "grad_norm": 0.17581412196159363, | |
| "learning_rate": 7.402908775933419e-06, | |
| "loss": 1.126, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.47161572052401746, | |
| "grad_norm": 0.1623380184173584, | |
| "learning_rate": 7.104673812141676e-06, | |
| "loss": 1.1392, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4890829694323144, | |
| "grad_norm": 0.19948747754096985, | |
| "learning_rate": 6.797038864187564e-06, | |
| "loss": 1.0956, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5065502183406113, | |
| "grad_norm": 0.1480165272951126, | |
| "learning_rate": 6.481377904428171e-06, | |
| "loss": 1.1984, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5240174672489083, | |
| "grad_norm": 0.15460729598999023, | |
| "learning_rate": 6.1591007513376425e-06, | |
| "loss": 1.1759, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5414847161572053, | |
| "grad_norm": 0.13603241741657257, | |
| "learning_rate": 5.831646772915651e-06, | |
| "loss": 1.182, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5589519650655022, | |
| "grad_norm": 0.15064558386802673, | |
| "learning_rate": 5.500478458120493e-06, | |
| "loss": 1.1191, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5764192139737991, | |
| "grad_norm": 0.1394384205341339, | |
| "learning_rate": 5.1670748850383734e-06, | |
| "loss": 1.1359, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5938864628820961, | |
| "grad_norm": 0.12493956089019775, | |
| "learning_rate": 4.832925114961629e-06, | |
| "loss": 1.1747, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.611353711790393, | |
| "grad_norm": 0.14052054286003113, | |
| "learning_rate": 4.499521541879508e-06, | |
| "loss": 1.1116, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.62882096069869, | |
| "grad_norm": 0.1254061758518219, | |
| "learning_rate": 4.1683532270843505e-06, | |
| "loss": 1.1836, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6462882096069869, | |
| "grad_norm": 0.1256641447544098, | |
| "learning_rate": 3.840899248662358e-06, | |
| "loss": 1.1166, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6637554585152838, | |
| "grad_norm": 0.22417481243610382, | |
| "learning_rate": 3.518622095571831e-06, | |
| "loss": 1.1714, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6812227074235808, | |
| "grad_norm": 0.11602552980184555, | |
| "learning_rate": 3.202961135812437e-06, | |
| "loss": 1.1894, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "grad_norm": 0.19411428272724152, | |
| "learning_rate": 2.8953261878583263e-06, | |
| "loss": 1.1708, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7161572052401747, | |
| "grad_norm": 0.13553348183631897, | |
| "learning_rate": 2.5970912240665815e-06, | |
| "loss": 1.0575, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7336244541484717, | |
| "grad_norm": 0.10409089922904968, | |
| "learning_rate": 2.309588234183137e-06, | |
| "loss": 1.1015, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7510917030567685, | |
| "grad_norm": 0.11063861846923828, | |
| "learning_rate": 2.0341012763532243e-06, | |
| "loss": 1.1157, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7685589519650655, | |
| "grad_norm": 0.11219683289527893, | |
| "learning_rate": 1.771860742205988e-06, | |
| "loss": 1.182, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7860262008733624, | |
| "grad_norm": 0.11221789568662643, | |
| "learning_rate": 1.5240378616267887e-06, | |
| "loss": 1.0891, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8034934497816594, | |
| "grad_norm": 0.11372566968202591, | |
| "learning_rate": 1.2917394717602123e-06, | |
| "loss": 1.141, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8209606986899564, | |
| "grad_norm": 0.10632464289665222, | |
| "learning_rate": 1.0760030736066952e-06, | |
| "loss": 1.0804, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8384279475982532, | |
| "grad_norm": 0.11523567885160446, | |
| "learning_rate": 8.777921982911996e-07, | |
| "loss": 1.0865, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8558951965065502, | |
| "grad_norm": 0.13787008821964264, | |
| "learning_rate": 6.979921036993042e-07, | |
| "loss": 1.1934, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8733624454148472, | |
| "grad_norm": 0.11613141745328903, | |
| "learning_rate": 5.374058207005945e-07, | |
| "loss": 1.1211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8908296943231441, | |
| "grad_norm": 0.11686104536056519, | |
| "learning_rate": 3.9675056661785563e-07, | |
| "loss": 1.1523, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9082969432314411, | |
| "grad_norm": 0.11762232333421707, | |
| "learning_rate": 2.7665454196040665e-07, | |
| "loss": 1.132, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.925764192139738, | |
| "grad_norm": 0.12294066697359085, | |
| "learning_rate": 1.776541247281177e-07, | |
| "loss": 1.1347, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9432314410480349, | |
| "grad_norm": 0.13556340336799622, | |
| "learning_rate": 1.0019147481706626e-07, | |
| "loss": 1.1571, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9606986899563319, | |
| "grad_norm": 0.11323779076337814, | |
| "learning_rate": 4.461255922609986e-08, | |
| "loss": 1.1618, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9781659388646288, | |
| "grad_norm": 0.1132877767086029, | |
| "learning_rate": 1.1165606884234182e-08, | |
| "loss": 1.1674, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9956331877729258, | |
| "grad_norm": 0.10288415104150772, | |
| "learning_rate": 0.0, | |
| "loss": 1.1306, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 57, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 19, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.90947182212599e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |