| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7748934521503293, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012914890869172156, | |
| "grad_norm": 0.9891569018363953, | |
| "learning_rate": 1.974170218261656e-05, | |
| "loss": 1.6595, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025829781738344312, | |
| "grad_norm": 0.24901358783245087, | |
| "learning_rate": 1.9483404365233117e-05, | |
| "loss": 1.4216, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03874467260751647, | |
| "grad_norm": 1.108109951019287, | |
| "learning_rate": 1.922510654784967e-05, | |
| "loss": 1.383, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.051659563476688625, | |
| "grad_norm": 0.7391151785850525, | |
| "learning_rate": 1.896680873046623e-05, | |
| "loss": 1.408, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06457445434586077, | |
| "grad_norm": 0.9414256811141968, | |
| "learning_rate": 1.8708510913082787e-05, | |
| "loss": 1.3439, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07748934521503294, | |
| "grad_norm": 0.7522476315498352, | |
| "learning_rate": 1.845021309569934e-05, | |
| "loss": 1.272, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09040423608420509, | |
| "grad_norm": 0.32411837577819824, | |
| "learning_rate": 1.81919152783159e-05, | |
| "loss": 1.16, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.10331912695337725, | |
| "grad_norm": 0.8460651636123657, | |
| "learning_rate": 1.7933617460932457e-05, | |
| "loss": 1.1753, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1162340178225494, | |
| "grad_norm": 1.0593210458755493, | |
| "learning_rate": 1.7675319643549015e-05, | |
| "loss": 1.2417, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.12914890869172155, | |
| "grad_norm": 1.2058868408203125, | |
| "learning_rate": 1.741702182616557e-05, | |
| "loss": 1.381, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1420637995608937, | |
| "grad_norm": 0.36752256751060486, | |
| "learning_rate": 1.7158724008782127e-05, | |
| "loss": 1.2031, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.15497869043006587, | |
| "grad_norm": 0.3617095351219177, | |
| "learning_rate": 1.6900426191398685e-05, | |
| "loss": 1.2186, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.167893581299238, | |
| "grad_norm": 1.2740339040756226, | |
| "learning_rate": 1.664212837401524e-05, | |
| "loss": 1.2354, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.18080847216841017, | |
| "grad_norm": 1.0895512104034424, | |
| "learning_rate": 1.6383830556631797e-05, | |
| "loss": 1.1308, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.19372336303758234, | |
| "grad_norm": 0.28641125559806824, | |
| "learning_rate": 1.6125532739248355e-05, | |
| "loss": 1.1459, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2066382539067545, | |
| "grad_norm": 0.7633489966392517, | |
| "learning_rate": 1.5867234921864912e-05, | |
| "loss": 1.083, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.21955314477592663, | |
| "grad_norm": 0.9854117035865784, | |
| "learning_rate": 1.5608937104481467e-05, | |
| "loss": 1.1526, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2324680356450988, | |
| "grad_norm": 1.0833749771118164, | |
| "learning_rate": 1.5350639287098025e-05, | |
| "loss": 1.0866, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.24538292651427096, | |
| "grad_norm": 1.2186298370361328, | |
| "learning_rate": 1.5092341469714582e-05, | |
| "loss": 1.0898, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.2582978173834431, | |
| "grad_norm": 0.976441502571106, | |
| "learning_rate": 1.4834043652331138e-05, | |
| "loss": 1.2018, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2712127082526153, | |
| "grad_norm": 1.0837169885635376, | |
| "learning_rate": 1.4575745834947696e-05, | |
| "loss": 1.1264, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.2841275991217874, | |
| "grad_norm": 0.8157379031181335, | |
| "learning_rate": 1.4317448017564252e-05, | |
| "loss": 1.2216, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.29704248999095956, | |
| "grad_norm": 0.4470981955528259, | |
| "learning_rate": 1.4059150200180808e-05, | |
| "loss": 1.1543, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.30995738086013175, | |
| "grad_norm": 0.9872229695320129, | |
| "learning_rate": 1.3800852382797368e-05, | |
| "loss": 1.1293, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.3228722717293039, | |
| "grad_norm": 1.2851194143295288, | |
| "learning_rate": 1.3542554565413924e-05, | |
| "loss": 1.1619, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.335787162598476, | |
| "grad_norm": 1.0529409646987915, | |
| "learning_rate": 1.328425674803048e-05, | |
| "loss": 1.0468, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.3487020534676482, | |
| "grad_norm": 1.2335134744644165, | |
| "learning_rate": 1.3025958930647038e-05, | |
| "loss": 1.1292, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.36161694433682035, | |
| "grad_norm": 1.165204405784607, | |
| "learning_rate": 1.2767661113263594e-05, | |
| "loss": 1.0324, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.37453183520599254, | |
| "grad_norm": 0.4545508623123169, | |
| "learning_rate": 1.250936329588015e-05, | |
| "loss": 1.0776, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.38744672607516467, | |
| "grad_norm": 1.1217703819274902, | |
| "learning_rate": 1.225106547849671e-05, | |
| "loss": 1.0673, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.4003616169443368, | |
| "grad_norm": 1.204528570175171, | |
| "learning_rate": 1.1992767661113265e-05, | |
| "loss": 1.1664, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.413276507813509, | |
| "grad_norm": 1.8890794515609741, | |
| "learning_rate": 1.1734469843729821e-05, | |
| "loss": 1.0947, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.42619139868268113, | |
| "grad_norm": 1.4399609565734863, | |
| "learning_rate": 1.147617202634638e-05, | |
| "loss": 1.115, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.43910628955185327, | |
| "grad_norm": 0.8998225331306458, | |
| "learning_rate": 1.1217874208962935e-05, | |
| "loss": 1.0569, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.45202118042102546, | |
| "grad_norm": 1.2747713327407837, | |
| "learning_rate": 1.0959576391579491e-05, | |
| "loss": 1.0758, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.4649360712901976, | |
| "grad_norm": 1.2398267984390259, | |
| "learning_rate": 1.0701278574196047e-05, | |
| "loss": 1.0722, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.47785096215936973, | |
| "grad_norm": 0.7766038179397583, | |
| "learning_rate": 1.0442980756812607e-05, | |
| "loss": 1.1556, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.4907658530285419, | |
| "grad_norm": 1.2244646549224854, | |
| "learning_rate": 1.0184682939429163e-05, | |
| "loss": 1.1066, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.5036807438977141, | |
| "grad_norm": 1.1265727281570435, | |
| "learning_rate": 9.926385122045719e-06, | |
| "loss": 1.0832, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.5165956347668862, | |
| "grad_norm": 1.4965732097625732, | |
| "learning_rate": 9.668087304662275e-06, | |
| "loss": 1.1945, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.5295105256360584, | |
| "grad_norm": 1.170291543006897, | |
| "learning_rate": 9.409789487278833e-06, | |
| "loss": 1.079, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.5424254165052306, | |
| "grad_norm": 0.47167250514030457, | |
| "learning_rate": 9.15149166989539e-06, | |
| "loss": 1.0811, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.5553403073744027, | |
| "grad_norm": 1.5530108213424683, | |
| "learning_rate": 8.893193852511947e-06, | |
| "loss": 1.0456, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.5682551982435748, | |
| "grad_norm": 1.426579475402832, | |
| "learning_rate": 8.634896035128504e-06, | |
| "loss": 1.0797, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.581170089112747, | |
| "grad_norm": 1.656485676765442, | |
| "learning_rate": 8.37659821774506e-06, | |
| "loss": 1.1384, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5940849799819191, | |
| "grad_norm": 1.8213322162628174, | |
| "learning_rate": 8.118300400361617e-06, | |
| "loss": 1.0484, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.6069998708510913, | |
| "grad_norm": 0.9146257042884827, | |
| "learning_rate": 7.860002582978174e-06, | |
| "loss": 1.0798, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.6199147617202635, | |
| "grad_norm": 0.8420510292053223, | |
| "learning_rate": 7.601704765594732e-06, | |
| "loss": 1.1371, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.6328296525894356, | |
| "grad_norm": 1.728549599647522, | |
| "learning_rate": 7.343406948211288e-06, | |
| "loss": 1.1104, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.6457445434586078, | |
| "grad_norm": 0.6792052388191223, | |
| "learning_rate": 7.085109130827845e-06, | |
| "loss": 1.1497, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.65865943432778, | |
| "grad_norm": 1.167297124862671, | |
| "learning_rate": 6.826811313444401e-06, | |
| "loss": 1.1146, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.671574325196952, | |
| "grad_norm": 0.5329355001449585, | |
| "learning_rate": 6.568513496060959e-06, | |
| "loss": 1.0569, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.6844892160661242, | |
| "grad_norm": 1.3186862468719482, | |
| "learning_rate": 6.310215678677516e-06, | |
| "loss": 1.023, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.6974041069352964, | |
| "grad_norm": 1.4624109268188477, | |
| "learning_rate": 6.051917861294072e-06, | |
| "loss": 1.1174, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.7103189978044685, | |
| "grad_norm": 1.1120996475219727, | |
| "learning_rate": 5.79362004391063e-06, | |
| "loss": 1.048, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.7232338886736407, | |
| "grad_norm": 1.1070384979248047, | |
| "learning_rate": 5.535322226527187e-06, | |
| "loss": 1.1, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.7361487795428129, | |
| "grad_norm": 0.46000921726226807, | |
| "learning_rate": 5.277024409143743e-06, | |
| "loss": 1.0562, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.7490636704119851, | |
| "grad_norm": 1.4388511180877686, | |
| "learning_rate": 5.0187265917603005e-06, | |
| "loss": 1.0263, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.7619785612811572, | |
| "grad_norm": 1.0894064903259277, | |
| "learning_rate": 4.7604287743768566e-06, | |
| "loss": 1.0688, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.7748934521503293, | |
| "grad_norm": 0.36538398265838623, | |
| "learning_rate": 4.5021309569934135e-06, | |
| "loss": 1.0626, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7743, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.988164550656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |