| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030517578125, | |
| "eval_steps": 500, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003814697265625, | |
| "grad_norm": 1.8202160596847534, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7732, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.000762939453125, | |
| "grad_norm": 1.0439223051071167, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3055, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0011444091796875, | |
| "grad_norm": 0.49549755454063416, | |
| "learning_rate": 0.00012, | |
| "loss": 0.2596, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00152587890625, | |
| "grad_norm": 0.9390599727630615, | |
| "learning_rate": 0.00016, | |
| "loss": 0.2547, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0019073486328125, | |
| "grad_norm": 0.4973730444908142, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2534, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.002288818359375, | |
| "grad_norm": 0.45400354266166687, | |
| "learning_rate": 0.000199748427672956, | |
| "loss": 0.2446, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0026702880859375, | |
| "grad_norm": 0.39165329933166504, | |
| "learning_rate": 0.00019949685534591195, | |
| "loss": 0.2411, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0030517578125, | |
| "grad_norm": 0.4248354434967041, | |
| "learning_rate": 0.00019924528301886794, | |
| "loss": 0.2392, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0034332275390625, | |
| "grad_norm": 0.35752373933792114, | |
| "learning_rate": 0.0001989937106918239, | |
| "loss": 0.236, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.003814697265625, | |
| "grad_norm": 0.39206448197364807, | |
| "learning_rate": 0.00019874213836477988, | |
| "loss": 0.2322, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0041961669921875, | |
| "grad_norm": 0.3509558439254761, | |
| "learning_rate": 0.00019849056603773587, | |
| "loss": 0.2312, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.00457763671875, | |
| "grad_norm": 0.3513820171356201, | |
| "learning_rate": 0.00019823899371069183, | |
| "loss": 0.2308, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.0049591064453125, | |
| "grad_norm": 0.434176504611969, | |
| "learning_rate": 0.0001979874213836478, | |
| "loss": 0.2284, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.005340576171875, | |
| "grad_norm": 0.37612399458885193, | |
| "learning_rate": 0.0001977358490566038, | |
| "loss": 0.2289, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.0057220458984375, | |
| "grad_norm": 0.3991953134536743, | |
| "learning_rate": 0.00019748427672955975, | |
| "loss": 0.23, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.006103515625, | |
| "grad_norm": 0.4121605157852173, | |
| "learning_rate": 0.00019723270440251574, | |
| "loss": 0.2284, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.0064849853515625, | |
| "grad_norm": 0.3937987983226776, | |
| "learning_rate": 0.0001969811320754717, | |
| "loss": 0.2249, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.006866455078125, | |
| "grad_norm": 0.2995181083679199, | |
| "learning_rate": 0.00019672955974842768, | |
| "loss": 0.2257, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.0072479248046875, | |
| "grad_norm": 0.5119357705116272, | |
| "learning_rate": 0.00019647798742138367, | |
| "loss": 0.2292, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.00762939453125, | |
| "grad_norm": 0.31295427680015564, | |
| "learning_rate": 0.00019622641509433963, | |
| "loss": 0.2289, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0080108642578125, | |
| "grad_norm": 0.2797456979751587, | |
| "learning_rate": 0.0001959748427672956, | |
| "loss": 0.2232, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.008392333984375, | |
| "grad_norm": 0.45458996295928955, | |
| "learning_rate": 0.00019572327044025157, | |
| "loss": 0.2244, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.0087738037109375, | |
| "grad_norm": 0.29631954431533813, | |
| "learning_rate": 0.00019547169811320755, | |
| "loss": 0.2234, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.0091552734375, | |
| "grad_norm": 0.5060445070266724, | |
| "learning_rate": 0.00019522012578616354, | |
| "loss": 0.2265, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.0095367431640625, | |
| "grad_norm": 0.28566980361938477, | |
| "learning_rate": 0.0001949685534591195, | |
| "loss": 0.2279, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.009918212890625, | |
| "grad_norm": 0.24325500428676605, | |
| "learning_rate": 0.00019471698113207548, | |
| "loss": 0.2306, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.0102996826171875, | |
| "grad_norm": 0.3140350878238678, | |
| "learning_rate": 0.00019446540880503147, | |
| "loss": 0.2234, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.01068115234375, | |
| "grad_norm": 0.4366394877433777, | |
| "learning_rate": 0.00019421383647798743, | |
| "loss": 0.2224, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.0110626220703125, | |
| "grad_norm": 0.27782708406448364, | |
| "learning_rate": 0.0001939622641509434, | |
| "loss": 0.2236, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.011444091796875, | |
| "grad_norm": 0.3332788944244385, | |
| "learning_rate": 0.00019371069182389937, | |
| "loss": 0.2241, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0118255615234375, | |
| "grad_norm": 0.3888827860355377, | |
| "learning_rate": 0.00019345911949685536, | |
| "loss": 0.2217, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.01220703125, | |
| "grad_norm": 0.24029745161533356, | |
| "learning_rate": 0.00019320754716981134, | |
| "loss": 0.2216, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.0125885009765625, | |
| "grad_norm": 1.8477509021759033, | |
| "learning_rate": 0.0001929559748427673, | |
| "loss": 0.2252, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.012969970703125, | |
| "grad_norm": 0.5924927592277527, | |
| "learning_rate": 0.00019270440251572328, | |
| "loss": 0.2352, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.0133514404296875, | |
| "grad_norm": 0.33940935134887695, | |
| "learning_rate": 0.00019245283018867927, | |
| "loss": 0.2253, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.01373291015625, | |
| "grad_norm": 0.3898316025733948, | |
| "learning_rate": 0.00019220125786163523, | |
| "loss": 0.2216, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.0141143798828125, | |
| "grad_norm": 0.2601265609264374, | |
| "learning_rate": 0.0001919496855345912, | |
| "loss": 0.2261, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.014495849609375, | |
| "grad_norm": 0.32615959644317627, | |
| "learning_rate": 0.00019169811320754717, | |
| "loss": 0.2225, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.0148773193359375, | |
| "grad_norm": 0.2891947627067566, | |
| "learning_rate": 0.00019144654088050316, | |
| "loss": 0.2216, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.0152587890625, | |
| "grad_norm": 0.2846430242061615, | |
| "learning_rate": 0.00019119496855345914, | |
| "loss": 0.2197, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0156402587890625, | |
| "grad_norm": 0.2938269078731537, | |
| "learning_rate": 0.0001909433962264151, | |
| "loss": 0.2212, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.016021728515625, | |
| "grad_norm": 0.2718958258628845, | |
| "learning_rate": 0.00019069182389937108, | |
| "loss": 0.2205, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.0164031982421875, | |
| "grad_norm": 0.3561397194862366, | |
| "learning_rate": 0.00019044025157232704, | |
| "loss": 0.2205, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.01678466796875, | |
| "grad_norm": 0.4546607732772827, | |
| "learning_rate": 0.00019018867924528303, | |
| "loss": 0.2234, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.0171661376953125, | |
| "grad_norm": 0.29250577092170715, | |
| "learning_rate": 0.00018993710691823901, | |
| "loss": 0.2197, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.017547607421875, | |
| "grad_norm": 1.6952908039093018, | |
| "learning_rate": 0.00018968553459119497, | |
| "loss": 0.2217, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.0179290771484375, | |
| "grad_norm": 0.3261864483356476, | |
| "learning_rate": 0.00018943396226415096, | |
| "loss": 0.2269, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.018310546875, | |
| "grad_norm": 0.2668060064315796, | |
| "learning_rate": 0.00018918238993710694, | |
| "loss": 0.2203, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.0186920166015625, | |
| "grad_norm": 0.31689000129699707, | |
| "learning_rate": 0.0001889308176100629, | |
| "loss": 0.2201, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.019073486328125, | |
| "grad_norm": 0.26320216059684753, | |
| "learning_rate": 0.00018867924528301889, | |
| "loss": 0.2214, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.0194549560546875, | |
| "grad_norm": 0.26768413186073303, | |
| "learning_rate": 0.00018842767295597484, | |
| "loss": 0.2225, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.01983642578125, | |
| "grad_norm": 0.2808452248573303, | |
| "learning_rate": 0.00018817610062893083, | |
| "loss": 0.2208, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.0202178955078125, | |
| "grad_norm": 0.25958341360092163, | |
| "learning_rate": 0.00018792452830188681, | |
| "loss": 0.2207, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.020599365234375, | |
| "grad_norm": 0.22953402996063232, | |
| "learning_rate": 0.00018767295597484277, | |
| "loss": 0.2193, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.0209808349609375, | |
| "grad_norm": 0.9375737905502319, | |
| "learning_rate": 0.00018742138364779876, | |
| "loss": 0.2206, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.0213623046875, | |
| "grad_norm": 0.2852359712123871, | |
| "learning_rate": 0.00018716981132075472, | |
| "loss": 0.2211, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.0217437744140625, | |
| "grad_norm": 0.25367122888565063, | |
| "learning_rate": 0.0001869182389937107, | |
| "loss": 0.2191, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.022125244140625, | |
| "grad_norm": 0.2215207815170288, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 0.2218, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.0225067138671875, | |
| "grad_norm": 0.24178574979305267, | |
| "learning_rate": 0.00018641509433962264, | |
| "loss": 0.2283, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.02288818359375, | |
| "grad_norm": 0.3638046979904175, | |
| "learning_rate": 0.00018616352201257863, | |
| "loss": 0.2217, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.0232696533203125, | |
| "grad_norm": 0.40834301710128784, | |
| "learning_rate": 0.00018591194968553462, | |
| "loss": 0.2204, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.023651123046875, | |
| "grad_norm": 0.24277737736701965, | |
| "learning_rate": 0.00018566037735849057, | |
| "loss": 0.2178, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.0240325927734375, | |
| "grad_norm": 0.3276098370552063, | |
| "learning_rate": 0.00018540880503144656, | |
| "loss": 0.2245, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.0244140625, | |
| "grad_norm": 0.40407466888427734, | |
| "learning_rate": 0.00018515723270440252, | |
| "loss": 0.2258, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.0247955322265625, | |
| "grad_norm": 0.31675395369529724, | |
| "learning_rate": 0.0001849056603773585, | |
| "loss": 0.223, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.025177001953125, | |
| "grad_norm": 0.2858389616012573, | |
| "learning_rate": 0.0001846540880503145, | |
| "loss": 0.2201, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.0255584716796875, | |
| "grad_norm": 0.2711004912853241, | |
| "learning_rate": 0.00018440251572327045, | |
| "loss": 0.2175, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.02593994140625, | |
| "grad_norm": 0.24398334324359894, | |
| "learning_rate": 0.00018415094339622643, | |
| "loss": 0.2195, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.0263214111328125, | |
| "grad_norm": 0.29580453038215637, | |
| "learning_rate": 0.0001838993710691824, | |
| "loss": 0.2198, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.026702880859375, | |
| "grad_norm": 0.2624952495098114, | |
| "learning_rate": 0.00018364779874213837, | |
| "loss": 0.217, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.0270843505859375, | |
| "grad_norm": 0.2129925936460495, | |
| "learning_rate": 0.00018339622641509436, | |
| "loss": 0.2188, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.0274658203125, | |
| "grad_norm": 0.27471479773521423, | |
| "learning_rate": 0.00018314465408805032, | |
| "loss": 0.2174, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.0278472900390625, | |
| "grad_norm": 1.0204274654388428, | |
| "learning_rate": 0.0001828930817610063, | |
| "loss": 0.2186, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.028228759765625, | |
| "grad_norm": 0.5174055695533752, | |
| "learning_rate": 0.0001826415094339623, | |
| "loss": 0.2198, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.0286102294921875, | |
| "grad_norm": 1.7667677402496338, | |
| "learning_rate": 0.00018238993710691825, | |
| "loss": 0.2221, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.02899169921875, | |
| "grad_norm": 0.34651100635528564, | |
| "learning_rate": 0.00018213836477987423, | |
| "loss": 0.2215, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.0293731689453125, | |
| "grad_norm": 0.2900320589542389, | |
| "learning_rate": 0.0001818867924528302, | |
| "loss": 0.2184, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.029754638671875, | |
| "grad_norm": 0.21523432433605194, | |
| "learning_rate": 0.00018163522012578617, | |
| "loss": 0.2171, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.0301361083984375, | |
| "grad_norm": 0.28846126794815063, | |
| "learning_rate": 0.00018138364779874216, | |
| "loss": 0.2175, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.030517578125, | |
| "grad_norm": 0.27318933606147766, | |
| "learning_rate": 0.00018113207547169812, | |
| "loss": 0.218, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 80000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.909320422780109e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |