| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998652991321415, | |
| "eval_steps": 500, | |
| "global_step": 6495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015394384898108415, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 1.9692070823710548e-05, | |
| "loss": 1.1459, | |
| "num_input_tokens_seen": 3815960, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03078876979621683, | |
| "grad_norm": 1.5703125, | |
| "learning_rate": 1.9384141647421097e-05, | |
| "loss": 1.0878, | |
| "num_input_tokens_seen": 7588127, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04618315469432525, | |
| "grad_norm": 1.625, | |
| "learning_rate": 1.907621247113164e-05, | |
| "loss": 1.0942, | |
| "num_input_tokens_seen": 11373466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06157753959243366, | |
| "grad_norm": 1.6328125, | |
| "learning_rate": 1.876828329484219e-05, | |
| "loss": 1.0788, | |
| "num_input_tokens_seen": 15148940, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07697192449054208, | |
| "grad_norm": 1.703125, | |
| "learning_rate": 1.8460354118552735e-05, | |
| "loss": 1.0807, | |
| "num_input_tokens_seen": 18941722, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0923663093886505, | |
| "grad_norm": 1.765625, | |
| "learning_rate": 1.815242494226328e-05, | |
| "loss": 1.0628, | |
| "num_input_tokens_seen": 22691439, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1077606942867589, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 1.7844495765973827e-05, | |
| "loss": 1.057, | |
| "num_input_tokens_seen": 26519584, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12315507918486732, | |
| "grad_norm": 1.59375, | |
| "learning_rate": 1.7536566589684373e-05, | |
| "loss": 1.0591, | |
| "num_input_tokens_seen": 30335003, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13854946408297575, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 1.722863741339492e-05, | |
| "loss": 1.0597, | |
| "num_input_tokens_seen": 34122220, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15394384898108415, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.6920708237105468e-05, | |
| "loss": 1.0784, | |
| "num_input_tokens_seen": 37937918, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16933823387919256, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 1.6612779060816014e-05, | |
| "loss": 1.0598, | |
| "num_input_tokens_seen": 41762422, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.184732618777301, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 1.630484988452656e-05, | |
| "loss": 1.0658, | |
| "num_input_tokens_seen": 45541351, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2001270036754094, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 1.5996920708237106e-05, | |
| "loss": 1.0557, | |
| "num_input_tokens_seen": 49317373, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.2155213885735178, | |
| "grad_norm": 1.765625, | |
| "learning_rate": 1.5688991531947652e-05, | |
| "loss": 1.0597, | |
| "num_input_tokens_seen": 53117895, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23091577347162623, | |
| "grad_norm": 1.765625, | |
| "learning_rate": 1.53810623556582e-05, | |
| "loss": 1.0616, | |
| "num_input_tokens_seen": 56839161, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24631015836973463, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 1.5073133179368746e-05, | |
| "loss": 1.053, | |
| "num_input_tokens_seen": 60623928, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26170454326784304, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 1.4765204003079292e-05, | |
| "loss": 1.0483, | |
| "num_input_tokens_seen": 64408460, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2770989281659515, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 1.445727482678984e-05, | |
| "loss": 1.049, | |
| "num_input_tokens_seen": 68223027, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.2924933130640599, | |
| "grad_norm": 1.953125, | |
| "learning_rate": 1.4149345650500385e-05, | |
| "loss": 1.0482, | |
| "num_input_tokens_seen": 71994158, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3078876979621683, | |
| "grad_norm": 1.765625, | |
| "learning_rate": 1.3841416474210933e-05, | |
| "loss": 1.0497, | |
| "num_input_tokens_seen": 75865760, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3232820828602767, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.3533487297921479e-05, | |
| "loss": 1.0409, | |
| "num_input_tokens_seen": 79623921, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3386764677583851, | |
| "grad_norm": 1.7890625, | |
| "learning_rate": 1.3225558121632025e-05, | |
| "loss": 1.0501, | |
| "num_input_tokens_seen": 83411874, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.3540708526564935, | |
| "grad_norm": 1.6328125, | |
| "learning_rate": 1.2917628945342572e-05, | |
| "loss": 1.0542, | |
| "num_input_tokens_seen": 87182489, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.369465237554602, | |
| "grad_norm": 1.8671875, | |
| "learning_rate": 1.2609699769053118e-05, | |
| "loss": 1.0482, | |
| "num_input_tokens_seen": 90989837, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.3848596224527104, | |
| "grad_norm": 1.9375, | |
| "learning_rate": 1.2301770592763664e-05, | |
| "loss": 1.0404, | |
| "num_input_tokens_seen": 94853551, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4002540073508188, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.1993841416474212e-05, | |
| "loss": 1.0401, | |
| "num_input_tokens_seen": 98649900, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4156483922489272, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 1.1685912240184758e-05, | |
| "loss": 1.0453, | |
| "num_input_tokens_seen": 102455430, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.4310427771470356, | |
| "grad_norm": 1.75, | |
| "learning_rate": 1.1377983063895306e-05, | |
| "loss": 1.0335, | |
| "num_input_tokens_seen": 106279858, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.44643716204514405, | |
| "grad_norm": 1.6484375, | |
| "learning_rate": 1.1070053887605852e-05, | |
| "loss": 1.0486, | |
| "num_input_tokens_seen": 110042375, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.46183154694325246, | |
| "grad_norm": 1.703125, | |
| "learning_rate": 1.0762124711316398e-05, | |
| "loss": 1.0347, | |
| "num_input_tokens_seen": 113836688, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47722593184136086, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 1.0454195535026945e-05, | |
| "loss": 1.041, | |
| "num_input_tokens_seen": 117581458, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.49262031673946927, | |
| "grad_norm": 1.8359375, | |
| "learning_rate": 1.0146266358737491e-05, | |
| "loss": 1.0357, | |
| "num_input_tokens_seen": 121341275, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5080147016375777, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 9.838337182448037e-06, | |
| "loss": 1.0374, | |
| "num_input_tokens_seen": 125088162, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.5234090865356861, | |
| "grad_norm": 1.4453125, | |
| "learning_rate": 9.530408006158585e-06, | |
| "loss": 1.0255, | |
| "num_input_tokens_seen": 128901749, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.5388034714337945, | |
| "grad_norm": 1.46875, | |
| "learning_rate": 9.22247882986913e-06, | |
| "loss": 1.0282, | |
| "num_input_tokens_seen": 132736866, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.554197856331903, | |
| "grad_norm": 1.6953125, | |
| "learning_rate": 8.914549653579677e-06, | |
| "loss": 1.0398, | |
| "num_input_tokens_seen": 136595429, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5695922412300114, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 8.606620477290224e-06, | |
| "loss": 1.025, | |
| "num_input_tokens_seen": 140426462, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.5849866261281198, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 8.29869130100077e-06, | |
| "loss": 1.0291, | |
| "num_input_tokens_seen": 144234914, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.6003810110262282, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 7.990762124711316e-06, | |
| "loss": 1.0233, | |
| "num_input_tokens_seen": 148032058, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6157753959243366, | |
| "grad_norm": 1.734375, | |
| "learning_rate": 7.682832948421864e-06, | |
| "loss": 1.0347, | |
| "num_input_tokens_seen": 151814536, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.631169780822445, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 7.37490377213241e-06, | |
| "loss": 1.0457, | |
| "num_input_tokens_seen": 155598931, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.6465641657205534, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 7.066974595842957e-06, | |
| "loss": 1.0473, | |
| "num_input_tokens_seen": 159326528, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.6619585506186618, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 6.7590454195535035e-06, | |
| "loss": 1.0482, | |
| "num_input_tokens_seen": 163084806, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.6773529355167702, | |
| "grad_norm": 1.734375, | |
| "learning_rate": 6.4511162432640495e-06, | |
| "loss": 1.0267, | |
| "num_input_tokens_seen": 166891971, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.6927473204148786, | |
| "grad_norm": 1.703125, | |
| "learning_rate": 6.143187066974596e-06, | |
| "loss": 1.0165, | |
| "num_input_tokens_seen": 170700927, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.708141705312987, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 5.835257890685143e-06, | |
| "loss": 1.0386, | |
| "num_input_tokens_seen": 174509215, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.7235360902110956, | |
| "grad_norm": 1.859375, | |
| "learning_rate": 5.52732871439569e-06, | |
| "loss": 1.0286, | |
| "num_input_tokens_seen": 178355672, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.738930475109204, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 5.219399538106236e-06, | |
| "loss": 1.0199, | |
| "num_input_tokens_seen": 182172598, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.7543248600073124, | |
| "grad_norm": 1.7734375, | |
| "learning_rate": 4.911470361816783e-06, | |
| "loss": 1.023, | |
| "num_input_tokens_seen": 185945174, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.7697192449054208, | |
| "grad_norm": 1.4765625, | |
| "learning_rate": 4.6035411855273295e-06, | |
| "loss": 1.0317, | |
| "num_input_tokens_seen": 189723364, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.7851136298035292, | |
| "grad_norm": 1.53125, | |
| "learning_rate": 4.2956120092378755e-06, | |
| "loss": 1.0262, | |
| "num_input_tokens_seen": 193515488, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8005080147016376, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 3.987682832948422e-06, | |
| "loss": 1.0276, | |
| "num_input_tokens_seen": 197294619, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.815902399599746, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 3.6797536566589687e-06, | |
| "loss": 1.0141, | |
| "num_input_tokens_seen": 201079998, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.8312967844978544, | |
| "grad_norm": 1.875, | |
| "learning_rate": 3.3718244803695155e-06, | |
| "loss": 1.0406, | |
| "num_input_tokens_seen": 204892665, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.8466911693959628, | |
| "grad_norm": 1.75, | |
| "learning_rate": 3.063895304080062e-06, | |
| "loss": 1.0144, | |
| "num_input_tokens_seen": 208692509, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.8620855542940712, | |
| "grad_norm": 1.625, | |
| "learning_rate": 2.7559661277906087e-06, | |
| "loss": 1.0328, | |
| "num_input_tokens_seen": 212482079, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.8774799391921797, | |
| "grad_norm": 1.4453125, | |
| "learning_rate": 2.4480369515011547e-06, | |
| "loss": 1.0158, | |
| "num_input_tokens_seen": 216265581, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.8928743240902881, | |
| "grad_norm": 1.421875, | |
| "learning_rate": 2.1401077752117015e-06, | |
| "loss": 1.0376, | |
| "num_input_tokens_seen": 220058453, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.9082687089883965, | |
| "grad_norm": 1.875, | |
| "learning_rate": 1.8321785989222479e-06, | |
| "loss": 1.0116, | |
| "num_input_tokens_seen": 223849666, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.9236630938865049, | |
| "grad_norm": 1.671875, | |
| "learning_rate": 1.5242494226327945e-06, | |
| "loss": 1.0319, | |
| "num_input_tokens_seen": 227586204, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9390574787846133, | |
| "grad_norm": 1.578125, | |
| "learning_rate": 1.216320246343341e-06, | |
| "loss": 1.0248, | |
| "num_input_tokens_seen": 231383644, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.9544518636827217, | |
| "grad_norm": 1.71875, | |
| "learning_rate": 9.083910700538877e-07, | |
| "loss": 1.0252, | |
| "num_input_tokens_seen": 235171998, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.9698462485808301, | |
| "grad_norm": 1.59375, | |
| "learning_rate": 6.004618937644343e-07, | |
| "loss": 1.033, | |
| "num_input_tokens_seen": 238903492, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.9852406334789385, | |
| "grad_norm": 1.671875, | |
| "learning_rate": 2.9253271747498076e-07, | |
| "loss": 1.0206, | |
| "num_input_tokens_seen": 242682149, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.9998652991321415, | |
| "num_input_tokens_seen": 246267812, | |
| "step": 6495, | |
| "total_flos": 1.1089328326722978e+19, | |
| "train_loss": 1.0435700872478528, | |
| "train_runtime": 38249.836, | |
| "train_samples_per_second": 5.434, | |
| "train_steps_per_second": 0.17, | |
| "train_tokens_per_second": 1606.468 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 6495, | |
| "num_input_tokens_seen": 246267812, | |
| "num_train_epochs": 1, | |
| "save_steps": 800, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1089328326722978e+19, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |