| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 2.17, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.06213930632535284, | |
| "eval_loss": 2.0546875, | |
| "eval_runtime": 3.2113, | |
| "eval_samples_per_second": 26.781, | |
| "eval_steps_per_second": 0.934, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1814, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.06213930632535284, | |
| "eval_loss": 2.0546875, | |
| "eval_runtime": 3.0319, | |
| "eval_samples_per_second": 28.365, | |
| "eval_steps_per_second": 0.989, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.99178284305241e-05, | |
| "loss": 2.0963, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.06251071367350437, | |
| "eval_loss": 2.0234375, | |
| "eval_runtime": 3.4167, | |
| "eval_samples_per_second": 25.17, | |
| "eval_steps_per_second": 0.878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.9672214011007087e-05, | |
| "loss": 2.1383, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.062453574081481056, | |
| "eval_loss": 2.01953125, | |
| "eval_runtime": 3.4275, | |
| "eval_samples_per_second": 25.091, | |
| "eval_steps_per_second": 0.875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 2.1625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.062453574081481056, | |
| "eval_loss": 2.01953125, | |
| "eval_runtime": 3.4165, | |
| "eval_samples_per_second": 25.172, | |
| "eval_steps_per_second": 0.878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.8703181864639013e-05, | |
| "loss": 2.1808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.06241071938746357, | |
| "eval_loss": 2.015625, | |
| "eval_runtime": 3.0274, | |
| "eval_samples_per_second": 28.408, | |
| "eval_steps_per_second": 0.991, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.7990381056766583e-05, | |
| "loss": 2.1587, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.06255356836752185, | |
| "eval_loss": 2.017578125, | |
| "eval_runtime": 3.4415, | |
| "eval_samples_per_second": 24.989, | |
| "eval_steps_per_second": 0.872, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 2.0847, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.06273927204159763, | |
| "eval_loss": 2.013671875, | |
| "eval_runtime": 3.4339, | |
| "eval_samples_per_second": 25.045, | |
| "eval_steps_per_second": 0.874, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 2.0336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.06273927204159763, | |
| "eval_loss": 2.013671875, | |
| "eval_runtime": 3.4267, | |
| "eval_samples_per_second": 25.097, | |
| "eval_steps_per_second": 0.875, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.6147172382160913e-05, | |
| "loss": 2.1777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.06286783612365007, | |
| "eval_loss": 2.005859375, | |
| "eval_runtime": 3.4314, | |
| "eval_samples_per_second": 25.062, | |
| "eval_steps_per_second": 0.874, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.5036959095382875e-05, | |
| "loss": 2.2034, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.06299640020570253, | |
| "eval_loss": 2.0, | |
| "eval_runtime": 3.0112, | |
| "eval_samples_per_second": 28.56, | |
| "eval_steps_per_second": 0.996, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.3816778784387097e-05, | |
| "loss": 2.1665, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.06283926632763842, | |
| "eval_loss": 1.994140625, | |
| "eval_runtime": 2.8048, | |
| "eval_samples_per_second": 30.661, | |
| "eval_steps_per_second": 1.07, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.0352, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.0628821210216559, | |
| "eval_loss": 1.98828125, | |
| "eval_runtime": 2.7144, | |
| "eval_samples_per_second": 31.682, | |
| "eval_steps_per_second": 1.105, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.1101049646137008e-05, | |
| "loss": 2.1263, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.06281069653162677, | |
| "eval_loss": 1.9833984375, | |
| "eval_runtime": 3.4127, | |
| "eval_samples_per_second": 25.2, | |
| "eval_steps_per_second": 0.879, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 2.1282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.06315353408376664, | |
| "eval_loss": 1.978515625, | |
| "eval_runtime": 3.4158, | |
| "eval_samples_per_second": 25.177, | |
| "eval_steps_per_second": 0.878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.8118675362266388e-05, | |
| "loss": 1.7159, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.0633392377578424, | |
| "eval_loss": 1.9765625, | |
| "eval_runtime": 3.3102, | |
| "eval_samples_per_second": 25.98, | |
| "eval_steps_per_second": 0.906, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.6567926949014805e-05, | |
| "loss": 1.8346, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.06351065653391234, | |
| "eval_loss": 1.9775390625, | |
| "eval_runtime": 2.7366, | |
| "eval_samples_per_second": 31.426, | |
| "eval_steps_per_second": 1.096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.7183, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.06342494714587738, | |
| "eval_loss": 1.982421875, | |
| "eval_runtime": 3.4207, | |
| "eval_samples_per_second": 25.141, | |
| "eval_steps_per_second": 0.877, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.3432073050985201e-05, | |
| "loss": 1.6086, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.06346780183989487, | |
| "eval_loss": 1.98828125, | |
| "eval_runtime": 3.4214, | |
| "eval_samples_per_second": 25.136, | |
| "eval_steps_per_second": 0.877, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.1881324637733613e-05, | |
| "loss": 1.6497, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_accuracy": 0.0634392320438832, | |
| "eval_loss": 1.9892578125, | |
| "eval_runtime": 3.3147, | |
| "eval_samples_per_second": 25.945, | |
| "eval_steps_per_second": 0.905, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 1.6267, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.06368207530998228, | |
| "eval_loss": 1.9853515625, | |
| "eval_runtime": 2.7501, | |
| "eval_samples_per_second": 31.272, | |
| "eval_steps_per_second": 1.091, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.898950353863e-06, | |
| "loss": 1.5962, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_accuracy": 0.06368207530998228, | |
| "eval_loss": 1.9765625, | |
| "eval_runtime": 3.1007, | |
| "eval_samples_per_second": 27.736, | |
| "eval_steps_per_second": 0.968, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.500000000000004e-06, | |
| "loss": 1.5168, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.06372493000399977, | |
| "eval_loss": 1.9697265625, | |
| "eval_runtime": 3.0137, | |
| "eval_samples_per_second": 28.536, | |
| "eval_steps_per_second": 0.995, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.1832212156129045e-06, | |
| "loss": 1.6213, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.06372493000399977, | |
| "eval_loss": 1.9619140625, | |
| "eval_runtime": 3.4172, | |
| "eval_samples_per_second": 25.167, | |
| "eval_steps_per_second": 0.878, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.963040904617131e-06, | |
| "loss": 1.4789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.06382492429004057, | |
| "eval_loss": 1.9580078125, | |
| "eval_runtime": 2.7014, | |
| "eval_samples_per_second": 31.836, | |
| "eval_steps_per_second": 1.111, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.852827617839085e-06, | |
| "loss": 1.6796, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.06378206959602309, | |
| "eval_loss": 1.955078125, | |
| "eval_runtime": 3.0318, | |
| "eval_samples_per_second": 28.366, | |
| "eval_steps_per_second": 0.99, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 1.5964, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.06383920918804639, | |
| "eval_loss": 1.953125, | |
| "eval_runtime": 3.4212, | |
| "eval_samples_per_second": 25.137, | |
| "eval_steps_per_second": 0.877, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0096189432334194e-06, | |
| "loss": 1.787, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.0639392034740872, | |
| "eval_loss": 1.951171875, | |
| "eval_runtime": 3.4776, | |
| "eval_samples_per_second": 24.729, | |
| "eval_steps_per_second": 0.863, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.2968181353609854e-06, | |
| "loss": 1.6536, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.0639963430661105, | |
| "eval_loss": 1.94921875, | |
| "eval_runtime": 3.3251, | |
| "eval_samples_per_second": 25.864, | |
| "eval_steps_per_second": 0.902, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.341522555726971e-07, | |
| "loss": 1.7178, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.06395348837209303, | |
| "eval_loss": 1.9482421875, | |
| "eval_runtime": 3.013, | |
| "eval_samples_per_second": 28.543, | |
| "eval_steps_per_second": 0.996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 30, | |
| "total_flos": 3114896719872.0, | |
| "train_loss": 1.8948323567708334, | |
| "train_runtime": 176.8477, | |
| "train_samples_per_second": 5.191, | |
| "train_steps_per_second": 0.17 | |
| } | |
| ], | |
| "max_steps": 30, | |
| "num_train_epochs": 2, | |
| "total_flos": 3114896719872.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |