| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.05133992343294669, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 4.2504, | |
| "eval_samples_per_second": 20.234, | |
| "eval_steps_per_second": 1.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.05133992343294669, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 3.4208, | |
| "eval_samples_per_second": 25.14, | |
| "eval_steps_per_second": 1.754, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.9912069357315394e-05, | |
| "loss": 2.5964, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.05192560425118565, | |
| "eval_loss": 2.560546875, | |
| "eval_runtime": 4.3956, | |
| "eval_samples_per_second": 19.565, | |
| "eval_steps_per_second": 1.365, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.96493083356513e-05, | |
| "loss": 2.7302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.05265413404948289, | |
| "eval_loss": 2.5234375, | |
| "eval_runtime": 4.277, | |
| "eval_samples_per_second": 20.107, | |
| "eval_steps_per_second": 1.403, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.9214797567742036e-05, | |
| "loss": 2.7, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.05283983772355865, | |
| "eval_loss": 2.5078125, | |
| "eval_runtime": 4.3806, | |
| "eval_samples_per_second": 19.632, | |
| "eval_steps_per_second": 1.37, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.861363129506436e-05, | |
| "loss": 2.5674, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.05323981486772184, | |
| "eval_loss": 2.494140625, | |
| "eval_runtime": 4.3576, | |
| "eval_samples_per_second": 19.736, | |
| "eval_steps_per_second": 1.377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 2.6406, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.0533683789497743, | |
| "eval_loss": 2.48828125, | |
| "eval_runtime": 3.6815, | |
| "eval_samples_per_second": 23.36, | |
| "eval_steps_per_second": 1.63, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.6941395985584656e-05, | |
| "loss": 2.5315, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.05362550711387921, | |
| "eval_loss": 2.48046875, | |
| "eval_runtime": 4.3687, | |
| "eval_samples_per_second": 19.686, | |
| "eval_steps_per_second": 1.373, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.5889932378846963e-05, | |
| "loss": 2.7202, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.05369693160390835, | |
| "eval_loss": 2.47265625, | |
| "eval_runtime": 4.3981, | |
| "eval_samples_per_second": 19.554, | |
| "eval_steps_per_second": 1.364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.4710794271727415e-05, | |
| "loss": 2.5144, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.05362550711387921, | |
| "eval_loss": 2.46484375, | |
| "eval_runtime": 4.3729, | |
| "eval_samples_per_second": 19.667, | |
| "eval_steps_per_second": 1.372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.341780598043574e-05, | |
| "loss": 2.4983, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.05366836180789669, | |
| "eval_loss": 2.451171875, | |
| "eval_runtime": 3.9723, | |
| "eval_samples_per_second": 21.65, | |
| "eval_steps_per_second": 1.51, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.2026126610496852e-05, | |
| "loss": 2.7029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.05386835037997829, | |
| "eval_loss": 2.44140625, | |
| "eval_runtime": 3.3723, | |
| "eval_samples_per_second": 25.502, | |
| "eval_steps_per_second": 1.779, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.055207233009872e-05, | |
| "loss": 2.5198, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.054039769156048224, | |
| "eval_loss": 2.43359375, | |
| "eval_runtime": 4.2557, | |
| "eval_samples_per_second": 20.208, | |
| "eval_steps_per_second": 1.41, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.9012925077938318e-05, | |
| "loss": 2.5706, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.0544826009942289, | |
| "eval_loss": 2.42578125, | |
| "eval_runtime": 4.3775, | |
| "eval_samples_per_second": 19.646, | |
| "eval_steps_per_second": 1.371, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.7426729948291474e-05, | |
| "loss": 2.5688, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.054768298954345464, | |
| "eval_loss": 2.41796875, | |
| "eval_runtime": 3.7002, | |
| "eval_samples_per_second": 23.242, | |
| "eval_steps_per_second": 1.622, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.5812083628781265e-05, | |
| "loss": 2.3793, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.05518256099651449, | |
| "eval_loss": 2.41015625, | |
| "eval_runtime": 4.2835, | |
| "eval_samples_per_second": 20.077, | |
| "eval_steps_per_second": 1.401, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.4187916371218739e-05, | |
| "loss": 2.4785, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.055353979772584425, | |
| "eval_loss": 2.404296875, | |
| "eval_runtime": 4.3709, | |
| "eval_samples_per_second": 19.676, | |
| "eval_steps_per_second": 1.373, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.2573270051708529e-05, | |
| "loss": 2.4688, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.05529684018056111, | |
| "eval_loss": 2.3984375, | |
| "eval_runtime": 3.974, | |
| "eval_samples_per_second": 21.641, | |
| "eval_steps_per_second": 1.51, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.2573270051708529e-05, | |
| "loss": 2.5674, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.05529684018056111, | |
| "eval_loss": 2.3984375, | |
| "eval_runtime": 3.4463, | |
| "eval_samples_per_second": 24.954, | |
| "eval_steps_per_second": 1.741, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.098707492206169e-05, | |
| "loss": 2.5054, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.05536826467059025, | |
| "eval_loss": 2.39453125, | |
| "eval_runtime": 4.3854, | |
| "eval_samples_per_second": 19.61, | |
| "eval_steps_per_second": 1.368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.447927669901284e-06, | |
| "loss": 2.452, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.055511113650648536, | |
| "eval_loss": 2.388671875, | |
| "eval_runtime": 4.3743, | |
| "eval_samples_per_second": 19.66, | |
| "eval_steps_per_second": 1.372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.97387338950315e-06, | |
| "loss": 2.5999, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.05558253814067768, | |
| "eval_loss": 2.3828125, | |
| "eval_runtime": 4.3782, | |
| "eval_samples_per_second": 19.643, | |
| "eval_steps_per_second": 1.37, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.582194019564266e-06, | |
| "loss": 2.3665, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.055596823038683504, | |
| "eval_loss": 2.37890625, | |
| "eval_runtime": 4.2553, | |
| "eval_samples_per_second": 20.21, | |
| "eval_steps_per_second": 1.41, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.289205728272587e-06, | |
| "loss": 2.6223, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.055653962630706814, | |
| "eval_loss": 2.375, | |
| "eval_runtime": 3.3625, | |
| "eval_samples_per_second": 25.576, | |
| "eval_steps_per_second": 1.784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.110067621153041e-06, | |
| "loss": 2.3562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.055653962630706814, | |
| "eval_loss": 2.37109375, | |
| "eval_runtime": 4.3982, | |
| "eval_samples_per_second": 19.554, | |
| "eval_steps_per_second": 1.364, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.0586040144153436e-06, | |
| "loss": 2.429, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.0556968173247243, | |
| "eval_loss": 2.369140625, | |
| "eval_runtime": 4.3664, | |
| "eval_samples_per_second": 19.696, | |
| "eval_steps_per_second": 1.374, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.1471423574861643e-06, | |
| "loss": 2.563, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.0557968116107651, | |
| "eval_loss": 2.3671875, | |
| "eval_runtime": 3.6475, | |
| "eval_samples_per_second": 23.578, | |
| "eval_steps_per_second": 1.645, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3863687049356465e-06, | |
| "loss": 2.4573, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.055753956916747616, | |
| "eval_loss": 2.365234375, | |
| "eval_runtime": 4.2765, | |
| "eval_samples_per_second": 20.11, | |
| "eval_steps_per_second": 1.403, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.852024322579649e-07, | |
| "loss": 2.4883, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.05582538140677676, | |
| "eval_loss": 2.365234375, | |
| "eval_runtime": 4.3983, | |
| "eval_samples_per_second": 19.553, | |
| "eval_steps_per_second": 1.364, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 29, | |
| "total_flos": 1557448359936.0, | |
| "train_loss": 2.5467823949353448, | |
| "train_runtime": 555.4959, | |
| "train_samples_per_second": 0.826, | |
| "train_steps_per_second": 0.052 | |
| } | |
| ], | |
| "max_steps": 29, | |
| "num_train_epochs": 1, | |
| "total_flos": 1557448359936.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |