| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0, | |
| "loss": 2.9912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.040365853658536587, | |
| "eval_loss": 2.744140625, | |
| "eval_runtime": 4.8585, | |
| "eval_samples_per_second": 20.583, | |
| "eval_steps_per_second": 0.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0, | |
| "loss": 2.9329, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.040365853658536587, | |
| "eval_loss": 2.744140625, | |
| "eval_runtime": 6.3845, | |
| "eval_samples_per_second": 15.663, | |
| "eval_steps_per_second": 0.313, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0, | |
| "loss": 2.9138, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.038902439024390244, | |
| "eval_loss": 2.826171875, | |
| "eval_runtime": 5.4611, | |
| "eval_samples_per_second": 18.311, | |
| "eval_steps_per_second": 0.366, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9395, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.038902439024390244, | |
| "eval_loss": 2.826171875, | |
| "eval_runtime": 6.1625, | |
| "eval_samples_per_second": 16.227, | |
| "eval_steps_per_second": 0.325, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9109, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.03985772357723577, | |
| "eval_loss": 2.794921875, | |
| "eval_runtime": 6.2368, | |
| "eval_samples_per_second": 16.034, | |
| "eval_steps_per_second": 0.321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.04030487804878049, | |
| "eval_loss": 2.74609375, | |
| "eval_runtime": 6.1734, | |
| "eval_samples_per_second": 16.198, | |
| "eval_steps_per_second": 0.324, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9365, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.03985772357723577, | |
| "eval_loss": 2.720703125, | |
| "eval_runtime": 6.2486, | |
| "eval_samples_per_second": 16.004, | |
| "eval_steps_per_second": 0.32, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.040325203252032524, | |
| "eval_loss": 2.70703125, | |
| "eval_runtime": 6.0675, | |
| "eval_samples_per_second": 16.481, | |
| "eval_steps_per_second": 0.33, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.04073170731707317, | |
| "eval_loss": 2.681640625, | |
| "eval_runtime": 6.0505, | |
| "eval_samples_per_second": 16.528, | |
| "eval_steps_per_second": 0.331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5e-05, | |
| "loss": 2.844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.040426829268292684, | |
| "eval_loss": 2.673828125, | |
| "eval_runtime": 5.8947, | |
| "eval_samples_per_second": 16.964, | |
| "eval_steps_per_second": 0.339, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5e-05, | |
| "loss": 2.731, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.04056910569105691, | |
| "eval_loss": 2.66796875, | |
| "eval_runtime": 5.7332, | |
| "eval_samples_per_second": 17.442, | |
| "eval_steps_per_second": 0.349, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7434, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.04040650406504065, | |
| "eval_loss": 2.669921875, | |
| "eval_runtime": 5.6141, | |
| "eval_samples_per_second": 17.812, | |
| "eval_steps_per_second": 0.356, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9043, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.039979674796747966, | |
| "eval_loss": 2.685546875, | |
| "eval_runtime": 5.112, | |
| "eval_samples_per_second": 19.562, | |
| "eval_steps_per_second": 0.391, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8564, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.039979674796747966, | |
| "eval_loss": 2.685546875, | |
| "eval_runtime": 6.1791, | |
| "eval_samples_per_second": 16.184, | |
| "eval_steps_per_second": 0.324, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.039979674796747966, | |
| "eval_loss": 2.685546875, | |
| "eval_runtime": 6.2221, | |
| "eval_samples_per_second": 16.072, | |
| "eval_steps_per_second": 0.321, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.896, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.03975609756097561, | |
| "eval_loss": 2.6953125, | |
| "eval_runtime": 5.7373, | |
| "eval_samples_per_second": 17.43, | |
| "eval_steps_per_second": 0.349, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9858, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.039979674796747966, | |
| "eval_loss": 2.70703125, | |
| "eval_runtime": 5.5135, | |
| "eval_samples_per_second": 18.137, | |
| "eval_steps_per_second": 0.363, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0563, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.040020325203252036, | |
| "eval_loss": 2.728515625, | |
| "eval_runtime": 6.3828, | |
| "eval_samples_per_second": 15.667, | |
| "eval_steps_per_second": 0.313, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 5e-05, | |
| "loss": 2.04, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.03981707317073171, | |
| "eval_loss": 2.767578125, | |
| "eval_runtime": 5.4095, | |
| "eval_samples_per_second": 18.486, | |
| "eval_steps_per_second": 0.37, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.03955284552845528, | |
| "eval_loss": 2.791015625, | |
| "eval_runtime": 5.4272, | |
| "eval_samples_per_second": 18.426, | |
| "eval_steps_per_second": 0.369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5e-05, | |
| "loss": 2.09, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.03930894308943089, | |
| "eval_loss": 2.796875, | |
| "eval_runtime": 6.3475, | |
| "eval_samples_per_second": 15.754, | |
| "eval_steps_per_second": 0.315, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5e-05, | |
| "loss": 2.059, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.03951219512195122, | |
| "eval_loss": 2.810546875, | |
| "eval_runtime": 6.0188, | |
| "eval_samples_per_second": 16.615, | |
| "eval_steps_per_second": 0.332, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0498, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.03975609756097561, | |
| "eval_loss": 2.79296875, | |
| "eval_runtime": 5.4742, | |
| "eval_samples_per_second": 18.268, | |
| "eval_steps_per_second": 0.365, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9568, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.04008130081300813, | |
| "eval_loss": 2.791015625, | |
| "eval_runtime": 5.9198, | |
| "eval_samples_per_second": 16.892, | |
| "eval_steps_per_second": 0.338, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1418, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.039776422764227645, | |
| "eval_loss": 2.79296875, | |
| "eval_runtime": 5.5505, | |
| "eval_samples_per_second": 18.016, | |
| "eval_steps_per_second": 0.36, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5e-05, | |
| "loss": 1.975, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.03967479674796748, | |
| "eval_loss": 2.79296875, | |
| "eval_runtime": 5.108, | |
| "eval_samples_per_second": 19.577, | |
| "eval_steps_per_second": 0.392, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 5e-05, | |
| "loss": 1.996, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.03932926829268293, | |
| "eval_loss": 2.794921875, | |
| "eval_runtime": 5.1867, | |
| "eval_samples_per_second": 19.28, | |
| "eval_steps_per_second": 0.386, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9617, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.03916666666666667, | |
| "eval_loss": 2.8046875, | |
| "eval_runtime": 5.8792, | |
| "eval_samples_per_second": 17.009, | |
| "eval_steps_per_second": 0.34, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2062, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_accuracy": 0.038760162601626014, | |
| "eval_loss": 2.814453125, | |
| "eval_runtime": 5.1614, | |
| "eval_samples_per_second": 19.375, | |
| "eval_steps_per_second": 0.387, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_accuracy": 0.038597560975609756, | |
| "eval_loss": 2.814453125, | |
| "eval_runtime": 5.7986, | |
| "eval_samples_per_second": 17.245, | |
| "eval_steps_per_second": 0.345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9235, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.039004065040650404, | |
| "eval_loss": 2.828125, | |
| "eval_runtime": 6.2602, | |
| "eval_samples_per_second": 15.974, | |
| "eval_steps_per_second": 0.319, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9127, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.03882113821138211, | |
| "eval_loss": 2.857421875, | |
| "eval_runtime": 5.5269, | |
| "eval_samples_per_second": 18.093, | |
| "eval_steps_per_second": 0.362, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 32, | |
| "total_flos": 10341801000960.0, | |
| "train_loss": 2.4493942260742188, | |
| "train_runtime": 515.1457, | |
| "train_samples_per_second": 3.882, | |
| "train_steps_per_second": 0.062 | |
| } | |
| ], | |
| "max_steps": 32, | |
| "num_train_epochs": 2, | |
| "total_flos": 10341801000960.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |