| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0, | |
| "loss": 3.2024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.038495934959349595, | |
| "eval_loss": 2.912109375, | |
| "eval_runtime": 2.0553, | |
| "eval_samples_per_second": 48.656, | |
| "eval_steps_per_second": 0.973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0, | |
| "loss": 3.1226, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.038495934959349595, | |
| "eval_loss": 2.912109375, | |
| "eval_runtime": 2.5287, | |
| "eval_samples_per_second": 39.546, | |
| "eval_steps_per_second": 0.791, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0, | |
| "loss": 3.1321, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.03936991869918699, | |
| "eval_loss": 2.84765625, | |
| "eval_runtime": 2.4969, | |
| "eval_samples_per_second": 40.05, | |
| "eval_steps_per_second": 0.801, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.03936991869918699, | |
| "eval_loss": 2.84765625, | |
| "eval_runtime": 2.5942, | |
| "eval_samples_per_second": 38.548, | |
| "eval_steps_per_second": 0.771, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9717, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.03910569105691057, | |
| "eval_loss": 2.85546875, | |
| "eval_runtime": 2.4958, | |
| "eval_samples_per_second": 40.068, | |
| "eval_steps_per_second": 0.801, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.03920731707317073, | |
| "eval_loss": 2.84375, | |
| "eval_runtime": 2.6044, | |
| "eval_samples_per_second": 38.396, | |
| "eval_steps_per_second": 0.768, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0376, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.03957317073170732, | |
| "eval_loss": 2.818359375, | |
| "eval_runtime": 2.2607, | |
| "eval_samples_per_second": 44.235, | |
| "eval_steps_per_second": 0.885, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8164, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.039532520325203255, | |
| "eval_loss": 2.798828125, | |
| "eval_runtime": 2.0579, | |
| "eval_samples_per_second": 48.594, | |
| "eval_steps_per_second": 0.972, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.03936991869918699, | |
| "eval_loss": 2.798828125, | |
| "eval_runtime": 2.0436, | |
| "eval_samples_per_second": 48.933, | |
| "eval_steps_per_second": 0.979, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9492, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.03947154471544716, | |
| "eval_loss": 2.796875, | |
| "eval_runtime": 2.6006, | |
| "eval_samples_per_second": 38.452, | |
| "eval_steps_per_second": 0.769, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8633, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.03947154471544716, | |
| "eval_loss": 2.796875, | |
| "eval_runtime": 2.0146, | |
| "eval_samples_per_second": 49.639, | |
| "eval_steps_per_second": 0.993, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8994, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.03979674796747967, | |
| "eval_loss": 2.791015625, | |
| "eval_runtime": 1.8459, | |
| "eval_samples_per_second": 54.174, | |
| "eval_steps_per_second": 1.083, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0024, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.040121951219512196, | |
| "eval_loss": 2.78125, | |
| "eval_runtime": 2.5067, | |
| "eval_samples_per_second": 39.892, | |
| "eval_steps_per_second": 0.798, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5e-05, | |
| "loss": 2.937, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.03991869918699187, | |
| "eval_loss": 2.78125, | |
| "eval_runtime": 2.3271, | |
| "eval_samples_per_second": 42.972, | |
| "eval_steps_per_second": 0.859, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9963, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.039878048780487806, | |
| "eval_loss": 2.78125, | |
| "eval_runtime": 1.8105, | |
| "eval_samples_per_second": 55.232, | |
| "eval_steps_per_second": 1.105, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0168, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.04, | |
| "eval_loss": 2.775390625, | |
| "eval_runtime": 2.6001, | |
| "eval_samples_per_second": 38.46, | |
| "eval_steps_per_second": 0.769, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2589, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.03971544715447155, | |
| "eval_loss": 2.771484375, | |
| "eval_runtime": 2.0378, | |
| "eval_samples_per_second": 49.072, | |
| "eval_steps_per_second": 0.981, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2568, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.03951219512195122, | |
| "eval_loss": 2.779296875, | |
| "eval_runtime": 2.5986, | |
| "eval_samples_per_second": 38.482, | |
| "eval_steps_per_second": 0.77, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3138, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.03930894308943089, | |
| "eval_loss": 2.802734375, | |
| "eval_runtime": 2.2441, | |
| "eval_samples_per_second": 44.561, | |
| "eval_steps_per_second": 0.891, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2759, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.039288617886178864, | |
| "eval_loss": 2.818359375, | |
| "eval_runtime": 2.3006, | |
| "eval_samples_per_second": 43.467, | |
| "eval_steps_per_second": 0.869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5137, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.039044715447154474, | |
| "eval_loss": 2.826171875, | |
| "eval_runtime": 2.6018, | |
| "eval_samples_per_second": 38.434, | |
| "eval_steps_per_second": 0.769, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2997, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.03878048780487805, | |
| "eval_loss": 2.83203125, | |
| "eval_runtime": 2.6159, | |
| "eval_samples_per_second": 38.228, | |
| "eval_steps_per_second": 0.765, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2693, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.03916666666666667, | |
| "eval_loss": 2.8359375, | |
| "eval_runtime": 2.0432, | |
| "eval_samples_per_second": 48.943, | |
| "eval_steps_per_second": 0.979, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5e-05, | |
| "loss": 2.204, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.038739837398373986, | |
| "eval_loss": 2.837890625, | |
| "eval_runtime": 2.2494, | |
| "eval_samples_per_second": 44.456, | |
| "eval_steps_per_second": 0.889, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.039146341463414634, | |
| "eval_loss": 2.8359375, | |
| "eval_runtime": 2.0551, | |
| "eval_samples_per_second": 48.659, | |
| "eval_steps_per_second": 0.973, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3448, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.03910569105691057, | |
| "eval_loss": 2.833984375, | |
| "eval_runtime": 2.6076, | |
| "eval_samples_per_second": 38.349, | |
| "eval_steps_per_second": 0.767, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 5e-05, | |
| "loss": 2.217, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.03910569105691057, | |
| "eval_loss": 2.8359375, | |
| "eval_runtime": 1.8526, | |
| "eval_samples_per_second": 53.979, | |
| "eval_steps_per_second": 1.08, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3082, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.038455284552845526, | |
| "eval_loss": 2.837890625, | |
| "eval_runtime": 2.2452, | |
| "eval_samples_per_second": 44.54, | |
| "eval_steps_per_second": 0.891, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2878, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_accuracy": 0.03855691056910569, | |
| "eval_loss": 2.837890625, | |
| "eval_runtime": 2.2035, | |
| "eval_samples_per_second": 45.381, | |
| "eval_steps_per_second": 0.908, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_accuracy": 0.03847560975609756, | |
| "eval_loss": 2.837890625, | |
| "eval_runtime": 2.0495, | |
| "eval_samples_per_second": 48.792, | |
| "eval_steps_per_second": 0.976, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2838, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.03851626016260162, | |
| "eval_loss": 2.8359375, | |
| "eval_runtime": 2.5995, | |
| "eval_samples_per_second": 38.469, | |
| "eval_steps_per_second": 0.769, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4038, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.038739837398373986, | |
| "eval_loss": 2.837890625, | |
| "eval_runtime": 2.6048, | |
| "eval_samples_per_second": 38.391, | |
| "eval_steps_per_second": 0.768, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8481, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.03841463414634146, | |
| "eval_loss": 2.85546875, | |
| "eval_runtime": 2.6153, | |
| "eval_samples_per_second": 38.237, | |
| "eval_steps_per_second": 0.765, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5e-05, | |
| "loss": 1.657, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.038211382113821135, | |
| "eval_loss": 2.896484375, | |
| "eval_runtime": 2.1039, | |
| "eval_samples_per_second": 47.53, | |
| "eval_steps_per_second": 0.951, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6996, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.03804878048780488, | |
| "eval_loss": 2.958984375, | |
| "eval_runtime": 2.051, | |
| "eval_samples_per_second": 48.757, | |
| "eval_steps_per_second": 0.975, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6741, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.037865853658536584, | |
| "eval_loss": 3.03125, | |
| "eval_runtime": 2.6053, | |
| "eval_samples_per_second": 38.383, | |
| "eval_steps_per_second": 0.768, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 5e-05, | |
| "loss": 1.594, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.037967479674796745, | |
| "eval_loss": 3.041015625, | |
| "eval_runtime": 2.5975, | |
| "eval_samples_per_second": 38.498, | |
| "eval_steps_per_second": 0.77, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5201, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.038109756097560975, | |
| "eval_loss": 3.015625, | |
| "eval_runtime": 2.6045, | |
| "eval_samples_per_second": 38.396, | |
| "eval_steps_per_second": 0.768, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5149, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.03798780487804878, | |
| "eval_loss": 3.013671875, | |
| "eval_runtime": 2.3613, | |
| "eval_samples_per_second": 42.349, | |
| "eval_steps_per_second": 0.847, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5521, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.03788617886178862, | |
| "eval_loss": 3.017578125, | |
| "eval_runtime": 2.601, | |
| "eval_samples_per_second": 38.446, | |
| "eval_steps_per_second": 0.769, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5364, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.03780487804878049, | |
| "eval_loss": 3.02734375, | |
| "eval_runtime": 2.6044, | |
| "eval_samples_per_second": 38.397, | |
| "eval_steps_per_second": 0.768, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.037967479674796745, | |
| "eval_loss": 3.0390625, | |
| "eval_runtime": 2.5064, | |
| "eval_samples_per_second": 39.899, | |
| "eval_steps_per_second": 0.798, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4794, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_accuracy": 0.038008130081300814, | |
| "eval_loss": 3.048828125, | |
| "eval_runtime": 2.1015, | |
| "eval_samples_per_second": 47.584, | |
| "eval_steps_per_second": 0.952, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4313, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_accuracy": 0.03782520325203252, | |
| "eval_loss": 3.052734375, | |
| "eval_runtime": 2.4538, | |
| "eval_samples_per_second": 40.753, | |
| "eval_steps_per_second": 0.815, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5071, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.03784552845528455, | |
| "eval_loss": 3.046875, | |
| "eval_runtime": 2.1003, | |
| "eval_samples_per_second": 47.611, | |
| "eval_steps_per_second": 0.952, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4799, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.037764227642276424, | |
| "eval_loss": 3.044921875, | |
| "eval_runtime": 2.6039, | |
| "eval_samples_per_second": 38.404, | |
| "eval_steps_per_second": 0.768, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5e-05, | |
| "loss": 1.521, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.037967479674796745, | |
| "eval_loss": 3.037109375, | |
| "eval_runtime": 2.6013, | |
| "eval_samples_per_second": 38.443, | |
| "eval_steps_per_second": 0.769, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4603, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.03788617886178862, | |
| "eval_loss": 3.041015625, | |
| "eval_runtime": 2.0826, | |
| "eval_samples_per_second": 48.016, | |
| "eval_steps_per_second": 0.96, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 5e-05, | |
| "loss": 1.25, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.03813008130081301, | |
| "eval_loss": 3.0859375, | |
| "eval_runtime": 2.5454, | |
| "eval_samples_per_second": 39.287, | |
| "eval_steps_per_second": 0.786, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0411, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.03754065040650407, | |
| "eval_loss": 3.1796875, | |
| "eval_runtime": 2.6016, | |
| "eval_samples_per_second": 38.438, | |
| "eval_steps_per_second": 0.769, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0385, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.037113821138211385, | |
| "eval_loss": 3.296875, | |
| "eval_runtime": 2.6072, | |
| "eval_samples_per_second": 38.355, | |
| "eval_steps_per_second": 0.767, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0254, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.03670731707317073, | |
| "eval_loss": 3.361328125, | |
| "eval_runtime": 2.2651, | |
| "eval_samples_per_second": 44.148, | |
| "eval_steps_per_second": 0.883, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9656, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_accuracy": 0.036829268292682925, | |
| "eval_loss": 3.36328125, | |
| "eval_runtime": 2.6237, | |
| "eval_samples_per_second": 38.115, | |
| "eval_steps_per_second": 0.762, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5e-05, | |
| "loss": 1.036, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_accuracy": 0.03664634146341463, | |
| "eval_loss": 3.3359375, | |
| "eval_runtime": 2.5895, | |
| "eval_samples_per_second": 38.618, | |
| "eval_steps_per_second": 0.772, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9366, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_accuracy": 0.036565040650406506, | |
| "eval_loss": 3.294921875, | |
| "eval_runtime": 2.2574, | |
| "eval_samples_per_second": 44.298, | |
| "eval_steps_per_second": 0.886, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9712, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.03666666666666667, | |
| "eval_loss": 3.26953125, | |
| "eval_runtime": 2.6146, | |
| "eval_samples_per_second": 38.247, | |
| "eval_steps_per_second": 0.765, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0066, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_accuracy": 0.036565040650406506, | |
| "eval_loss": 3.267578125, | |
| "eval_runtime": 2.6062, | |
| "eval_samples_per_second": 38.37, | |
| "eval_steps_per_second": 0.767, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9952, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_accuracy": 0.03676829268292683, | |
| "eval_loss": 3.27734375, | |
| "eval_runtime": 2.5965, | |
| "eval_samples_per_second": 38.513, | |
| "eval_steps_per_second": 0.77, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0352, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.0366869918699187, | |
| "eval_loss": 3.2890625, | |
| "eval_runtime": 2.3047, | |
| "eval_samples_per_second": 43.39, | |
| "eval_steps_per_second": 0.868, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0212, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_accuracy": 0.036178861788617886, | |
| "eval_loss": 3.31640625, | |
| "eval_runtime": 2.6015, | |
| "eval_samples_per_second": 38.439, | |
| "eval_steps_per_second": 0.769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9468, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_accuracy": 0.036036585365853656, | |
| "eval_loss": 3.3203125, | |
| "eval_runtime": 2.2607, | |
| "eval_samples_per_second": 44.233, | |
| "eval_steps_per_second": 0.885, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9155, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_accuracy": 0.03664634146341463, | |
| "eval_loss": 3.322265625, | |
| "eval_runtime": 2.6074, | |
| "eval_samples_per_second": 38.352, | |
| "eval_steps_per_second": 0.767, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8552, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.03701219512195122, | |
| "eval_loss": 3.326171875, | |
| "eval_runtime": 2.2425, | |
| "eval_samples_per_second": 44.594, | |
| "eval_steps_per_second": 0.892, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9575, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.03699186991869919, | |
| "eval_loss": 3.333984375, | |
| "eval_runtime": 2.0082, | |
| "eval_samples_per_second": 49.796, | |
| "eval_steps_per_second": 0.996, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6384, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_accuracy": 0.036971544715447155, | |
| "eval_loss": 3.375, | |
| "eval_runtime": 2.5098, | |
| "eval_samples_per_second": 39.844, | |
| "eval_steps_per_second": 0.797, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6436, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_accuracy": 0.03636178861788618, | |
| "eval_loss": 3.4453125, | |
| "eval_runtime": 2.6062, | |
| "eval_samples_per_second": 38.37, | |
| "eval_steps_per_second": 0.767, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5752, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_accuracy": 0.035792682926829265, | |
| "eval_loss": 3.5390625, | |
| "eval_runtime": 2.6001, | |
| "eval_samples_per_second": 38.46, | |
| "eval_steps_per_second": 0.769, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6542, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "eval_accuracy": 0.03540650406504065, | |
| "eval_loss": 3.6015625, | |
| "eval_runtime": 2.4568, | |
| "eval_samples_per_second": 40.704, | |
| "eval_steps_per_second": 0.814, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6724, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_accuracy": 0.03540650406504065, | |
| "eval_loss": 3.6015625, | |
| "eval_runtime": 2.0755, | |
| "eval_samples_per_second": 48.182, | |
| "eval_steps_per_second": 0.964, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 5e-05, | |
| "loss": 0.591, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.03591463414634146, | |
| "eval_loss": 3.59375, | |
| "eval_runtime": 2.3021, | |
| "eval_samples_per_second": 43.439, | |
| "eval_steps_per_second": 0.869, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5346, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_accuracy": 0.03613821138211382, | |
| "eval_loss": 3.580078125, | |
| "eval_runtime": 2.0073, | |
| "eval_samples_per_second": 49.819, | |
| "eval_steps_per_second": 0.996, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5112, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_accuracy": 0.036077235772357726, | |
| "eval_loss": 3.576171875, | |
| "eval_runtime": 2.6065, | |
| "eval_samples_per_second": 38.365, | |
| "eval_steps_per_second": 0.767, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5443, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_accuracy": 0.03619918699186992, | |
| "eval_loss": 3.583984375, | |
| "eval_runtime": 2.6395, | |
| "eval_samples_per_second": 37.886, | |
| "eval_steps_per_second": 0.758, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5689, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "eval_accuracy": 0.035833333333333335, | |
| "eval_loss": 3.615234375, | |
| "eval_runtime": 2.4972, | |
| "eval_samples_per_second": 40.046, | |
| "eval_steps_per_second": 0.801, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5667, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_accuracy": 0.0357520325203252, | |
| "eval_loss": 3.6328125, | |
| "eval_runtime": 2.4508, | |
| "eval_samples_per_second": 40.803, | |
| "eval_steps_per_second": 0.816, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 5e-05, | |
| "loss": 0.554, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_accuracy": 0.03573170731707317, | |
| "eval_loss": 3.634765625, | |
| "eval_runtime": 2.0574, | |
| "eval_samples_per_second": 48.604, | |
| "eval_steps_per_second": 0.972, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6087, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_accuracy": 0.03552845528455285, | |
| "eval_loss": 3.625, | |
| "eval_runtime": 2.6082, | |
| "eval_samples_per_second": 38.34, | |
| "eval_steps_per_second": 0.767, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5236, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_accuracy": 0.03552845528455285, | |
| "eval_loss": 3.615234375, | |
| "eval_runtime": 1.8631, | |
| "eval_samples_per_second": 53.674, | |
| "eval_steps_per_second": 1.073, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5458, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_accuracy": 0.03550813008130081, | |
| "eval_loss": 3.578125, | |
| "eval_runtime": 2.6009, | |
| "eval_samples_per_second": 38.449, | |
| "eval_steps_per_second": 0.769, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5702, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.03550813008130081, | |
| "eval_loss": 3.548828125, | |
| "eval_runtime": 2.5127, | |
| "eval_samples_per_second": 39.798, | |
| "eval_steps_per_second": 0.796, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 80, | |
| "total_flos": 9903514583040.0, | |
| "train_loss": 1.6890087127685547, | |
| "train_runtime": 406.6939, | |
| "train_samples_per_second": 12.294, | |
| "train_steps_per_second": 0.197 | |
| } | |
| ], | |
| "max_steps": 80, | |
| "num_train_epochs": 5, | |
| "total_flos": 9903514583040.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |