| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 22, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.3955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.3998, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 2.516, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.3958, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.3902, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 2.299, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.997718922447667e-05, | |
| "loss": 2.1911, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.990877771116589e-05, | |
| "loss": 2.2146, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.979482788085454e-05, | |
| "loss": 2.0744, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 2.0069, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.943077061037671e-05, | |
| "loss": 2.1008, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.918099534735718e-05, | |
| "loss": 1.8843, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.888634581854234e-05, | |
| "loss": 1.8236, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 2.1407, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.816354005237583e-05, | |
| "loss": 2.1441, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.773604332542729e-05, | |
| "loss": 2.0154, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.726499075173201e-05, | |
| "loss": 1.8462, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 2.0586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0088, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.559499229960451e-05, | |
| "loss": 1.9887, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.495440568827129e-05, | |
| "loss": 2.0002, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 1.9048, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.921988606452942, | |
| "eval_runtime": 62.7536, | |
| "eval_samples_per_second": 1.753, | |
| "eval_steps_per_second": 0.223, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.355080099977578e-05, | |
| "loss": 1.8774, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.278906361507238e-05, | |
| "loss": 1.9554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.19882841613699e-05, | |
| "loss": 1.8387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 1.7612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.02725566275473e-05, | |
| "loss": 2.0803, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 8.935917403045251e-05, | |
| "loss": 1.9799, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 8.840987890201403e-05, | |
| "loss": 2.0421, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 1.9403, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.640704769378942e-05, | |
| "loss": 1.8666, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0529, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.427137111675199e-05, | |
| "loss": 1.8445, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.315613291203976e-05, | |
| "loss": 1.8299, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.201064202312441e-05, | |
| "loss": 1.8462, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.083594363142717e-05, | |
| "loss": 1.8504, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.963310956820085e-05, | |
| "loss": 1.7768, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 1.7158, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.714744911007394e-05, | |
| "loss": 1.6559, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.586689070888284e-05, | |
| "loss": 2.0479, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.456273055419388e-05, | |
| "loss": 2.0672, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.323615860218843e-05, | |
| "loss": 2.0359, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.188838525826702e-05, | |
| "loss": 2.0495, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.052064027263786e-05, | |
| "loss": 1.824, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8808680772781372, | |
| "eval_runtime": 62.6947, | |
| "eval_samples_per_second": 1.755, | |
| "eval_steps_per_second": 0.223, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 1.9359, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 6.631013946104347e-05, | |
| "loss": 1.9485, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.487515269276016e-05, | |
| "loss": 1.8043, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.342659337371885e-05, | |
| "loss": 1.9166, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 6.19657832143779e-05, | |
| "loss": 1.8612, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.049405510324238e-05, | |
| "loss": 1.8936, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.90127518906953e-05, | |
| "loss": 1.6797, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.752322516373916e-05, | |
| "loss": 1.951, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 1.9156, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.45249437914819e-05, | |
| "loss": 1.804, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.3018924871114305e-05, | |
| "loss": 1.9628, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.151015139004445e-05, | |
| "loss": 1.8577, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0029, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.848984860995557e-05, | |
| "loss": 1.765, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.6981075128885693e-05, | |
| "loss": 1.7553, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.547505620851811e-05, | |
| "loss": 1.8855, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 1.8231, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.2476774836260845e-05, | |
| "loss": 1.8003, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.0987248109304714e-05, | |
| "loss": 1.7616, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.950594489675763e-05, | |
| "loss": 1.8023, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.803421678562213e-05, | |
| "loss": 1.6784, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.861940860748291, | |
| "eval_runtime": 62.7157, | |
| "eval_samples_per_second": 1.754, | |
| "eval_steps_per_second": 0.223, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.657340662628116e-05, | |
| "loss": 1.6669, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.512484730723986e-05, | |
| "loss": 1.6333, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.368986053895655e-05, | |
| "loss": 1.9278, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 1.9157, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8783, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.9479359727362173e-05, | |
| "loss": 1.7518, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.811161474173297e-05, | |
| "loss": 1.8523, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.6763841397811573e-05, | |
| "loss": 1.7893, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.5437269445806145e-05, | |
| "loss": 1.7636, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.4133109291117156e-05, | |
| "loss": 1.8228, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.2852550889926067e-05, | |
| "loss": 1.7656, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 1.746, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.0366890431799167e-05, | |
| "loss": 1.7256, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.9164056368572846e-05, | |
| "loss": 1.6128, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.7989357976875603e-05, | |
| "loss": 1.6727, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.684386708796025e-05, | |
| "loss": 2.0976, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.5728628883248007e-05, | |
| "loss": 1.8464, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0062, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.3592952306210588e-05, | |
| "loss": 1.837, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 1.8183, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.159012109798598e-05, | |
| "loss": 1.8, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.0640825969547496e-05, | |
| "loss": 1.77, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.8537334203720093, | |
| "eval_runtime": 62.6147, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.224, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.7274433724527e-06, | |
| "loss": 1.914, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.850806705317183e-06, | |
| "loss": 1.8016, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.011715838630107e-06, | |
| "loss": 1.7734, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.21093638492763e-06, | |
| "loss": 1.7373, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 6.449199000224221e-06, | |
| "loss": 1.7791, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 1.5139, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 5.045594311728707e-06, | |
| "loss": 1.9854, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.405007700395497e-06, | |
| "loss": 1.9952, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9239, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.249187865729264e-06, | |
| "loss": 1.8075, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.7350092482679836e-06, | |
| "loss": 1.7052, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.2639566745727205e-06, | |
| "loss": 1.9388, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.8364599476241862e-06, | |
| "loss": 1.8453, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.6221, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.1136541814576573e-06, | |
| "loss": 1.7256, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.190046526428242e-07, | |
| "loss": 1.7185, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 5.692293896232936e-07, | |
| "loss": 1.7981, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.6455629509730136e-07, | |
| "loss": 1.7508, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.0517211914545254e-07, | |
| "loss": 1.5822, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.12222888341252e-08, | |
| "loss": 1.9108, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.2810775523329773e-08, | |
| "loss": 1.758, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.6501, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8522212505340576, | |
| "eval_runtime": 62.6224, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.224, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 110, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1.2865354251706368e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |