| { | |
| "best_metric": 6.5507588386535645, | |
| "best_model_checkpoint": "poetry-author/checkpoint-4960", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 4960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 7.2029, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.919354838709678e-06, | |
| "loss": 7.1816, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.419354838709678e-06, | |
| "loss": 7.1418, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.919354838709679e-06, | |
| "loss": 7.1678, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.2379032258064517e-05, | |
| "loss": 7.1274, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4879032258064519e-05, | |
| "loss": 7.1285, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.7379032258064517e-05, | |
| "loss": 7.108, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.9879032258064516e-05, | |
| "loss": 7.0809, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.2379032258064516e-05, | |
| "loss": 7.1026, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.4879032258064516e-05, | |
| "loss": 7.0691, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.737903225806452e-05, | |
| "loss": 7.0714, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.9879032258064516e-05, | |
| "loss": 7.0847, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.2379032258064515e-05, | |
| "loss": 7.0491, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.487903225806452e-05, | |
| "loss": 7.0685, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7379032258064515e-05, | |
| "loss": 7.038, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.987903225806452e-05, | |
| "loss": 7.0614, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.2379032258064514e-05, | |
| "loss": 7.0234, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.487903225806452e-05, | |
| "loss": 6.9863, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.737903225806452e-05, | |
| "loss": 6.9664, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.987903225806452e-05, | |
| "loss": 6.9782, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.02056451612903226, | |
| "eval_f1_macro": 0.0006143466739070911, | |
| "eval_f1_micro": 0.02056451612903226, | |
| "eval_f1_weighted": 0.004146182182163288, | |
| "eval_loss": 6.874168395996094, | |
| "eval_precision_macro": 0.0003535209813895348, | |
| "eval_precision_micro": 0.02056451612903226, | |
| "eval_precision_weighted": 0.0024119848598185387, | |
| "eval_recall_macro": 0.0037010590753155195, | |
| "eval_recall_micro": 0.02056451612903226, | |
| "eval_recall_weighted": 0.02056451612903226, | |
| "eval_runtime": 5.5652, | |
| "eval_samples_per_second": 445.625, | |
| "eval_steps_per_second": 27.852, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.9735663082437276e-05, | |
| "loss": 6.9144, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.94578853046595e-05, | |
| "loss": 6.8315, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.9180107526881726e-05, | |
| "loss": 6.8663, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.89068100358423e-05, | |
| "loss": 6.837, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.862903225806452e-05, | |
| "loss": 6.7745, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.835125448028674e-05, | |
| "loss": 6.8747, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.807347670250896e-05, | |
| "loss": 6.8005, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.7795698924731186e-05, | |
| "loss": 6.8131, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.751792114695341e-05, | |
| "loss": 6.7554, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.724014336917563e-05, | |
| "loss": 6.774, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.696236559139785e-05, | |
| "loss": 6.7964, | |
| "step": 1922 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.6684587813620074e-05, | |
| "loss": 6.8653, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.64068100358423e-05, | |
| "loss": 6.8209, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.612903225806452e-05, | |
| "loss": 6.7755, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.585125448028674e-05, | |
| "loss": 6.8384, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.557347670250896e-05, | |
| "loss": 6.7932, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.5295698924731187e-05, | |
| "loss": 6.8017, | |
| "step": 2294 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.5017921146953405e-05, | |
| "loss": 6.7575, | |
| "step": 2356 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.474014336917563e-05, | |
| "loss": 6.7087, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.4462365591397856e-05, | |
| "loss": 6.8306, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.027822580645161292, | |
| "eval_f1_macro": 0.002895880527713299, | |
| "eval_f1_micro": 0.027822580645161292, | |
| "eval_f1_weighted": 0.011518078961075304, | |
| "eval_loss": 6.696753025054932, | |
| "eval_precision_macro": 0.002399325952306467, | |
| "eval_precision_micro": 0.027822580645161292, | |
| "eval_precision_weighted": 0.008800287744676547, | |
| "eval_recall_macro": 0.005697363214948901, | |
| "eval_recall_micro": 0.027822580645161292, | |
| "eval_recall_weighted": 0.027822580645161292, | |
| "eval_runtime": 5.6109, | |
| "eval_samples_per_second": 441.997, | |
| "eval_steps_per_second": 27.625, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.4184587813620074e-05, | |
| "loss": 6.5756, | |
| "step": 2542 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 6.5611, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 4.362903225806452e-05, | |
| "loss": 6.6159, | |
| "step": 2666 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 4.335125448028674e-05, | |
| "loss": 6.5746, | |
| "step": 2728 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.307347670250896e-05, | |
| "loss": 6.4498, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.279569892473119e-05, | |
| "loss": 6.5829, | |
| "step": 2852 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.2517921146953405e-05, | |
| "loss": 6.4411, | |
| "step": 2914 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.224014336917563e-05, | |
| "loss": 6.5321, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.196236559139785e-05, | |
| "loss": 6.5179, | |
| "step": 3038 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.1684587813620074e-05, | |
| "loss": 6.5047, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.14068100358423e-05, | |
| "loss": 6.5946, | |
| "step": 3162 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.112903225806452e-05, | |
| "loss": 6.519, | |
| "step": 3224 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.0851254480286736e-05, | |
| "loss": 6.4516, | |
| "step": 3286 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.057347670250896e-05, | |
| "loss": 6.5272, | |
| "step": 3348 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.029569892473119e-05, | |
| "loss": 6.5356, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.0017921146953405e-05, | |
| "loss": 6.5008, | |
| "step": 3472 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.974014336917563e-05, | |
| "loss": 6.5357, | |
| "step": 3534 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.94668458781362e-05, | |
| "loss": 6.5125, | |
| "step": 3596 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.918906810035842e-05, | |
| "loss": 6.5182, | |
| "step": 3658 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.891129032258065e-05, | |
| "loss": 6.4911, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.03951612903225806, | |
| "eval_f1_macro": 0.005772741775243502, | |
| "eval_f1_micro": 0.03951612903225806, | |
| "eval_f1_weighted": 0.01871310289711212, | |
| "eval_loss": 6.559847354888916, | |
| "eval_precision_macro": 0.005108167219150119, | |
| "eval_precision_micro": 0.03951612903225806, | |
| "eval_precision_weighted": 0.015116924332361547, | |
| "eval_recall_macro": 0.010902113654450544, | |
| "eval_recall_micro": 0.03951612903225806, | |
| "eval_recall_weighted": 0.03951612903225806, | |
| "eval_runtime": 5.604, | |
| "eval_samples_per_second": 442.538, | |
| "eval_steps_per_second": 27.659, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.863351254480287e-05, | |
| "loss": 6.111, | |
| "step": 3782 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.835573476702509e-05, | |
| "loss": 6.2635, | |
| "step": 3844 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 3.8077956989247316e-05, | |
| "loss": 6.1807, | |
| "step": 3906 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.780017921146954e-05, | |
| "loss": 6.2969, | |
| "step": 3968 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.752240143369175e-05, | |
| "loss": 6.1509, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.724462365591398e-05, | |
| "loss": 6.1196, | |
| "step": 4092 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.69668458781362e-05, | |
| "loss": 6.1425, | |
| "step": 4154 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.668906810035843e-05, | |
| "loss": 6.1487, | |
| "step": 4216 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.641129032258065e-05, | |
| "loss": 6.1336, | |
| "step": 4278 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.6133512544802866e-05, | |
| "loss": 6.1035, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 3.585573476702509e-05, | |
| "loss": 6.168, | |
| "step": 4402 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 3.5577956989247316e-05, | |
| "loss": 6.283, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.5300179211469535e-05, | |
| "loss": 6.146, | |
| "step": 4526 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 3.502240143369176e-05, | |
| "loss": 6.1099, | |
| "step": 4588 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.4744623655913985e-05, | |
| "loss": 6.2278, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.4466845878136204e-05, | |
| "loss": 6.0957, | |
| "step": 4712 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 3.418906810035842e-05, | |
| "loss": 6.0431, | |
| "step": 4774 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.391129032258065e-05, | |
| "loss": 6.0954, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 3.363351254480287e-05, | |
| "loss": 6.1678, | |
| "step": 4898 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.335573476702509e-05, | |
| "loss": 6.1257, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.04596774193548387, | |
| "eval_f1_macro": 0.007553613837545024, | |
| "eval_f1_micro": 0.04596774193548386, | |
| "eval_f1_weighted": 0.02342410713485415, | |
| "eval_loss": 6.5507588386535645, | |
| "eval_precision_macro": 0.0064405619945614515, | |
| "eval_precision_micro": 0.04596774193548387, | |
| "eval_precision_weighted": 0.020352886732684962, | |
| "eval_recall_macro": 0.017759772448305164, | |
| "eval_recall_micro": 0.04596774193548387, | |
| "eval_recall_weighted": 0.04596774193548387, | |
| "eval_runtime": 5.6061, | |
| "eval_samples_per_second": 442.376, | |
| "eval_steps_per_second": 27.649, | |
| "step": 4960 | |
| } | |
| ], | |
| "logging_steps": 62, | |
| "max_steps": 12400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2638150224863232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |