| { | |
| "best_metric": 3.473081588745117, | |
| "best_model_checkpoint": "domain-adapted-contriever/checkpoint-1440", | |
| "epoch": 48.0, | |
| "global_step": 1440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 10.873493194580078, | |
| "eval_runtime": 0.0467, | |
| "eval_samples_per_second": 449.222, | |
| "eval_steps_per_second": 64.175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 9.2319917678833, | |
| "eval_runtime": 0.0465, | |
| "eval_samples_per_second": 451.748, | |
| "eval_steps_per_second": 64.535, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 7.761892318725586, | |
| "eval_runtime": 0.0466, | |
| "eval_samples_per_second": 450.664, | |
| "eval_steps_per_second": 64.381, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 7.499742031097412, | |
| "eval_runtime": 0.0467, | |
| "eval_samples_per_second": 449.436, | |
| "eval_steps_per_second": 64.205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6.862554550170898, | |
| "eval_runtime": 0.0466, | |
| "eval_samples_per_second": 450.876, | |
| "eval_steps_per_second": 64.411, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6.674304962158203, | |
| "eval_runtime": 0.0466, | |
| "eval_samples_per_second": 450.913, | |
| "eval_steps_per_second": 64.416, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6.445440292358398, | |
| "eval_runtime": 0.0466, | |
| "eval_samples_per_second": 450.283, | |
| "eval_steps_per_second": 64.326, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6.35595178604126, | |
| "eval_runtime": 0.0468, | |
| "eval_samples_per_second": 448.943, | |
| "eval_steps_per_second": 64.135, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6.049570083618164, | |
| "eval_runtime": 0.0468, | |
| "eval_samples_per_second": 448.913, | |
| "eval_steps_per_second": 64.13, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 5.842072486877441, | |
| "eval_runtime": 0.0468, | |
| "eval_samples_per_second": 448.648, | |
| "eval_steps_per_second": 64.093, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 6.05306339263916, | |
| "eval_runtime": 0.0467, | |
| "eval_samples_per_second": 449.222, | |
| "eval_steps_per_second": 64.175, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 5.601278781890869, | |
| "eval_runtime": 0.0474, | |
| "eval_samples_per_second": 443.192, | |
| "eval_steps_per_second": 63.313, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 5.842929363250732, | |
| "eval_runtime": 0.048, | |
| "eval_samples_per_second": 437.952, | |
| "eval_steps_per_second": 62.565, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 5.403830528259277, | |
| "eval_runtime": 0.0476, | |
| "eval_samples_per_second": 440.999, | |
| "eval_steps_per_second": 63.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 5.1446332931518555, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 448.066, | |
| "eval_steps_per_second": 64.009, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 4.861954689025879, | |
| "eval_runtime": 0.0478, | |
| "eval_samples_per_second": 439.045, | |
| "eval_steps_per_second": 62.721, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 1.9840000000000003e-05, | |
| "loss": 6.8332, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 5.051825046539307, | |
| "eval_runtime": 0.0484, | |
| "eval_samples_per_second": 433.592, | |
| "eval_steps_per_second": 61.942, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 4.834855556488037, | |
| "eval_runtime": 0.0475, | |
| "eval_samples_per_second": 442.506, | |
| "eval_steps_per_second": 63.215, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 4.873433589935303, | |
| "eval_runtime": 0.0478, | |
| "eval_samples_per_second": 439.758, | |
| "eval_steps_per_second": 62.823, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 4.606621265411377, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.719, | |
| "eval_steps_per_second": 63.674, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 4.420989513397217, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.929, | |
| "eval_steps_per_second": 63.99, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 4.37644100189209, | |
| "eval_runtime": 0.0472, | |
| "eval_samples_per_second": 445.111, | |
| "eval_steps_per_second": 63.587, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 4.4230475425720215, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.941, | |
| "eval_steps_per_second": 63.992, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 4.332743167877197, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.731, | |
| "eval_steps_per_second": 63.676, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 4.291798114776611, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.429, | |
| "eval_steps_per_second": 63.633, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 4.197042942047119, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.494, | |
| "eval_steps_per_second": 63.642, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 4.085911273956299, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 446.664, | |
| "eval_steps_per_second": 63.809, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 4.071910858154297, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.733, | |
| "eval_steps_per_second": 63.676, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 4.150127410888672, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 446.266, | |
| "eval_steps_per_second": 63.752, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 3.875171184539795, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.781, | |
| "eval_steps_per_second": 63.969, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 3.8007264137268066, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 447.009, | |
| "eval_steps_per_second": 63.858, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 3.7663497924804688, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 447.099, | |
| "eval_steps_per_second": 63.871, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 4.154388427734375, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 445.803, | |
| "eval_steps_per_second": 63.686, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 1.008e-05, | |
| "loss": 4.123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 3.6973140239715576, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 448.23, | |
| "eval_steps_per_second": 64.033, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 4.152168273925781, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 448.137, | |
| "eval_steps_per_second": 64.02, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 3.746863603591919, | |
| "eval_runtime": 0.0473, | |
| "eval_samples_per_second": 443.569, | |
| "eval_steps_per_second": 63.367, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 3.8012099266052246, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 446.105, | |
| "eval_steps_per_second": 63.729, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 3.714829683303833, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.308, | |
| "eval_steps_per_second": 63.901, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 3.4752964973449707, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 447.127, | |
| "eval_steps_per_second": 63.875, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 3.982607126235962, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.311, | |
| "eval_steps_per_second": 63.902, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 3.850808620452881, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.856, | |
| "eval_steps_per_second": 63.979, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 4.094546794891357, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 448.002, | |
| "eval_steps_per_second": 64.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 3.4853432178497314, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 446.474, | |
| "eval_steps_per_second": 63.782, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 3.5112228393554688, | |
| "eval_runtime": 0.0471, | |
| "eval_samples_per_second": 446.02, | |
| "eval_steps_per_second": 63.717, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 3.7965281009674072, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 446.759, | |
| "eval_steps_per_second": 63.823, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 3.6154186725616455, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 448.15, | |
| "eval_steps_per_second": 64.021, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 3.5226211547851562, | |
| "eval_runtime": 0.0468, | |
| "eval_samples_per_second": 448.964, | |
| "eval_steps_per_second": 64.138, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 3.473081588745117, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 447.779, | |
| "eval_steps_per_second": 63.968, | |
| "step": 1440 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 50, | |
| "total_flos": 739079114342400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |