| { | |
| "best_metric": 0.5734456777572632, | |
| "best_model_checkpoint": "./CodePhi2/checkpoint-750", | |
| "epoch": 1.7492233266219035, | |
| "eval_steps": 250, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5503875968992248e-05, | |
| "loss": 0.9039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.1007751937984497e-05, | |
| "loss": 0.59, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.651162790697675e-05, | |
| "loss": 0.5942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 6.201550387596899e-05, | |
| "loss": 0.5905, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.751937984496124e-05, | |
| "loss": 0.6012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.30232558139535e-05, | |
| "loss": 0.5978, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00010852713178294573, | |
| "loss": 0.5982, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012403100775193799, | |
| "loss": 0.6037, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00013953488372093025, | |
| "loss": 0.6101, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001550387596899225, | |
| "loss": 0.6177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00017054263565891473, | |
| "loss": 0.62, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000186046511627907, | |
| "loss": 0.6398, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00019982683982683983, | |
| "loss": 0.6363, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001980952380952381, | |
| "loss": 0.6317, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 0.6322, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019463203463203463, | |
| "loss": 0.6435, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019290043290043292, | |
| "loss": 0.6384, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019116883116883119, | |
| "loss": 0.6342, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00018943722943722942, | |
| "loss": 0.626, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00018770562770562772, | |
| "loss": 0.6225, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00018597402597402598, | |
| "loss": 0.6195, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018424242424242427, | |
| "loss": 0.6244, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001825108225108225, | |
| "loss": 0.6292, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018077922077922078, | |
| "loss": 0.6289, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017904761904761907, | |
| "loss": 0.6331, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.6136361360549927, | |
| "eval_runtime": 316.7992, | |
| "eval_samples_per_second": 38.498, | |
| "eval_steps_per_second": 4.814, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00017731601731601733, | |
| "loss": 0.6191, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00017558441558441557, | |
| "loss": 0.6127, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017385281385281386, | |
| "loss": 0.6198, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00017212121212121213, | |
| "loss": 0.6103, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001703896103896104, | |
| "loss": 0.6123, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00016865800865800866, | |
| "loss": 0.6115, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00016692640692640693, | |
| "loss": 0.6118, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00016519480519480522, | |
| "loss": 0.6127, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016346320346320348, | |
| "loss": 0.6027, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016173160173160172, | |
| "loss": 0.6041, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6118, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015826839826839828, | |
| "loss": 0.6052, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00015653679653679654, | |
| "loss": 0.6124, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001548051948051948, | |
| "loss": 0.6029, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00015307359307359307, | |
| "loss": 0.6013, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015134199134199134, | |
| "loss": 0.6006, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00014961038961038963, | |
| "loss": 0.6055, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001478787878787879, | |
| "loss": 0.5916, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00014614718614718613, | |
| "loss": 0.4963, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014441558441558443, | |
| "loss": 0.5066, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001426839826839827, | |
| "loss": 0.4997, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014095238095238096, | |
| "loss": 0.494, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00013922077922077922, | |
| "loss": 0.4925, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001374891774891775, | |
| "loss": 0.4944, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00013575757575757578, | |
| "loss": 0.5007, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.5911308526992798, | |
| "eval_runtime": 316.8116, | |
| "eval_samples_per_second": 38.496, | |
| "eval_steps_per_second": 4.814, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00013402597402597404, | |
| "loss": 0.5004, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00013229437229437228, | |
| "loss": 0.4985, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00013056277056277057, | |
| "loss": 0.4983, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00012883116883116884, | |
| "loss": 0.4974, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001270995670995671, | |
| "loss": 0.4988, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00012536796536796537, | |
| "loss": 0.5051, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 0.499, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00012190476190476193, | |
| "loss": 0.5018, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00012017316017316018, | |
| "loss": 0.5027, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00011844155844155844, | |
| "loss": 0.502, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00011670995670995672, | |
| "loss": 0.4987, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00011497835497835499, | |
| "loss": 0.5002, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00011324675324675324, | |
| "loss": 0.4934, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00011151515151515153, | |
| "loss": 0.4978, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00010978354978354978, | |
| "loss": 0.4957, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00010805194805194805, | |
| "loss": 0.4958, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00010632034632034633, | |
| "loss": 0.4968, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00010458874458874459, | |
| "loss": 0.4957, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00010285714285714286, | |
| "loss": 0.4982, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00010112554112554114, | |
| "loss": 0.4968, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.939393939393939e-05, | |
| "loss": 0.4951, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.766233766233767e-05, | |
| "loss": 0.4952, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 9.593073593073593e-05, | |
| "loss": 0.5001, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.419913419913421e-05, | |
| "loss": 0.4982, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.246753246753248e-05, | |
| "loss": 0.4945, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.5734456777572632, | |
| "eval_runtime": 316.4801, | |
| "eval_samples_per_second": 38.536, | |
| "eval_steps_per_second": 4.819, | |
| "step": 750 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1284, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 250, | |
| "total_flos": 5.360478675518669e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |