| { | |
| "best_metric": 1.8564728498458862, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8733624454148472, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 0.5114005208015442, | |
| "learning_rate": 5e-05, | |
| "loss": 2.399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017467248908296942, | |
| "eval_loss": 2.095630168914795, | |
| "eval_runtime": 9.2162, | |
| "eval_samples_per_second": 41.883, | |
| "eval_steps_per_second": 5.317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 0.5091593265533447, | |
| "learning_rate": 0.0001, | |
| "loss": 2.466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 0.4823155999183655, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5316, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 0.30862247943878174, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2703, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "grad_norm": 0.33223703503608704, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3973, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10480349344978165, | |
| "grad_norm": 0.3087231516838074, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2734, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1222707423580786, | |
| "grad_norm": 0.3192172050476074, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2835, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 0.32516586780548096, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3483, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "grad_norm": 0.29455697536468506, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "grad_norm": 0.3054976761341095, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19213973799126638, | |
| "grad_norm": 0.3713310956954956, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4072, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2096069868995633, | |
| "grad_norm": 0.40929102897644043, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0596, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22707423580786026, | |
| "grad_norm": 0.8402824997901917, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9913, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2445414847161572, | |
| "grad_norm": 0.5595530271530151, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.291, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26200873362445415, | |
| "grad_norm": 0.2685498595237732, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.204, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2794759825327511, | |
| "grad_norm": 0.2504390776157379, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1882, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29694323144104806, | |
| "grad_norm": 0.22610808908939362, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.314410480349345, | |
| "grad_norm": 0.25485333800315857, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3318777292576419, | |
| "grad_norm": 0.24564465880393982, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.268, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "grad_norm": 0.2573384642601013, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36681222707423583, | |
| "grad_norm": 0.2677813768386841, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.155, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38427947598253276, | |
| "grad_norm": 0.31837937235832214, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2531, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4017467248908297, | |
| "grad_norm": 0.4004027843475342, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9684, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4192139737991266, | |
| "grad_norm": 0.20169611275196075, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0428, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4366812227074236, | |
| "grad_norm": 0.32077139616012573, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0347, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4366812227074236, | |
| "eval_loss": 1.8789408206939697, | |
| "eval_runtime": 9.2126, | |
| "eval_samples_per_second": 41.899, | |
| "eval_steps_per_second": 5.319, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45414847161572053, | |
| "grad_norm": 0.2208106517791748, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2395, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.47161572052401746, | |
| "grad_norm": 0.2533266246318817, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2826, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4890829694323144, | |
| "grad_norm": 0.22869157791137695, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.2854, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5065502183406113, | |
| "grad_norm": 0.21572184562683105, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.1784, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5240174672489083, | |
| "grad_norm": 0.21361880004405975, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.1801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5414847161572053, | |
| "grad_norm": 0.20447427034378052, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.169, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5589519650655022, | |
| "grad_norm": 0.21110278367996216, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5764192139737991, | |
| "grad_norm": 0.21510860323905945, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.1632, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5938864628820961, | |
| "grad_norm": 0.2602185308933258, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3162, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.611353711790393, | |
| "grad_norm": 0.28548145294189453, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.9825, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.62882096069869, | |
| "grad_norm": 0.14463306963443756, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5298, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6462882096069869, | |
| "grad_norm": 0.04139815643429756, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0034, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6637554585152838, | |
| "grad_norm": 0.21067368984222412, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9263, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6812227074235808, | |
| "grad_norm": 0.18605366349220276, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2741, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "grad_norm": 0.20509853959083557, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7161572052401747, | |
| "grad_norm": 0.1972036212682724, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2469, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7336244541484717, | |
| "grad_norm": 0.19003644585609436, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.283, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7510917030567685, | |
| "grad_norm": 0.1818603128194809, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2192, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7685589519650655, | |
| "grad_norm": 0.19268260896205902, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1306, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7860262008733624, | |
| "grad_norm": 0.19862526655197144, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1101, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8034934497816594, | |
| "grad_norm": 0.22022812068462372, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1762, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8209606986899564, | |
| "grad_norm": 0.287217378616333, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.1762, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8384279475982532, | |
| "grad_norm": 0.338515967130661, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.7232, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8558951965065502, | |
| "grad_norm": 0.03698641434311867, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.013, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8733624454148472, | |
| "grad_norm": 0.04879317060112953, | |
| "learning_rate": 0.0, | |
| "loss": 0.0051, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8733624454148472, | |
| "eval_loss": 1.8564728498458862, | |
| "eval_runtime": 9.2884, | |
| "eval_samples_per_second": 41.557, | |
| "eval_steps_per_second": 5.275, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9545134732201165e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |