| { | |
| "best_metric": 0.09737779200077057, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.37418147801683815, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007483629560336763, | |
| "grad_norm": 2838.466552734375, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007483629560336763, | |
| "eval_loss": 4.760346412658691, | |
| "eval_runtime": 26.2697, | |
| "eval_samples_per_second": 34.298, | |
| "eval_steps_per_second": 4.302, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014967259120673527, | |
| "grad_norm": 2971.39404296875, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4899, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02245088868101029, | |
| "grad_norm": 410.34173583984375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029934518241347054, | |
| "grad_norm": 595.5108642578125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8279, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.037418147801683815, | |
| "grad_norm": 479.4752197265625, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.4751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04490177736202058, | |
| "grad_norm": 1233.6602783203125, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9894, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.052385406922357346, | |
| "grad_norm": 268.8088684082031, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1187, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05986903648269411, | |
| "grad_norm": 29.148767471313477, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0332, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06735266604303088, | |
| "grad_norm": 27.497814178466797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0315, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07483629560336763, | |
| "grad_norm": 33.24267578125, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0823199251637044, | |
| "grad_norm": 55.90046691894531, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0182, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08980355472404115, | |
| "grad_norm": 28.329374313354492, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09728718428437792, | |
| "grad_norm": 1446.1328125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4276, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10477081384471469, | |
| "grad_norm": 286.21722412109375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6691, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11225444340505145, | |
| "grad_norm": 182.7144012451172, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4678, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11973807296538821, | |
| "grad_norm": 260.8122863769531, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12722170252572498, | |
| "grad_norm": 82.4249267578125, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2788, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13470533208606175, | |
| "grad_norm": 27.6737117767334, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0278, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1421889616463985, | |
| "grad_norm": 19.36988639831543, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14967259120673526, | |
| "grad_norm": 32.1801872253418, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15715622076707203, | |
| "grad_norm": 23.90668296813965, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1646398503274088, | |
| "grad_norm": 88.59371185302734, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0605, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17212347988774557, | |
| "grad_norm": 79.72174835205078, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0299, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1796071094480823, | |
| "grad_norm": 89.27919006347656, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "grad_norm": 11.256178855895996, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "eval_loss": 0.20019382238388062, | |
| "eval_runtime": 26.2485, | |
| "eval_samples_per_second": 34.326, | |
| "eval_steps_per_second": 4.305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19457436856875585, | |
| "grad_norm": 134.28933715820312, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5206, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.20205799812909261, | |
| "grad_norm": 90.19445037841797, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4137, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20954162768942938, | |
| "grad_norm": 30.906604766845703, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3565, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21702525724976612, | |
| "grad_norm": 47.67278289794922, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3031, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2245088868101029, | |
| "grad_norm": 38.380367279052734, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.119, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23199251637043966, | |
| "grad_norm": 40.00833511352539, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0969, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23947614593077643, | |
| "grad_norm": 125.88969421386719, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0652, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2469597754911132, | |
| "grad_norm": 16.30948257446289, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0244, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25444340505144997, | |
| "grad_norm": 7.882120132446289, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0111, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.26192703461178674, | |
| "grad_norm": 10.894170761108398, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0194, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2694106641721235, | |
| "grad_norm": 17.481016159057617, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2768942937324602, | |
| "grad_norm": 8.537217140197754, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0026, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.284377923292797, | |
| "grad_norm": 59.2493896484375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2544, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.29186155285313375, | |
| "grad_norm": 69.87789916992188, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3332, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2993451824134705, | |
| "grad_norm": 62.049102783203125, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3479, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3068288119738073, | |
| "grad_norm": 47.844940185546875, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3231, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.31431244153414406, | |
| "grad_norm": 32.43928146362305, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1896, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.32179607109448083, | |
| "grad_norm": 17.590641021728516, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0433, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3292797006548176, | |
| "grad_norm": 16.18429946899414, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0399, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.33676333021515437, | |
| "grad_norm": 8.45818042755127, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0182, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.34424695977549113, | |
| "grad_norm": 13.13820743560791, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0156, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3517305893358279, | |
| "grad_norm": 7.652195930480957, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0156, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3592142188961646, | |
| "grad_norm": 12.8060884475708, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0252, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3666978484565014, | |
| "grad_norm": 6.800826549530029, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "grad_norm": 6.836678981781006, | |
| "learning_rate": 0.0, | |
| "loss": 0.0027, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "eval_loss": 0.09737779200077057, | |
| "eval_runtime": 26.2411, | |
| "eval_samples_per_second": 34.335, | |
| "eval_steps_per_second": 4.306, | |
| "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": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |