| { | |
| "best_metric": 11.930976867675781, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.6500541711809318, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00866738894907909, | |
| "grad_norm": 0.014205647632479668, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.9344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00866738894907909, | |
| "eval_loss": 11.943220138549805, | |
| "eval_runtime": 0.2668, | |
| "eval_samples_per_second": 187.436, | |
| "eval_steps_per_second": 48.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 0.021280059590935707, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9345, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02600216684723727, | |
| "grad_norm": 0.026625456288456917, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 0.031291306018829346, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.9349, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04333694474539545, | |
| "grad_norm": 0.036243926733732224, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.9361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 0.04476647451519966, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06067172264355363, | |
| "grad_norm": 0.05329675227403641, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.9366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 0.05616913363337517, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.9381, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0780065005417118, | |
| "grad_norm": 0.06590206176042557, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0866738894907909, | |
| "grad_norm": 0.08881666511297226, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.9406, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09534127843986999, | |
| "grad_norm": 0.11582574248313904, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.9429, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10400866738894908, | |
| "grad_norm": 0.15351854264736176, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9471, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 0.02668151818215847, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.9345, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12134344528710726, | |
| "grad_norm": 0.022617211565375328, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.9325, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13001083423618634, | |
| "grad_norm": 0.027192845940589905, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9352, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13867822318526543, | |
| "grad_norm": 0.03240914270281792, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.9353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14734561213434452, | |
| "grad_norm": 0.042475830763578415, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.935, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1560130010834236, | |
| "grad_norm": 0.049555882811546326, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9354, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1646803900325027, | |
| "grad_norm": 0.053182654082775116, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.935, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1733477789815818, | |
| "grad_norm": 0.06439302861690521, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1820151679306609, | |
| "grad_norm": 0.07124801725149155, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19068255687973998, | |
| "grad_norm": 0.09465167671442032, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.9363, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19934994582881907, | |
| "grad_norm": 0.12675674259662628, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.9384, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20801733477789816, | |
| "grad_norm": 0.16636888682842255, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9427, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "grad_norm": 0.2566799223423004, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.9439, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "eval_loss": 11.938733100891113, | |
| "eval_runtime": 0.2609, | |
| "eval_samples_per_second": 191.665, | |
| "eval_steps_per_second": 49.833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.024506624788045883, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 11.932, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23401950162513543, | |
| "grad_norm": 0.03506021574139595, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.933, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24268689057421453, | |
| "grad_norm": 0.04695020988583565, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 11.9338, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2513542795232936, | |
| "grad_norm": 0.05981919541954994, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 11.9342, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2600216684723727, | |
| "grad_norm": 0.061907246708869934, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9334, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26868905742145177, | |
| "grad_norm": 0.07472109794616699, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 11.9334, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27735644637053086, | |
| "grad_norm": 0.09128537774085999, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 11.9335, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28602383531960995, | |
| "grad_norm": 0.10218062251806259, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9348, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29469122426868904, | |
| "grad_norm": 0.11169303208589554, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 11.9348, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30335861321776814, | |
| "grad_norm": 0.14492186903953552, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 11.9349, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3120260021668472, | |
| "grad_norm": 0.18491142988204956, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9366, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3206933911159263, | |
| "grad_norm": 0.245423823595047, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 11.9378, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3293607800650054, | |
| "grad_norm": 0.05013355612754822, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 11.9315, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.047407366335392, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9323, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3466955579631636, | |
| "grad_norm": 0.055343057960271835, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 11.9334, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3553629469122427, | |
| "grad_norm": 0.07278693467378616, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 11.9319, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3640303358613218, | |
| "grad_norm": 0.08519124239683151, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9313, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37269772481040087, | |
| "grad_norm": 0.09722817689180374, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 11.9318, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38136511375947996, | |
| "grad_norm": 0.0941312164068222, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 11.9312, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39003250270855905, | |
| "grad_norm": 0.12124495208263397, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.931, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39869989165763814, | |
| "grad_norm": 0.12268517166376114, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 11.9317, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40736728060671723, | |
| "grad_norm": 0.16867737472057343, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 11.9314, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4160346695557963, | |
| "grad_norm": 0.18943016231060028, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.933, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4247020585048754, | |
| "grad_norm": 0.24677303433418274, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 11.9336, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "grad_norm": 0.34038564562797546, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 11.9339, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "eval_loss": 11.933380126953125, | |
| "eval_runtime": 0.2591, | |
| "eval_samples_per_second": 192.978, | |
| "eval_steps_per_second": 50.174, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4420368364030336, | |
| "grad_norm": 0.04358985275030136, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.931, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 0.06944932788610458, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 11.931, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4593716143011918, | |
| "grad_norm": 0.07410332560539246, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 11.9319, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46803900325027087, | |
| "grad_norm": 0.08937946707010269, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9307, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47670639219934996, | |
| "grad_norm": 0.09634770452976227, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 11.9313, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48537378114842905, | |
| "grad_norm": 0.09646016359329224, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 11.9307, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.49404117009750814, | |
| "grad_norm": 0.11758565157651901, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9291, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5027085590465872, | |
| "grad_norm": 0.12455835193395615, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 11.9313, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5113759479956663, | |
| "grad_norm": 0.1459084004163742, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 11.9316, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5200433369447454, | |
| "grad_norm": 0.1777600347995758, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.93, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5287107258938245, | |
| "grad_norm": 0.2380158007144928, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 11.931, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5373781148429035, | |
| "grad_norm": 0.30322137475013733, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 11.9312, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5460455037919827, | |
| "grad_norm": 0.0573463998734951, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9318, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5547128927410617, | |
| "grad_norm": 0.06148889288306236, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 11.9306, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 0.07989097386598587, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 11.9313, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5720476706392199, | |
| "grad_norm": 0.0917278379201889, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9306, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.580715059588299, | |
| "grad_norm": 0.09770037978887558, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 11.9305, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5893824485373781, | |
| "grad_norm": 0.1190197691321373, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 11.9297, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5980498374864572, | |
| "grad_norm": 0.12440388649702072, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9297, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6067172264355363, | |
| "grad_norm": 0.1328328549861908, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 11.9293, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.1649710088968277, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 11.9295, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6240520043336945, | |
| "grad_norm": 0.16425499320030212, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9306, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6327193932827736, | |
| "grad_norm": 0.1935925930738449, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 11.9294, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6413867822318526, | |
| "grad_norm": 0.2569132447242737, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 11.9302, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6500541711809318, | |
| "grad_norm": 0.3602008521556854, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9282, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6500541711809318, | |
| "eval_loss": 11.930976867675781, | |
| "eval_runtime": 0.2483, | |
| "eval_samples_per_second": 201.391, | |
| "eval_steps_per_second": 52.362, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 1567487852544.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |