| { | |
| "best_metric": 0.09525119513273239, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1347517730496455, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02269503546099291, | |
| "grad_norm": 3.707425355911255, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02269503546099291, | |
| "eval_loss": 3.157935619354248, | |
| "eval_runtime": 10.3884, | |
| "eval_samples_per_second": 28.59, | |
| "eval_steps_per_second": 3.658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04539007092198582, | |
| "grad_norm": 2.988710403442383, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0746, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 2.8525102138519287, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.8503, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09078014184397164, | |
| "grad_norm": 3.226891279220581, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3066, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 3.3439524173736572, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5979, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 2.541489839553833, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0652, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15886524822695036, | |
| "grad_norm": 2.874752998352051, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8488, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18156028368794327, | |
| "grad_norm": 1.9258209466934204, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6106, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 2.166975736618042, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4708, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 2.4708149433135986, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24964539007092199, | |
| "grad_norm": 1.1950278282165527, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.3468, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 2.3396644592285156, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8357, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2950354609929078, | |
| "grad_norm": 1.6584240198135376, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2608, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3177304964539007, | |
| "grad_norm": 1.1248372793197632, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2431, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.824798583984375, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2055, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.36312056737588655, | |
| "grad_norm": 0.5345423817634583, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1942, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.38581560283687943, | |
| "grad_norm": 0.8675239086151123, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1951, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": 0.7862822413444519, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1883, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43120567375886526, | |
| "grad_norm": 0.8981381058692932, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1988, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.7145481705665588, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4765957446808511, | |
| "grad_norm": 0.5971248745918274, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1773, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49929078014184397, | |
| "grad_norm": 0.5785800814628601, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1825, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5219858156028369, | |
| "grad_norm": 2.1194076538085938, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5239, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": 1.3546996116638184, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2566, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 1.551795244216919, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.186, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "eval_loss": 0.16990284621715546, | |
| "eval_runtime": 10.3949, | |
| "eval_samples_per_second": 28.572, | |
| "eval_steps_per_second": 3.656, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5900709219858156, | |
| "grad_norm": 1.0504887104034424, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1402, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6127659574468085, | |
| "grad_norm": 0.6791476607322693, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1174, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6354609929078014, | |
| "grad_norm": 0.574073851108551, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1246, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6581560283687943, | |
| "grad_norm": 0.8718014359474182, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1079, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.8603816032409668, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7035460992907802, | |
| "grad_norm": 0.7203976511955261, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1024, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7262411347517731, | |
| "grad_norm": 0.6164019703865051, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0965, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7489361702127659, | |
| "grad_norm": 0.4194211959838867, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0835, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7716312056737589, | |
| "grad_norm": 1.5366965532302856, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3735, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 0.730464518070221, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0878, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8170212765957446, | |
| "grad_norm": 0.671379566192627, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0951, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8397163120567376, | |
| "grad_norm": 0.6115317344665527, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0982, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8624113475177305, | |
| "grad_norm": 0.5566378235816956, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0809, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8851063829787233, | |
| "grad_norm": 0.5277712345123291, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0827, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 0.65236896276474, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0913, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9304964539007092, | |
| "grad_norm": 0.4440590441226959, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0578, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9531914893617022, | |
| "grad_norm": 0.6070952415466309, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0818, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.975886524822695, | |
| "grad_norm": 0.5152663588523865, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0693, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9985815602836879, | |
| "grad_norm": 0.532758891582489, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0815, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 5.1196417808532715, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6883, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0439716312056737, | |
| "grad_norm": 1.095219373703003, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1155, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.7534624934196472, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0801, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0893617021276596, | |
| "grad_norm": 1.4827603101730347, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0699, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1120567375886525, | |
| "grad_norm": 1.102303385734558, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0714, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 0.5766385197639465, | |
| "learning_rate": 0.0, | |
| "loss": 0.0585, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "eval_loss": 0.09525119513273239, | |
| "eval_runtime": 10.142, | |
| "eval_samples_per_second": 29.284, | |
| "eval_steps_per_second": 3.747, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 6.212826358674883e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |