| { | |
| "best_metric": 1.3878036737442017, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02178886588953045, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000435777317790609, | |
| "grad_norm": 2.0851054191589355, | |
| "learning_rate": 5e-06, | |
| "loss": 1.6817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000435777317790609, | |
| "eval_loss": 2.0230047702789307, | |
| "eval_runtime": 315.559, | |
| "eval_samples_per_second": 12.248, | |
| "eval_steps_per_second": 6.126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000871554635581218, | |
| "grad_norm": 2.216548204421997, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8021, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001307331953371827, | |
| "grad_norm": 2.3968324661254883, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.9165, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001743109271162436, | |
| "grad_norm": 2.045064926147461, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8139, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002178886588953045, | |
| "grad_norm": 2.1230273246765137, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.8931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002614663906743654, | |
| "grad_norm": 1.675313949584961, | |
| "learning_rate": 3e-05, | |
| "loss": 1.762, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003050441224534263, | |
| "grad_norm": 1.3971757888793945, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.5999, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003486218542324872, | |
| "grad_norm": 1.214509129524231, | |
| "learning_rate": 4e-05, | |
| "loss": 1.663, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003921995860115481, | |
| "grad_norm": 1.1938960552215576, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.6785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00435777317790609, | |
| "grad_norm": 1.2489292621612549, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5493, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004793550495696699, | |
| "grad_norm": 1.2138938903808594, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.622, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005229327813487308, | |
| "grad_norm": 1.2661142349243164, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5328, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005665105131277917, | |
| "grad_norm": 1.047982931137085, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.5021, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006100882449068526, | |
| "grad_norm": 0.9978450536727905, | |
| "learning_rate": 7e-05, | |
| "loss": 1.6194, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006536659766859135, | |
| "grad_norm": 0.8680281043052673, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3816, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006972437084649744, | |
| "grad_norm": 0.9196011424064636, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5334, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007408214402440353, | |
| "grad_norm": 0.9667453765869141, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.4741, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007843991720230961, | |
| "grad_norm": 0.8727541565895081, | |
| "learning_rate": 9e-05, | |
| "loss": 1.4547, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008279769038021571, | |
| "grad_norm": 0.9195423722267151, | |
| "learning_rate": 9.5e-05, | |
| "loss": 1.5097, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00871554635581218, | |
| "grad_norm": 1.05409574508667, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4515, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00915132367360279, | |
| "grad_norm": 0.8618441820144653, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 1.3947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009587100991393397, | |
| "grad_norm": 0.8809842467308044, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.4563, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010022878309184007, | |
| "grad_norm": 0.8538223505020142, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 1.4483, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010458655626974615, | |
| "grad_norm": 0.8714299201965332, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010894432944765225, | |
| "grad_norm": 0.8516822457313538, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.382, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011330210262555833, | |
| "grad_norm": 0.9048829078674316, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.469, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011765987580346443, | |
| "grad_norm": 0.8362917900085449, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 1.4376, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012201764898137051, | |
| "grad_norm": 0.8152568936347961, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.4729, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012637542215927661, | |
| "grad_norm": 0.8475168943405151, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.4389, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01307331953371827, | |
| "grad_norm": 0.8305416703224182, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013509096851508879, | |
| "grad_norm": 0.8335140943527222, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 1.3876, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013944874169299489, | |
| "grad_norm": 0.8393346667289734, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.4717, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014380651487090097, | |
| "grad_norm": 0.8358327150344849, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 1.3911, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014816428804880707, | |
| "grad_norm": 0.8287831544876099, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.3734, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015252206122671315, | |
| "grad_norm": 0.7427653670310974, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3105, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015687983440461923, | |
| "grad_norm": 0.8388314843177795, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.4373, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016123760758252535, | |
| "grad_norm": 0.7671462297439575, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 1.3883, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016559538076043143, | |
| "grad_norm": 0.8673655986785889, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3485, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01699531539383375, | |
| "grad_norm": 0.8480393290519714, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 1.4058, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01743109271162436, | |
| "grad_norm": 0.8280643820762634, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.47, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01786687002941497, | |
| "grad_norm": 0.7347378730773926, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 1.2069, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01830264734720558, | |
| "grad_norm": 0.8081456422805786, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.4003, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018738424664996187, | |
| "grad_norm": 0.7185221314430237, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 1.2813, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019174201982786795, | |
| "grad_norm": 0.7656445503234863, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4089, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.019609979300577406, | |
| "grad_norm": 0.936586320400238, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.3603, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020045756618368014, | |
| "grad_norm": 0.7969225645065308, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.3352, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020481533936158623, | |
| "grad_norm": 0.8012515306472778, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 1.3508, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02091731125394923, | |
| "grad_norm": 0.7480721473693848, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.3603, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.021353088571739842, | |
| "grad_norm": 0.814703643321991, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 1.3205, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02178886588953045, | |
| "grad_norm": 0.9260087609291077, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02178886588953045, | |
| "eval_loss": 1.3878036737442017, | |
| "eval_runtime": 317.8565, | |
| "eval_samples_per_second": 12.16, | |
| "eval_steps_per_second": 6.081, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.171470498830746e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |