| { | |
| "best_metric": 1.0751440525054932, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11723329425556858, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023446658851113715, | |
| "grad_norm": 23.239633560180664, | |
| "learning_rate": 1e-05, | |
| "loss": 5.4807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023446658851113715, | |
| "eval_loss": 1.620888352394104, | |
| "eval_runtime": 52.8298, | |
| "eval_samples_per_second": 13.591, | |
| "eval_steps_per_second": 3.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004689331770222743, | |
| "grad_norm": 30.096290588378906, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8935, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007033997655334115, | |
| "grad_norm": 25.60515785217285, | |
| "learning_rate": 3e-05, | |
| "loss": 5.8402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009378663540445486, | |
| "grad_norm": 23.096664428710938, | |
| "learning_rate": 4e-05, | |
| "loss": 5.3388, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011723329425556858, | |
| "grad_norm": 23.348421096801758, | |
| "learning_rate": 5e-05, | |
| "loss": 5.397, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01406799531066823, | |
| "grad_norm": 16.431598663330078, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016412661195779603, | |
| "grad_norm": 16.66216468811035, | |
| "learning_rate": 7e-05, | |
| "loss": 4.2424, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01875732708089097, | |
| "grad_norm": 13.334493637084961, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021101992966002344, | |
| "grad_norm": 11.975020408630371, | |
| "learning_rate": 9e-05, | |
| "loss": 3.9145, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023446658851113716, | |
| "grad_norm": 11.74121379852295, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02579132473622509, | |
| "grad_norm": 12.151472091674805, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 3.9669, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02813599062133646, | |
| "grad_norm": 10.813011169433594, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.9362, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03048065650644783, | |
| "grad_norm": 14.49845027923584, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 4.221, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032825322391559206, | |
| "grad_norm": 9.16484546661377, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 3.3724, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.035169988276670575, | |
| "grad_norm": 13.538769721984863, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.8166, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03751465416178194, | |
| "grad_norm": 9.84959602355957, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 3.6727, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03985932004689332, | |
| "grad_norm": 10.60831356048584, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 3.5212, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04220398593200469, | |
| "grad_norm": 9.566568374633789, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.7478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044548651817116064, | |
| "grad_norm": 8.169366836547852, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.3065, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04689331770222743, | |
| "grad_norm": 7.885672569274902, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.1369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0492379835873388, | |
| "grad_norm": 8.924588203430176, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.5698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05158264947245018, | |
| "grad_norm": 8.621098518371582, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.5412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053927315357561546, | |
| "grad_norm": 8.363326072692871, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 3.3901, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05627198124267292, | |
| "grad_norm": 8.602740287780762, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.0478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05861664712778429, | |
| "grad_norm": 11.961050987243652, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 3.8124, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06096131301289566, | |
| "grad_norm": 8.368843078613281, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 3.413, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06330597889800703, | |
| "grad_norm": 13.979700088500977, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 3.3493, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06565064478311841, | |
| "grad_norm": 10.302687644958496, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.1922, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06799531066822978, | |
| "grad_norm": 8.424847602844238, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.0255, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07033997655334115, | |
| "grad_norm": 8.677651405334473, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.9156, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07268464243845252, | |
| "grad_norm": 8.514183044433594, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 3.0409, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07502930832356389, | |
| "grad_norm": 8.841915130615234, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.0594, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07737397420867527, | |
| "grad_norm": 9.110976219177246, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 3.2144, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07971864009378664, | |
| "grad_norm": 8.615434646606445, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.9209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08206330597889801, | |
| "grad_norm": 8.627106666564941, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 3.3399, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08440797186400938, | |
| "grad_norm": 8.770901679992676, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 3.0987, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08675263774912075, | |
| "grad_norm": 9.875587463378906, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.2772, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08909730363423213, | |
| "grad_norm": 9.106793403625488, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 3.3099, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0914419695193435, | |
| "grad_norm": 7.894020080566406, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 3.2431, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09378663540445487, | |
| "grad_norm": 8.276036262512207, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.3587, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09613130128956623, | |
| "grad_norm": 12.071616172790527, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.2565, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0984759671746776, | |
| "grad_norm": 8.251750946044922, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 2.8408, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10082063305978899, | |
| "grad_norm": 7.910401344299316, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 2.7768, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10316529894490035, | |
| "grad_norm": 9.235706329345703, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.1056, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10550996483001172, | |
| "grad_norm": 9.143514633178711, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.5952, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10785463071512309, | |
| "grad_norm": 8.614946365356445, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 2.6248, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11019929660023446, | |
| "grad_norm": 8.619750022888184, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 2.4423, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11254396248534584, | |
| "grad_norm": 9.125701904296875, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.4764, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11488862837045721, | |
| "grad_norm": 9.610570907592773, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 2.1642, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11723329425556858, | |
| "grad_norm": 11.419136047363281, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.8759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11723329425556858, | |
| "eval_loss": 1.0751440525054932, | |
| "eval_runtime": 53.7599, | |
| "eval_samples_per_second": 13.356, | |
| "eval_steps_per_second": 3.348, | |
| "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": 7.19077308849193e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |