| { | |
| "best_metric": 1.390590786933899, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1564945226917058, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003129890453834116, | |
| "grad_norm": 83.8933334350586, | |
| "learning_rate": 1e-05, | |
| "loss": 10.5413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003129890453834116, | |
| "eval_loss": 2.9433071613311768, | |
| "eval_runtime": 49.9776, | |
| "eval_samples_per_second": 10.785, | |
| "eval_steps_per_second": 2.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006259780907668232, | |
| "grad_norm": 73.74372863769531, | |
| "learning_rate": 2e-05, | |
| "loss": 10.704, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009389671361502348, | |
| "grad_norm": 49.65017318725586, | |
| "learning_rate": 3e-05, | |
| "loss": 10.9243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012519561815336464, | |
| "grad_norm": 42.6108512878418, | |
| "learning_rate": 4e-05, | |
| "loss": 9.9771, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "grad_norm": 35.75225830078125, | |
| "learning_rate": 5e-05, | |
| "loss": 8.5201, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018779342723004695, | |
| "grad_norm": 34.45755386352539, | |
| "learning_rate": 6e-05, | |
| "loss": 8.7165, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02190923317683881, | |
| "grad_norm": 35.77829360961914, | |
| "learning_rate": 7e-05, | |
| "loss": 8.9756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.025039123630672927, | |
| "grad_norm": 37.6871337890625, | |
| "learning_rate": 8e-05, | |
| "loss": 8.8051, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 41.72507858276367, | |
| "learning_rate": 9e-05, | |
| "loss": 8.6268, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "grad_norm": 31.615625381469727, | |
| "learning_rate": 0.0001, | |
| "loss": 7.8727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03442879499217527, | |
| "grad_norm": 33.186031341552734, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 9.2117, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03755868544600939, | |
| "grad_norm": 33.494564056396484, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 7.0062, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0406885758998435, | |
| "grad_norm": 31.77089500427246, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 7.8004, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04381846635367762, | |
| "grad_norm": 31.947071075439453, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 7.7758, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.046948356807511735, | |
| "grad_norm": 32.472782135009766, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 7.4786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050078247261345854, | |
| "grad_norm": 24.537351608276367, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 6.2569, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.053208137715179966, | |
| "grad_norm": 33.11750793457031, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 7.5808, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 26.680910110473633, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 7.6116, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0594679186228482, | |
| "grad_norm": 25.24735450744629, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 7.8923, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06259780907668232, | |
| "grad_norm": 23.690746307373047, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 5.5552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06572769953051644, | |
| "grad_norm": 24.43379783630371, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 5.7128, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06885758998435054, | |
| "grad_norm": 26.594310760498047, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 5.9577, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07198748043818466, | |
| "grad_norm": 26.899511337280273, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 5.7076, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07511737089201878, | |
| "grad_norm": 26.310029983520508, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 5.8776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0782472613458529, | |
| "grad_norm": 20.84659194946289, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 6.1357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.081377151799687, | |
| "grad_norm": 22.88994789123535, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 6.6307, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 20.51585578918457, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 4.2293, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08763693270735524, | |
| "grad_norm": 25.414339065551758, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 6.9259, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09076682316118936, | |
| "grad_norm": 18.835140228271484, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.94, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09389671361502347, | |
| "grad_norm": 21.440311431884766, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 6.3151, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09702660406885759, | |
| "grad_norm": 26.966928482055664, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 7.0147, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10015649452269171, | |
| "grad_norm": 20.210208892822266, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 7.4799, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10328638497652583, | |
| "grad_norm": 17.627716064453125, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.6791, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10641627543035993, | |
| "grad_norm": 21.506210327148438, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 6.3717, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10954616588419405, | |
| "grad_norm": 24.187419891357422, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 5.8736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 21.968637466430664, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 7.358, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11580594679186229, | |
| "grad_norm": 19.923280715942383, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 5.8589, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1189358372456964, | |
| "grad_norm": 18.508562088012695, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 5.0105, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12206572769953052, | |
| "grad_norm": 22.998958587646484, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 6.4225, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12519561815336464, | |
| "grad_norm": 25.26504898071289, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 5.3981, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12832550860719874, | |
| "grad_norm": 20.1059627532959, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 5.5859, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13145539906103287, | |
| "grad_norm": 16.89756965637207, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 4.4125, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13458528951486698, | |
| "grad_norm": 19.683380126953125, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 6.3446, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13771517996870108, | |
| "grad_norm": 20.562591552734375, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 5.902, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 18.05992889404297, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 6.2402, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14397496087636932, | |
| "grad_norm": 19.82953643798828, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 6.349, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14710485133020346, | |
| "grad_norm": 21.304370880126953, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 6.3377, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15023474178403756, | |
| "grad_norm": 19.656156539916992, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.2723, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15336463223787167, | |
| "grad_norm": 20.485694885253906, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 4.8062, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1564945226917058, | |
| "grad_norm": 21.565053939819336, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 7.1065, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1564945226917058, | |
| "eval_loss": 1.390590786933899, | |
| "eval_runtime": 50.8832, | |
| "eval_samples_per_second": 10.593, | |
| "eval_steps_per_second": 2.653, | |
| "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": 7.15499004493824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |