| { | |
| "best_metric": 0.8329792022705078, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008840951286358412, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017681902572716824, | |
| "grad_norm": 31.273752212524414, | |
| "learning_rate": 1e-05, | |
| "loss": 5.7904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017681902572716824, | |
| "eval_loss": 1.5057493448257446, | |
| "eval_runtime": 707.0176, | |
| "eval_samples_per_second": 13.472, | |
| "eval_steps_per_second": 3.369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003536380514543365, | |
| "grad_norm": 33.96555709838867, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1229, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005304570771815047, | |
| "grad_norm": 22.80571937561035, | |
| "learning_rate": 3e-05, | |
| "loss": 5.831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000707276102908673, | |
| "grad_norm": 17.077383041381836, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8649, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008840951286358412, | |
| "grad_norm": 15.064048767089844, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010609141543630094, | |
| "grad_norm": 12.101446151733398, | |
| "learning_rate": 6e-05, | |
| "loss": 3.9707, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012377331800901778, | |
| "grad_norm": 10.376118659973145, | |
| "learning_rate": 7e-05, | |
| "loss": 3.7705, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001414552205817346, | |
| "grad_norm": 10.354647636413574, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001591371231544514, | |
| "grad_norm": 10.469047546386719, | |
| "learning_rate": 9e-05, | |
| "loss": 3.4053, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017681902572716825, | |
| "grad_norm": 9.278939247131348, | |
| "learning_rate": 0.0001, | |
| "loss": 3.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019450092829988506, | |
| "grad_norm": 15.399981498718262, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 3.6484, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002121828308726019, | |
| "grad_norm": 10.160966873168945, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.5971, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002298647334453187, | |
| "grad_norm": 7.888012886047363, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.4807, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0024754663601803555, | |
| "grad_norm": 7.219862937927246, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 3.3483, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0026522853859075237, | |
| "grad_norm": 6.999874114990234, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.27, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002829104411634692, | |
| "grad_norm": 6.7764692306518555, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 3.2381, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00300592343736186, | |
| "grad_norm": 7.229355812072754, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 3.1572, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003182742463089028, | |
| "grad_norm": 7.318708419799805, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.2629, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033595614888161968, | |
| "grad_norm": 7.011357307434082, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.1216, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003536380514543365, | |
| "grad_norm": 6.351388454437256, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.1227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003713199540270533, | |
| "grad_norm": 6.193704128265381, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.0576, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0038900185659977013, | |
| "grad_norm": 6.23767614364624, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.1666, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00406683759172487, | |
| "grad_norm": 5.724069118499756, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 3.0868, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004243656617452038, | |
| "grad_norm": 6.114058494567871, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.1426, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004420475643179206, | |
| "grad_norm": 6.249318599700928, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 3.1009, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004597294668906374, | |
| "grad_norm": 5.979328632354736, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 3.0182, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0047741136946335425, | |
| "grad_norm": 5.138391971588135, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 2.7047, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004950932720360711, | |
| "grad_norm": 5.40130090713501, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.1115, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005127751746087879, | |
| "grad_norm": 5.664342403411865, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.8735, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005304570771815047, | |
| "grad_norm": 5.740615367889404, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.1383, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005481389797542215, | |
| "grad_norm": 5.822990417480469, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 2.7514, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005658208823269384, | |
| "grad_norm": 6.541563034057617, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 2.896, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005835027848996552, | |
| "grad_norm": 5.708773612976074, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.9389, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00601184687472372, | |
| "grad_norm": 5.139838218688965, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.85, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006188665900450889, | |
| "grad_norm": 4.9747796058654785, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.9934, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006365484926178056, | |
| "grad_norm": 4.744929313659668, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.893, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006542303951905225, | |
| "grad_norm": 5.647818088531494, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.0005, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0067191229776323936, | |
| "grad_norm": 5.120396614074707, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 2.8626, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006895942003359561, | |
| "grad_norm": 5.247471809387207, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 2.9666, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00707276102908673, | |
| "grad_norm": 5.75712251663208, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 2.7657, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007249580054813898, | |
| "grad_norm": 5.175816535949707, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 2.9367, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007426399080541066, | |
| "grad_norm": 5.635525703430176, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 2.8576, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007603218106268235, | |
| "grad_norm": 4.829882621765137, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 2.6487, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0077800371319954025, | |
| "grad_norm": 4.661524295806885, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 2.7636, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007956856157722571, | |
| "grad_norm": 5.161839008331299, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.7386, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00813367518344974, | |
| "grad_norm": 5.641641616821289, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 2.6801, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008310494209176908, | |
| "grad_norm": 5.284437656402588, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 2.7854, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008487313234904075, | |
| "grad_norm": 4.893701076507568, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.6241, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008664132260631244, | |
| "grad_norm": 5.710663795471191, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 2.6486, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008840951286358412, | |
| "grad_norm": 5.808746337890625, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.8028, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008840951286358412, | |
| "eval_loss": 0.8329792022705078, | |
| "eval_runtime": 712.2685, | |
| "eval_samples_per_second": 13.373, | |
| "eval_steps_per_second": 3.344, | |
| "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": 7.15499809800192e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |