| { | |
| "best_metric": 0.7088869214057922, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3669724770642202, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007339449541284404, | |
| "grad_norm": 1.2558354139328003, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007339449541284404, | |
| "eval_loss": 1.086421012878418, | |
| "eval_runtime": 7.422, | |
| "eval_samples_per_second": 30.989, | |
| "eval_steps_per_second": 7.815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014678899082568808, | |
| "grad_norm": 1.3153743743896484, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9991, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022018348623853212, | |
| "grad_norm": 1.2754677534103394, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0084, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029357798165137616, | |
| "grad_norm": 1.09935462474823, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8748, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 0.9235318899154663, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.044036697247706424, | |
| "grad_norm": 0.8946143388748169, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6866, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05137614678899083, | |
| "grad_norm": 0.7832019329071045, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8417, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05871559633027523, | |
| "grad_norm": 0.6342179179191589, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8374, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06605504587155964, | |
| "grad_norm": 0.8697676062583923, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8561, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07339449541284404, | |
| "grad_norm": 0.6957120895385742, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7363, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08073394495412844, | |
| "grad_norm": 0.7035614252090454, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.6709, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08807339449541285, | |
| "grad_norm": 0.7856741547584534, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.7045, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09541284403669725, | |
| "grad_norm": 0.6767359972000122, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.7028, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10275229357798166, | |
| "grad_norm": 0.6897175312042236, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.8113, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.6219428181648254, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.7361, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11743119266055047, | |
| "grad_norm": 0.5864216685295105, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.7374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12477064220183487, | |
| "grad_norm": 0.5672091245651245, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.6956, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13211009174311927, | |
| "grad_norm": 0.679236650466919, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.8077, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13944954128440368, | |
| "grad_norm": 0.533450186252594, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.7256, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.5469915270805359, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.7653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15412844036697249, | |
| "grad_norm": 0.5419031381607056, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.6857, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1614678899082569, | |
| "grad_norm": 0.570133626461029, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.7016, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1688073394495413, | |
| "grad_norm": 0.5922853946685791, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.7305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1761467889908257, | |
| "grad_norm": 0.5787784457206726, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.7127, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "grad_norm": 0.638210117816925, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7038, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1908256880733945, | |
| "grad_norm": 0.7027117013931274, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.8599, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1981651376146789, | |
| "grad_norm": 0.6234266757965088, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.9354, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20550458715596331, | |
| "grad_norm": 0.6509023904800415, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.8259, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21284403669724772, | |
| "grad_norm": 0.6378542184829712, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.8374, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22018348623853212, | |
| "grad_norm": 0.6379691958427429, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.8669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22752293577981653, | |
| "grad_norm": 0.6336305737495422, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.826, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23486238532110093, | |
| "grad_norm": 0.6773037314414978, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.9538, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.24220183486238533, | |
| "grad_norm": 0.7563718557357788, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.9694, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24954128440366974, | |
| "grad_norm": 1.450920820236206, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.2884, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.25688073394495414, | |
| "grad_norm": 0.45205074548721313, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.5391, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.26422018348623855, | |
| "grad_norm": 0.4610302746295929, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.5379, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27155963302752295, | |
| "grad_norm": 0.43490421772003174, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.5828, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.27889908256880735, | |
| "grad_norm": 0.440649151802063, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.6633, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.28623853211009176, | |
| "grad_norm": 0.39390572905540466, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.5561, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29357798165137616, | |
| "grad_norm": 0.38463252782821655, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30091743119266057, | |
| "grad_norm": 0.582129955291748, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.5935, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.30825688073394497, | |
| "grad_norm": 0.39041706919670105, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.7517, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3155963302752294, | |
| "grad_norm": 0.398325115442276, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.7902, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3229357798165138, | |
| "grad_norm": 0.3442983031272888, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.4754, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3302752293577982, | |
| "grad_norm": 0.37911897897720337, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.5692, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3376146788990826, | |
| "grad_norm": 0.40420764684677124, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.625, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.344954128440367, | |
| "grad_norm": 0.4506022036075592, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.6983, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3522935779816514, | |
| "grad_norm": 0.415752649307251, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7061, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3596330275229358, | |
| "grad_norm": 0.42149221897125244, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.6839, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 0.4243476390838623, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.5976, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "eval_loss": 0.7088869214057922, | |
| "eval_runtime": 7.4157, | |
| "eval_samples_per_second": 31.015, | |
| "eval_steps_per_second": 7.821, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 7728482431795200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |