| { | |
| "best_metric": 6.705550670623779, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04367765887748417, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008735531775496833, | |
| "grad_norm": 1.4449435472488403, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9978, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008735531775496833, | |
| "eval_loss": 6.968753814697266, | |
| "eval_runtime": 1.4941, | |
| "eval_samples_per_second": 322.608, | |
| "eval_steps_per_second": 161.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017471063550993666, | |
| "grad_norm": 1.4993380308151245, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9928, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00262065953264905, | |
| "grad_norm": 1.4574459791183472, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.9832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003494212710198733, | |
| "grad_norm": 1.419170618057251, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.9316, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0043677658877484165, | |
| "grad_norm": 1.4240509271621704, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.9141, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0052413190652981, | |
| "grad_norm": 1.5392475128173828, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006114872242847783, | |
| "grad_norm": 1.274932861328125, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.9167, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006988425420397466, | |
| "grad_norm": 1.3888661861419678, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.9092, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00786197859794715, | |
| "grad_norm": 1.465202808380127, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.9068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008735531775496833, | |
| "grad_norm": 1.5591522455215454, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.8868, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009609084953046517, | |
| "grad_norm": 1.8067896366119385, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.9096, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0104826381305962, | |
| "grad_norm": 1.6886250972747803, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.8846, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011356191308145884, | |
| "grad_norm": 1.358983039855957, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.8703, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012229744485695566, | |
| "grad_norm": 1.5614206790924072, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.8547, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01310329766324525, | |
| "grad_norm": 1.5108997821807861, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.8602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013976850840794933, | |
| "grad_norm": 1.530328631401062, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.845, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014850404018344617, | |
| "grad_norm": 1.5476664304733276, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.8489, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0157239571958943, | |
| "grad_norm": 1.597213625907898, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.8427, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 1.7457237243652344, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.8468, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.017471063550993666, | |
| "grad_norm": 1.5299166440963745, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.8158, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018344616728543352, | |
| "grad_norm": 1.5395684242248535, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.8128, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019218169906093034, | |
| "grad_norm": 2.1613576412200928, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.7643, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020091723083642717, | |
| "grad_norm": 1.7371824979782104, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.8261, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0209652762611924, | |
| "grad_norm": 1.7352039813995361, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.7951, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021838829438742085, | |
| "grad_norm": 1.7246216535568237, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.7577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021838829438742085, | |
| "eval_loss": 6.769979000091553, | |
| "eval_runtime": 1.4861, | |
| "eval_samples_per_second": 324.343, | |
| "eval_steps_per_second": 162.171, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022712382616291767, | |
| "grad_norm": 1.6252830028533936, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7582, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02358593579384145, | |
| "grad_norm": 2.0401527881622314, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.793, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024459488971391132, | |
| "grad_norm": 1.6296247243881226, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.7417, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.025333042148940818, | |
| "grad_norm": 1.617932677268982, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.7578, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0262065953264905, | |
| "grad_norm": 1.6912728548049927, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.7625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027080148504040183, | |
| "grad_norm": 1.5618200302124023, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.7321, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.027953701681589865, | |
| "grad_norm": 1.3636630773544312, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.7536, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02882725485913955, | |
| "grad_norm": 1.4335569143295288, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.6962, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.029700808036689234, | |
| "grad_norm": 1.4494646787643433, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.7455, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.030574361214238916, | |
| "grad_norm": 1.7528541088104248, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.7389, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0314479143917886, | |
| "grad_norm": 1.5459141731262207, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.7231, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.032321467569338284, | |
| "grad_norm": 1.9405611753463745, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.7433, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 1.3924881219863892, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.7279, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03406857392443765, | |
| "grad_norm": 1.5491060018539429, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.7159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03494212710198733, | |
| "grad_norm": 1.3519071340560913, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.035815680279537014, | |
| "grad_norm": 1.2949579954147339, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.7065, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.036689233457086703, | |
| "grad_norm": 1.5274921655654907, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.7177, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.037562786634636386, | |
| "grad_norm": 1.569133996963501, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.7193, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03843633981218607, | |
| "grad_norm": 1.6965569257736206, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.6912, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03930989298973575, | |
| "grad_norm": 1.5818424224853516, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.7327, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04018344616728543, | |
| "grad_norm": 1.557110071182251, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.7336, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.041056999344835116, | |
| "grad_norm": 1.4650180339813232, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.7215, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0419305525223848, | |
| "grad_norm": 1.3557387590408325, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.7157, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04280410569993448, | |
| "grad_norm": 1.563228964805603, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.6898, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04367765887748417, | |
| "grad_norm": 1.5504145622253418, | |
| "learning_rate": 0.0, | |
| "loss": 6.707, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04367765887748417, | |
| "eval_loss": 6.705550670623779, | |
| "eval_runtime": 1.4939, | |
| "eval_samples_per_second": 322.655, | |
| "eval_steps_per_second": 161.328, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 589302988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |