| { | |
| "best_metric": 2.1148202419281006, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0432432432432432, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 0.11914951354265213, | |
| "learning_rate": 5e-05, | |
| "loss": 2.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "eval_loss": 2.171900749206543, | |
| "eval_runtime": 4.7024, | |
| "eval_samples_per_second": 16.587, | |
| "eval_steps_per_second": 2.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 0.17773401737213135, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1798, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 0.13660414516925812, | |
| "learning_rate": 9.977359612865423e-05, | |
| "loss": 2.24, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 0.10524311661720276, | |
| "learning_rate": 9.909643486313533e-05, | |
| "loss": 2.2441, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.1374163031578064, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 2.1152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.518918918918919, | |
| "grad_norm": 0.12284191697835922, | |
| "learning_rate": 9.641839665080363e-05, | |
| "loss": 2.2278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6054054054054054, | |
| "grad_norm": 0.10054270923137665, | |
| "learning_rate": 9.444177243274618e-05, | |
| "loss": 2.2079, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6918918918918919, | |
| "grad_norm": 0.12604913115501404, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 2.0979, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7783783783783784, | |
| "grad_norm": 0.07987943291664124, | |
| "learning_rate": 8.930265473713938e-05, | |
| "loss": 2.246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.0755382850766182, | |
| "learning_rate": 8.618670190525352e-05, | |
| "loss": 2.2098, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9513513513513514, | |
| "grad_norm": 0.13505445420742035, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 2.185, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0432432432432432, | |
| "grad_norm": 0.14861004054546356, | |
| "learning_rate": 7.900284547855991e-05, | |
| "loss": 3.3208, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1297297297297297, | |
| "grad_norm": 0.12275723367929459, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3568, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 0.11123108863830566, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 1.6117, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3027027027027027, | |
| "grad_norm": 0.10868777334690094, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 2.5143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3891891891891892, | |
| "grad_norm": 0.1214822381734848, | |
| "learning_rate": 6.178794677547137e-05, | |
| "loss": 2.3654, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4756756756756757, | |
| "grad_norm": 0.08418556302785873, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 1.3169, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5621621621621622, | |
| "grad_norm": 0.1199982762336731, | |
| "learning_rate": 5.2379095791187124e-05, | |
| "loss": 2.9381, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6486486486486487, | |
| "grad_norm": 0.13079090416431427, | |
| "learning_rate": 4.762090420881289e-05, | |
| "loss": 2.2235, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7351351351351352, | |
| "grad_norm": 0.09654580801725388, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 1.6745, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8216216216216217, | |
| "grad_norm": 0.11459948122501373, | |
| "learning_rate": 3.821205322452863e-05, | |
| "loss": 2.6848, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9081081081081082, | |
| "grad_norm": 0.14537884294986725, | |
| "learning_rate": 3.364660183412892e-05, | |
| "loss": 2.1633, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9945945945945946, | |
| "grad_norm": 0.11259680986404419, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 3.0638, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0864864864864865, | |
| "grad_norm": 0.06317701935768127, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "grad_norm": 0.0733196958899498, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 2.1368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "eval_loss": 2.1148202419281006, | |
| "eval_runtime": 4.4265, | |
| "eval_samples_per_second": 17.621, | |
| "eval_steps_per_second": 2.259, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2594594594594595, | |
| "grad_norm": 0.08170148730278015, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 2.1414, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.345945945945946, | |
| "grad_norm": 0.06469491124153137, | |
| "learning_rate": 1.3813298094746491e-05, | |
| "loss": 2.2124, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 0.08539947867393494, | |
| "learning_rate": 1.0697345262860636e-05, | |
| "loss": 2.0401, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.518918918918919, | |
| "grad_norm": 0.08035576343536377, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 2.1775, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6054054054054054, | |
| "grad_norm": 0.06767440587282181, | |
| "learning_rate": 5.558227567253832e-06, | |
| "loss": 2.224, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.691891891891892, | |
| "grad_norm": 0.08720237016677856, | |
| "learning_rate": 3.581603349196372e-06, | |
| "loss": 2.1221, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.7783783783783784, | |
| "grad_norm": 0.06554112583398819, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 2.1821, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.864864864864865, | |
| "grad_norm": 0.06643765419721603, | |
| "learning_rate": 9.035651368646648e-07, | |
| "loss": 2.1201, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.9513513513513514, | |
| "grad_norm": 0.10307445377111435, | |
| "learning_rate": 2.2640387134577058e-07, | |
| "loss": 2.0542, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0432432432432432, | |
| "grad_norm": 0.13227105140686035, | |
| "learning_rate": 0.0, | |
| "loss": 3.2883, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.841261823000576e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |