| { | |
| "best_metric": 11.930004119873047, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1966173361522197, | |
| "eval_steps": 25, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06765327695560254, | |
| "grad_norm": 0.0392795167863369, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06765327695560254, | |
| "eval_loss": 11.933514595031738, | |
| "eval_runtime": 0.1761, | |
| "eval_samples_per_second": 283.878, | |
| "eval_steps_per_second": 73.808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13530655391120508, | |
| "grad_norm": 0.04598506912589073, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9315, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2029598308668076, | |
| "grad_norm": 0.04669319838285446, | |
| "learning_rate": 9.987995276485983e-05, | |
| "loss": 11.9328, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27061310782241016, | |
| "grad_norm": 0.04279451444745064, | |
| "learning_rate": 9.952045156337997e-05, | |
| "loss": 11.9325, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3382663847780127, | |
| "grad_norm": 0.04721859097480774, | |
| "learning_rate": 9.892341449001673e-05, | |
| "loss": 11.9311, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4059196617336152, | |
| "grad_norm": 0.05670558288693428, | |
| "learning_rate": 9.809202699587827e-05, | |
| "loss": 11.9316, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47357293868921774, | |
| "grad_norm": 0.057297077029943466, | |
| "learning_rate": 9.703072489296466e-05, | |
| "loss": 11.9331, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5412262156448203, | |
| "grad_norm": 0.05174463614821434, | |
| "learning_rate": 9.574517068719161e-05, | |
| "loss": 11.931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6088794926004228, | |
| "grad_norm": 0.059148453176021576, | |
| "learning_rate": 9.424222336647135e-05, | |
| "loss": 11.9318, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6765327695560254, | |
| "grad_norm": 0.05975916236639023, | |
| "learning_rate": 9.252990180504451e-05, | |
| "loss": 11.9317, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.04641880840063095, | |
| "learning_rate": 9.061734197931644e-05, | |
| "loss": 11.931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8118393234672304, | |
| "grad_norm": 0.06561887264251709, | |
| "learning_rate": 8.851474822347019e-05, | |
| "loss": 11.9304, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.879492600422833, | |
| "grad_norm": 0.0627252608537674, | |
| "learning_rate": 8.623333878492854e-05, | |
| "loss": 11.9309, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9471458773784355, | |
| "grad_norm": 0.07406969368457794, | |
| "learning_rate": 8.37852859701501e-05, | |
| "loss": 11.9298, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.06553911205074, | |
| "grad_norm": 0.1514955312013626, | |
| "learning_rate": 8.118365120010789e-05, | |
| "loss": 23.6349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1331923890063424, | |
| "grad_norm": 0.08357280492782593, | |
| "learning_rate": 7.844231532195686e-05, | |
| "loss": 11.8246, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.200845665961945, | |
| "grad_norm": 0.08903574198484421, | |
| "learning_rate": 7.557590454870874e-05, | |
| "loss": 11.8898, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2684989429175475, | |
| "grad_norm": 0.07034370303153992, | |
| "learning_rate": 7.259971242205702e-05, | |
| "loss": 11.9294, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3361522198731501, | |
| "grad_norm": 0.08530696481466293, | |
| "learning_rate": 6.952961821471509e-05, | |
| "loss": 11.9744, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4038054968287526, | |
| "grad_norm": 0.08774761110544205, | |
| "learning_rate": 6.638200220762563e-05, | |
| "loss": 11.9067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4714587737843552, | |
| "grad_norm": 0.09668412059545517, | |
| "learning_rate": 6.317365829407465e-05, | |
| "loss": 12.0467, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5391120507399578, | |
| "grad_norm": 0.08837971091270447, | |
| "learning_rate": 5.992170437700436e-05, | |
| "loss": 11.9084, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6067653276955602, | |
| "grad_norm": 0.09495086222887039, | |
| "learning_rate": 5.6643491037594666e-05, | |
| "loss": 11.8547, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6744186046511627, | |
| "grad_norm": 0.09795354306697845, | |
| "learning_rate": 5.335650896240535e-05, | |
| "loss": 11.9338, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7420718816067653, | |
| "grad_norm": 0.0874452292919159, | |
| "learning_rate": 5.0078295622995664e-05, | |
| "loss": 11.8838, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7420718816067653, | |
| "eval_loss": 11.930004119873047, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 309.787, | |
| "eval_steps_per_second": 80.545, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.809725158562368, | |
| "grad_norm": 0.10472561419010162, | |
| "learning_rate": 4.682634170592537e-05, | |
| "loss": 11.9661, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8773784355179703, | |
| "grad_norm": 0.10933728516101837, | |
| "learning_rate": 4.3617997792374365e-05, | |
| "loss": 11.9384, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.945031712473573, | |
| "grad_norm": 0.10500363260507584, | |
| "learning_rate": 4.0470381785284936e-05, | |
| "loss": 11.9867, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.063424947145877, | |
| "grad_norm": 0.202621728181839, | |
| "learning_rate": 3.7400287577942993e-05, | |
| "loss": 23.6529, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.13107822410148, | |
| "grad_norm": 0.1180591881275177, | |
| "learning_rate": 3.4424095451291274e-05, | |
| "loss": 11.6859, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1987315010570825, | |
| "grad_norm": 0.1156446561217308, | |
| "learning_rate": 3.155768467804314e-05, | |
| "loss": 11.953, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.266384778012685, | |
| "grad_norm": 0.10630480200052261, | |
| "learning_rate": 2.8816348799892133e-05, | |
| "loss": 11.8165, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3340380549682873, | |
| "grad_norm": 0.11527036130428314, | |
| "learning_rate": 2.621471402984991e-05, | |
| "loss": 12.0291, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.40169133192389, | |
| "grad_norm": 0.11367418617010117, | |
| "learning_rate": 2.3766661215071475e-05, | |
| "loss": 11.9994, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4693446088794926, | |
| "grad_norm": 0.11251702904701233, | |
| "learning_rate": 2.148525177652982e-05, | |
| "loss": 12.0468, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.536997885835095, | |
| "grad_norm": 0.11068017780780792, | |
| "learning_rate": 1.938265802068357e-05, | |
| "loss": 12.0091, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.604651162790698, | |
| "grad_norm": 0.11702769994735718, | |
| "learning_rate": 1.74700981949555e-05, | |
| "loss": 11.6006, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6723044397463003, | |
| "grad_norm": 0.12750905752182007, | |
| "learning_rate": 1.5757776633528655e-05, | |
| "loss": 12.0497, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7399577167019027, | |
| "grad_norm": 0.11485005170106888, | |
| "learning_rate": 1.4254829312808404e-05, | |
| "loss": 11.7737, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.807610993657505, | |
| "grad_norm": 0.12216285616159439, | |
| "learning_rate": 1.2969275107035345e-05, | |
| "loss": 12.0644, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.875264270613108, | |
| "grad_norm": 0.11762136220932007, | |
| "learning_rate": 1.1907973004121738e-05, | |
| "loss": 11.9411, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9429175475687104, | |
| "grad_norm": 0.11637993156909943, | |
| "learning_rate": 1.1076585509983283e-05, | |
| "loss": 12.1162, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.061310782241015, | |
| "grad_norm": 0.2240166813135147, | |
| "learning_rate": 1.0479548436620041e-05, | |
| "loss": 23.5234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.1289640591966172, | |
| "grad_norm": 0.1293584406375885, | |
| "learning_rate": 1.0120047235140178e-05, | |
| "loss": 11.7586, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.1966173361522197, | |
| "grad_norm": 0.13719302415847778, | |
| "learning_rate": 1e-05, | |
| "loss": 11.948, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 45, | |
| "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": 938244833280.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |