| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0508474576271185, | |
| "eval_steps": 25, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1505, | |
| "eval_samples_per_second": 12.047, | |
| "eval_steps_per_second": 3.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987995276485983e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.952045156337997e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.892341449001673e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.809202699587827e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.703072489296466e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.574517068719161e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.424222336647135e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.252990180504451e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.061734197931644e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.851474822347019e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.623333878492854e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.37852859701501e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.118365120010789e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.844231532195686e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.152542372881356, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.557590454870874e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.259971242205702e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.288135593220339, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.952961821471509e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.638200220762563e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.423728813559322, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.317365829407465e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.992170437700436e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.559322033898305, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6643491037594666e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.335650896240535e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0078295622995664e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.1071, | |
| "eval_samples_per_second": 12.174, | |
| "eval_steps_per_second": 3.165, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.682634170592537e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8305084745762712, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3617997792374365e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0470381785284936e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.9661016949152543, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7400287577942993e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4424095451291274e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1016949152542375, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.155768467804314e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8816348799892133e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.23728813559322, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.621471402984991e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3766661215071475e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.148525177652982e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.938265802068357e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.5084745762711864, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.74700981949555e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.576271186440678, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5757776633528655e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.6440677966101696, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4254829312808404e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2969275107035345e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.7796610169491527, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1907973004121738e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.847457627118644, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1076585509983283e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.915254237288136, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0479548436620041e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0120047235140178e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.0508474576271185, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "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": 4.7747558377783296e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |