| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.7410228509249184, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03482045701849837, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03482045701849837, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4909, | |
| "eval_samples_per_second": 33.537, | |
| "eval_steps_per_second": 8.72, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06964091403699674, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1044613710554951, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13928182807399347, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17410228509249184, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996776896673492e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2089227421109902, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987112203758434e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24374319912948858, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.971019765834333e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27856365614798695, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.948522635163499e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3133841131664853, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.919653038668912e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3482045701849837, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.88445233176946e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.383025027203482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8429709391387e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4178454842219804, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.795268282471998e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45266594124047876, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.741412695365528e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.48748639825897716, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.681481325429045e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5223068552774756, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.615560023772684e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5571273122959739, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.543743222026071e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5919477693144722, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.46613379706592e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6267682263329706, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.382842923645904e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.661588683351469, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.29398991513988e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6964091403699674, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.199702052626646e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7312295973884657, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.100114402561006e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.766050054406964, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.995369623292385e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8008705114254625, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.885617760708116e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8356909684439608, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771016033294148e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8705114254624592, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.651728606921079e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8705114254624592, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4905, | |
| "eval_samples_per_second": 33.546, | |
| "eval_steps_per_second": 8.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9053318824809575, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.527926359678135e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.940152339499456, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.399786637091947e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9749727965179543, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.267492998080791e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0097932535364527, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.131234952008212e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0446137105549511, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.99120768721268e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0794341675734493, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.847611791402181e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1142546245919478, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.70065296431425e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1490750816104462, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.550541723053088e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1838955386289445, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.397493100525829e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.218715995647443, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.241726337409979e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2535364526659412, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.083464568093249e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2883569096844396, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.922934501035709e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.323177366702938, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.760366094012083e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3579978237214363, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.595992224699463e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3928182807399347, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.430048357082287e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.427638737758433, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.262772204152436e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4624591947769314, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0944033873876616e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4972796517954299, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9251830934961414e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5321001088139283, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.755353728918834e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5669205658324266, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5851585725845854e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6017410228509248, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4148414274154156e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6365614798694232, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2446462710811675e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6713819368879217, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0748169065038596e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7062023939064201, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.905596612612341e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7410228509249184, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.737227795847565e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7410228509249184, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4904, | |
| "eval_samples_per_second": 33.548, | |
| "eval_steps_per_second": 8.722, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 87, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.305284264198144e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |