| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.905525846702317, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.318, | |
| "eval_samples_per_second": 11.579, | |
| "eval_steps_per_second": 3.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991464979316699e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.965892293523712e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.864086212157544e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.39928698752228164, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.788239001922206e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4563279857397504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.588093723187857e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5704099821746881, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.46455487428603e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6844919786096256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.172886105602998e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7415329768270945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.005862585365517e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7985739750445633, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.632602756833172e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9126559714795008, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.42778235091909e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.053475935828877, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.985642378322276e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1105169340463459, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1675579322638145, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2245989304812834, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.254036429817058e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2816399286987523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.995596597658468e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.338680926916221, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3957219251336899, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462698874429239e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4527629233511585, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.190262446954085e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4527629233511585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3166, | |
| "eval_samples_per_second": 11.583, | |
| "eval_steps_per_second": 3.012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5098039215686274, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9152076175848594e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5668449197860963, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6385777635027684e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6238859180035652, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.361422236497235e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6809269162210339, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0847923824151424e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7379679144385025, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.809737553045916e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7950089126559714, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.537301125570763e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8520499108734403, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.268516544675628e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.004403402341532e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.966131907308378, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7459635701829435e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.049910873440285, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.494177399005578e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.106951871657754, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.163992869875223, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.014357621677724e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.2210338680926918, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7881441362933468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2780748663101607, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5722176490809118e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.335115864527629, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3673972431668306e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.392156862745098, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1744598725070347e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.449197860962567, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.994137414634483e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.5062388591800357, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.827113894397003e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5632798573975046, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.674022889216737e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.620320855614973, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.53544512571397e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.677361853832442, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4119062768121433e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.734402852049911, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3038749676803994e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7914438502673797, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2117609980777959e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8484848484848486, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1359137878424578e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.905525846702317, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.076621051422442e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.905525846702317, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3476, | |
| "eval_samples_per_second": 11.501, | |
| "eval_steps_per_second": 2.99, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 53, | |
| "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": 5.6711086619806925e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |