| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.16622691292876, | |
| "eval_steps": 25, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08443271767810026, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 86339.9141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08443271767810026, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2197, | |
| "eval_samples_per_second": 9.579, | |
| "eval_steps_per_second": 2.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16886543535620052, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2532981530343008, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.980803793327656e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.33773087071240104, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42216358839050133, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828215394277687e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5065963060686016, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5910290237467019, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.528234811097782e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6754617414248021, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7598944591029023, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.091077522761079e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8443271767810027, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9287598944591029, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.531630396409507e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0554089709762533, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1398416886543536, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.868944732948101e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2242744063324538, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3087071240105541, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.12558749784219e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3931398416886545, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4775725593667546, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.326872830174567e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.562005277044855, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9152076175848594e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6464379947229553, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7308707124010554, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0847923824151424e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8153034300791555, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.673127169825433e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.899736147757256, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.268516544675628e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0263852242744065, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8744125021578126e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1108179419525066, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.494177399005578e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.1952506596306067, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1310552670518986e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1952506596306067, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9759, | |
| "eval_samples_per_second": 10.048, | |
| "eval_steps_per_second": 2.613, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2796833773087073, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7881441362933468e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3641160949868074, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4683696035904928e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4485488126649075, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1744598725070347e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.532981530343008, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9089224772389225e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6174142480211082, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.674022889216737e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.7018469656992083, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4717651889022202e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.786279683377309, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3038749676803994e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.870712401055409, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1717846057223144e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.955145118733509, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.076621051422442e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0817941952506596, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.019196206672345e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.16622691292876, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "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": 4.725976251372667e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |