| { | |
| "best_metric": 1.7354482412338257, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01994813484939158, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "grad_norm": 2.8758528232574463, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "eval_loss": 3.5597481727600098, | |
| "eval_runtime": 112.8506, | |
| "eval_samples_per_second": 4.679, | |
| "eval_steps_per_second": 2.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 2.3059797286987305, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7981, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "grad_norm": 2.3253207206726074, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4762, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 3.0633058547973633, | |
| "learning_rate": 8e-05, | |
| "loss": 4.314, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "grad_norm": 2.5281550884246826, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6369, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "eval_loss": 3.4488863945007324, | |
| "eval_runtime": 113.3494, | |
| "eval_samples_per_second": 4.658, | |
| "eval_steps_per_second": 2.329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.609208822250366, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4644, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005585477757829643, | |
| "grad_norm": 3.4844303131103516, | |
| "learning_rate": 0.00014, | |
| "loss": 3.608, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 4.003000736236572, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1775, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "grad_norm": 2.684307813644409, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7451, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 3.117142677307129, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "eval_loss": 2.5102765560150146, | |
| "eval_runtime": 112.4497, | |
| "eval_samples_per_second": 4.695, | |
| "eval_steps_per_second": 2.348, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008777179333732297, | |
| "grad_norm": 3.2941677570343018, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.6612, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009575104727707959, | |
| "grad_norm": 3.6355504989624023, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.4075, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010373030121683623, | |
| "grad_norm": 3.447693109512329, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7719, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011170955515659286, | |
| "grad_norm": 4.26869010925293, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.0118, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "grad_norm": 4.2341389656066895, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9992, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "eval_loss": 1.9001727104187012, | |
| "eval_runtime": 111.7285, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 2.363, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012766806303610613, | |
| "grad_norm": 3.968799352645874, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0193, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013564731697586275, | |
| "grad_norm": 4.071308612823486, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.7212, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 2.9081594944000244, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5923, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015160582485537602, | |
| "grad_norm": 2.9626481533050537, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7981, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "grad_norm": 3.4484167098999023, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "eval_loss": 1.7614365816116333, | |
| "eval_runtime": 114.7069, | |
| "eval_samples_per_second": 4.603, | |
| "eval_steps_per_second": 2.302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016756433273488927, | |
| "grad_norm": 3.320969581604004, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.9593, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017554358667464593, | |
| "grad_norm": 3.7878010272979736, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.0258, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018352284061440256, | |
| "grad_norm": 2.8557920455932617, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6035, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019150209455415918, | |
| "grad_norm": 3.2410473823547363, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.8767, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "grad_norm": 2.478067636489868, | |
| "learning_rate": 0.0, | |
| "loss": 1.454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "eval_loss": 1.7354482412338257, | |
| "eval_runtime": 110.8877, | |
| "eval_samples_per_second": 4.762, | |
| "eval_steps_per_second": 2.381, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 4623910620364800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |