| { | |
| "best_metric": 11.736578941345215, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0386740331491713, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08839779005524862, | |
| "grad_norm": 0.18353284895420074, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08839779005524862, | |
| "eval_loss": 11.764076232910156, | |
| "eval_runtime": 0.2313, | |
| "eval_samples_per_second": 328.575, | |
| "eval_steps_per_second": 43.234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17679558011049723, | |
| "grad_norm": 0.2731476128101349, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 0.2726351320743561, | |
| "learning_rate": 9.975923633360985e-05, | |
| "loss": 11.7504, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.35359116022099446, | |
| "grad_norm": 0.21370616555213928, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.7589, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4419889502762431, | |
| "grad_norm": 0.31159594655036926, | |
| "learning_rate": 9.784701678661045e-05, | |
| "loss": 11.7572, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5303867403314917, | |
| "grad_norm": 0.24750736355781555, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.7589, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6187845303867403, | |
| "grad_norm": 0.24531951546669006, | |
| "learning_rate": 9.409606321741775e-05, | |
| "loss": 11.7569, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7071823204419889, | |
| "grad_norm": 0.3198428750038147, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.7423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7955801104972375, | |
| "grad_norm": 0.20434612035751343, | |
| "learning_rate": 8.865052266813685e-05, | |
| "loss": 11.7466, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8839779005524862, | |
| "grad_norm": 0.2541300654411316, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.7433, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9723756906077348, | |
| "grad_norm": 0.3244708180427551, | |
| "learning_rate": 8.171966420818228e-05, | |
| "loss": 11.7352, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0718232044198894, | |
| "grad_norm": 0.45572996139526367, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 21.3282, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.160220994475138, | |
| "grad_norm": 0.28523340821266174, | |
| "learning_rate": 7.35698368412999e-05, | |
| "loss": 11.7556, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2486187845303867, | |
| "grad_norm": 0.31561416387557983, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.7718, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3370165745856353, | |
| "grad_norm": 0.21716861426830292, | |
| "learning_rate": 6.451423386272312e-05, | |
| "loss": 11.8288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4254143646408841, | |
| "grad_norm": 0.30432766675949097, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.6526, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5138121546961325, | |
| "grad_norm": 0.2790243923664093, | |
| "learning_rate": 5.490085701647805e-05, | |
| "loss": 11.4799, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6022099447513813, | |
| "grad_norm": 0.2546989321708679, | |
| "learning_rate": 5e-05, | |
| "loss": 12.0539, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6906077348066297, | |
| "grad_norm": 0.3556356430053711, | |
| "learning_rate": 4.509914298352197e-05, | |
| "loss": 11.5273, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7790055248618786, | |
| "grad_norm": 0.25871017575263977, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.7603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.867403314917127, | |
| "grad_norm": 0.28713786602020264, | |
| "learning_rate": 3.5485766137276894e-05, | |
| "loss": 11.8601, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9558011049723758, | |
| "grad_norm": 0.3975193202495575, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.6956, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0552486187845305, | |
| "grad_norm": 0.43229255080223083, | |
| "learning_rate": 2.6430163158700115e-05, | |
| "loss": 21.1999, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.143646408839779, | |
| "grad_norm": 0.3099013566970825, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.836, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2320441988950277, | |
| "grad_norm": 0.38912683725357056, | |
| "learning_rate": 1.8280335791817733e-05, | |
| "loss": 11.786, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2320441988950277, | |
| "eval_loss": 11.736578941345215, | |
| "eval_runtime": 0.2257, | |
| "eval_samples_per_second": 336.673, | |
| "eval_steps_per_second": 44.299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.320441988950276, | |
| "grad_norm": 0.2449338138103485, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.7723, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.408839779005525, | |
| "grad_norm": 0.32377758622169495, | |
| "learning_rate": 1.134947733186315e-05, | |
| "loss": 11.6414, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4972375690607733, | |
| "grad_norm": 0.3684104382991791, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.7025, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.585635359116022, | |
| "grad_norm": 0.22891204059123993, | |
| "learning_rate": 5.903936782582253e-06, | |
| "loss": 11.8576, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6740331491712706, | |
| "grad_norm": 0.35814169049263, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.5289, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.7624309392265194, | |
| "grad_norm": 0.3069237768650055, | |
| "learning_rate": 2.152983213389559e-06, | |
| "loss": 11.6858, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.8508287292817682, | |
| "grad_norm": 0.3071037828922272, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.8644, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.9392265193370166, | |
| "grad_norm": 0.36816585063934326, | |
| "learning_rate": 2.407636663901591e-07, | |
| "loss": 11.7761, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.0386740331491713, | |
| "grad_norm": 0.5083048343658447, | |
| "learning_rate": 0.0, | |
| "loss": 20.9873, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "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": 111442573393920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |