| { | |
| "best_metric": 0.3243732452392578, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.041275410174388606, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016510164069755444, | |
| "grad_norm": 3.0247745513916016, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016510164069755444, | |
| "eval_loss": 0.5801298022270203, | |
| "eval_runtime": 152.3421, | |
| "eval_samples_per_second": 26.788, | |
| "eval_steps_per_second": 3.354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033020328139510887, | |
| "grad_norm": 0.26526594161987305, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5465, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004953049220926633, | |
| "grad_norm": 0.2640111446380615, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5798, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006604065627902177, | |
| "grad_norm": 0.2363673597574234, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008255082034877721, | |
| "grad_norm": 0.211054265499115, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5095, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009906098441853266, | |
| "grad_norm": 0.18822599947452545, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01155711484882881, | |
| "grad_norm": 0.20426109433174133, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5167, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013208131255804355, | |
| "grad_norm": 0.2221483439207077, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4754, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014859147662779898, | |
| "grad_norm": 0.18756835162639618, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4448, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016510164069755442, | |
| "grad_norm": 0.16543976962566376, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.416, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018161180476730987, | |
| "grad_norm": 0.7194027900695801, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2621, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019812196883706532, | |
| "grad_norm": 0.17668159306049347, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1983, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021463213290682077, | |
| "grad_norm": 0.1292767971754074, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2998, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02311422969765762, | |
| "grad_norm": 0.15346571803092957, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3568, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.024765246104633164, | |
| "grad_norm": 0.1705729067325592, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3867, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02641626251160871, | |
| "grad_norm": 0.1557266265153885, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4098, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028067278918584255, | |
| "grad_norm": 0.13209468126296997, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029718295325559797, | |
| "grad_norm": 0.11559902131557465, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3883, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03136931173253534, | |
| "grad_norm": 0.09431163221597672, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3791, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.033020328139510884, | |
| "grad_norm": 0.09266266971826553, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03467134454648643, | |
| "grad_norm": 0.10236460715532303, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3849, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036322360953461974, | |
| "grad_norm": 0.10628839582204819, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3592, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03797337736043752, | |
| "grad_norm": 0.1099647805094719, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2481, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.039624393767413064, | |
| "grad_norm": 0.10537803918123245, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1525, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.041275410174388606, | |
| "grad_norm": 0.16766606271266937, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2986, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041275410174388606, | |
| "eval_loss": 0.3243732452392578, | |
| "eval_runtime": 152.2878, | |
| "eval_samples_per_second": 26.798, | |
| "eval_steps_per_second": 3.355, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.127523877752668e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |