| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.24106066693451186, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032141422257934912, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032141422257934912, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.7668, | |
| "eval_samples_per_second": 10.766, | |
| "eval_steps_per_second": 5.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0064282844515869825, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009642426677380474, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012856568903173965, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016070711128967456, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019284853354760947, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02249899558055444, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02571313780634793, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02892728003214142, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03214142225793491, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035355564483728404, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019988322268323268, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.038569706709521895, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019953316347176488, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.041783848935315386, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001989506399451051, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04499799116110888, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019813701261394136, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04821213338690237, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05142627561269586, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019582458291091663, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05464041783848935, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001943311813257743, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05785456006428284, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019261746489577765, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019068743608505455, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06428284451586982, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06749698674166332, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018619696668800492, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07071112896745681, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018364701380102266, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0739252711932503, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07713941341904379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017796743540632223, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08035355564483729, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08035355564483729, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.3741, | |
| "eval_samples_per_second": 10.853, | |
| "eval_steps_per_second": 5.437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08356769787063077, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017155989607441213, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08678184009642427, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016810158587867973, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08999598232221775, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016448422127361706, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09321012454801125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016071625078187114, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09642426677380474, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09963840899959824, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001527640244106133, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10285255122539172, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001485983413242606, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10606669345118522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014431915455992414, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1092808356769787, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013993645835656953, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1124949779027722, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11570912012856568, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11892326235435918, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001262707378198587, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012157841967678063, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12535154680594615, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011683570413470383, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12856568903173965, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001120536680255323, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13177983125753315, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010724348001617625, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13499397348332665, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010241637452361323, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13820811570912012, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75836254763868e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14142225793491361, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.275651998382377e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1446364001607071, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1478505423865006, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.316429586529615e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15106468461229408, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.84215803232194e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15427882683808758, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.372926218014131e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15749296906388108, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16070711128967458, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.453951129574644e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16070711128967458, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.3643, | |
| "eval_samples_per_second": 10.855, | |
| "eval_steps_per_second": 5.438, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16392125351546805, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.006354164343046e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16713539574126154, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.568084544007588e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.17034953796705504, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.14016586757394e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.17356368019284854, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.723597558938672e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.176777822418642, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1799919646444355, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9283749218128885e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.183206106870229, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5515778726382966e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1864202490960225, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1898414121320276e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.189634391321816, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.84401039255879e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.19284853354760947, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.514892518288988e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19606267577340297, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2032564593677774e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19927681799919647, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.20249096022498997, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6352986198977325e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.20570510245078344, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3803033311995072e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.20891924467657694, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21213338690237044, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.31256391494546e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21534752912816393, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.382535104222366e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2185616713539574, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.668818674225685e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2217758135797509, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.175417089083378e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2249899558055444, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.905818257394799e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2282040980313379, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8629873860586566e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.23141824025713137, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0493600548948878e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.23463238248292487, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.668365282351372e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23784652470871837, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1677731676733584e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.24106066693451186, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24106066693451186, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.3572, | |
| "eval_samples_per_second": 10.857, | |
| "eval_steps_per_second": 5.439, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.064189343563776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |