{ "best_metric": 3.7259087562561035, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.05422993492407809, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010845986984815619, "grad_norm": 0.4245043396949768, "learning_rate": 4e-05, "loss": 3.4003, "step": 1 }, { "epoch": 0.0010845986984815619, "eval_loss": 4.960307598114014, "eval_runtime": 61.399, "eval_samples_per_second": 6.336, "eval_steps_per_second": 3.176, "step": 1 }, { "epoch": 0.0021691973969631237, "grad_norm": 0.5715564489364624, "learning_rate": 8e-05, "loss": 3.2689, "step": 2 }, { "epoch": 0.0032537960954446853, "grad_norm": 0.6942621469497681, "learning_rate": 0.00012, "loss": 3.5922, "step": 3 }, { "epoch": 0.004338394793926247, "grad_norm": 0.7214824557304382, "learning_rate": 0.00016, "loss": 3.5445, "step": 4 }, { "epoch": 0.005422993492407809, "grad_norm": 0.7759473919868469, "learning_rate": 0.0002, "loss": 3.6989, "step": 5 }, { "epoch": 0.006507592190889371, "grad_norm": 0.8291571140289307, "learning_rate": 0.00019994532573409262, "loss": 3.6764, "step": 6 }, { "epoch": 0.007592190889370932, "grad_norm": 0.9556029438972473, "learning_rate": 0.00019978136272187747, "loss": 3.795, "step": 7 }, { "epoch": 0.008676789587852495, "grad_norm": 1.144549012184143, "learning_rate": 0.00019950829025450114, "loss": 3.7248, "step": 8 }, { "epoch": 0.009761388286334056, "grad_norm": 1.3234285116195679, "learning_rate": 0.00019912640693269752, "loss": 3.4539, "step": 9 }, { "epoch": 0.010845986984815618, "grad_norm": 1.3614262342453003, "learning_rate": 0.00019863613034027224, "loss": 3.6047, "step": 10 }, { "epoch": 0.01193058568329718, "grad_norm": 1.3756049871444702, "learning_rate": 0.00019803799658748094, "loss": 3.5436, "step": 11 }, { "epoch": 0.013015184381778741, "grad_norm": 1.3219250440597534, "learning_rate": 0.0001973326597248006, "loss": 3.5493, "step": 12 }, { "epoch": 0.014099783080260303, "grad_norm": 1.5447579622268677, "learning_rate": 0.00019652089102773488, "loss": 3.8956, "step": 13 }, { "epoch": 0.015184381778741865, "grad_norm": 1.5959620475769043, "learning_rate": 0.00019560357815343577, "loss": 3.6478, "step": 14 }, { "epoch": 0.016268980477223426, "grad_norm": 1.4933563470840454, "learning_rate": 0.00019458172417006347, "loss": 3.42, "step": 15 }, { "epoch": 0.01735357917570499, "grad_norm": 1.5751827955245972, "learning_rate": 0.0001934564464599461, "loss": 3.6736, "step": 16 }, { "epoch": 0.01843817787418655, "grad_norm": 1.5476410388946533, "learning_rate": 0.00019222897549773848, "loss": 3.4862, "step": 17 }, { "epoch": 0.019522776572668113, "grad_norm": 1.7731746435165405, "learning_rate": 0.00019090065350491626, "loss": 3.4728, "step": 18 }, { "epoch": 0.020607375271149676, "grad_norm": 1.502807855606079, "learning_rate": 0.00018947293298207635, "loss": 3.3609, "step": 19 }, { "epoch": 0.021691973969631236, "grad_norm": 1.6433446407318115, "learning_rate": 0.0001879473751206489, "loss": 3.7856, "step": 20 }, { "epoch": 0.0227765726681128, "grad_norm": 1.743554949760437, "learning_rate": 0.00018632564809575742, "loss": 3.8198, "step": 21 }, { "epoch": 0.02386117136659436, "grad_norm": 1.7356516122817993, "learning_rate": 0.00018460952524209355, "loss": 3.5733, "step": 22 }, { "epoch": 0.024945770065075923, "grad_norm": 1.7563503980636597, "learning_rate": 0.00018280088311480201, "loss": 3.2573, "step": 23 }, { "epoch": 0.026030368763557483, "grad_norm": 1.850996971130371, "learning_rate": 0.00018090169943749476, "loss": 3.5953, "step": 24 }, { "epoch": 0.027114967462039046, "grad_norm": 1.810422420501709, "learning_rate": 0.00017891405093963938, "loss": 3.4128, "step": 25 }, { "epoch": 0.027114967462039046, "eval_loss": 3.7259087562561035, "eval_runtime": 62.2613, "eval_samples_per_second": 6.248, "eval_steps_per_second": 3.132, "step": 25 }, { "epoch": 0.028199566160520606, "grad_norm": 1.8431979417800903, "learning_rate": 0.00017684011108568592, "loss": 3.2201, "step": 26 }, { "epoch": 0.02928416485900217, "grad_norm": 2.0144472122192383, "learning_rate": 0.0001746821476984154, "loss": 3.8161, "step": 27 }, { "epoch": 0.03036876355748373, "grad_norm": 2.105778694152832, "learning_rate": 0.00017244252047910892, "loss": 3.7448, "step": 28 }, { "epoch": 0.031453362255965296, "grad_norm": 2.065922737121582, "learning_rate": 0.00017012367842724887, "loss": 3.5692, "step": 29 }, { "epoch": 0.03253796095444685, "grad_norm": 2.4118812084198, "learning_rate": 0.00016772815716257412, "loss": 3.5881, "step": 30 }, { "epoch": 0.033622559652928416, "grad_norm": 2.6568493843078613, "learning_rate": 0.00016525857615241687, "loss": 3.729, "step": 31 }, { "epoch": 0.03470715835140998, "grad_norm": 2.1998934745788574, "learning_rate": 0.0001627176358473537, "loss": 3.6211, "step": 32 }, { "epoch": 0.03579175704989154, "grad_norm": 2.378908395767212, "learning_rate": 0.00016010811472830252, "loss": 3.9732, "step": 33 }, { "epoch": 0.0368763557483731, "grad_norm": 2.6396965980529785, "learning_rate": 0.00015743286626829437, "loss": 3.6206, "step": 34 }, { "epoch": 0.03796095444685466, "grad_norm": 2.891078472137451, "learning_rate": 0.00015469481581224272, "loss": 3.6655, "step": 35 }, { "epoch": 0.039045553145336226, "grad_norm": 2.687089204788208, "learning_rate": 0.00015189695737812152, "loss": 3.7126, "step": 36 }, { "epoch": 0.04013015184381779, "grad_norm": 3.26758074760437, "learning_rate": 0.00014904235038305083, "loss": 3.4765, "step": 37 }, { "epoch": 0.04121475054229935, "grad_norm": 2.8796169757843018, "learning_rate": 0.0001461341162978688, "loss": 3.3265, "step": 38 }, { "epoch": 0.04229934924078091, "grad_norm": 2.7735259532928467, "learning_rate": 0.00014317543523384928, "loss": 3.3651, "step": 39 }, { "epoch": 0.04338394793926247, "grad_norm": 2.856086254119873, "learning_rate": 0.00014016954246529696, "loss": 3.4886, "step": 40 }, { "epoch": 0.044468546637744036, "grad_norm": 3.116877794265747, "learning_rate": 0.00013711972489182208, "loss": 3.2934, "step": 41 }, { "epoch": 0.0455531453362256, "grad_norm": 3.317661762237549, "learning_rate": 0.00013402931744416433, "loss": 3.9233, "step": 42 }, { "epoch": 0.046637744034707156, "grad_norm": 3.2693092823028564, "learning_rate": 0.00013090169943749476, "loss": 3.6349, "step": 43 }, { "epoch": 0.04772234273318872, "grad_norm": 3.303534984588623, "learning_rate": 0.00012774029087618446, "loss": 3.4023, "step": 44 }, { "epoch": 0.04880694143167028, "grad_norm": 3.6019227504730225, "learning_rate": 0.00012454854871407994, "loss": 3.3989, "step": 45 }, { "epoch": 0.049891540130151846, "grad_norm": 4.163827419281006, "learning_rate": 0.0001213299630743747, "loss": 3.7876, "step": 46 }, { "epoch": 0.0509761388286334, "grad_norm": 3.6856470108032227, "learning_rate": 0.000118088053433211, "loss": 3.3211, "step": 47 }, { "epoch": 0.052060737527114966, "grad_norm": 4.466559886932373, "learning_rate": 0.0001148263647711842, "loss": 3.3403, "step": 48 }, { "epoch": 0.05314533622559653, "grad_norm": 5.289233684539795, "learning_rate": 0.00011154846369695863, "loss": 3.9621, "step": 49 }, { "epoch": 0.05422993492407809, "grad_norm": 8.265725135803223, "learning_rate": 0.00010825793454723325, "loss": 4.6722, "step": 50 }, { "epoch": 0.05422993492407809, "eval_loss": 3.752061605453491, "eval_runtime": 62.2465, "eval_samples_per_second": 6.249, "eval_steps_per_second": 3.133, "step": 50 } ], "logging_steps": 1, "max_steps": 100, "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": 1 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.79484292923392e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }