| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2782931354359926, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037105751391465678, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037105751391465678, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9596, | |
| "eval_samples_per_second": 9.532, | |
| "eval_steps_per_second": 4.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0074211502782931356, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011131725417439703, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014842300556586271, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01855287569573284, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022263450834879406, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025974025974025976, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03339517625231911, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03710575139146568, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04452690166975881, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04823747680890538, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.055658627087198514, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06307977736549165, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06679035250463822, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07050092764378478, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07421150278293136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07792207792207792, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08534322820037106, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09276437847866419, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09276437847866419, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9895, | |
| "eval_samples_per_second": 9.508, | |
| "eval_steps_per_second": 4.754, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09647495361781076, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.84324902086706e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10018552875695733, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10760667903525047, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11131725417439703, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1150278293135436, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11873840445269017, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1261595547309833, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0410990348452573e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13358070500927643, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.137291280148423, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14100185528756956, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14471243042671614, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3909515315866605e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15213358070500926, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15955473098330242, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.958900965154743e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16697588126159554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17068645640074212, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7482355012393177e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17439703153988867, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17810760667903525, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18552875695732837, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3456284669124158e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18552875695732837, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9855, | |
| "eval_samples_per_second": 9.512, | |
| "eval_steps_per_second": 4.756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18923933209647495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.19294990723562153, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.19666048237476808, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.20037105751391465, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.110244809608495e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.21150278293135436, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.21521335807050093, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2189239332096475, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.22263450834879406, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22634508348794063, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2300556586270872, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.23376623376623376, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.23747680890538034, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8247291705444575e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.24118738404452691, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.24860853432282004, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2523191094619666, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2560296846011132, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.925998220016659e-07, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2634508348794063, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.26716141001855287, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.27087198515769945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.274582560296846, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3794460453555047e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2782931354359926, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2782931354359926, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.9772, | |
| "eval_samples_per_second": 9.518, | |
| "eval_steps_per_second": 4.759, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.30671428698112e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |