| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06830601092896176, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009107468123861566, | |
| "grad_norm": 2.0517091751098633, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.0497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009107468123861566, | |
| "eval_loss": 3.038726806640625, | |
| "eval_runtime": 37.7451, | |
| "eval_samples_per_second": 12.266, | |
| "eval_steps_per_second": 6.146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018214936247723133, | |
| "grad_norm": 2.4123470783233643, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1416, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00273224043715847, | |
| "grad_norm": 2.62890887260437, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2335, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036429872495446266, | |
| "grad_norm": 1.9658619165420532, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 1.3257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004553734061930784, | |
| "grad_norm": 2.432122230529785, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 1.3111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00546448087431694, | |
| "grad_norm": 2.159250020980835, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 1.2293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006375227686703097, | |
| "grad_norm": 2.4166738986968994, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 1.2834, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007285974499089253, | |
| "grad_norm": 1.835946798324585, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 1.3864, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00819672131147541, | |
| "grad_norm": 1.3662729263305664, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.9429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009107468123861567, | |
| "grad_norm": 1.5126519203186035, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 1.1026, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010018214936247723, | |
| "grad_norm": 1.6885071992874146, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 1.1962, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01092896174863388, | |
| "grad_norm": 1.6031856536865234, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 1.2799, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011839708561020037, | |
| "grad_norm": 1.7740166187286377, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 1.3683, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012750455373406194, | |
| "grad_norm": 1.8252534866333008, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 1.3839, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01366120218579235, | |
| "grad_norm": 2.1907145977020264, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 1.5108, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014571948998178506, | |
| "grad_norm": 2.0855190753936768, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 1.2246, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015482695810564663, | |
| "grad_norm": 2.3677632808685303, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 1.6782, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01639344262295082, | |
| "grad_norm": 2.1821441650390625, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 1.367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017304189435336976, | |
| "grad_norm": 2.4834225177764893, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 1.4051, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018214936247723135, | |
| "grad_norm": 2.456498861312866, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 1.361, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01912568306010929, | |
| "grad_norm": 2.4951350688934326, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 1.2409, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020036429872495445, | |
| "grad_norm": 2.790161371231079, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 1.3919, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020947176684881604, | |
| "grad_norm": 3.7281408309936523, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 1.5667, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 3.095154047012329, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 1.3851, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022768670309653915, | |
| "grad_norm": 3.579331159591675, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 1.547, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022768670309653915, | |
| "eval_loss": 1.554518461227417, | |
| "eval_runtime": 37.7497, | |
| "eval_samples_per_second": 12.265, | |
| "eval_steps_per_second": 6.146, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023679417122040074, | |
| "grad_norm": 3.8335983753204346, | |
| "learning_rate": 3.84324902086706e-05, | |
| "loss": 1.6246, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02459016393442623, | |
| "grad_norm": 4.2963151931762695, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.8721, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025500910746812388, | |
| "grad_norm": 4.064708709716797, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 1.6337, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026411657559198543, | |
| "grad_norm": 3.6003475189208984, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 1.1948, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0273224043715847, | |
| "grad_norm": 4.95332145690918, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 1.7435, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028233151183970857, | |
| "grad_norm": 5.380415439605713, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 1.3499, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.029143897996357013, | |
| "grad_norm": 4.800806522369385, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 1.5518, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.030054644808743168, | |
| "grad_norm": 4.674807071685791, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 1.5142, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030965391621129327, | |
| "grad_norm": 4.52117919921875, | |
| "learning_rate": 3.0410990348452573e-05, | |
| "loss": 1.4617, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.031876138433515486, | |
| "grad_norm": 5.159020900726318, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 1.3345, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 5.662403583526611, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 1.4164, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.033697632058287796, | |
| "grad_norm": 5.426482677459717, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 1.2144, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03460837887067395, | |
| "grad_norm": 5.797895908355713, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 1.3768, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03551912568306011, | |
| "grad_norm": 6.419762134552002, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4736, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03642987249544627, | |
| "grad_norm": 5.924313545227051, | |
| "learning_rate": 2.3909515315866605e-05, | |
| "loss": 1.2825, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.037340619307832425, | |
| "grad_norm": 6.173450469970703, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 1.3105, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03825136612021858, | |
| "grad_norm": 8.242639541625977, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 1.3073, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.039162112932604735, | |
| "grad_norm": 8.869377136230469, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 1.4705, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04007285974499089, | |
| "grad_norm": 8.427241325378418, | |
| "learning_rate": 1.958900965154743e-05, | |
| "loss": 1.6696, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.040983606557377046, | |
| "grad_norm": 9.052663803100586, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 1.2254, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04189435336976321, | |
| "grad_norm": 7.14196252822876, | |
| "learning_rate": 1.7482355012393177e-05, | |
| "loss": 1.314, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.042805100182149364, | |
| "grad_norm": 10.285764694213867, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 1.9592, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 11.626080513000488, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 1.7412, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.044626593806921674, | |
| "grad_norm": 16.58131217956543, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 2.785, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04553734061930783, | |
| "grad_norm": 47.45877456665039, | |
| "learning_rate": 1.3456284669124158e-05, | |
| "loss": 4.9434, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04553734061930783, | |
| "eval_loss": 1.322178840637207, | |
| "eval_runtime": 37.7906, | |
| "eval_samples_per_second": 12.252, | |
| "eval_steps_per_second": 6.139, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04644808743169399, | |
| "grad_norm": 1.0157305002212524, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.7862, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04735883424408015, | |
| "grad_norm": 1.3376152515411377, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 1.1578, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0482695810564663, | |
| "grad_norm": 1.4561330080032349, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 1.0865, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04918032786885246, | |
| "grad_norm": 1.1816233396530151, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.9107, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05009107468123861, | |
| "grad_norm": 1.1890616416931152, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.8108, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.051001821493624776, | |
| "grad_norm": 1.186021089553833, | |
| "learning_rate": 8.110244809608495e-06, | |
| "loss": 0.8508, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05191256830601093, | |
| "grad_norm": 1.1916978359222412, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.8236, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.052823315118397086, | |
| "grad_norm": 1.3242887258529663, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 0.9529, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05373406193078324, | |
| "grad_norm": 1.2892563343048096, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.8467, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0546448087431694, | |
| "grad_norm": 1.4728500843048096, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.9437, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.306962490081787, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 0.7965, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.056466302367941715, | |
| "grad_norm": 1.478961706161499, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 0.9545, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05737704918032787, | |
| "grad_norm": 1.672711730003357, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 1.1629, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.058287795992714025, | |
| "grad_norm": 1.666373610496521, | |
| "learning_rate": 2.8247291705444575e-06, | |
| "loss": 1.1792, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05919854280510018, | |
| "grad_norm": 1.9274945259094238, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 1.1452, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.060109289617486336, | |
| "grad_norm": 2.060487747192383, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 1.2432, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0610200364298725, | |
| "grad_norm": 2.072204828262329, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 1.161, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.061930783242258654, | |
| "grad_norm": 2.055114984512329, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 1.0735, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.06284153005464481, | |
| "grad_norm": 2.482335329055786, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 1.1558, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06375227686703097, | |
| "grad_norm": 2.711244821548462, | |
| "learning_rate": 5.925998220016659e-07, | |
| "loss": 1.2527, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06466302367941712, | |
| "grad_norm": 2.62081241607666, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 1.2273, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 2.8418915271759033, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 1.451, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06648451730418943, | |
| "grad_norm": 2.660665988922119, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 1.3604, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06739526411657559, | |
| "grad_norm": 2.826326847076416, | |
| "learning_rate": 2.3794460453555047e-08, | |
| "loss": 1.0152, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06830601092896176, | |
| "grad_norm": 3.0708837509155273, | |
| "learning_rate": 0.0, | |
| "loss": 1.0459, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06830601092896176, | |
| "eval_loss": 1.2876240015029907, | |
| "eval_runtime": 37.5565, | |
| "eval_samples_per_second": 12.328, | |
| "eval_steps_per_second": 6.177, | |
| "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": 1.5638785450573824e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |