| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9244992295839753, | |
| "eval_steps": 10, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001027221366204417, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002054442732408834, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7541, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030816640986132513, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8031, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004108885464817668, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005136106831022085, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0061633281972265025, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7949, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007190549563430919, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7657, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008217770929635337, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.803, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009244992295839754, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01027221366204417, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7935, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01027221366204417, | |
| "eval_loss": 2.8114004135131836, | |
| "eval_runtime": 37.8463, | |
| "eval_samples_per_second": 26.423, | |
| "eval_steps_per_second": 1.11, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011299435028248588, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7546, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012326656394453005, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7423, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01335387776065742, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8057, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014381099126861838, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7663, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015408320493066256, | |
| "grad_norm": 4.694424152374268, | |
| "learning_rate": 1.7123287671232876e-08, | |
| "loss": 2.7715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016435541859270673, | |
| "grad_norm": 4.905329704284668, | |
| "learning_rate": 3.424657534246575e-08, | |
| "loss": 2.751, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01746276322547509, | |
| "grad_norm": 4.705279350280762, | |
| "learning_rate": 5.136986301369863e-08, | |
| "loss": 2.7186, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01848998459167951, | |
| "grad_norm": 5.154810905456543, | |
| "learning_rate": 6.84931506849315e-08, | |
| "loss": 2.8073, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019517205957883924, | |
| "grad_norm": 5.070403099060059, | |
| "learning_rate": 8.561643835616439e-08, | |
| "loss": 2.7237, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02054442732408834, | |
| "grad_norm": 4.901423454284668, | |
| "learning_rate": 1.0273972602739726e-07, | |
| "loss": 2.7882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02054442732408834, | |
| "eval_loss": 2.810307502746582, | |
| "eval_runtime": 37.65, | |
| "eval_samples_per_second": 26.56, | |
| "eval_steps_per_second": 1.116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02157164869029276, | |
| "grad_norm": 4.914156436920166, | |
| "learning_rate": 1.1986301369863014e-07, | |
| "loss": 2.8005, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 4.937129974365234, | |
| "learning_rate": 1.36986301369863e-07, | |
| "loss": 2.7902, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02362609142270159, | |
| "grad_norm": 5.0690202713012695, | |
| "learning_rate": 1.541095890410959e-07, | |
| "loss": 2.7474, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02465331278890601, | |
| "grad_norm": 4.980844974517822, | |
| "learning_rate": 1.7123287671232878e-07, | |
| "loss": 2.7695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025680534155110426, | |
| "grad_norm": 4.8092451095581055, | |
| "learning_rate": 1.8835616438356165e-07, | |
| "loss": 2.7611, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02670775552131484, | |
| "grad_norm": 4.765528202056885, | |
| "learning_rate": 2.0547945205479452e-07, | |
| "loss": 2.7823, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02773497688751926, | |
| "grad_norm": 3.9759938716888428, | |
| "learning_rate": 2.226027397260274e-07, | |
| "loss": 2.7445, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028762198253723677, | |
| "grad_norm": 4.023419380187988, | |
| "learning_rate": 2.397260273972603e-07, | |
| "loss": 2.7679, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029789419619928096, | |
| "grad_norm": 4.161378383636475, | |
| "learning_rate": 2.568493150684932e-07, | |
| "loss": 2.7704, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030816640986132512, | |
| "grad_norm": 3.8363842964172363, | |
| "learning_rate": 2.73972602739726e-07, | |
| "loss": 2.7598, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030816640986132512, | |
| "eval_loss": 2.772540330886841, | |
| "eval_runtime": 37.2624, | |
| "eval_samples_per_second": 26.837, | |
| "eval_steps_per_second": 1.127, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03184386235233693, | |
| "grad_norm": 3.718747615814209, | |
| "learning_rate": 2.910958904109589e-07, | |
| "loss": 2.7241, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03287108371854135, | |
| "grad_norm": 3.555985927581787, | |
| "learning_rate": 3.082191780821918e-07, | |
| "loss": 2.7751, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 3.6041972637176514, | |
| "learning_rate": 3.2534246575342466e-07, | |
| "loss": 2.7322, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03492552645095018, | |
| "grad_norm": 3.4408438205718994, | |
| "learning_rate": 3.4246575342465755e-07, | |
| "loss": 2.727, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.035952747817154594, | |
| "grad_norm": 3.4169280529022217, | |
| "learning_rate": 3.595890410958904e-07, | |
| "loss": 2.7062, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03697996918335902, | |
| "grad_norm": 3.3882925510406494, | |
| "learning_rate": 3.767123287671233e-07, | |
| "loss": 2.6271, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03800719054956343, | |
| "grad_norm": 3.0491855144500732, | |
| "learning_rate": 3.938356164383562e-07, | |
| "loss": 2.7309, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03903441191576785, | |
| "grad_norm": 2.8444902896881104, | |
| "learning_rate": 4.1095890410958903e-07, | |
| "loss": 2.647, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.040061633281972264, | |
| "grad_norm": 2.7438602447509766, | |
| "learning_rate": 4.2808219178082193e-07, | |
| "loss": 2.6478, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04108885464817668, | |
| "grad_norm": 2.8886020183563232, | |
| "learning_rate": 4.452054794520548e-07, | |
| "loss": 2.7065, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04108885464817668, | |
| "eval_loss": 2.7021424770355225, | |
| "eval_runtime": 37.3227, | |
| "eval_samples_per_second": 26.793, | |
| "eval_steps_per_second": 1.125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.042116076014381096, | |
| "grad_norm": 2.8825268745422363, | |
| "learning_rate": 4.6232876712328767e-07, | |
| "loss": 2.6666, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04314329738058552, | |
| "grad_norm": 2.8848748207092285, | |
| "learning_rate": 4.794520547945206e-07, | |
| "loss": 2.597, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.044170518746789934, | |
| "grad_norm": 2.9176979064941406, | |
| "learning_rate": 4.965753424657534e-07, | |
| "loss": 2.6638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 2.6903059482574463, | |
| "learning_rate": 5.136986301369864e-07, | |
| "loss": 2.6202, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.046224961479198766, | |
| "grad_norm": 2.5349855422973633, | |
| "learning_rate": 5.308219178082192e-07, | |
| "loss": 2.6466, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04725218284540318, | |
| "grad_norm": 2.405383825302124, | |
| "learning_rate": 5.47945205479452e-07, | |
| "loss": 2.6291, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.048279404211607604, | |
| "grad_norm": 2.526106595993042, | |
| "learning_rate": 5.65068493150685e-07, | |
| "loss": 2.6718, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04930662557781202, | |
| "grad_norm": 2.3981597423553467, | |
| "learning_rate": 5.821917808219178e-07, | |
| "loss": 2.592, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.050333846944016436, | |
| "grad_norm": 2.61842679977417, | |
| "learning_rate": 5.993150684931507e-07, | |
| "loss": 2.6039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "grad_norm": 2.3001420497894287, | |
| "learning_rate": 6.164383561643836e-07, | |
| "loss": 2.5481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "eval_loss": 2.6244444847106934, | |
| "eval_runtime": 37.3248, | |
| "eval_samples_per_second": 26.792, | |
| "eval_steps_per_second": 1.125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05238828967642527, | |
| "grad_norm": 2.12744140625, | |
| "learning_rate": 6.335616438356165e-07, | |
| "loss": 2.5336, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05341551104262968, | |
| "grad_norm": 1.974413275718689, | |
| "learning_rate": 6.506849315068493e-07, | |
| "loss": 2.5882, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.054442732408834106, | |
| "grad_norm": 2.098527669906616, | |
| "learning_rate": 6.678082191780823e-07, | |
| "loss": 2.5073, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05546995377503852, | |
| "grad_norm": 2.056288719177246, | |
| "learning_rate": 6.849315068493151e-07, | |
| "loss": 2.5612, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05649717514124294, | |
| "grad_norm": 2.2291629314422607, | |
| "learning_rate": 7.020547945205481e-07, | |
| "loss": 2.527, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05752439650744735, | |
| "grad_norm": 2.140164375305176, | |
| "learning_rate": 7.191780821917808e-07, | |
| "loss": 2.4972, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05855161787365177, | |
| "grad_norm": 1.8682485818862915, | |
| "learning_rate": 7.363013698630137e-07, | |
| "loss": 2.5231, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05957883923985619, | |
| "grad_norm": 1.9373308420181274, | |
| "learning_rate": 7.534246575342466e-07, | |
| "loss": 2.4509, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 1.8535712957382202, | |
| "learning_rate": 7.705479452054795e-07, | |
| "loss": 2.5164, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.061633281972265024, | |
| "grad_norm": 1.7497329711914062, | |
| "learning_rate": 7.876712328767124e-07, | |
| "loss": 2.5177, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.061633281972265024, | |
| "eval_loss": 2.5608646869659424, | |
| "eval_runtime": 37.3426, | |
| "eval_samples_per_second": 26.779, | |
| "eval_steps_per_second": 1.125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06266050333846944, | |
| "grad_norm": 1.8476629257202148, | |
| "learning_rate": 8.047945205479453e-07, | |
| "loss": 2.4838, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06368772470467386, | |
| "grad_norm": 1.7130696773529053, | |
| "learning_rate": 8.219178082191781e-07, | |
| "loss": 2.473, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06471494607087827, | |
| "grad_norm": 1.751081109046936, | |
| "learning_rate": 8.39041095890411e-07, | |
| "loss": 2.5152, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0657421674370827, | |
| "grad_norm": 1.7758578062057495, | |
| "learning_rate": 8.561643835616439e-07, | |
| "loss": 2.5031, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0667693888032871, | |
| "grad_norm": 1.9316363334655762, | |
| "learning_rate": 8.732876712328768e-07, | |
| "loss": 2.3695, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 1.7765878438949585, | |
| "learning_rate": 8.904109589041097e-07, | |
| "loss": 2.4669, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06882383153569595, | |
| "grad_norm": 1.7339810132980347, | |
| "learning_rate": 9.075342465753426e-07, | |
| "loss": 2.4112, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06985105290190036, | |
| "grad_norm": 1.717781662940979, | |
| "learning_rate": 9.246575342465753e-07, | |
| "loss": 2.4677, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07087827426810478, | |
| "grad_norm": 1.7711046934127808, | |
| "learning_rate": 9.417808219178083e-07, | |
| "loss": 2.4131, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07190549563430919, | |
| "grad_norm": 1.708680510520935, | |
| "learning_rate": 9.589041095890411e-07, | |
| "loss": 2.5191, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07190549563430919, | |
| "eval_loss": 2.4920735359191895, | |
| "eval_runtime": 37.3501, | |
| "eval_samples_per_second": 26.774, | |
| "eval_steps_per_second": 1.124, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07293271700051361, | |
| "grad_norm": 1.9429680109024048, | |
| "learning_rate": 9.76027397260274e-07, | |
| "loss": 2.4099, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07395993836671803, | |
| "grad_norm": 1.7411247491836548, | |
| "learning_rate": 9.931506849315068e-07, | |
| "loss": 2.3632, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07498715973292244, | |
| "grad_norm": 1.7577983140945435, | |
| "learning_rate": 1.0102739726027399e-06, | |
| "loss": 2.4214, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07601438109912687, | |
| "grad_norm": 2.025926351547241, | |
| "learning_rate": 1.0273972602739727e-06, | |
| "loss": 2.394, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07704160246533127, | |
| "grad_norm": 2.4366860389709473, | |
| "learning_rate": 1.0445205479452056e-06, | |
| "loss": 2.3943, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0780688238315357, | |
| "grad_norm": 2.437108278274536, | |
| "learning_rate": 1.0616438356164384e-06, | |
| "loss": 2.3844, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.07909604519774012, | |
| "grad_norm": 2.1352434158325195, | |
| "learning_rate": 1.0787671232876712e-06, | |
| "loss": 2.3871, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08012326656394453, | |
| "grad_norm": 1.8895397186279297, | |
| "learning_rate": 1.095890410958904e-06, | |
| "loss": 2.3927, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08115048793014895, | |
| "grad_norm": 2.2960093021392822, | |
| "learning_rate": 1.1130136986301371e-06, | |
| "loss": 2.3343, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08217770929635336, | |
| "grad_norm": 2.0891849994659424, | |
| "learning_rate": 1.13013698630137e-06, | |
| "loss": 2.3732, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08217770929635336, | |
| "eval_loss": 2.4189229011535645, | |
| "eval_runtime": 37.3645, | |
| "eval_samples_per_second": 26.763, | |
| "eval_steps_per_second": 1.124, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08320493066255778, | |
| "grad_norm": 2.450587034225464, | |
| "learning_rate": 1.1472602739726028e-06, | |
| "loss": 2.3163, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08423215202876219, | |
| "grad_norm": 2.079949378967285, | |
| "learning_rate": 1.1643835616438357e-06, | |
| "loss": 2.3381, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08525937339496661, | |
| "grad_norm": 2.160737991333008, | |
| "learning_rate": 1.1815068493150685e-06, | |
| "loss": 2.3376, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08628659476117104, | |
| "grad_norm": 2.463890552520752, | |
| "learning_rate": 1.1986301369863014e-06, | |
| "loss": 2.308, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08731381612737545, | |
| "grad_norm": 2.3923065662384033, | |
| "learning_rate": 1.2157534246575344e-06, | |
| "loss": 2.2682, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08834103749357987, | |
| "grad_norm": 2.2096004486083984, | |
| "learning_rate": 1.2328767123287673e-06, | |
| "loss": 2.3256, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.08936825885978428, | |
| "grad_norm": 2.1402556896209717, | |
| "learning_rate": 1.25e-06, | |
| "loss": 2.2767, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 2.500629186630249, | |
| "learning_rate": 1.267123287671233e-06, | |
| "loss": 2.2576, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09142270159219312, | |
| "grad_norm": 2.0257675647735596, | |
| "learning_rate": 1.284246575342466e-06, | |
| "loss": 2.2722, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09244992295839753, | |
| "grad_norm": 2.148428440093994, | |
| "learning_rate": 1.3013698630136986e-06, | |
| "loss": 2.2309, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09244992295839753, | |
| "eval_loss": 2.3439993858337402, | |
| "eval_runtime": 37.3803, | |
| "eval_samples_per_second": 26.752, | |
| "eval_steps_per_second": 1.124, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09347714432460195, | |
| "grad_norm": 2.3541946411132812, | |
| "learning_rate": 1.3184931506849317e-06, | |
| "loss": 2.2347, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.09450436569080636, | |
| "grad_norm": 2.6239383220672607, | |
| "learning_rate": 1.3356164383561645e-06, | |
| "loss": 2.2589, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09553158705701079, | |
| "grad_norm": 2.1981804370880127, | |
| "learning_rate": 1.3527397260273976e-06, | |
| "loss": 2.2372, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09655880842321521, | |
| "grad_norm": 2.3652358055114746, | |
| "learning_rate": 1.3698630136986302e-06, | |
| "loss": 2.2169, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.09758602978941962, | |
| "grad_norm": 2.2078158855438232, | |
| "learning_rate": 1.386986301369863e-06, | |
| "loss": 2.2761, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09861325115562404, | |
| "grad_norm": 2.494685649871826, | |
| "learning_rate": 1.4041095890410961e-06, | |
| "loss": 2.1691, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.09964047252182845, | |
| "grad_norm": 2.3293051719665527, | |
| "learning_rate": 1.421232876712329e-06, | |
| "loss": 2.2246, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.10066769388803287, | |
| "grad_norm": 2.410687208175659, | |
| "learning_rate": 1.4383561643835616e-06, | |
| "loss": 2.1166, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 2.5168960094451904, | |
| "learning_rate": 1.4554794520547946e-06, | |
| "loss": 2.1417, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1027221366204417, | |
| "grad_norm": 2.178412914276123, | |
| "learning_rate": 1.4726027397260275e-06, | |
| "loss": 2.1638, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1027221366204417, | |
| "eval_loss": 2.273622751235962, | |
| "eval_runtime": 37.3892, | |
| "eval_samples_per_second": 26.746, | |
| "eval_steps_per_second": 1.123, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10374935798664613, | |
| "grad_norm": 2.8951706886291504, | |
| "learning_rate": 1.4897260273972605e-06, | |
| "loss": 2.1631, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.10477657935285054, | |
| "grad_norm": 2.103206157684326, | |
| "learning_rate": 1.5068493150684932e-06, | |
| "loss": 2.1419, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.10580380071905496, | |
| "grad_norm": 2.495969772338867, | |
| "learning_rate": 1.5239726027397262e-06, | |
| "loss": 2.1029, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.10683102208525937, | |
| "grad_norm": 2.5686826705932617, | |
| "learning_rate": 1.541095890410959e-06, | |
| "loss": 2.1235, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.10785824345146379, | |
| "grad_norm": 3.4710471630096436, | |
| "learning_rate": 1.5582191780821921e-06, | |
| "loss": 2.1832, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10888546481766821, | |
| "grad_norm": 2.2563316822052, | |
| "learning_rate": 1.5753424657534248e-06, | |
| "loss": 2.1441, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.10991268618387262, | |
| "grad_norm": 3.860506534576416, | |
| "learning_rate": 1.5924657534246576e-06, | |
| "loss": 2.1764, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.11093990755007704, | |
| "grad_norm": 2.550135850906372, | |
| "learning_rate": 1.6095890410958907e-06, | |
| "loss": 2.1455, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11196712891628145, | |
| "grad_norm": 3.168283700942993, | |
| "learning_rate": 1.6267123287671235e-06, | |
| "loss": 2.0246, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 2.577069044113159, | |
| "learning_rate": 1.6438356164383561e-06, | |
| "loss": 2.0921, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "eval_loss": 2.2218997478485107, | |
| "eval_runtime": 37.246, | |
| "eval_samples_per_second": 26.849, | |
| "eval_steps_per_second": 1.128, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1140215716486903, | |
| "grad_norm": 2.3515374660491943, | |
| "learning_rate": 1.6609589041095892e-06, | |
| "loss": 2.0209, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1150487930148947, | |
| "grad_norm": 2.7660279273986816, | |
| "learning_rate": 1.678082191780822e-06, | |
| "loss": 2.1165, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.11607601438109913, | |
| "grad_norm": 2.567336082458496, | |
| "learning_rate": 1.695205479452055e-06, | |
| "loss": 2.0529, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.11710323574730354, | |
| "grad_norm": 2.4126152992248535, | |
| "learning_rate": 1.7123287671232877e-06, | |
| "loss": 2.1028, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.11813045711350796, | |
| "grad_norm": 3.577528476715088, | |
| "learning_rate": 1.7294520547945206e-06, | |
| "loss": 2.0317, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11915767847971238, | |
| "grad_norm": 2.9624195098876953, | |
| "learning_rate": 1.7465753424657536e-06, | |
| "loss": 2.1318, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12018489984591679, | |
| "grad_norm": 2.789854049682617, | |
| "learning_rate": 1.7636986301369865e-06, | |
| "loss": 2.0822, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 2.8168365955352783, | |
| "learning_rate": 1.7808219178082193e-06, | |
| "loss": 2.08, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.12223934257832562, | |
| "grad_norm": 2.7616257667541504, | |
| "learning_rate": 1.7979452054794521e-06, | |
| "loss": 2.0668, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.12326656394453005, | |
| "grad_norm": 2.5610315799713135, | |
| "learning_rate": 1.8150684931506852e-06, | |
| "loss": 2.1518, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12326656394453005, | |
| "eval_loss": 2.184033155441284, | |
| "eval_runtime": 37.3784, | |
| "eval_samples_per_second": 26.753, | |
| "eval_steps_per_second": 1.124, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12429378531073447, | |
| "grad_norm": 2.817063093185425, | |
| "learning_rate": 1.832191780821918e-06, | |
| "loss": 2.0813, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.12532100667693888, | |
| "grad_norm": 2.987205982208252, | |
| "learning_rate": 1.8493150684931507e-06, | |
| "loss": 2.0421, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1263482280431433, | |
| "grad_norm": 2.8480496406555176, | |
| "learning_rate": 1.8664383561643837e-06, | |
| "loss": 2.0018, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.12737544940934772, | |
| "grad_norm": 2.994274616241455, | |
| "learning_rate": 1.8835616438356166e-06, | |
| "loss": 2.0266, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.12840267077555212, | |
| "grad_norm": 2.64136004447937, | |
| "learning_rate": 1.9006849315068496e-06, | |
| "loss": 1.9873, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12942989214175654, | |
| "grad_norm": 2.9426915645599365, | |
| "learning_rate": 1.9178082191780823e-06, | |
| "loss": 2.0566, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.13045711350796096, | |
| "grad_norm": 2.9018619060516357, | |
| "learning_rate": 1.9349315068493153e-06, | |
| "loss": 1.9674, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1314843348741654, | |
| "grad_norm": 3.6921045780181885, | |
| "learning_rate": 1.952054794520548e-06, | |
| "loss": 2.0295, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.1325115562403698, | |
| "grad_norm": 2.4194657802581787, | |
| "learning_rate": 1.969178082191781e-06, | |
| "loss": 2.0639, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1335387776065742, | |
| "grad_norm": 3.252349615097046, | |
| "learning_rate": 1.9863013698630136e-06, | |
| "loss": 2.0613, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1335387776065742, | |
| "eval_loss": 2.153157949447632, | |
| "eval_runtime": 37.394, | |
| "eval_samples_per_second": 26.742, | |
| "eval_steps_per_second": 1.123, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13456599897277863, | |
| "grad_norm": 2.9361023902893066, | |
| "learning_rate": 2.0034246575342467e-06, | |
| "loss": 1.9817, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 2.834803581237793, | |
| "learning_rate": 2.0205479452054797e-06, | |
| "loss": 2.0539, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.13662044170518747, | |
| "grad_norm": 2.8814785480499268, | |
| "learning_rate": 2.037671232876713e-06, | |
| "loss": 2.0296, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1376476630713919, | |
| "grad_norm": 2.647125482559204, | |
| "learning_rate": 2.0547945205479454e-06, | |
| "loss": 1.9739, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1386748844375963, | |
| "grad_norm": 2.9608750343322754, | |
| "learning_rate": 2.071917808219178e-06, | |
| "loss": 2.0083, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1397021058038007, | |
| "grad_norm": 2.8570032119750977, | |
| "learning_rate": 2.089041095890411e-06, | |
| "loss": 2.0216, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.14072932717000514, | |
| "grad_norm": 2.806358575820923, | |
| "learning_rate": 2.106164383561644e-06, | |
| "loss": 1.9457, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.14175654853620956, | |
| "grad_norm": 3.1003353595733643, | |
| "learning_rate": 2.123287671232877e-06, | |
| "loss": 2.0324, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.14278376990241398, | |
| "grad_norm": 2.679588556289673, | |
| "learning_rate": 2.14041095890411e-06, | |
| "loss": 1.9699, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.14381099126861838, | |
| "grad_norm": 2.9436194896698, | |
| "learning_rate": 2.1575342465753425e-06, | |
| "loss": 1.9824, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14381099126861838, | |
| "eval_loss": 2.123953104019165, | |
| "eval_runtime": 37.4214, | |
| "eval_samples_per_second": 26.723, | |
| "eval_steps_per_second": 1.122, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1448382126348228, | |
| "grad_norm": 3.088301420211792, | |
| "learning_rate": 2.1746575342465755e-06, | |
| "loss": 1.9861, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.14586543400102722, | |
| "grad_norm": 3.011859178543091, | |
| "learning_rate": 2.191780821917808e-06, | |
| "loss": 1.9383, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.14689265536723164, | |
| "grad_norm": 2.930264472961426, | |
| "learning_rate": 2.2089041095890412e-06, | |
| "loss": 2.0674, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.14791987673343607, | |
| "grad_norm": 3.361328601837158, | |
| "learning_rate": 2.2260273972602743e-06, | |
| "loss": 1.9495, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.14894709809964046, | |
| "grad_norm": 2.7825112342834473, | |
| "learning_rate": 2.243150684931507e-06, | |
| "loss": 1.9335, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.14997431946584489, | |
| "grad_norm": 3.7215847969055176, | |
| "learning_rate": 2.26027397260274e-06, | |
| "loss": 1.9403, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.1510015408320493, | |
| "grad_norm": 2.5125460624694824, | |
| "learning_rate": 2.2773972602739726e-06, | |
| "loss": 1.9437, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.15202876219825373, | |
| "grad_norm": 3.0963492393493652, | |
| "learning_rate": 2.2945205479452057e-06, | |
| "loss": 1.9651, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.15305598356445815, | |
| "grad_norm": 2.9147121906280518, | |
| "learning_rate": 2.3116438356164387e-06, | |
| "loss": 2.0567, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.15408320493066255, | |
| "grad_norm": 3.5275802612304688, | |
| "learning_rate": 2.3287671232876713e-06, | |
| "loss": 1.9773, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15408320493066255, | |
| "eval_loss": 2.112344264984131, | |
| "eval_runtime": 37.4142, | |
| "eval_samples_per_second": 26.728, | |
| "eval_steps_per_second": 1.123, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15511042629686697, | |
| "grad_norm": 3.013786554336548, | |
| "learning_rate": 2.3458904109589044e-06, | |
| "loss": 1.8753, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.1561376476630714, | |
| "grad_norm": 3.433615207672119, | |
| "learning_rate": 2.363013698630137e-06, | |
| "loss": 1.9256, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.15716486902927582, | |
| "grad_norm": 3.1526033878326416, | |
| "learning_rate": 2.38013698630137e-06, | |
| "loss": 1.9815, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.15819209039548024, | |
| "grad_norm": 3.2099974155426025, | |
| "learning_rate": 2.3972602739726027e-06, | |
| "loss": 1.9628, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.15921931176168463, | |
| "grad_norm": 3.2713584899902344, | |
| "learning_rate": 2.4143835616438358e-06, | |
| "loss": 1.9128, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16024653312788906, | |
| "grad_norm": 3.287649393081665, | |
| "learning_rate": 2.431506849315069e-06, | |
| "loss": 1.8764, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.16127375449409348, | |
| "grad_norm": 3.1439101696014404, | |
| "learning_rate": 2.4486301369863015e-06, | |
| "loss": 1.9428, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1623009758602979, | |
| "grad_norm": 3.006457805633545, | |
| "learning_rate": 2.4657534246575345e-06, | |
| "loss": 1.9516, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.1633281972265023, | |
| "grad_norm": 2.9567787647247314, | |
| "learning_rate": 2.482876712328767e-06, | |
| "loss": 1.915, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.16435541859270672, | |
| "grad_norm": 3.2475216388702393, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.9451, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16435541859270672, | |
| "eval_loss": 2.086299419403076, | |
| "eval_runtime": 37.3939, | |
| "eval_samples_per_second": 26.742, | |
| "eval_steps_per_second": 1.123, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16538263995891114, | |
| "grad_norm": 2.9586498737335205, | |
| "learning_rate": 2.5171232876712333e-06, | |
| "loss": 1.9298, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.16640986132511557, | |
| "grad_norm": 3.066910982131958, | |
| "learning_rate": 2.534246575342466e-06, | |
| "loss": 1.9103, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.16743708269132, | |
| "grad_norm": 2.814741611480713, | |
| "learning_rate": 2.551369863013699e-06, | |
| "loss": 1.8678, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.16846430405752438, | |
| "grad_norm": 3.7239339351654053, | |
| "learning_rate": 2.568493150684932e-06, | |
| "loss": 1.9321, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 2.829899787902832, | |
| "learning_rate": 2.585616438356164e-06, | |
| "loss": 1.9587, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.17051874678993323, | |
| "grad_norm": 3.826289176940918, | |
| "learning_rate": 2.6027397260273973e-06, | |
| "loss": 1.9288, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.17154596815613765, | |
| "grad_norm": 3.1028499603271484, | |
| "learning_rate": 2.6198630136986303e-06, | |
| "loss": 1.8685, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.17257318952234207, | |
| "grad_norm": 3.6923508644104004, | |
| "learning_rate": 2.6369863013698634e-06, | |
| "loss": 1.9276, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.17360041088854647, | |
| "grad_norm": 3.0577642917633057, | |
| "learning_rate": 2.654109589041096e-06, | |
| "loss": 1.9653, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.1746276322547509, | |
| "grad_norm": 3.363762617111206, | |
| "learning_rate": 2.671232876712329e-06, | |
| "loss": 1.9465, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1746276322547509, | |
| "eval_loss": 2.0753531455993652, | |
| "eval_runtime": 37.3955, | |
| "eval_samples_per_second": 26.741, | |
| "eval_steps_per_second": 1.123, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17565485362095531, | |
| "grad_norm": 2.9063165187835693, | |
| "learning_rate": 2.688356164383562e-06, | |
| "loss": 1.8827, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.17668207498715974, | |
| "grad_norm": 3.4709181785583496, | |
| "learning_rate": 2.705479452054795e-06, | |
| "loss": 1.882, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.17770929635336416, | |
| "grad_norm": 3.395397663116455, | |
| "learning_rate": 2.7226027397260274e-06, | |
| "loss": 1.8711, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.17873651771956856, | |
| "grad_norm": 3.9973363876342773, | |
| "learning_rate": 2.7397260273972604e-06, | |
| "loss": 1.8223, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.17976373908577298, | |
| "grad_norm": 3.1841156482696533, | |
| "learning_rate": 2.7568493150684935e-06, | |
| "loss": 1.947, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 3.1841156482696533, | |
| "learning_rate": 2.7568493150684935e-06, | |
| "loss": 1.9192, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 3.84712290763855, | |
| "learning_rate": 2.773972602739726e-06, | |
| "loss": 1.8344, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.18284540318438625, | |
| "grad_norm": 3.487525463104248, | |
| "learning_rate": 2.791095890410959e-06, | |
| "loss": 1.9242, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.18387262455059064, | |
| "grad_norm": 3.1980319023132324, | |
| "learning_rate": 2.8082191780821922e-06, | |
| "loss": 1.7959, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.18489984591679506, | |
| "grad_norm": 3.56462025642395, | |
| "learning_rate": 2.8253424657534253e-06, | |
| "loss": 1.9668, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18489984591679506, | |
| "eval_loss": 2.0606908798217773, | |
| "eval_runtime": 37.3994, | |
| "eval_samples_per_second": 26.738, | |
| "eval_steps_per_second": 1.123, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1859270672829995, | |
| "grad_norm": 3.613842248916626, | |
| "learning_rate": 2.842465753424658e-06, | |
| "loss": 1.925, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.1869542886492039, | |
| "grad_norm": 2.9755642414093018, | |
| "learning_rate": 2.8595890410958905e-06, | |
| "loss": 1.9251, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.18798151001540833, | |
| "grad_norm": 2.9678146839141846, | |
| "learning_rate": 2.876712328767123e-06, | |
| "loss": 1.9406, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.18900873138161273, | |
| "grad_norm": 3.3536393642425537, | |
| "learning_rate": 2.8938356164383562e-06, | |
| "loss": 1.8041, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.19003595274781715, | |
| "grad_norm": 2.714902877807617, | |
| "learning_rate": 2.9109589041095893e-06, | |
| "loss": 1.8213, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.19106317411402157, | |
| "grad_norm": 3.0686237812042236, | |
| "learning_rate": 2.9280821917808223e-06, | |
| "loss": 1.817, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.192090395480226, | |
| "grad_norm": 3.510448932647705, | |
| "learning_rate": 2.945205479452055e-06, | |
| "loss": 1.8317, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.19311761684643042, | |
| "grad_norm": 3.2060787677764893, | |
| "learning_rate": 2.962328767123288e-06, | |
| "loss": 1.894, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.1941448382126348, | |
| "grad_norm": 3.1756906509399414, | |
| "learning_rate": 2.979452054794521e-06, | |
| "loss": 1.8788, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.19517205957883924, | |
| "grad_norm": 3.059863805770874, | |
| "learning_rate": 2.9965753424657533e-06, | |
| "loss": 1.8198, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19517205957883924, | |
| "eval_loss": 2.0506513118743896, | |
| "eval_runtime": 37.4014, | |
| "eval_samples_per_second": 26.737, | |
| "eval_steps_per_second": 1.123, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19619928094504366, | |
| "grad_norm": 3.193685531616211, | |
| "learning_rate": 3.0136986301369864e-06, | |
| "loss": 1.8818, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.19722650231124808, | |
| "grad_norm": 2.905402183532715, | |
| "learning_rate": 3.0308219178082194e-06, | |
| "loss": 1.8546, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1982537236774525, | |
| "grad_norm": 3.423109531402588, | |
| "learning_rate": 3.0479452054794525e-06, | |
| "loss": 1.8142, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.1992809450436569, | |
| "grad_norm": 3.136094331741333, | |
| "learning_rate": 3.065068493150685e-06, | |
| "loss": 1.8553, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.20030816640986132, | |
| "grad_norm": 3.0746538639068604, | |
| "learning_rate": 3.082191780821918e-06, | |
| "loss": 1.8153, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.20133538777606574, | |
| "grad_norm": 2.9354681968688965, | |
| "learning_rate": 3.099315068493151e-06, | |
| "loss": 1.8301, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.20236260914227017, | |
| "grad_norm": 3.00426983833313, | |
| "learning_rate": 3.1164383561643843e-06, | |
| "loss": 1.8233, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 3.2754054069519043, | |
| "learning_rate": 3.1335616438356165e-06, | |
| "loss": 1.787, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.20441705187467898, | |
| "grad_norm": 2.9854509830474854, | |
| "learning_rate": 3.1506849315068495e-06, | |
| "loss": 1.9341, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.2054442732408834, | |
| "grad_norm": 3.5655088424682617, | |
| "learning_rate": 3.167808219178082e-06, | |
| "loss": 1.7964, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2054442732408834, | |
| "eval_loss": 2.0440263748168945, | |
| "eval_runtime": 37.4054, | |
| "eval_samples_per_second": 26.734, | |
| "eval_steps_per_second": 1.123, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20647149460708783, | |
| "grad_norm": 3.132373571395874, | |
| "learning_rate": 3.184931506849315e-06, | |
| "loss": 1.8019, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.20749871597329225, | |
| "grad_norm": 3.3017780780792236, | |
| "learning_rate": 3.2020547945205483e-06, | |
| "loss": 1.7786, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.20852593733949668, | |
| "grad_norm": 3.009382486343384, | |
| "learning_rate": 3.2191780821917813e-06, | |
| "loss": 1.7639, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.20955315870570107, | |
| "grad_norm": 3.5784854888916016, | |
| "learning_rate": 3.236301369863014e-06, | |
| "loss": 1.76, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2105803800719055, | |
| "grad_norm": 3.236858367919922, | |
| "learning_rate": 3.253424657534247e-06, | |
| "loss": 1.7295, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.21160760143810992, | |
| "grad_norm": 3.6157479286193848, | |
| "learning_rate": 3.2705479452054796e-06, | |
| "loss": 1.8287, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.21263482280431434, | |
| "grad_norm": 3.51790452003479, | |
| "learning_rate": 3.2876712328767123e-06, | |
| "loss": 1.8004, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.21366204417051873, | |
| "grad_norm": 3.0700764656066895, | |
| "learning_rate": 3.3047945205479453e-06, | |
| "loss": 1.7581, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.21468926553672316, | |
| "grad_norm": 3.2651591300964355, | |
| "learning_rate": 3.3219178082191784e-06, | |
| "loss": 1.7724, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.21571648690292758, | |
| "grad_norm": 2.9267404079437256, | |
| "learning_rate": 3.3390410958904114e-06, | |
| "loss": 1.8154, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.21571648690292758, | |
| "eval_loss": 2.0323731899261475, | |
| "eval_runtime": 37.2156, | |
| "eval_samples_per_second": 26.87, | |
| "eval_steps_per_second": 1.129, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.216743708269132, | |
| "grad_norm": 3.463411808013916, | |
| "learning_rate": 3.356164383561644e-06, | |
| "loss": 1.8309, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.21777092963533642, | |
| "grad_norm": 3.123573064804077, | |
| "learning_rate": 3.373287671232877e-06, | |
| "loss": 1.8793, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.21879815100154082, | |
| "grad_norm": 3.427051305770874, | |
| "learning_rate": 3.39041095890411e-06, | |
| "loss": 1.8259, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.21982537236774524, | |
| "grad_norm": 3.306366443634033, | |
| "learning_rate": 3.4075342465753424e-06, | |
| "loss": 1.8565, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.22085259373394966, | |
| "grad_norm": 3.557340383529663, | |
| "learning_rate": 3.4246575342465754e-06, | |
| "loss": 1.7531, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2218798151001541, | |
| "grad_norm": 3.20525860786438, | |
| "learning_rate": 3.4417808219178085e-06, | |
| "loss": 1.8032, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.2229070364663585, | |
| "grad_norm": 3.2657511234283447, | |
| "learning_rate": 3.458904109589041e-06, | |
| "loss": 1.8026, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.2239342578325629, | |
| "grad_norm": 3.1869699954986572, | |
| "learning_rate": 3.476027397260274e-06, | |
| "loss": 1.814, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.22496147919876733, | |
| "grad_norm": 2.661536931991577, | |
| "learning_rate": 3.4931506849315072e-06, | |
| "loss": 1.8005, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 3.1108739376068115, | |
| "learning_rate": 3.5102739726027403e-06, | |
| "loss": 1.8095, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 2.015268325805664, | |
| "eval_runtime": 37.2867, | |
| "eval_samples_per_second": 26.819, | |
| "eval_steps_per_second": 1.126, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22701592193117617, | |
| "grad_norm": 2.8078837394714355, | |
| "learning_rate": 3.527397260273973e-06, | |
| "loss": 1.8016, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.2280431432973806, | |
| "grad_norm": 3.131399631500244, | |
| "learning_rate": 3.5445205479452056e-06, | |
| "loss": 1.7787, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.229070364663585, | |
| "grad_norm": 3.114422559738159, | |
| "learning_rate": 3.5616438356164386e-06, | |
| "loss": 1.7899, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.2300975860297894, | |
| "grad_norm": 3.040816068649292, | |
| "learning_rate": 3.5787671232876712e-06, | |
| "loss": 1.8601, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.23112480739599384, | |
| "grad_norm": 3.043100357055664, | |
| "learning_rate": 3.5958904109589043e-06, | |
| "loss": 1.8244, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23215202876219826, | |
| "grad_norm": 3.4232981204986572, | |
| "learning_rate": 3.6130136986301373e-06, | |
| "loss": 1.7634, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.23317925012840268, | |
| "grad_norm": 2.8170571327209473, | |
| "learning_rate": 3.6301369863013704e-06, | |
| "loss": 1.7793, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.23420647149460708, | |
| "grad_norm": 3.9133572578430176, | |
| "learning_rate": 3.647260273972603e-06, | |
| "loss": 1.8239, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.2352336928608115, | |
| "grad_norm": 2.7053382396698, | |
| "learning_rate": 3.664383561643836e-06, | |
| "loss": 1.8209, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.23626091422701592, | |
| "grad_norm": 3.4366891384124756, | |
| "learning_rate": 3.6815068493150687e-06, | |
| "loss": 1.7539, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.23626091422701592, | |
| "eval_loss": 2.0176751613616943, | |
| "eval_runtime": 37.3064, | |
| "eval_samples_per_second": 26.805, | |
| "eval_steps_per_second": 1.126, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.23728813559322035, | |
| "grad_norm": 2.592280149459839, | |
| "learning_rate": 3.6986301369863014e-06, | |
| "loss": 1.7858, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.23831535695942477, | |
| "grad_norm": 2.8370869159698486, | |
| "learning_rate": 3.7157534246575344e-06, | |
| "loss": 1.7414, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.23934257832562916, | |
| "grad_norm": 3.2120535373687744, | |
| "learning_rate": 3.7328767123287675e-06, | |
| "loss": 1.8467, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.24036979969183359, | |
| "grad_norm": 2.9314255714416504, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.7602, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.241397021058038, | |
| "grad_norm": 3.056293249130249, | |
| "learning_rate": 3.767123287671233e-06, | |
| "loss": 1.7972, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 2.5918917655944824, | |
| "learning_rate": 3.784246575342466e-06, | |
| "loss": 1.8274, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.24345146379044685, | |
| "grad_norm": 2.7911906242370605, | |
| "learning_rate": 3.8013698630136993e-06, | |
| "loss": 1.753, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.24447868515665125, | |
| "grad_norm": 2.810612916946411, | |
| "learning_rate": 3.818493150684932e-06, | |
| "loss": 1.7822, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.24550590652285567, | |
| "grad_norm": 2.8863744735717773, | |
| "learning_rate": 3.8356164383561645e-06, | |
| "loss": 1.7258, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.2465331278890601, | |
| "grad_norm": 3.002087116241455, | |
| "learning_rate": 3.852739726027397e-06, | |
| "loss": 1.8423, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2465331278890601, | |
| "eval_loss": 2.020223617553711, | |
| "eval_runtime": 37.3197, | |
| "eval_samples_per_second": 26.796, | |
| "eval_steps_per_second": 1.125, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.24756034925526452, | |
| "grad_norm": 2.892317056655884, | |
| "learning_rate": 3.869863013698631e-06, | |
| "loss": 1.8181, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.24858757062146894, | |
| "grad_norm": 2.895620584487915, | |
| "learning_rate": 3.886986301369863e-06, | |
| "loss": 1.7538, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.24961479198767333, | |
| "grad_norm": 3.015660524368286, | |
| "learning_rate": 3.904109589041096e-06, | |
| "loss": 1.766, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.25064201335387776, | |
| "grad_norm": 2.7516112327575684, | |
| "learning_rate": 3.921232876712329e-06, | |
| "loss": 1.7324, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.2516692347200822, | |
| "grad_norm": 2.937777519226074, | |
| "learning_rate": 3.938356164383562e-06, | |
| "loss": 1.7468, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2526964560862866, | |
| "grad_norm": 3.1706550121307373, | |
| "learning_rate": 3.9554794520547955e-06, | |
| "loss": 1.7035, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.253723677452491, | |
| "grad_norm": 2.7795372009277344, | |
| "learning_rate": 3.972602739726027e-06, | |
| "loss": 1.7912, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.25475089881869545, | |
| "grad_norm": 3.0375940799713135, | |
| "learning_rate": 3.989726027397261e-06, | |
| "loss": 1.7208, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.25577812018489987, | |
| "grad_norm": 2.863913059234619, | |
| "learning_rate": 4.006849315068493e-06, | |
| "loss": 1.7891, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.25680534155110424, | |
| "grad_norm": 3.02720046043396, | |
| "learning_rate": 4.023972602739726e-06, | |
| "loss": 1.7864, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25680534155110424, | |
| "eval_loss": 1.9981943368911743, | |
| "eval_runtime": 37.3019, | |
| "eval_samples_per_second": 26.808, | |
| "eval_steps_per_second": 1.126, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25783256291730866, | |
| "grad_norm": 2.90144681930542, | |
| "learning_rate": 4.0410958904109595e-06, | |
| "loss": 1.7508, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.2588597842835131, | |
| "grad_norm": 2.7670342922210693, | |
| "learning_rate": 4.058219178082192e-06, | |
| "loss": 1.7668, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.2598870056497175, | |
| "grad_norm": 3.0309600830078125, | |
| "learning_rate": 4.075342465753426e-06, | |
| "loss": 1.7853, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.26091422701592193, | |
| "grad_norm": 2.995190143585205, | |
| "learning_rate": 4.092465753424658e-06, | |
| "loss": 1.7409, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.26194144838212635, | |
| "grad_norm": 3.127767324447632, | |
| "learning_rate": 4.109589041095891e-06, | |
| "loss": 1.743, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2629686697483308, | |
| "grad_norm": 3.7104549407958984, | |
| "learning_rate": 4.1267123287671235e-06, | |
| "loss": 1.8149, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.2639958911145352, | |
| "grad_norm": 3.042569160461426, | |
| "learning_rate": 4.143835616438356e-06, | |
| "loss": 1.7544, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.2650231124807396, | |
| "grad_norm": 2.9337198734283447, | |
| "learning_rate": 4.16095890410959e-06, | |
| "loss": 1.823, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.26605033384694404, | |
| "grad_norm": 3.1853089332580566, | |
| "learning_rate": 4.178082191780822e-06, | |
| "loss": 1.8002, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.2670775552131484, | |
| "grad_norm": 2.9620680809020996, | |
| "learning_rate": 4.195205479452055e-06, | |
| "loss": 1.7401, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2670775552131484, | |
| "eval_loss": 1.9844669103622437, | |
| "eval_runtime": 37.3162, | |
| "eval_samples_per_second": 26.798, | |
| "eval_steps_per_second": 1.126, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.26810477657935283, | |
| "grad_norm": 3.477985382080078, | |
| "learning_rate": 4.212328767123288e-06, | |
| "loss": 1.7456, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.26913199794555726, | |
| "grad_norm": 2.881277084350586, | |
| "learning_rate": 4.229452054794521e-06, | |
| "loss": 1.7427, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.2701592193117617, | |
| "grad_norm": 3.3313355445861816, | |
| "learning_rate": 4.246575342465754e-06, | |
| "loss": 1.7537, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 2.947119951248169, | |
| "learning_rate": 4.263698630136986e-06, | |
| "loss": 1.7349, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.2722136620441705, | |
| "grad_norm": 3.0780889987945557, | |
| "learning_rate": 4.28082191780822e-06, | |
| "loss": 1.694, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.27324088341037495, | |
| "grad_norm": 3.3371143341064453, | |
| "learning_rate": 4.297945205479452e-06, | |
| "loss": 1.8489, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.27426810477657937, | |
| "grad_norm": 3.01694917678833, | |
| "learning_rate": 4.315068493150685e-06, | |
| "loss": 1.7478, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.2752953261427838, | |
| "grad_norm": 3.001850128173828, | |
| "learning_rate": 4.3321917808219185e-06, | |
| "loss": 1.7298, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.2763225475089882, | |
| "grad_norm": 2.9096696376800537, | |
| "learning_rate": 4.349315068493151e-06, | |
| "loss": 1.7542, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "grad_norm": 3.209601402282715, | |
| "learning_rate": 4.3664383561643846e-06, | |
| "loss": 1.7248, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "eval_loss": 1.9732507467269897, | |
| "eval_runtime": 37.3151, | |
| "eval_samples_per_second": 26.799, | |
| "eval_steps_per_second": 1.126, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.278376990241397, | |
| "grad_norm": 2.9635558128356934, | |
| "learning_rate": 4.383561643835616e-06, | |
| "loss": 1.727, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.2794042116076014, | |
| "grad_norm": 3.143821954727173, | |
| "learning_rate": 4.40068493150685e-06, | |
| "loss": 1.8045, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.28043143297380585, | |
| "grad_norm": 3.4248714447021484, | |
| "learning_rate": 4.4178082191780825e-06, | |
| "loss": 1.7649, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.2814586543400103, | |
| "grad_norm": 2.902162790298462, | |
| "learning_rate": 4.434931506849315e-06, | |
| "loss": 1.7324, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.2824858757062147, | |
| "grad_norm": 2.8899712562561035, | |
| "learning_rate": 4.4520547945205486e-06, | |
| "loss": 1.6886, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.2835130970724191, | |
| "grad_norm": 3.2267258167266846, | |
| "learning_rate": 4.469178082191781e-06, | |
| "loss": 1.7442, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.28454031843862354, | |
| "grad_norm": 3.275735378265381, | |
| "learning_rate": 4.486301369863014e-06, | |
| "loss": 1.7334, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.28556753980482796, | |
| "grad_norm": 2.991509199142456, | |
| "learning_rate": 4.503424657534247e-06, | |
| "loss": 1.7853, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.28659476117103233, | |
| "grad_norm": 2.8380391597747803, | |
| "learning_rate": 4.52054794520548e-06, | |
| "loss": 1.6885, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.28762198253723675, | |
| "grad_norm": 2.909980297088623, | |
| "learning_rate": 4.537671232876713e-06, | |
| "loss": 1.7146, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.28762198253723675, | |
| "eval_loss": 1.9755980968475342, | |
| "eval_runtime": 37.3524, | |
| "eval_samples_per_second": 26.772, | |
| "eval_steps_per_second": 1.124, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2886492039034412, | |
| "grad_norm": 3.2689175605773926, | |
| "learning_rate": 4.554794520547945e-06, | |
| "loss": 1.7747, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.2896764252696456, | |
| "grad_norm": 2.8242290019989014, | |
| "learning_rate": 4.571917808219179e-06, | |
| "loss": 1.7657, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.29070364663585, | |
| "grad_norm": 3.03828501701355, | |
| "learning_rate": 4.589041095890411e-06, | |
| "loss": 1.7555, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.29173086800205444, | |
| "grad_norm": 2.714351177215576, | |
| "learning_rate": 4.606164383561644e-06, | |
| "loss": 1.7055, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.29275808936825887, | |
| "grad_norm": 2.9540348052978516, | |
| "learning_rate": 4.6232876712328774e-06, | |
| "loss": 1.7258, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2937853107344633, | |
| "grad_norm": 3.107060670852661, | |
| "learning_rate": 4.64041095890411e-06, | |
| "loss": 1.7376, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.2948125321006677, | |
| "grad_norm": 3.3266639709472656, | |
| "learning_rate": 4.657534246575343e-06, | |
| "loss": 1.7063, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.29583975346687214, | |
| "grad_norm": 3.3113174438476562, | |
| "learning_rate": 4.674657534246575e-06, | |
| "loss": 1.7514, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.2968669748330765, | |
| "grad_norm": 3.313321352005005, | |
| "learning_rate": 4.691780821917809e-06, | |
| "loss": 1.73, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.2978941961992809, | |
| "grad_norm": 2.901522159576416, | |
| "learning_rate": 4.7089041095890414e-06, | |
| "loss": 1.7709, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2978941961992809, | |
| "eval_loss": 1.9608837366104126, | |
| "eval_runtime": 37.3687, | |
| "eval_samples_per_second": 26.76, | |
| "eval_steps_per_second": 1.124, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.29892141756548535, | |
| "grad_norm": 3.4208264350891113, | |
| "learning_rate": 4.726027397260274e-06, | |
| "loss": 1.73, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.29994863893168977, | |
| "grad_norm": 2.8982441425323486, | |
| "learning_rate": 4.7431506849315075e-06, | |
| "loss": 1.7416, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.3009758602978942, | |
| "grad_norm": 3.2743732929229736, | |
| "learning_rate": 4.76027397260274e-06, | |
| "loss": 1.7443, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.3020030816640986, | |
| "grad_norm": 3.028764486312866, | |
| "learning_rate": 4.777397260273973e-06, | |
| "loss": 1.6879, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 3.3531785011291504, | |
| "learning_rate": 4.7945205479452054e-06, | |
| "loss": 1.7096, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.30405752439650746, | |
| "grad_norm": 2.5602540969848633, | |
| "learning_rate": 4.811643835616439e-06, | |
| "loss": 1.7125, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.3050847457627119, | |
| "grad_norm": 3.1823129653930664, | |
| "learning_rate": 4.8287671232876716e-06, | |
| "loss": 1.6531, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.3061119671289163, | |
| "grad_norm": 2.6700282096862793, | |
| "learning_rate": 4.845890410958904e-06, | |
| "loss": 1.6983, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.3071391884951207, | |
| "grad_norm": 2.7118732929229736, | |
| "learning_rate": 4.863013698630138e-06, | |
| "loss": 1.7056, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.3081664098613251, | |
| "grad_norm": 3.3493311405181885, | |
| "learning_rate": 4.88013698630137e-06, | |
| "loss": 1.6944, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3081664098613251, | |
| "eval_loss": 1.9489911794662476, | |
| "eval_runtime": 37.35, | |
| "eval_samples_per_second": 26.774, | |
| "eval_steps_per_second": 1.124, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3091936312275295, | |
| "grad_norm": 2.9436538219451904, | |
| "learning_rate": 4.897260273972603e-06, | |
| "loss": 1.6717, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.31022085259373394, | |
| "grad_norm": 2.894737482070923, | |
| "learning_rate": 4.914383561643836e-06, | |
| "loss": 1.7895, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.31124807395993837, | |
| "grad_norm": 2.8645665645599365, | |
| "learning_rate": 4.931506849315069e-06, | |
| "loss": 1.721, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.3122752953261428, | |
| "grad_norm": 3.050203323364258, | |
| "learning_rate": 4.948630136986302e-06, | |
| "loss": 1.7564, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3133025166923472, | |
| "grad_norm": 3.146395206451416, | |
| "learning_rate": 4.965753424657534e-06, | |
| "loss": 1.7938, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.31432973805855163, | |
| "grad_norm": 3.1021251678466797, | |
| "learning_rate": 4.982876712328768e-06, | |
| "loss": 1.6682, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.31535695942475606, | |
| "grad_norm": 2.7301125526428223, | |
| "learning_rate": 5e-06, | |
| "loss": 1.6974, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 2.7602250576019287, | |
| "learning_rate": 4.998096688237534e-06, | |
| "loss": 1.6523, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.31741140215716485, | |
| "grad_norm": 2.8149876594543457, | |
| "learning_rate": 4.996193376475067e-06, | |
| "loss": 1.7535, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.31843862352336927, | |
| "grad_norm": 2.54823637008667, | |
| "learning_rate": 4.9942900647126005e-06, | |
| "loss": 1.63, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.31843862352336927, | |
| "eval_loss": 1.928893804550171, | |
| "eval_runtime": 37.2236, | |
| "eval_samples_per_second": 26.865, | |
| "eval_steps_per_second": 1.128, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3194658448895737, | |
| "grad_norm": 2.7819766998291016, | |
| "learning_rate": 4.992386752950134e-06, | |
| "loss": 1.6461, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3204930662557781, | |
| "grad_norm": 2.999209403991699, | |
| "learning_rate": 4.990483441187667e-06, | |
| "loss": 1.6861, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.32152028762198254, | |
| "grad_norm": 2.7288851737976074, | |
| "learning_rate": 4.9885801294252e-06, | |
| "loss": 1.7076, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.32254750898818696, | |
| "grad_norm": 2.8722457885742188, | |
| "learning_rate": 4.986676817662733e-06, | |
| "loss": 1.7079, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.3235747303543914, | |
| "grad_norm": 2.853344678878784, | |
| "learning_rate": 4.9847735059002665e-06, | |
| "loss": 1.6699, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3246019517205958, | |
| "grad_norm": 2.7404720783233643, | |
| "learning_rate": 4.9828701941378e-06, | |
| "loss": 1.7423, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.3256291730868002, | |
| "grad_norm": 2.6062633991241455, | |
| "learning_rate": 4.980966882375333e-06, | |
| "loss": 1.6811, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.3266563944530046, | |
| "grad_norm": 2.834162712097168, | |
| "learning_rate": 4.979063570612867e-06, | |
| "loss": 1.6575, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.327683615819209, | |
| "grad_norm": 2.7741048336029053, | |
| "learning_rate": 4.9771602588504e-06, | |
| "loss": 1.6158, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.32871083718541344, | |
| "grad_norm": 2.6216888427734375, | |
| "learning_rate": 4.975256947087933e-06, | |
| "loss": 1.7295, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.32871083718541344, | |
| "eval_loss": 1.9309543371200562, | |
| "eval_runtime": 37.3489, | |
| "eval_samples_per_second": 26.775, | |
| "eval_steps_per_second": 1.125, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.32973805855161786, | |
| "grad_norm": 2.6282548904418945, | |
| "learning_rate": 4.973353635325467e-06, | |
| "loss": 1.6266, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.3307652799178223, | |
| "grad_norm": 2.632124662399292, | |
| "learning_rate": 4.971450323563e-06, | |
| "loss": 1.6887, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.3317925012840267, | |
| "grad_norm": 2.5844857692718506, | |
| "learning_rate": 4.969547011800533e-06, | |
| "loss": 1.6287, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.33281972265023113, | |
| "grad_norm": 2.597620964050293, | |
| "learning_rate": 4.967643700038067e-06, | |
| "loss": 1.6876, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.33384694401643555, | |
| "grad_norm": 2.6529343128204346, | |
| "learning_rate": 4.9657403882756e-06, | |
| "loss": 1.6883, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.33487416538264, | |
| "grad_norm": 2.592874526977539, | |
| "learning_rate": 4.9638370765131335e-06, | |
| "loss": 1.653, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.3359013867488444, | |
| "grad_norm": 2.523489236831665, | |
| "learning_rate": 4.961933764750667e-06, | |
| "loss": 1.6501, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.33692860811504877, | |
| "grad_norm": 2.6721699237823486, | |
| "learning_rate": 4.9600304529882e-06, | |
| "loss": 1.7126, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.3379558294812532, | |
| "grad_norm": 2.513122797012329, | |
| "learning_rate": 4.9581271412257335e-06, | |
| "loss": 1.7268, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 2.571118116378784, | |
| "learning_rate": 4.956223829463266e-06, | |
| "loss": 1.6862, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "eval_loss": 1.9501315355300903, | |
| "eval_runtime": 37.3287, | |
| "eval_samples_per_second": 26.789, | |
| "eval_steps_per_second": 1.125, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.34001027221366203, | |
| "grad_norm": 2.5783371925354004, | |
| "learning_rate": 4.954320517700799e-06, | |
| "loss": 1.6041, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.34103749357986646, | |
| "grad_norm": 2.6829233169555664, | |
| "learning_rate": 4.952417205938333e-06, | |
| "loss": 1.7111, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.3420647149460709, | |
| "grad_norm": 2.6643247604370117, | |
| "learning_rate": 4.950513894175866e-06, | |
| "loss": 1.6797, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.3430919363122753, | |
| "grad_norm": 2.776308298110962, | |
| "learning_rate": 4.9486105824133995e-06, | |
| "loss": 1.6766, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.3441191576784797, | |
| "grad_norm": 2.722667932510376, | |
| "learning_rate": 4.946707270650933e-06, | |
| "loss": 1.6865, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.34514637904468415, | |
| "grad_norm": 2.7050845623016357, | |
| "learning_rate": 4.944803958888466e-06, | |
| "loss": 1.6967, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.34617360041088857, | |
| "grad_norm": 3.0009098052978516, | |
| "learning_rate": 4.942900647126e-06, | |
| "loss": 1.714, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.34720082177709294, | |
| "grad_norm": 2.793621301651001, | |
| "learning_rate": 4.940997335363533e-06, | |
| "loss": 1.6591, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.34822804314329736, | |
| "grad_norm": 2.844383478164673, | |
| "learning_rate": 4.939094023601066e-06, | |
| "loss": 1.611, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.3492552645095018, | |
| "grad_norm": 2.829378366470337, | |
| "learning_rate": 4.9371907118386e-06, | |
| "loss": 1.666, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3492552645095018, | |
| "eval_loss": 1.96309494972229, | |
| "eval_runtime": 37.3346, | |
| "eval_samples_per_second": 26.785, | |
| "eval_steps_per_second": 1.125, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3502824858757062, | |
| "grad_norm": 2.9702041149139404, | |
| "learning_rate": 4.935287400076133e-06, | |
| "loss": 1.6703, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.35130970724191063, | |
| "grad_norm": 2.7555935382843018, | |
| "learning_rate": 4.933384088313666e-06, | |
| "loss": 1.6879, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.35233692860811505, | |
| "grad_norm": 2.8968169689178467, | |
| "learning_rate": 4.9314807765512e-06, | |
| "loss": 1.6342, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.3533641499743195, | |
| "grad_norm": 3.010115385055542, | |
| "learning_rate": 4.929577464788733e-06, | |
| "loss": 1.5883, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.3543913713405239, | |
| "grad_norm": 2.6449785232543945, | |
| "learning_rate": 4.9276741530262665e-06, | |
| "loss": 1.654, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3554185927067283, | |
| "grad_norm": 2.976109266281128, | |
| "learning_rate": 4.9257708412638e-06, | |
| "loss": 1.6483, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.35644581407293274, | |
| "grad_norm": 2.856144666671753, | |
| "learning_rate": 4.923867529501332e-06, | |
| "loss": 1.6536, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.3574730354391371, | |
| "grad_norm": 2.8142166137695312, | |
| "learning_rate": 4.921964217738866e-06, | |
| "loss": 1.6415, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.35850025680534153, | |
| "grad_norm": 2.70807147026062, | |
| "learning_rate": 4.920060905976399e-06, | |
| "loss": 1.7099, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.35952747817154596, | |
| "grad_norm": 2.7715506553649902, | |
| "learning_rate": 4.9181575942139325e-06, | |
| "loss": 1.6947, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.35952747817154596, | |
| "eval_loss": 1.9507063627243042, | |
| "eval_runtime": 37.3094, | |
| "eval_samples_per_second": 26.803, | |
| "eval_steps_per_second": 1.126, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3605546995377504, | |
| "grad_norm": 2.8816769123077393, | |
| "learning_rate": 4.916254282451466e-06, | |
| "loss": 1.6906, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 3.08797025680542, | |
| "learning_rate": 4.914350970688999e-06, | |
| "loss": 1.7387, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.3626091422701592, | |
| "grad_norm": 2.6018118858337402, | |
| "learning_rate": 4.9124476589265325e-06, | |
| "loss": 1.6319, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 2.7790255546569824, | |
| "learning_rate": 4.910544347164066e-06, | |
| "loss": 1.6357, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.36466358500256807, | |
| "grad_norm": 2.7360289096832275, | |
| "learning_rate": 4.908641035401599e-06, | |
| "loss": 1.7127, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3656908063687725, | |
| "grad_norm": 2.6693854331970215, | |
| "learning_rate": 4.906737723639133e-06, | |
| "loss": 1.7747, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.3667180277349769, | |
| "grad_norm": 2.642868995666504, | |
| "learning_rate": 4.904834411876665e-06, | |
| "loss": 1.6401, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.3677452491011813, | |
| "grad_norm": 2.7230374813079834, | |
| "learning_rate": 4.902931100114199e-06, | |
| "loss": 1.6833, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.3687724704673857, | |
| "grad_norm": 2.499457359313965, | |
| "learning_rate": 4.901027788351733e-06, | |
| "loss": 1.6007, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.3697996918335901, | |
| "grad_norm": 2.7695276737213135, | |
| "learning_rate": 4.899124476589266e-06, | |
| "loss": 1.6486, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3697996918335901, | |
| "eval_loss": 1.9434194564819336, | |
| "eval_runtime": 37.3126, | |
| "eval_samples_per_second": 26.801, | |
| "eval_steps_per_second": 1.126, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.37082691319979455, | |
| "grad_norm": 2.5715794563293457, | |
| "learning_rate": 4.8972211648267994e-06, | |
| "loss": 1.6183, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.371854134565999, | |
| "grad_norm": 2.637859582901001, | |
| "learning_rate": 4.895317853064333e-06, | |
| "loss": 1.6648, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.3728813559322034, | |
| "grad_norm": 2.5601117610931396, | |
| "learning_rate": 4.893414541301866e-06, | |
| "loss": 1.6475, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.3739085772984078, | |
| "grad_norm": 2.429337739944458, | |
| "learning_rate": 4.891511229539399e-06, | |
| "loss": 1.6435, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.37493579866461224, | |
| "grad_norm": 2.6890885829925537, | |
| "learning_rate": 4.889607917776932e-06, | |
| "loss": 1.6577, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.37596302003081666, | |
| "grad_norm": 2.55492901802063, | |
| "learning_rate": 4.887704606014465e-06, | |
| "loss": 1.6523, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.37699024139702103, | |
| "grad_norm": 2.841362476348877, | |
| "learning_rate": 4.885801294251999e-06, | |
| "loss": 1.6742, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.37801746276322545, | |
| "grad_norm": 2.8041367530822754, | |
| "learning_rate": 4.883897982489532e-06, | |
| "loss": 1.5946, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.3790446841294299, | |
| "grad_norm": 2.7135822772979736, | |
| "learning_rate": 4.8819946707270655e-06, | |
| "loss": 1.6909, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.3800719054956343, | |
| "grad_norm": 2.9020211696624756, | |
| "learning_rate": 4.880091358964599e-06, | |
| "loss": 1.6804, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3800719054956343, | |
| "eval_loss": 1.9353317022323608, | |
| "eval_runtime": 37.3188, | |
| "eval_samples_per_second": 26.796, | |
| "eval_steps_per_second": 1.125, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3810991268618387, | |
| "grad_norm": 2.567310333251953, | |
| "learning_rate": 4.878188047202132e-06, | |
| "loss": 1.5885, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.38212634822804314, | |
| "grad_norm": 2.910834789276123, | |
| "learning_rate": 4.876284735439666e-06, | |
| "loss": 1.7681, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.38315356959424757, | |
| "grad_norm": 2.7507543563842773, | |
| "learning_rate": 4.874381423677199e-06, | |
| "loss": 1.7228, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.384180790960452, | |
| "grad_norm": 2.9230854511260986, | |
| "learning_rate": 4.8724781119147315e-06, | |
| "loss": 1.6491, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.3852080123266564, | |
| "grad_norm": 2.608980178833008, | |
| "learning_rate": 4.870574800152265e-06, | |
| "loss": 1.6757, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.38623523369286084, | |
| "grad_norm": 2.9557063579559326, | |
| "learning_rate": 4.868671488389798e-06, | |
| "loss": 1.607, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.3872624550590652, | |
| "grad_norm": 2.982243537902832, | |
| "learning_rate": 4.8667681766273316e-06, | |
| "loss": 1.6169, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.3882896764252696, | |
| "grad_norm": 2.775012254714966, | |
| "learning_rate": 4.864864864864866e-06, | |
| "loss": 1.5835, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.38931689779147405, | |
| "grad_norm": 2.9500741958618164, | |
| "learning_rate": 4.862961553102399e-06, | |
| "loss": 1.6504, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.39034411915767847, | |
| "grad_norm": 2.889702796936035, | |
| "learning_rate": 4.8610582413399325e-06, | |
| "loss": 1.6814, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.39034411915767847, | |
| "eval_loss": 1.9426418542861938, | |
| "eval_runtime": 37.3276, | |
| "eval_samples_per_second": 26.79, | |
| "eval_steps_per_second": 1.125, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3913713405238829, | |
| "grad_norm": 2.5075154304504395, | |
| "learning_rate": 4.859154929577465e-06, | |
| "loss": 1.6368, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.3923985618900873, | |
| "grad_norm": 2.6461148262023926, | |
| "learning_rate": 4.857251617814998e-06, | |
| "loss": 1.6526, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.39342578325629174, | |
| "grad_norm": 2.681501626968384, | |
| "learning_rate": 4.855348306052532e-06, | |
| "loss": 1.6846, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.39445300462249616, | |
| "grad_norm": 2.557311773300171, | |
| "learning_rate": 4.853444994290065e-06, | |
| "loss": 1.6645, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.3954802259887006, | |
| "grad_norm": 2.6819186210632324, | |
| "learning_rate": 4.8515416825275985e-06, | |
| "loss": 1.6323, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.396507447354905, | |
| "grad_norm": 2.8803794384002686, | |
| "learning_rate": 4.849638370765132e-06, | |
| "loss": 1.6991, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.3975346687211094, | |
| "grad_norm": 2.7181358337402344, | |
| "learning_rate": 4.847735059002665e-06, | |
| "loss": 1.6256, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.3985618900873138, | |
| "grad_norm": 2.5668489933013916, | |
| "learning_rate": 4.8458317472401985e-06, | |
| "loss": 1.58, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.3995891114535182, | |
| "grad_norm": 2.708804130554199, | |
| "learning_rate": 4.843928435477732e-06, | |
| "loss": 1.67, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.40061633281972264, | |
| "grad_norm": 2.6565728187561035, | |
| "learning_rate": 4.842025123715265e-06, | |
| "loss": 1.622, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.40061633281972264, | |
| "eval_loss": 1.9529728889465332, | |
| "eval_runtime": 37.3489, | |
| "eval_samples_per_second": 26.775, | |
| "eval_steps_per_second": 1.125, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.40164355418592707, | |
| "grad_norm": 2.8743324279785156, | |
| "learning_rate": 4.840121811952798e-06, | |
| "loss": 1.6618, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.4026707755521315, | |
| "grad_norm": 2.86134672164917, | |
| "learning_rate": 4.838218500190331e-06, | |
| "loss": 1.6544, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.4036979969183359, | |
| "grad_norm": 3.3492071628570557, | |
| "learning_rate": 4.8363151884278645e-06, | |
| "loss": 1.6683, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.40472521828454033, | |
| "grad_norm": 2.6630825996398926, | |
| "learning_rate": 4.834411876665398e-06, | |
| "loss": 1.6447, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.40575243965074476, | |
| "grad_norm": 2.820096492767334, | |
| "learning_rate": 4.832508564902931e-06, | |
| "loss": 1.6579, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 3.076234817504883, | |
| "learning_rate": 4.830605253140465e-06, | |
| "loss": 1.6039, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.40780688238315355, | |
| "grad_norm": 2.667719841003418, | |
| "learning_rate": 4.828701941377998e-06, | |
| "loss": 1.6364, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.40883410374935797, | |
| "grad_norm": 3.2132771015167236, | |
| "learning_rate": 4.826798629615531e-06, | |
| "loss": 1.5906, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.4098613251155624, | |
| "grad_norm": 2.661484479904175, | |
| "learning_rate": 4.824895317853065e-06, | |
| "loss": 1.613, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.4108885464817668, | |
| "grad_norm": 3.002636671066284, | |
| "learning_rate": 4.822992006090598e-06, | |
| "loss": 1.6305, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4108885464817668, | |
| "eval_loss": 1.9345510005950928, | |
| "eval_runtime": 37.3369, | |
| "eval_samples_per_second": 26.783, | |
| "eval_steps_per_second": 1.125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41191576784797124, | |
| "grad_norm": 2.6405227184295654, | |
| "learning_rate": 4.821088694328131e-06, | |
| "loss": 1.5881, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.41294298921417566, | |
| "grad_norm": 3.006169080734253, | |
| "learning_rate": 4.819185382565665e-06, | |
| "loss": 1.6126, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.4139702105803801, | |
| "grad_norm": 2.7614858150482178, | |
| "learning_rate": 4.817282070803198e-06, | |
| "loss": 1.6695, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.4149974319465845, | |
| "grad_norm": 2.797260046005249, | |
| "learning_rate": 4.8153787590407315e-06, | |
| "loss": 1.6539, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.41602465331278893, | |
| "grad_norm": 2.8156301975250244, | |
| "learning_rate": 4.813475447278265e-06, | |
| "loss": 1.5845, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.41705187467899335, | |
| "grad_norm": 2.74100399017334, | |
| "learning_rate": 4.811572135515798e-06, | |
| "loss": 1.6699, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.4180790960451977, | |
| "grad_norm": 2.7785775661468506, | |
| "learning_rate": 4.809668823753332e-06, | |
| "loss": 1.5987, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.41910631741140214, | |
| "grad_norm": 2.663504123687744, | |
| "learning_rate": 4.807765511990864e-06, | |
| "loss": 1.5987, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.42013353877760656, | |
| "grad_norm": 2.903374433517456, | |
| "learning_rate": 4.8058622002283975e-06, | |
| "loss": 1.6302, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.421160760143811, | |
| "grad_norm": 2.696049690246582, | |
| "learning_rate": 4.803958888465931e-06, | |
| "loss": 1.671, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.421160760143811, | |
| "eval_loss": 1.9333878755569458, | |
| "eval_runtime": 37.2472, | |
| "eval_samples_per_second": 26.848, | |
| "eval_steps_per_second": 1.128, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4221879815100154, | |
| "grad_norm": 2.486461877822876, | |
| "learning_rate": 4.802055576703464e-06, | |
| "loss": 1.6282, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.42321520287621983, | |
| "grad_norm": 2.6812057495117188, | |
| "learning_rate": 4.8001522649409976e-06, | |
| "loss": 1.7144, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 2.8370249271392822, | |
| "learning_rate": 4.798248953178531e-06, | |
| "loss": 1.5979, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.4252696456086287, | |
| "grad_norm": 2.6073036193847656, | |
| "learning_rate": 4.796345641416064e-06, | |
| "loss": 1.5703, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.4262968669748331, | |
| "grad_norm": 2.5891220569610596, | |
| "learning_rate": 4.794442329653598e-06, | |
| "loss": 1.6212, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.42732408834103747, | |
| "grad_norm": 2.6296865940093994, | |
| "learning_rate": 4.792539017891131e-06, | |
| "loss": 1.6711, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.4283513097072419, | |
| "grad_norm": 2.573472499847412, | |
| "learning_rate": 4.790635706128664e-06, | |
| "loss": 1.5994, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.4293785310734463, | |
| "grad_norm": 2.734464168548584, | |
| "learning_rate": 4.788732394366197e-06, | |
| "loss": 1.6383, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.43040575243965074, | |
| "grad_norm": 2.6412851810455322, | |
| "learning_rate": 4.786829082603731e-06, | |
| "loss": 1.5646, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.43143297380585516, | |
| "grad_norm": 2.5065555572509766, | |
| "learning_rate": 4.7849257708412645e-06, | |
| "loss": 1.5636, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.43143297380585516, | |
| "eval_loss": 1.9357348680496216, | |
| "eval_runtime": 37.372, | |
| "eval_samples_per_second": 26.758, | |
| "eval_steps_per_second": 1.124, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4324601951720596, | |
| "grad_norm": 2.4889843463897705, | |
| "learning_rate": 4.783022459078798e-06, | |
| "loss": 1.6457, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.433487416538264, | |
| "grad_norm": 2.544801950454712, | |
| "learning_rate": 4.781119147316331e-06, | |
| "loss": 1.5897, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.4345146379044684, | |
| "grad_norm": 2.7834064960479736, | |
| "learning_rate": 4.7792158355538645e-06, | |
| "loss": 1.6174, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.43554185927067285, | |
| "grad_norm": 2.602952480316162, | |
| "learning_rate": 4.777312523791398e-06, | |
| "loss": 1.6152, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.43656908063687727, | |
| "grad_norm": 2.629746198654175, | |
| "learning_rate": 4.77540921202893e-06, | |
| "loss": 1.5991, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.43759630200308164, | |
| "grad_norm": 2.4987270832061768, | |
| "learning_rate": 4.773505900266464e-06, | |
| "loss": 1.6342, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.43862352336928606, | |
| "grad_norm": 2.607611894607544, | |
| "learning_rate": 4.771602588503997e-06, | |
| "loss": 1.6145, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.4396507447354905, | |
| "grad_norm": 2.5654876232147217, | |
| "learning_rate": 4.7696992767415305e-06, | |
| "loss": 1.6162, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.4406779661016949, | |
| "grad_norm": 2.5701870918273926, | |
| "learning_rate": 4.767795964979064e-06, | |
| "loss": 1.6516, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.44170518746789933, | |
| "grad_norm": 2.8381104469299316, | |
| "learning_rate": 4.765892653216597e-06, | |
| "loss": 1.659, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.44170518746789933, | |
| "eval_loss": 1.9259562492370605, | |
| "eval_runtime": 37.3906, | |
| "eval_samples_per_second": 26.745, | |
| "eval_steps_per_second": 1.123, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.44273240883410375, | |
| "grad_norm": 2.5777862071990967, | |
| "learning_rate": 4.763989341454131e-06, | |
| "loss": 1.6571, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.4437596302003082, | |
| "grad_norm": 2.6656861305236816, | |
| "learning_rate": 4.762086029691664e-06, | |
| "loss": 1.5786, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.4447868515665126, | |
| "grad_norm": 2.724851131439209, | |
| "learning_rate": 4.760182717929197e-06, | |
| "loss": 1.5916, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.445814072932717, | |
| "grad_norm": 2.532191514968872, | |
| "learning_rate": 4.758279406166731e-06, | |
| "loss": 1.608, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.44684129429892144, | |
| "grad_norm": 2.6252050399780273, | |
| "learning_rate": 4.756376094404263e-06, | |
| "loss": 1.5297, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.4478685156651258, | |
| "grad_norm": 2.674530029296875, | |
| "learning_rate": 4.7544727826417966e-06, | |
| "loss": 1.615, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.44889573703133023, | |
| "grad_norm": 2.9209136962890625, | |
| "learning_rate": 4.75256947087933e-06, | |
| "loss": 1.6749, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.44992295839753466, | |
| "grad_norm": 2.4959394931793213, | |
| "learning_rate": 4.750666159116863e-06, | |
| "loss": 1.6186, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.4509501797637391, | |
| "grad_norm": 2.6317503452301025, | |
| "learning_rate": 4.7487628473543975e-06, | |
| "loss": 1.5873, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 2.6485610008239746, | |
| "learning_rate": 4.746859535591931e-06, | |
| "loss": 1.5451, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "eval_loss": 1.9235283136367798, | |
| "eval_runtime": 37.367, | |
| "eval_samples_per_second": 26.762, | |
| "eval_steps_per_second": 1.124, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4530046224961479, | |
| "grad_norm": 2.491852045059204, | |
| "learning_rate": 4.744956223829464e-06, | |
| "loss": 1.6016, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.45403184386235235, | |
| "grad_norm": 2.5354514122009277, | |
| "learning_rate": 4.743052912066997e-06, | |
| "loss": 1.5795, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.45505906522855677, | |
| "grad_norm": 2.7756357192993164, | |
| "learning_rate": 4.74114960030453e-06, | |
| "loss": 1.6299, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.4560862865947612, | |
| "grad_norm": 2.638906955718994, | |
| "learning_rate": 4.7392462885420635e-06, | |
| "loss": 1.6429, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.4571135079609656, | |
| "grad_norm": 2.5858829021453857, | |
| "learning_rate": 4.737342976779597e-06, | |
| "loss": 1.5316, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.45814072932717, | |
| "grad_norm": 2.798567295074463, | |
| "learning_rate": 4.73543966501713e-06, | |
| "loss": 1.6166, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.4591679506933744, | |
| "grad_norm": 2.512143135070801, | |
| "learning_rate": 4.7335363532546636e-06, | |
| "loss": 1.5952, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.4601951720595788, | |
| "grad_norm": 2.7063655853271484, | |
| "learning_rate": 4.731633041492197e-06, | |
| "loss": 1.6051, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.46122239342578325, | |
| "grad_norm": 2.6358017921447754, | |
| "learning_rate": 4.72972972972973e-06, | |
| "loss": 1.6008, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.4622496147919877, | |
| "grad_norm": 2.75992751121521, | |
| "learning_rate": 4.727826417967264e-06, | |
| "loss": 1.644, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4622496147919877, | |
| "eval_loss": 1.927345633506775, | |
| "eval_runtime": 37.3707, | |
| "eval_samples_per_second": 26.759, | |
| "eval_steps_per_second": 1.124, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4632768361581921, | |
| "grad_norm": 2.9103775024414062, | |
| "learning_rate": 4.725923106204797e-06, | |
| "loss": 1.6176, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.4643040575243965, | |
| "grad_norm": 2.627481460571289, | |
| "learning_rate": 4.72401979444233e-06, | |
| "loss": 1.586, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.46533127889060094, | |
| "grad_norm": 2.8432116508483887, | |
| "learning_rate": 4.722116482679863e-06, | |
| "loss": 1.6303, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.46635850025680536, | |
| "grad_norm": 2.8088958263397217, | |
| "learning_rate": 4.720213170917396e-06, | |
| "loss": 1.6163, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.46738572162300973, | |
| "grad_norm": 2.6040408611297607, | |
| "learning_rate": 4.71830985915493e-06, | |
| "loss": 1.6346, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.46841294298921415, | |
| "grad_norm": 2.8951191902160645, | |
| "learning_rate": 4.716406547392463e-06, | |
| "loss": 1.5859, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.4694401643554186, | |
| "grad_norm": 2.792473793029785, | |
| "learning_rate": 4.714503235629996e-06, | |
| "loss": 1.6441, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.470467385721623, | |
| "grad_norm": 2.6793878078460693, | |
| "learning_rate": 4.71259992386753e-06, | |
| "loss": 1.5699, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.4714946070878274, | |
| "grad_norm": 2.7223684787750244, | |
| "learning_rate": 4.710696612105063e-06, | |
| "loss": 1.6038, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.47252182845403184, | |
| "grad_norm": 2.8043856620788574, | |
| "learning_rate": 4.708793300342596e-06, | |
| "loss": 1.6018, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.47252182845403184, | |
| "eval_loss": 1.9213919639587402, | |
| "eval_runtime": 37.3451, | |
| "eval_samples_per_second": 26.777, | |
| "eval_steps_per_second": 1.125, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.47354904982023627, | |
| "grad_norm": 2.7657470703125, | |
| "learning_rate": 4.70688998858013e-06, | |
| "loss": 1.5896, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 2.8417739868164062, | |
| "learning_rate": 4.704986676817663e-06, | |
| "loss": 1.5892, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.4756034925526451, | |
| "grad_norm": 2.5660197734832764, | |
| "learning_rate": 4.7030833650551965e-06, | |
| "loss": 1.615, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.47663071391884954, | |
| "grad_norm": 2.762880325317383, | |
| "learning_rate": 4.70118005329273e-06, | |
| "loss": 1.5747, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.4776579352850539, | |
| "grad_norm": 2.7191319465637207, | |
| "learning_rate": 4.699276741530263e-06, | |
| "loss": 1.6529, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4786851566512583, | |
| "grad_norm": 2.4995453357696533, | |
| "learning_rate": 4.697373429767797e-06, | |
| "loss": 1.6285, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.47971237801746275, | |
| "grad_norm": 2.8300375938415527, | |
| "learning_rate": 4.69547011800533e-06, | |
| "loss": 1.6171, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.48073959938366717, | |
| "grad_norm": 2.6028811931610107, | |
| "learning_rate": 4.693566806242863e-06, | |
| "loss": 1.6014, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.4817668207498716, | |
| "grad_norm": 3.080156087875366, | |
| "learning_rate": 4.691663494480397e-06, | |
| "loss": 1.6055, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.482794042116076, | |
| "grad_norm": 2.6707916259765625, | |
| "learning_rate": 4.689760182717929e-06, | |
| "loss": 1.627, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.482794042116076, | |
| "eval_loss": 1.9015462398529053, | |
| "eval_runtime": 37.3476, | |
| "eval_samples_per_second": 26.776, | |
| "eval_steps_per_second": 1.125, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.48382126348228044, | |
| "grad_norm": 2.6820614337921143, | |
| "learning_rate": 4.6878568709554626e-06, | |
| "loss": 1.5261, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 2.841031789779663, | |
| "learning_rate": 4.685953559192996e-06, | |
| "loss": 1.5903, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.4858757062146893, | |
| "grad_norm": 2.470867156982422, | |
| "learning_rate": 4.684050247430529e-06, | |
| "loss": 1.6091, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.4869029275808937, | |
| "grad_norm": 2.4955153465270996, | |
| "learning_rate": 4.682146935668063e-06, | |
| "loss": 1.544, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.4879301489470981, | |
| "grad_norm": 2.9290695190429688, | |
| "learning_rate": 4.680243623905596e-06, | |
| "loss": 1.5893, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4889573703133025, | |
| "grad_norm": 2.5902767181396484, | |
| "learning_rate": 4.678340312143129e-06, | |
| "loss": 1.6117, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.4899845916795069, | |
| "grad_norm": 2.6067540645599365, | |
| "learning_rate": 4.676437000380663e-06, | |
| "loss": 1.5703, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.49101181304571134, | |
| "grad_norm": 2.490105152130127, | |
| "learning_rate": 4.674533688618196e-06, | |
| "loss": 1.6931, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.49203903441191577, | |
| "grad_norm": 2.7736282348632812, | |
| "learning_rate": 4.6726303768557295e-06, | |
| "loss": 1.6204, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.4930662557781202, | |
| "grad_norm": 2.741196870803833, | |
| "learning_rate": 4.670727065093263e-06, | |
| "loss": 1.5331, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4930662557781202, | |
| "eval_loss": 1.9095442295074463, | |
| "eval_runtime": 37.3351, | |
| "eval_samples_per_second": 26.784, | |
| "eval_steps_per_second": 1.125, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4940934771443246, | |
| "grad_norm": 2.7624332904815674, | |
| "learning_rate": 4.668823753330796e-06, | |
| "loss": 1.5591, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.49512069851052903, | |
| "grad_norm": 2.86407470703125, | |
| "learning_rate": 4.6669204415683295e-06, | |
| "loss": 1.5844, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.49614791987673346, | |
| "grad_norm": 2.770030975341797, | |
| "learning_rate": 4.665017129805863e-06, | |
| "loss": 1.6515, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 2.569862127304077, | |
| "learning_rate": 4.663113818043396e-06, | |
| "loss": 1.6228, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.49820236260914225, | |
| "grad_norm": 2.7176733016967773, | |
| "learning_rate": 4.66121050628093e-06, | |
| "loss": 1.5938, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.49922958397534667, | |
| "grad_norm": 2.4514758586883545, | |
| "learning_rate": 4.659307194518463e-06, | |
| "loss": 1.6307, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.5002568053415511, | |
| "grad_norm": 2.5439529418945312, | |
| "learning_rate": 4.6574038827559955e-06, | |
| "loss": 1.5855, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.5012840267077555, | |
| "grad_norm": 2.6395790576934814, | |
| "learning_rate": 4.655500570993529e-06, | |
| "loss": 1.6124, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.50231124807396, | |
| "grad_norm": 2.69413685798645, | |
| "learning_rate": 4.653597259231062e-06, | |
| "loss": 1.6358, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.5033384694401644, | |
| "grad_norm": 2.693129777908325, | |
| "learning_rate": 4.651693947468596e-06, | |
| "loss": 1.5218, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5033384694401644, | |
| "eval_loss": 1.9201244115829468, | |
| "eval_runtime": 37.3324, | |
| "eval_samples_per_second": 26.786, | |
| "eval_steps_per_second": 1.125, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5043656908063687, | |
| "grad_norm": 2.630596876144409, | |
| "learning_rate": 4.649790635706129e-06, | |
| "loss": 1.6719, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.5053929121725732, | |
| "grad_norm": 2.7230262756347656, | |
| "learning_rate": 4.647887323943662e-06, | |
| "loss": 1.5705, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.5064201335387776, | |
| "grad_norm": 2.529944896697998, | |
| "learning_rate": 4.645984012181196e-06, | |
| "loss": 1.5767, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.507447354904982, | |
| "grad_norm": 2.546849489212036, | |
| "learning_rate": 4.644080700418729e-06, | |
| "loss": 1.5039, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 2.6698246002197266, | |
| "learning_rate": 4.642177388656262e-06, | |
| "loss": 1.6229, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5095017976373909, | |
| "grad_norm": 2.7093148231506348, | |
| "learning_rate": 4.640274076893796e-06, | |
| "loss": 1.5797, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.5105290190035953, | |
| "grad_norm": 2.48629093170166, | |
| "learning_rate": 4.638370765131328e-06, | |
| "loss": 1.6366, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.5115562403697997, | |
| "grad_norm": 2.5818612575531006, | |
| "learning_rate": 4.636467453368862e-06, | |
| "loss": 1.5608, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.5125834617360041, | |
| "grad_norm": 2.6263651847839355, | |
| "learning_rate": 4.634564141606396e-06, | |
| "loss": 1.5518, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.5136106831022085, | |
| "grad_norm": 2.5724668502807617, | |
| "learning_rate": 4.632660829843929e-06, | |
| "loss": 1.6195, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5136106831022085, | |
| "eval_loss": 1.9094111919403076, | |
| "eval_runtime": 37.3483, | |
| "eval_samples_per_second": 26.775, | |
| "eval_steps_per_second": 1.125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.514637904468413, | |
| "grad_norm": 2.5028088092803955, | |
| "learning_rate": 4.630757518081463e-06, | |
| "loss": 1.5454, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.5156651258346173, | |
| "grad_norm": 2.588115692138672, | |
| "learning_rate": 4.628854206318996e-06, | |
| "loss": 1.6676, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.5166923472008218, | |
| "grad_norm": 2.9701285362243652, | |
| "learning_rate": 4.626950894556529e-06, | |
| "loss": 1.5822, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.5177195685670262, | |
| "grad_norm": 2.593867301940918, | |
| "learning_rate": 4.625047582794062e-06, | |
| "loss": 1.6091, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.5187467899332306, | |
| "grad_norm": 2.559642791748047, | |
| "learning_rate": 4.623144271031595e-06, | |
| "loss": 1.5359, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.519774011299435, | |
| "grad_norm": 2.4158153533935547, | |
| "learning_rate": 4.6212409592691286e-06, | |
| "loss": 1.5476, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.5208012326656395, | |
| "grad_norm": 2.666099786758423, | |
| "learning_rate": 4.619337647506662e-06, | |
| "loss": 1.6297, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.5218284540318439, | |
| "grad_norm": 2.7026472091674805, | |
| "learning_rate": 4.617434335744195e-06, | |
| "loss": 1.5891, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.5228556753980482, | |
| "grad_norm": 2.4591612815856934, | |
| "learning_rate": 4.615531023981729e-06, | |
| "loss": 1.5546, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.5238828967642527, | |
| "grad_norm": 2.870255708694458, | |
| "learning_rate": 4.613627712219262e-06, | |
| "loss": 1.5817, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5238828967642527, | |
| "eval_loss": 1.910629153251648, | |
| "eval_runtime": 37.1517, | |
| "eval_samples_per_second": 26.917, | |
| "eval_steps_per_second": 1.131, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5249101181304571, | |
| "grad_norm": 2.653801679611206, | |
| "learning_rate": 4.611724400456795e-06, | |
| "loss": 1.586, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.5259373394966615, | |
| "grad_norm": 2.4235377311706543, | |
| "learning_rate": 4.609821088694329e-06, | |
| "loss": 1.5886, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.5269645608628659, | |
| "grad_norm": 2.8782477378845215, | |
| "learning_rate": 4.607917776931862e-06, | |
| "loss": 1.5634, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.5279917822290704, | |
| "grad_norm": 2.792876958847046, | |
| "learning_rate": 4.606014465169395e-06, | |
| "loss": 1.6073, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.5290190035952748, | |
| "grad_norm": 2.5579030513763428, | |
| "learning_rate": 4.604111153406928e-06, | |
| "loss": 1.6161, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5300462249614792, | |
| "grad_norm": 2.6486189365386963, | |
| "learning_rate": 4.602207841644461e-06, | |
| "loss": 1.5297, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.5310734463276836, | |
| "grad_norm": 2.9047019481658936, | |
| "learning_rate": 4.600304529881995e-06, | |
| "loss": 1.626, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.5321006676938881, | |
| "grad_norm": 2.9164223670959473, | |
| "learning_rate": 4.598401218119528e-06, | |
| "loss": 1.6051, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.5331278890600925, | |
| "grad_norm": 2.544311046600342, | |
| "learning_rate": 4.5964979063570614e-06, | |
| "loss": 1.6247, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.5341551104262968, | |
| "grad_norm": 2.8632311820983887, | |
| "learning_rate": 4.594594594594596e-06, | |
| "loss": 1.5615, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5341551104262968, | |
| "eval_loss": 1.9171669483184814, | |
| "eval_runtime": 37.2243, | |
| "eval_samples_per_second": 26.864, | |
| "eval_steps_per_second": 1.128, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5351823317925013, | |
| "grad_norm": 2.507697105407715, | |
| "learning_rate": 4.592691282832128e-06, | |
| "loss": 1.5929, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.5362095531587057, | |
| "grad_norm": 2.657752752304077, | |
| "learning_rate": 4.5907879710696615e-06, | |
| "loss": 1.6159, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.5372367745249101, | |
| "grad_norm": 2.32254695892334, | |
| "learning_rate": 4.588884659307195e-06, | |
| "loss": 1.5318, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.5382639958911145, | |
| "grad_norm": 2.5979015827178955, | |
| "learning_rate": 4.586981347544728e-06, | |
| "loss": 1.5999, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.539291217257319, | |
| "grad_norm": 2.839956521987915, | |
| "learning_rate": 4.585078035782262e-06, | |
| "loss": 1.547, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5403184386235234, | |
| "grad_norm": 2.700131893157959, | |
| "learning_rate": 4.583174724019795e-06, | |
| "loss": 1.5831, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.5413456599897278, | |
| "grad_norm": 2.365183115005493, | |
| "learning_rate": 4.581271412257328e-06, | |
| "loss": 1.5357, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 2.675567865371704, | |
| "learning_rate": 4.579368100494862e-06, | |
| "loss": 1.5212, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.5434001027221366, | |
| "grad_norm": 2.9096713066101074, | |
| "learning_rate": 4.577464788732395e-06, | |
| "loss": 1.6196, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.544427324088341, | |
| "grad_norm": 2.6186270713806152, | |
| "learning_rate": 4.575561476969928e-06, | |
| "loss": 1.5895, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.544427324088341, | |
| "eval_loss": 1.926998496055603, | |
| "eval_runtime": 37.2248, | |
| "eval_samples_per_second": 26.864, | |
| "eval_steps_per_second": 1.128, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 2.7291345596313477, | |
| "learning_rate": 4.573658165207461e-06, | |
| "loss": 1.6335, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.5464817668207499, | |
| "grad_norm": 2.7084522247314453, | |
| "learning_rate": 4.571754853444994e-06, | |
| "loss": 1.5968, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.5475089881869543, | |
| "grad_norm": 2.699721336364746, | |
| "learning_rate": 4.569851541682528e-06, | |
| "loss": 1.5775, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.5485362095531587, | |
| "grad_norm": 2.602526903152466, | |
| "learning_rate": 4.567948229920061e-06, | |
| "loss": 1.5497, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.5495634309193631, | |
| "grad_norm": 2.597362518310547, | |
| "learning_rate": 4.566044918157594e-06, | |
| "loss": 1.5218, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5505906522855676, | |
| "grad_norm": 2.6624414920806885, | |
| "learning_rate": 4.564141606395128e-06, | |
| "loss": 1.5553, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.551617873651772, | |
| "grad_norm": 2.750807285308838, | |
| "learning_rate": 4.562238294632661e-06, | |
| "loss": 1.6078, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.5526450950179764, | |
| "grad_norm": 2.7480952739715576, | |
| "learning_rate": 4.5603349828701945e-06, | |
| "loss": 1.5707, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.5536723163841808, | |
| "grad_norm": 2.6287965774536133, | |
| "learning_rate": 4.558431671107728e-06, | |
| "loss": 1.5961, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "grad_norm": 2.721311569213867, | |
| "learning_rate": 4.556528359345261e-06, | |
| "loss": 1.6335, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "eval_loss": 1.9290324449539185, | |
| "eval_runtime": 37.2243, | |
| "eval_samples_per_second": 26.864, | |
| "eval_steps_per_second": 1.128, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5557267591165896, | |
| "grad_norm": 2.470325469970703, | |
| "learning_rate": 4.5546250475827946e-06, | |
| "loss": 1.5645, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.556753980482794, | |
| "grad_norm": 2.6089508533477783, | |
| "learning_rate": 4.552721735820328e-06, | |
| "loss": 1.5256, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.5577812018489985, | |
| "grad_norm": 2.541785478591919, | |
| "learning_rate": 4.550818424057861e-06, | |
| "loss": 1.5641, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.5588084232152029, | |
| "grad_norm": 2.6722488403320312, | |
| "learning_rate": 4.548915112295395e-06, | |
| "loss": 1.5708, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.5598356445814073, | |
| "grad_norm": 2.583695650100708, | |
| "learning_rate": 4.547011800532928e-06, | |
| "loss": 1.5799, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5608628659476117, | |
| "grad_norm": 2.956885576248169, | |
| "learning_rate": 4.545108488770461e-06, | |
| "loss": 1.5345, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.5618900873138162, | |
| "grad_norm": 2.5534746646881104, | |
| "learning_rate": 4.543205177007995e-06, | |
| "loss": 1.636, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.5629173086800205, | |
| "grad_norm": 2.8133325576782227, | |
| "learning_rate": 4.541301865245527e-06, | |
| "loss": 1.5678, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.5639445300462249, | |
| "grad_norm": 2.5969228744506836, | |
| "learning_rate": 4.539398553483061e-06, | |
| "loss": 1.5975, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "grad_norm": 2.7594687938690186, | |
| "learning_rate": 4.537495241720594e-06, | |
| "loss": 1.5622, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "eval_loss": 1.8870681524276733, | |
| "eval_runtime": 37.2094, | |
| "eval_samples_per_second": 26.875, | |
| "eval_steps_per_second": 1.129, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5659989727786338, | |
| "grad_norm": 2.7413411140441895, | |
| "learning_rate": 4.535591929958127e-06, | |
| "loss": 1.6031, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.5670261941448382, | |
| "grad_norm": 2.6182661056518555, | |
| "learning_rate": 4.533688618195661e-06, | |
| "loss": 1.5828, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.5680534155110426, | |
| "grad_norm": 2.5016422271728516, | |
| "learning_rate": 4.531785306433194e-06, | |
| "loss": 1.5712, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.5690806368772471, | |
| "grad_norm": 2.7788732051849365, | |
| "learning_rate": 4.529881994670727e-06, | |
| "loss": 1.5472, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.5701078582434514, | |
| "grad_norm": 2.7602436542510986, | |
| "learning_rate": 4.527978682908261e-06, | |
| "loss": 1.5526, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.5711350796096559, | |
| "grad_norm": 2.5898544788360596, | |
| "learning_rate": 4.526075371145794e-06, | |
| "loss": 1.5644, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.5721623009758603, | |
| "grad_norm": 2.439344882965088, | |
| "learning_rate": 4.5241720593833275e-06, | |
| "loss": 1.5892, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.5731895223420647, | |
| "grad_norm": 2.6324563026428223, | |
| "learning_rate": 4.52226874762086e-06, | |
| "loss": 1.5729, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.5742167437082691, | |
| "grad_norm": 2.674042224884033, | |
| "learning_rate": 4.520365435858393e-06, | |
| "loss": 1.6016, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.5752439650744735, | |
| "grad_norm": 2.692619800567627, | |
| "learning_rate": 4.518462124095928e-06, | |
| "loss": 1.6229, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5752439650744735, | |
| "eval_loss": 1.8689097166061401, | |
| "eval_runtime": 37.2177, | |
| "eval_samples_per_second": 26.869, | |
| "eval_steps_per_second": 1.128, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.576271186440678, | |
| "grad_norm": 2.636924982070923, | |
| "learning_rate": 4.516558812333461e-06, | |
| "loss": 1.5748, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.5772984078068824, | |
| "grad_norm": 2.549285888671875, | |
| "learning_rate": 4.514655500570994e-06, | |
| "loss": 1.5656, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.5783256291730868, | |
| "grad_norm": 2.5873067378997803, | |
| "learning_rate": 4.512752188808528e-06, | |
| "loss": 1.631, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.5793528505392912, | |
| "grad_norm": 2.552121162414551, | |
| "learning_rate": 4.510848877046061e-06, | |
| "loss": 1.6334, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.5803800719054957, | |
| "grad_norm": 2.697615146636963, | |
| "learning_rate": 4.5089455652835936e-06, | |
| "loss": 1.5951, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5814072932717, | |
| "grad_norm": 2.64585280418396, | |
| "learning_rate": 4.507042253521127e-06, | |
| "loss": 1.556, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.5824345146379045, | |
| "grad_norm": 2.6383707523345947, | |
| "learning_rate": 4.50513894175866e-06, | |
| "loss": 1.5184, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.5834617360041089, | |
| "grad_norm": 2.7571511268615723, | |
| "learning_rate": 4.503235629996194e-06, | |
| "loss": 1.5984, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.5844889573703133, | |
| "grad_norm": 2.6637237071990967, | |
| "learning_rate": 4.501332318233727e-06, | |
| "loss": 1.5989, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.5855161787365177, | |
| "grad_norm": 2.725754976272583, | |
| "learning_rate": 4.49942900647126e-06, | |
| "loss": 1.5594, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5855161787365177, | |
| "eval_loss": 1.8722314834594727, | |
| "eval_runtime": 37.1859, | |
| "eval_samples_per_second": 26.892, | |
| "eval_steps_per_second": 1.129, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5865434001027221, | |
| "grad_norm": 2.6657378673553467, | |
| "learning_rate": 4.497525694708794e-06, | |
| "loss": 1.5954, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 2.78940486907959, | |
| "learning_rate": 4.495622382946327e-06, | |
| "loss": 1.592, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.588597842835131, | |
| "grad_norm": 2.580956220626831, | |
| "learning_rate": 4.4937190711838605e-06, | |
| "loss": 1.5444, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.5896250642013354, | |
| "grad_norm": 2.7783710956573486, | |
| "learning_rate": 4.491815759421394e-06, | |
| "loss": 1.6257, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.5906522855675398, | |
| "grad_norm": 2.9381537437438965, | |
| "learning_rate": 4.489912447658926e-06, | |
| "loss": 1.5489, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5916795069337443, | |
| "grad_norm": 2.7915165424346924, | |
| "learning_rate": 4.48800913589646e-06, | |
| "loss": 1.5471, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.5927067282999486, | |
| "grad_norm": 2.5928280353546143, | |
| "learning_rate": 4.486105824133993e-06, | |
| "loss": 1.5864, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.593733949666153, | |
| "grad_norm": 2.844512462615967, | |
| "learning_rate": 4.4842025123715264e-06, | |
| "loss": 1.5841, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.5947611710323575, | |
| "grad_norm": 2.562718391418457, | |
| "learning_rate": 4.48229920060906e-06, | |
| "loss": 1.5476, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.5957883923985619, | |
| "grad_norm": 2.535759925842285, | |
| "learning_rate": 4.480395888846594e-06, | |
| "loss": 1.5274, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5957883923985619, | |
| "eval_loss": 1.8881579637527466, | |
| "eval_runtime": 37.2533, | |
| "eval_samples_per_second": 26.843, | |
| "eval_steps_per_second": 1.127, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5968156137647663, | |
| "grad_norm": 2.6940653324127197, | |
| "learning_rate": 4.478492577084127e-06, | |
| "loss": 1.6377, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.5978428351309707, | |
| "grad_norm": 2.4839298725128174, | |
| "learning_rate": 4.47658926532166e-06, | |
| "loss": 1.534, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.5988700564971752, | |
| "grad_norm": 2.5035688877105713, | |
| "learning_rate": 4.474685953559193e-06, | |
| "loss": 1.5764, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.5998972778633795, | |
| "grad_norm": 2.791907548904419, | |
| "learning_rate": 4.472782641796727e-06, | |
| "loss": 1.704, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.600924499229584, | |
| "grad_norm": 2.5384254455566406, | |
| "learning_rate": 4.47087933003426e-06, | |
| "loss": 1.5184, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.6019517205957884, | |
| "grad_norm": 2.4990930557250977, | |
| "learning_rate": 4.468976018271793e-06, | |
| "loss": 1.5335, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.6029789419619929, | |
| "grad_norm": 2.470872163772583, | |
| "learning_rate": 4.467072706509327e-06, | |
| "loss": 1.5464, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.6040061633281972, | |
| "grad_norm": 2.539036989212036, | |
| "learning_rate": 4.46516939474686e-06, | |
| "loss": 1.5793, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.6050333846944016, | |
| "grad_norm": 2.495309829711914, | |
| "learning_rate": 4.463266082984393e-06, | |
| "loss": 1.5312, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 2.5937912464141846, | |
| "learning_rate": 4.461362771221927e-06, | |
| "loss": 1.6508, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "eval_loss": 1.8893816471099854, | |
| "eval_runtime": 37.2539, | |
| "eval_samples_per_second": 26.843, | |
| "eval_steps_per_second": 1.127, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6070878274268104, | |
| "grad_norm": 2.53300404548645, | |
| "learning_rate": 4.45945945945946e-06, | |
| "loss": 1.5408, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.6081150487930149, | |
| "grad_norm": 2.5760276317596436, | |
| "learning_rate": 4.457556147696993e-06, | |
| "loss": 1.5575, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.6091422701592193, | |
| "grad_norm": 2.638353109359741, | |
| "learning_rate": 4.455652835934526e-06, | |
| "loss": 1.6286, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 2.916550397872925, | |
| "learning_rate": 4.453749524172059e-06, | |
| "loss": 1.6334, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.6111967128916281, | |
| "grad_norm": 2.560878038406372, | |
| "learning_rate": 4.451846212409593e-06, | |
| "loss": 1.5806, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6122239342578326, | |
| "grad_norm": 2.637882947921753, | |
| "learning_rate": 4.449942900647126e-06, | |
| "loss": 1.5791, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.613251155624037, | |
| "grad_norm": 2.752870798110962, | |
| "learning_rate": 4.4480395888846595e-06, | |
| "loss": 1.5117, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.6142783769902413, | |
| "grad_norm": 2.702087640762329, | |
| "learning_rate": 4.446136277122193e-06, | |
| "loss": 1.5783, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.6153055983564458, | |
| "grad_norm": 2.504819631576538, | |
| "learning_rate": 4.444232965359726e-06, | |
| "loss": 1.5136, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.6163328197226502, | |
| "grad_norm": 2.521670341491699, | |
| "learning_rate": 4.4423296535972596e-06, | |
| "loss": 1.5741, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6163328197226502, | |
| "eval_loss": 1.8973714113235474, | |
| "eval_runtime": 37.3167, | |
| "eval_samples_per_second": 26.798, | |
| "eval_steps_per_second": 1.126, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6173600410888547, | |
| "grad_norm": 2.927755355834961, | |
| "learning_rate": 4.440426341834793e-06, | |
| "loss": 1.5262, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.618387262455059, | |
| "grad_norm": 2.477053642272949, | |
| "learning_rate": 4.438523030072326e-06, | |
| "loss": 1.572, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.6194144838212635, | |
| "grad_norm": 2.6500253677368164, | |
| "learning_rate": 4.43661971830986e-06, | |
| "loss": 1.596, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.6204417051874679, | |
| "grad_norm": 2.5134825706481934, | |
| "learning_rate": 4.434716406547393e-06, | |
| "loss": 1.5432, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.6214689265536724, | |
| "grad_norm": 2.4142072200775146, | |
| "learning_rate": 4.432813094784926e-06, | |
| "loss": 1.5391, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6224961479198767, | |
| "grad_norm": 2.752556800842285, | |
| "learning_rate": 4.43090978302246e-06, | |
| "loss": 1.6055, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.6235233692860811, | |
| "grad_norm": 2.5731008052825928, | |
| "learning_rate": 4.429006471259993e-06, | |
| "loss": 1.5648, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.6245505906522856, | |
| "grad_norm": 2.531656503677368, | |
| "learning_rate": 4.4271031594975265e-06, | |
| "loss": 1.5492, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.6255778120184899, | |
| "grad_norm": 2.6665475368499756, | |
| "learning_rate": 4.425199847735059e-06, | |
| "loss": 1.5194, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.6266050333846944, | |
| "grad_norm": 2.437051773071289, | |
| "learning_rate": 4.423296535972592e-06, | |
| "loss": 1.5271, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6266050333846944, | |
| "eval_loss": 1.88953697681427, | |
| "eval_runtime": 36.8703, | |
| "eval_samples_per_second": 27.122, | |
| "eval_steps_per_second": 1.139, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6276322547508988, | |
| "grad_norm": 2.5932440757751465, | |
| "learning_rate": 4.421393224210126e-06, | |
| "loss": 1.5563, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.6286594761171033, | |
| "grad_norm": 2.589447021484375, | |
| "learning_rate": 4.419489912447659e-06, | |
| "loss": 1.5207, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.6296866974833076, | |
| "grad_norm": 2.570096731185913, | |
| "learning_rate": 4.4175866006851924e-06, | |
| "loss": 1.5995, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.6307139188495121, | |
| "grad_norm": 2.5356791019439697, | |
| "learning_rate": 4.415683288922726e-06, | |
| "loss": 1.5703, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.6317411402157165, | |
| "grad_norm": 2.705193281173706, | |
| "learning_rate": 4.413779977160259e-06, | |
| "loss": 1.5405, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 2.555168390274048, | |
| "learning_rate": 4.4118766653977925e-06, | |
| "loss": 1.5487, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.6337955829481253, | |
| "grad_norm": 2.804696559906006, | |
| "learning_rate": 4.409973353635326e-06, | |
| "loss": 1.6094, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.6348228043143297, | |
| "grad_norm": 2.6889376640319824, | |
| "learning_rate": 4.408070041872859e-06, | |
| "loss": 1.5656, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.6358500256805342, | |
| "grad_norm": 2.576746702194214, | |
| "learning_rate": 4.406166730110393e-06, | |
| "loss": 1.5244, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.6368772470467385, | |
| "grad_norm": 2.811156749725342, | |
| "learning_rate": 4.404263418347925e-06, | |
| "loss": 1.5153, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6368772470467385, | |
| "eval_loss": 1.8949775695800781, | |
| "eval_runtime": 36.978, | |
| "eval_samples_per_second": 27.043, | |
| "eval_steps_per_second": 1.136, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.637904468412943, | |
| "grad_norm": 2.6560428142547607, | |
| "learning_rate": 4.402360106585459e-06, | |
| "loss": 1.5347, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.6389316897791474, | |
| "grad_norm": 2.668100118637085, | |
| "learning_rate": 4.400456794822993e-06, | |
| "loss": 1.5236, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.6399589111453519, | |
| "grad_norm": 2.925978660583496, | |
| "learning_rate": 4.398553483060526e-06, | |
| "loss": 1.5494, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.6409861325115562, | |
| "grad_norm": 2.5964415073394775, | |
| "learning_rate": 4.396650171298059e-06, | |
| "loss": 1.522, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.6420133538777607, | |
| "grad_norm": 2.643888235092163, | |
| "learning_rate": 4.394746859535593e-06, | |
| "loss": 1.5332, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6430405752439651, | |
| "grad_norm": 2.805192708969116, | |
| "learning_rate": 4.392843547773125e-06, | |
| "loss": 1.5031, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.6440677966101694, | |
| "grad_norm": 2.6862149238586426, | |
| "learning_rate": 4.390940236010659e-06, | |
| "loss": 1.5335, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.6450950179763739, | |
| "grad_norm": 2.5579185485839844, | |
| "learning_rate": 4.389036924248192e-06, | |
| "loss": 1.5466, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.6461222393425783, | |
| "grad_norm": 2.4550797939300537, | |
| "learning_rate": 4.387133612485725e-06, | |
| "loss": 1.5776, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.6471494607087828, | |
| "grad_norm": 2.6051297187805176, | |
| "learning_rate": 4.385230300723259e-06, | |
| "loss": 1.5435, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6471494607087828, | |
| "eval_loss": 1.8860505819320679, | |
| "eval_runtime": 36.989, | |
| "eval_samples_per_second": 27.035, | |
| "eval_steps_per_second": 1.135, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6481766820749871, | |
| "grad_norm": 2.3723294734954834, | |
| "learning_rate": 4.383326988960792e-06, | |
| "loss": 1.5413, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.6492039034411916, | |
| "grad_norm": 2.44370174407959, | |
| "learning_rate": 4.3814236771983255e-06, | |
| "loss": 1.5152, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.650231124807396, | |
| "grad_norm": 2.474081039428711, | |
| "learning_rate": 4.379520365435859e-06, | |
| "loss": 1.579, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.6512583461736005, | |
| "grad_norm": 2.837843179702759, | |
| "learning_rate": 4.377617053673392e-06, | |
| "loss": 1.559, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.6522855675398048, | |
| "grad_norm": 2.593322515487671, | |
| "learning_rate": 4.3757137419109256e-06, | |
| "loss": 1.552, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6533127889060092, | |
| "grad_norm": 3.018051862716675, | |
| "learning_rate": 4.373810430148459e-06, | |
| "loss": 1.6231, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.6543400102722137, | |
| "grad_norm": 2.6338863372802734, | |
| "learning_rate": 4.3719071183859914e-06, | |
| "loss": 1.517, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.655367231638418, | |
| "grad_norm": 2.544140577316284, | |
| "learning_rate": 4.370003806623525e-06, | |
| "loss": 1.5763, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.6563944530046225, | |
| "grad_norm": 2.6375792026519775, | |
| "learning_rate": 4.368100494861058e-06, | |
| "loss": 1.5098, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.6574216743708269, | |
| "grad_norm": 2.5452051162719727, | |
| "learning_rate": 4.3661971830985915e-06, | |
| "loss": 1.5671, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6574216743708269, | |
| "eval_loss": 1.881069540977478, | |
| "eval_runtime": 36.9961, | |
| "eval_samples_per_second": 27.03, | |
| "eval_steps_per_second": 1.135, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6584488957370314, | |
| "grad_norm": 2.623411178588867, | |
| "learning_rate": 4.364293871336126e-06, | |
| "loss": 1.5215, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.6594761171032357, | |
| "grad_norm": 2.6149892807006836, | |
| "learning_rate": 4.362390559573659e-06, | |
| "loss": 1.5507, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.6605033384694402, | |
| "grad_norm": 2.5570266246795654, | |
| "learning_rate": 4.3604872478111925e-06, | |
| "loss": 1.5143, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.6615305598356446, | |
| "grad_norm": 2.4813005924224854, | |
| "learning_rate": 4.358583936048725e-06, | |
| "loss": 1.4518, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.662557781201849, | |
| "grad_norm": 3.0318472385406494, | |
| "learning_rate": 4.356680624286258e-06, | |
| "loss": 1.5812, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.6635850025680534, | |
| "grad_norm": 2.46936297416687, | |
| "learning_rate": 4.354777312523792e-06, | |
| "loss": 1.5396, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.6646122239342578, | |
| "grad_norm": 2.5295984745025635, | |
| "learning_rate": 4.352874000761325e-06, | |
| "loss": 1.586, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.6656394453004623, | |
| "grad_norm": 2.7826883792877197, | |
| "learning_rate": 4.3509706889988584e-06, | |
| "loss": 1.5339, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.4273526668548584, | |
| "learning_rate": 4.349067377236392e-06, | |
| "loss": 1.598, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.6676938880328711, | |
| "grad_norm": 2.644308090209961, | |
| "learning_rate": 4.347164065473925e-06, | |
| "loss": 1.5889, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6676938880328711, | |
| "eval_loss": 1.8861087560653687, | |
| "eval_runtime": 36.99, | |
| "eval_samples_per_second": 27.034, | |
| "eval_steps_per_second": 1.135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6687211093990755, | |
| "grad_norm": 2.827376127243042, | |
| "learning_rate": 4.3452607537114585e-06, | |
| "loss": 1.606, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.66974833076528, | |
| "grad_norm": 2.7463080883026123, | |
| "learning_rate": 4.343357441948992e-06, | |
| "loss": 1.5208, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.6707755521314843, | |
| "grad_norm": 2.6082730293273926, | |
| "learning_rate": 4.341454130186525e-06, | |
| "loss": 1.5597, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.6718027734976888, | |
| "grad_norm": 2.7131078243255615, | |
| "learning_rate": 4.339550818424058e-06, | |
| "loss": 1.526, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.6728299948638932, | |
| "grad_norm": 2.6635708808898926, | |
| "learning_rate": 4.337647506661591e-06, | |
| "loss": 1.5052, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.6738572162300975, | |
| "grad_norm": 2.5686581134796143, | |
| "learning_rate": 4.3357441948991245e-06, | |
| "loss": 1.5374, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.674884437596302, | |
| "grad_norm": 3.0532894134521484, | |
| "learning_rate": 4.333840883136658e-06, | |
| "loss": 1.5787, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.6759116589625064, | |
| "grad_norm": 2.6494507789611816, | |
| "learning_rate": 4.331937571374191e-06, | |
| "loss": 1.5121, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.6769388803287109, | |
| "grad_norm": 2.748142719268799, | |
| "learning_rate": 4.3300342596117246e-06, | |
| "loss": 1.5294, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 2.837799310684204, | |
| "learning_rate": 4.328130947849258e-06, | |
| "loss": 1.5424, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "eval_loss": 1.8644919395446777, | |
| "eval_runtime": 37.0096, | |
| "eval_samples_per_second": 27.02, | |
| "eval_steps_per_second": 1.135, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6789933230611197, | |
| "grad_norm": 2.7405757904052734, | |
| "learning_rate": 4.326227636086791e-06, | |
| "loss": 1.4949, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.6800205444273241, | |
| "grad_norm": 2.545466661453247, | |
| "learning_rate": 4.324324324324325e-06, | |
| "loss": 1.5445, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.6810477657935285, | |
| "grad_norm": 2.5715537071228027, | |
| "learning_rate": 4.322421012561858e-06, | |
| "loss": 1.5468, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.6820749871597329, | |
| "grad_norm": 2.7073662281036377, | |
| "learning_rate": 4.320517700799391e-06, | |
| "loss": 1.5293, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.6831022085259374, | |
| "grad_norm": 2.62264347076416, | |
| "learning_rate": 4.318614389036925e-06, | |
| "loss": 1.6258, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.6841294298921418, | |
| "grad_norm": 2.4506373405456543, | |
| "learning_rate": 4.316711077274458e-06, | |
| "loss": 1.5845, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.6851566512583461, | |
| "grad_norm": 2.849473237991333, | |
| "learning_rate": 4.3148077655119915e-06, | |
| "loss": 1.4959, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.6861838726245506, | |
| "grad_norm": 2.5865421295166016, | |
| "learning_rate": 4.312904453749525e-06, | |
| "loss": 1.599, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.687211093990755, | |
| "grad_norm": 2.4636387825012207, | |
| "learning_rate": 4.311001141987058e-06, | |
| "loss": 1.5495, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.6882383153569595, | |
| "grad_norm": 2.638047218322754, | |
| "learning_rate": 4.3090978302245916e-06, | |
| "loss": 1.5507, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6882383153569595, | |
| "eval_loss": 1.8834826946258545, | |
| "eval_runtime": 37.0335, | |
| "eval_samples_per_second": 27.003, | |
| "eval_steps_per_second": 1.134, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6892655367231638, | |
| "grad_norm": 2.669201612472534, | |
| "learning_rate": 4.307194518462124e-06, | |
| "loss": 1.5494, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.6902927580893683, | |
| "grad_norm": 2.634634494781494, | |
| "learning_rate": 4.3052912066996574e-06, | |
| "loss": 1.6177, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.6913199794555727, | |
| "grad_norm": 2.5489139556884766, | |
| "learning_rate": 4.303387894937191e-06, | |
| "loss": 1.5876, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.6923472008217771, | |
| "grad_norm": 2.580073833465576, | |
| "learning_rate": 4.301484583174724e-06, | |
| "loss": 1.5106, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.6933744221879815, | |
| "grad_norm": 2.5126636028289795, | |
| "learning_rate": 4.2995812714122575e-06, | |
| "loss": 1.4988, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6944016435541859, | |
| "grad_norm": 2.4630191326141357, | |
| "learning_rate": 4.297677959649791e-06, | |
| "loss": 1.5218, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.6954288649203904, | |
| "grad_norm": 2.8822433948516846, | |
| "learning_rate": 4.295774647887324e-06, | |
| "loss": 1.5592, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.6964560862865947, | |
| "grad_norm": 2.5498058795928955, | |
| "learning_rate": 4.293871336124858e-06, | |
| "loss": 1.5713, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.6974833076527992, | |
| "grad_norm": 2.6661157608032227, | |
| "learning_rate": 4.291968024362391e-06, | |
| "loss": 1.5431, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.6985105290190036, | |
| "grad_norm": 2.617971897125244, | |
| "learning_rate": 4.290064712599924e-06, | |
| "loss": 1.5792, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6985105290190036, | |
| "eval_loss": 1.8702285289764404, | |
| "eval_runtime": 37.0376, | |
| "eval_samples_per_second": 27.0, | |
| "eval_steps_per_second": 1.134, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.699537750385208, | |
| "grad_norm": 2.5892348289489746, | |
| "learning_rate": 4.288161400837458e-06, | |
| "loss": 1.5626, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.7005649717514124, | |
| "grad_norm": 2.5460269451141357, | |
| "learning_rate": 4.286258089074991e-06, | |
| "loss": 1.4876, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.7015921931176169, | |
| "grad_norm": 2.601632595062256, | |
| "learning_rate": 4.284354777312524e-06, | |
| "loss": 1.5547, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.7026194144838213, | |
| "grad_norm": 2.6032373905181885, | |
| "learning_rate": 4.282451465550058e-06, | |
| "loss": 1.5133, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.7036466358500256, | |
| "grad_norm": 2.6283886432647705, | |
| "learning_rate": 4.280548153787591e-06, | |
| "loss": 1.5375, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7046738572162301, | |
| "grad_norm": 2.5892159938812256, | |
| "learning_rate": 4.2786448420251245e-06, | |
| "loss": 1.5338, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.7057010785824345, | |
| "grad_norm": 2.518629789352417, | |
| "learning_rate": 4.276741530262658e-06, | |
| "loss": 1.5003, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.706728299948639, | |
| "grad_norm": 2.8705344200134277, | |
| "learning_rate": 4.27483821850019e-06, | |
| "loss": 1.5178, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.7077555213148433, | |
| "grad_norm": 2.7153639793395996, | |
| "learning_rate": 4.272934906737724e-06, | |
| "loss": 1.5914, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.7087827426810478, | |
| "grad_norm": 2.4585697650909424, | |
| "learning_rate": 4.271031594975257e-06, | |
| "loss": 1.5726, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7087827426810478, | |
| "eval_loss": 1.8637797832489014, | |
| "eval_runtime": 37.0465, | |
| "eval_samples_per_second": 26.993, | |
| "eval_steps_per_second": 1.134, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7098099640472522, | |
| "grad_norm": 2.6370503902435303, | |
| "learning_rate": 4.2691282832127905e-06, | |
| "loss": 1.5706, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.7108371854134566, | |
| "grad_norm": 2.70202898979187, | |
| "learning_rate": 4.267224971450324e-06, | |
| "loss": 1.5298, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.711864406779661, | |
| "grad_norm": 2.6149585247039795, | |
| "learning_rate": 4.265321659687857e-06, | |
| "loss": 1.477, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.7128916281458655, | |
| "grad_norm": 2.9561493396759033, | |
| "learning_rate": 4.2634183479253906e-06, | |
| "loss": 1.5189, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.7139188495120699, | |
| "grad_norm": 2.697680711746216, | |
| "learning_rate": 4.261515036162924e-06, | |
| "loss": 1.5001, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.7149460708782742, | |
| "grad_norm": 2.55727219581604, | |
| "learning_rate": 4.259611724400457e-06, | |
| "loss": 1.533, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.7159732922444787, | |
| "grad_norm": 2.854290723800659, | |
| "learning_rate": 4.257708412637991e-06, | |
| "loss": 1.5057, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.7170005136106831, | |
| "grad_norm": 2.73824405670166, | |
| "learning_rate": 4.255805100875523e-06, | |
| "loss": 1.4567, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.7180277349768875, | |
| "grad_norm": 2.730050802230835, | |
| "learning_rate": 4.2539017891130565e-06, | |
| "loss": 1.4873, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.7190549563430919, | |
| "grad_norm": 2.966660737991333, | |
| "learning_rate": 4.25199847735059e-06, | |
| "loss": 1.574, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7190549563430919, | |
| "eval_loss": 1.8623589277267456, | |
| "eval_runtime": 37.0761, | |
| "eval_samples_per_second": 26.972, | |
| "eval_steps_per_second": 1.133, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7200821777092964, | |
| "grad_norm": 2.7526276111602783, | |
| "learning_rate": 4.250095165588123e-06, | |
| "loss": 1.4831, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.7211093990755008, | |
| "grad_norm": 2.9722564220428467, | |
| "learning_rate": 4.2481918538256575e-06, | |
| "loss": 1.548, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.7221366204417052, | |
| "grad_norm": 2.679373025894165, | |
| "learning_rate": 4.246288542063191e-06, | |
| "loss": 1.5145, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 2.733139753341675, | |
| "learning_rate": 4.244385230300724e-06, | |
| "loss": 1.5542, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.724191063174114, | |
| "grad_norm": 2.6549174785614014, | |
| "learning_rate": 4.242481918538257e-06, | |
| "loss": 1.4958, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.7252182845403184, | |
| "grad_norm": 2.562958002090454, | |
| "learning_rate": 4.24057860677579e-06, | |
| "loss": 1.524, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.7262455059065228, | |
| "grad_norm": 2.641123056411743, | |
| "learning_rate": 4.2386752950133234e-06, | |
| "loss": 1.5723, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 2.8128373622894287, | |
| "learning_rate": 4.236771983250857e-06, | |
| "loss": 1.5151, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.7282999486389317, | |
| "grad_norm": 2.676765203475952, | |
| "learning_rate": 4.23486867148839e-06, | |
| "loss": 1.5024, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.7293271700051361, | |
| "grad_norm": 2.917178153991699, | |
| "learning_rate": 4.2329653597259235e-06, | |
| "loss": 1.5326, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7293271700051361, | |
| "eval_loss": 1.8676133155822754, | |
| "eval_runtime": 36.8304, | |
| "eval_samples_per_second": 27.152, | |
| "eval_steps_per_second": 1.14, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7303543913713405, | |
| "grad_norm": 2.8313796520233154, | |
| "learning_rate": 4.231062047963457e-06, | |
| "loss": 1.5623, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.731381612737545, | |
| "grad_norm": 2.61542010307312, | |
| "learning_rate": 4.22915873620099e-06, | |
| "loss": 1.5725, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.7324088341037494, | |
| "grad_norm": 2.5788609981536865, | |
| "learning_rate": 4.227255424438524e-06, | |
| "loss": 1.5381, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.7334360554699538, | |
| "grad_norm": 2.720306158065796, | |
| "learning_rate": 4.225352112676057e-06, | |
| "loss": 1.572, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.7344632768361582, | |
| "grad_norm": 2.780654191970825, | |
| "learning_rate": 4.2234488009135895e-06, | |
| "loss": 1.5084, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.7354904982023626, | |
| "grad_norm": 2.4448273181915283, | |
| "learning_rate": 4.221545489151123e-06, | |
| "loss": 1.4614, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.736517719568567, | |
| "grad_norm": 2.6579184532165527, | |
| "learning_rate": 4.219642177388656e-06, | |
| "loss": 1.5022, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.7375449409347714, | |
| "grad_norm": 2.7092721462249756, | |
| "learning_rate": 4.2177388656261896e-06, | |
| "loss": 1.5307, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.7385721623009759, | |
| "grad_norm": 2.65014910697937, | |
| "learning_rate": 4.215835553863723e-06, | |
| "loss": 1.4936, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.7395993836671803, | |
| "grad_norm": 2.7403628826141357, | |
| "learning_rate": 4.213932242101256e-06, | |
| "loss": 1.4458, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7395993836671803, | |
| "eval_loss": 1.8778676986694336, | |
| "eval_runtime": 36.9378, | |
| "eval_samples_per_second": 27.073, | |
| "eval_steps_per_second": 1.137, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7406266050333847, | |
| "grad_norm": 2.3937759399414062, | |
| "learning_rate": 4.21202893033879e-06, | |
| "loss": 1.5086, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.7416538263995891, | |
| "grad_norm": 2.5786867141723633, | |
| "learning_rate": 4.210125618576323e-06, | |
| "loss": 1.5321, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.7426810477657936, | |
| "grad_norm": 2.607236862182617, | |
| "learning_rate": 4.208222306813856e-06, | |
| "loss": 1.5244, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.743708269131998, | |
| "grad_norm": 2.5461602210998535, | |
| "learning_rate": 4.20631899505139e-06, | |
| "loss": 1.5841, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.7447354904982023, | |
| "grad_norm": 2.5051612854003906, | |
| "learning_rate": 4.204415683288923e-06, | |
| "loss": 1.43, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": 2.692816734313965, | |
| "learning_rate": 4.2025123715264565e-06, | |
| "loss": 1.5439, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.7467899332306112, | |
| "grad_norm": 2.4827022552490234, | |
| "learning_rate": 4.20060905976399e-06, | |
| "loss": 1.4987, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.7478171545968156, | |
| "grad_norm": 2.7261135578155518, | |
| "learning_rate": 4.198705748001523e-06, | |
| "loss": 1.4573, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.74884437596302, | |
| "grad_norm": 2.5710837841033936, | |
| "learning_rate": 4.1968024362390566e-06, | |
| "loss": 1.564, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.7498715973292245, | |
| "grad_norm": 2.61181640625, | |
| "learning_rate": 4.19489912447659e-06, | |
| "loss": 1.5211, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7498715973292245, | |
| "eval_loss": 1.8794434070587158, | |
| "eval_runtime": 36.9676, | |
| "eval_samples_per_second": 27.051, | |
| "eval_steps_per_second": 1.136, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7508988186954288, | |
| "grad_norm": 2.6946470737457275, | |
| "learning_rate": 4.192995812714123e-06, | |
| "loss": 1.5837, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.7519260400616333, | |
| "grad_norm": 2.5337390899658203, | |
| "learning_rate": 4.191092500951656e-06, | |
| "loss": 1.5251, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.7529532614278377, | |
| "grad_norm": 2.541532278060913, | |
| "learning_rate": 4.189189189189189e-06, | |
| "loss": 1.503, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.7539804827940421, | |
| "grad_norm": 2.639124631881714, | |
| "learning_rate": 4.1872858774267225e-06, | |
| "loss": 1.4963, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.7550077041602465, | |
| "grad_norm": 2.872861862182617, | |
| "learning_rate": 4.185382565664256e-06, | |
| "loss": 1.5632, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.7560349255264509, | |
| "grad_norm": 2.588980197906494, | |
| "learning_rate": 4.183479253901789e-06, | |
| "loss": 1.4998, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.7570621468926554, | |
| "grad_norm": 2.9199588298797607, | |
| "learning_rate": 4.181575942139323e-06, | |
| "loss": 1.466, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.7580893682588598, | |
| "grad_norm": 2.5677788257598877, | |
| "learning_rate": 4.179672630376856e-06, | |
| "loss": 1.5247, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.7591165896250642, | |
| "grad_norm": 2.481142520904541, | |
| "learning_rate": 4.177769318614389e-06, | |
| "loss": 1.4915, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.7601438109912686, | |
| "grad_norm": 2.7072012424468994, | |
| "learning_rate": 4.175866006851923e-06, | |
| "loss": 1.5783, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7601438109912686, | |
| "eval_loss": 1.8817057609558105, | |
| "eval_runtime": 36.9635, | |
| "eval_samples_per_second": 27.054, | |
| "eval_steps_per_second": 1.136, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7611710323574731, | |
| "grad_norm": 2.5433032512664795, | |
| "learning_rate": 4.173962695089456e-06, | |
| "loss": 1.5457, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.7621982537236774, | |
| "grad_norm": 2.702077627182007, | |
| "learning_rate": 4.1720593833269894e-06, | |
| "loss": 1.5285, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.7632254750898819, | |
| "grad_norm": 2.6678309440612793, | |
| "learning_rate": 4.170156071564523e-06, | |
| "loss": 1.5381, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.7642526964560863, | |
| "grad_norm": 2.6097185611724854, | |
| "learning_rate": 4.168252759802056e-06, | |
| "loss": 1.6076, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.7652799178222907, | |
| "grad_norm": 2.5975704193115234, | |
| "learning_rate": 4.1663494480395895e-06, | |
| "loss": 1.515, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.7663071391884951, | |
| "grad_norm": 2.6858558654785156, | |
| "learning_rate": 4.164446136277123e-06, | |
| "loss": 1.5499, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.7673343605546995, | |
| "grad_norm": 2.565023899078369, | |
| "learning_rate": 4.162542824514656e-06, | |
| "loss": 1.5502, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.768361581920904, | |
| "grad_norm": 2.61715030670166, | |
| "learning_rate": 4.16063951275219e-06, | |
| "loss": 1.5271, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.7693888032871083, | |
| "grad_norm": 2.564382314682007, | |
| "learning_rate": 4.158736200989722e-06, | |
| "loss": 1.4756, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.7704160246533128, | |
| "grad_norm": 2.64457368850708, | |
| "learning_rate": 4.1568328892272555e-06, | |
| "loss": 1.5246, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7704160246533128, | |
| "eval_loss": 1.8777766227722168, | |
| "eval_runtime": 36.9737, | |
| "eval_samples_per_second": 27.046, | |
| "eval_steps_per_second": 1.136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7714432460195172, | |
| "grad_norm": 2.773602247238159, | |
| "learning_rate": 4.154929577464789e-06, | |
| "loss": 1.5337, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.7724704673857217, | |
| "grad_norm": 2.5466997623443604, | |
| "learning_rate": 4.153026265702322e-06, | |
| "loss": 1.5269, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.773497688751926, | |
| "grad_norm": 2.702888250350952, | |
| "learning_rate": 4.1511229539398556e-06, | |
| "loss": 1.4636, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.7745249101181304, | |
| "grad_norm": 2.629251718521118, | |
| "learning_rate": 4.149219642177389e-06, | |
| "loss": 1.513, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.7755521314843349, | |
| "grad_norm": 2.52544903755188, | |
| "learning_rate": 4.147316330414922e-06, | |
| "loss": 1.5225, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.7765793528505393, | |
| "grad_norm": 2.4267778396606445, | |
| "learning_rate": 4.145413018652456e-06, | |
| "loss": 1.4377, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.7776065742167437, | |
| "grad_norm": 2.6061577796936035, | |
| "learning_rate": 4.143509706889989e-06, | |
| "loss": 1.5402, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.7786337955829481, | |
| "grad_norm": 2.6571085453033447, | |
| "learning_rate": 4.141606395127522e-06, | |
| "loss": 1.527, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.7796610169491526, | |
| "grad_norm": 2.48740291595459, | |
| "learning_rate": 4.139703083365056e-06, | |
| "loss": 1.517, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.7806882383153569, | |
| "grad_norm": 2.5044426918029785, | |
| "learning_rate": 4.137799771602588e-06, | |
| "loss": 1.5579, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7806882383153569, | |
| "eval_loss": 1.8778951168060303, | |
| "eval_runtime": 37.0045, | |
| "eval_samples_per_second": 27.024, | |
| "eval_steps_per_second": 1.135, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7817154596815614, | |
| "grad_norm": 2.4728074073791504, | |
| "learning_rate": 4.135896459840122e-06, | |
| "loss": 1.5321, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.7827426810477658, | |
| "grad_norm": 2.6541659832000732, | |
| "learning_rate": 4.133993148077656e-06, | |
| "loss": 1.4866, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.7837699024139703, | |
| "grad_norm": 2.526716947555542, | |
| "learning_rate": 4.132089836315189e-06, | |
| "loss": 1.5035, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.7847971237801746, | |
| "grad_norm": 2.683306932449341, | |
| "learning_rate": 4.1301865245527226e-06, | |
| "loss": 1.5221, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.785824345146379, | |
| "grad_norm": 2.4980056285858154, | |
| "learning_rate": 4.128283212790256e-06, | |
| "loss": 1.4643, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.7868515665125835, | |
| "grad_norm": 2.3985488414764404, | |
| "learning_rate": 4.1263799010277884e-06, | |
| "loss": 1.4348, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 2.600689649581909, | |
| "learning_rate": 4.124476589265322e-06, | |
| "loss": 1.5647, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.7889060092449923, | |
| "grad_norm": 2.5934395790100098, | |
| "learning_rate": 4.122573277502855e-06, | |
| "loss": 1.4887, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.7899332306111967, | |
| "grad_norm": 2.5209388732910156, | |
| "learning_rate": 4.1206699657403885e-06, | |
| "loss": 1.4893, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.7909604519774012, | |
| "grad_norm": 2.6656298637390137, | |
| "learning_rate": 4.118766653977922e-06, | |
| "loss": 1.5239, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.7909604519774012, | |
| "eval_loss": 1.8737632036209106, | |
| "eval_runtime": 37.056, | |
| "eval_samples_per_second": 26.986, | |
| "eval_steps_per_second": 1.133, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.7919876733436055, | |
| "grad_norm": 2.5147693157196045, | |
| "learning_rate": 4.116863342215455e-06, | |
| "loss": 1.5, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.79301489470981, | |
| "grad_norm": 2.4653773307800293, | |
| "learning_rate": 4.114960030452989e-06, | |
| "loss": 1.4802, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.7940421160760144, | |
| "grad_norm": 2.643160820007324, | |
| "learning_rate": 4.113056718690522e-06, | |
| "loss": 1.5086, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.7950693374422187, | |
| "grad_norm": 2.4873125553131104, | |
| "learning_rate": 4.111153406928055e-06, | |
| "loss": 1.4558, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.7960965588084232, | |
| "grad_norm": 2.541308879852295, | |
| "learning_rate": 4.109250095165589e-06, | |
| "loss": 1.5483, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7971237801746276, | |
| "grad_norm": 2.701874256134033, | |
| "learning_rate": 4.107346783403122e-06, | |
| "loss": 1.5551, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.7981510015408321, | |
| "grad_norm": 2.457371234893799, | |
| "learning_rate": 4.105443471640655e-06, | |
| "loss": 1.4968, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.7991782229070364, | |
| "grad_norm": 2.5294973850250244, | |
| "learning_rate": 4.103540159878188e-06, | |
| "loss": 1.4756, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.8002054442732409, | |
| "grad_norm": 2.464932918548584, | |
| "learning_rate": 4.101636848115721e-06, | |
| "loss": 1.5215, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.8012326656394453, | |
| "grad_norm": 2.5919454097747803, | |
| "learning_rate": 4.099733536353255e-06, | |
| "loss": 1.4807, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8012326656394453, | |
| "eval_loss": 1.875250220298767, | |
| "eval_runtime": 37.035, | |
| "eval_samples_per_second": 27.001, | |
| "eval_steps_per_second": 1.134, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8022598870056498, | |
| "grad_norm": 2.505749464035034, | |
| "learning_rate": 4.097830224590788e-06, | |
| "loss": 1.5224, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.8032871083718541, | |
| "grad_norm": 2.747262954711914, | |
| "learning_rate": 4.095926912828322e-06, | |
| "loss": 1.6051, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.8043143297380585, | |
| "grad_norm": 2.6147146224975586, | |
| "learning_rate": 4.094023601065855e-06, | |
| "loss": 1.565, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.805341551104263, | |
| "grad_norm": 2.5381031036376953, | |
| "learning_rate": 4.092120289303388e-06, | |
| "loss": 1.511, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.8063687724704673, | |
| "grad_norm": 2.6476190090179443, | |
| "learning_rate": 4.0902169775409215e-06, | |
| "loss": 1.5147, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.8073959938366718, | |
| "grad_norm": 2.486919641494751, | |
| "learning_rate": 4.088313665778455e-06, | |
| "loss": 1.4697, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.8084232152028762, | |
| "grad_norm": 2.7006654739379883, | |
| "learning_rate": 4.086410354015988e-06, | |
| "loss": 1.4965, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.8094504365690807, | |
| "grad_norm": 2.7587921619415283, | |
| "learning_rate": 4.0845070422535216e-06, | |
| "loss": 1.4781, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.810477657935285, | |
| "grad_norm": 2.64239501953125, | |
| "learning_rate": 4.082603730491055e-06, | |
| "loss": 1.4945, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.8115048793014895, | |
| "grad_norm": 2.659919261932373, | |
| "learning_rate": 4.080700418728588e-06, | |
| "loss": 1.5378, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8115048793014895, | |
| "eval_loss": 1.881503939628601, | |
| "eval_runtime": 37.2277, | |
| "eval_samples_per_second": 26.862, | |
| "eval_steps_per_second": 1.128, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8125321006676939, | |
| "grad_norm": 2.820996046066284, | |
| "learning_rate": 4.078797106966122e-06, | |
| "loss": 1.5134, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 2.4667489528656006, | |
| "learning_rate": 4.076893795203655e-06, | |
| "loss": 1.4165, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.8145865434001027, | |
| "grad_norm": 2.5528056621551514, | |
| "learning_rate": 4.074990483441188e-06, | |
| "loss": 1.481, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.8156137647663071, | |
| "grad_norm": 2.632922887802124, | |
| "learning_rate": 4.073087171678721e-06, | |
| "loss": 1.5502, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.8166409861325116, | |
| "grad_norm": 2.662536144256592, | |
| "learning_rate": 4.071183859916254e-06, | |
| "loss": 1.5302, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.8176682074987159, | |
| "grad_norm": 2.662454605102539, | |
| "learning_rate": 4.069280548153788e-06, | |
| "loss": 1.5131, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.8186954288649204, | |
| "grad_norm": 2.6387386322021484, | |
| "learning_rate": 4.067377236391321e-06, | |
| "loss": 1.4677, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.8197226502311248, | |
| "grad_norm": 2.8879177570343018, | |
| "learning_rate": 4.065473924628854e-06, | |
| "loss": 1.5106, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.8207498715973293, | |
| "grad_norm": 2.680610418319702, | |
| "learning_rate": 4.063570612866388e-06, | |
| "loss": 1.5389, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.8217770929635336, | |
| "grad_norm": 2.659590244293213, | |
| "learning_rate": 4.061667301103921e-06, | |
| "loss": 1.5254, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8217770929635336, | |
| "eval_loss": 1.881851077079773, | |
| "eval_runtime": 37.3385, | |
| "eval_samples_per_second": 26.782, | |
| "eval_steps_per_second": 1.125, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8228043143297381, | |
| "grad_norm": 2.711195945739746, | |
| "learning_rate": 4.0597639893414544e-06, | |
| "loss": 1.5026, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.8238315356959425, | |
| "grad_norm": 2.6387939453125, | |
| "learning_rate": 4.057860677578988e-06, | |
| "loss": 1.5101, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.8248587570621468, | |
| "grad_norm": 2.507387638092041, | |
| "learning_rate": 4.055957365816521e-06, | |
| "loss": 1.5277, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.8258859784283513, | |
| "grad_norm": 2.610370397567749, | |
| "learning_rate": 4.0540540540540545e-06, | |
| "loss": 1.4695, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.8269131997945557, | |
| "grad_norm": 2.8345787525177, | |
| "learning_rate": 4.052150742291588e-06, | |
| "loss": 1.467, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.8279404211607602, | |
| "grad_norm": 2.5142805576324463, | |
| "learning_rate": 4.050247430529121e-06, | |
| "loss": 1.4637, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.8289676425269645, | |
| "grad_norm": 2.7722535133361816, | |
| "learning_rate": 4.048344118766655e-06, | |
| "loss": 1.5427, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.829994863893169, | |
| "grad_norm": 2.816789150238037, | |
| "learning_rate": 4.046440807004188e-06, | |
| "loss": 1.5422, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.8310220852593734, | |
| "grad_norm": 2.6485376358032227, | |
| "learning_rate": 4.044537495241721e-06, | |
| "loss": 1.5078, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.8320493066255779, | |
| "grad_norm": 2.4760921001434326, | |
| "learning_rate": 4.042634183479255e-06, | |
| "loss": 1.4827, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8320493066255779, | |
| "eval_loss": 1.8709155321121216, | |
| "eval_runtime": 36.9015, | |
| "eval_samples_per_second": 27.099, | |
| "eval_steps_per_second": 1.138, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8330765279917822, | |
| "grad_norm": 2.658062219619751, | |
| "learning_rate": 4.040730871716787e-06, | |
| "loss": 1.5434, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.8341037493579867, | |
| "grad_norm": 2.5443618297576904, | |
| "learning_rate": 4.038827559954321e-06, | |
| "loss": 1.5165, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.8351309707241911, | |
| "grad_norm": 2.698432207107544, | |
| "learning_rate": 4.036924248191854e-06, | |
| "loss": 1.5553, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.8361581920903954, | |
| "grad_norm": 2.5598180294036865, | |
| "learning_rate": 4.035020936429387e-06, | |
| "loss": 1.5289, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.8371854134565999, | |
| "grad_norm": 2.7002663612365723, | |
| "learning_rate": 4.033117624666921e-06, | |
| "loss": 1.509, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.8382126348228043, | |
| "grad_norm": 2.7882776260375977, | |
| "learning_rate": 4.031214312904454e-06, | |
| "loss": 1.4787, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.8392398561890088, | |
| "grad_norm": 2.5583086013793945, | |
| "learning_rate": 4.029311001141987e-06, | |
| "loss": 1.4642, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.8402670775552131, | |
| "grad_norm": 2.584573268890381, | |
| "learning_rate": 4.027407689379521e-06, | |
| "loss": 1.4343, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.8412942989214176, | |
| "grad_norm": 2.5062575340270996, | |
| "learning_rate": 4.025504377617054e-06, | |
| "loss": 1.4975, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.842321520287622, | |
| "grad_norm": 2.3546457290649414, | |
| "learning_rate": 4.0236010658545875e-06, | |
| "loss": 1.4795, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.842321520287622, | |
| "eval_loss": 1.8716342449188232, | |
| "eval_runtime": 37.0473, | |
| "eval_samples_per_second": 26.993, | |
| "eval_steps_per_second": 1.134, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8433487416538265, | |
| "grad_norm": 2.513228178024292, | |
| "learning_rate": 4.02169775409212e-06, | |
| "loss": 1.5191, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.8443759630200308, | |
| "grad_norm": 2.6360220909118652, | |
| "learning_rate": 4.019794442329653e-06, | |
| "loss": 1.5739, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.8454031843862352, | |
| "grad_norm": 2.5351850986480713, | |
| "learning_rate": 4.0178911305671876e-06, | |
| "loss": 1.4487, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.8464304057524397, | |
| "grad_norm": 2.6693851947784424, | |
| "learning_rate": 4.015987818804721e-06, | |
| "loss": 1.5319, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 2.5210046768188477, | |
| "learning_rate": 4.014084507042254e-06, | |
| "loss": 1.4723, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 2.5799994468688965, | |
| "learning_rate": 4.012181195279788e-06, | |
| "loss": 1.4409, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.8495120698510529, | |
| "grad_norm": 2.5206313133239746, | |
| "learning_rate": 4.010277883517321e-06, | |
| "loss": 1.5449, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.8505392912172574, | |
| "grad_norm": 2.480584144592285, | |
| "learning_rate": 4.0083745717548535e-06, | |
| "loss": 1.5306, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.8515665125834617, | |
| "grad_norm": 2.5229053497314453, | |
| "learning_rate": 4.006471259992387e-06, | |
| "loss": 1.5001, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.8525937339496662, | |
| "grad_norm": 2.53357195854187, | |
| "learning_rate": 4.00456794822992e-06, | |
| "loss": 1.5188, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8525937339496662, | |
| "eval_loss": 1.8724256753921509, | |
| "eval_runtime": 37.1114, | |
| "eval_samples_per_second": 26.946, | |
| "eval_steps_per_second": 1.132, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8536209553158706, | |
| "grad_norm": 2.6796159744262695, | |
| "learning_rate": 4.002664636467454e-06, | |
| "loss": 1.5577, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.8546481766820749, | |
| "grad_norm": 2.4717817306518555, | |
| "learning_rate": 4.000761324704987e-06, | |
| "loss": 1.5124, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.8556753980482794, | |
| "grad_norm": 2.649057626724243, | |
| "learning_rate": 3.99885801294252e-06, | |
| "loss": 1.4516, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.8567026194144838, | |
| "grad_norm": 2.592406749725342, | |
| "learning_rate": 3.996954701180054e-06, | |
| "loss": 1.5215, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.8577298407806883, | |
| "grad_norm": 2.46956205368042, | |
| "learning_rate": 3.995051389417587e-06, | |
| "loss": 1.4324, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.8587570621468926, | |
| "grad_norm": 2.8484537601470947, | |
| "learning_rate": 3.9931480776551204e-06, | |
| "loss": 1.4574, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.8597842835130971, | |
| "grad_norm": 2.6475489139556885, | |
| "learning_rate": 3.991244765892654e-06, | |
| "loss": 1.5581, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.8608115048793015, | |
| "grad_norm": 2.527153491973877, | |
| "learning_rate": 3.989341454130186e-06, | |
| "loss": 1.4713, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.861838726245506, | |
| "grad_norm": 2.6767020225524902, | |
| "learning_rate": 3.98743814236772e-06, | |
| "loss": 1.4459, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.8628659476117103, | |
| "grad_norm": 2.6406850814819336, | |
| "learning_rate": 3.985534830605253e-06, | |
| "loss": 1.4964, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8628659476117103, | |
| "eval_loss": 1.886762261390686, | |
| "eval_runtime": 37.1378, | |
| "eval_samples_per_second": 26.927, | |
| "eval_steps_per_second": 1.131, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8638931689779148, | |
| "grad_norm": 2.466372489929199, | |
| "learning_rate": 3.983631518842786e-06, | |
| "loss": 1.5136, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.8649203903441192, | |
| "grad_norm": 2.830249071121216, | |
| "learning_rate": 3.98172820708032e-06, | |
| "loss": 1.5372, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.8659476117103235, | |
| "grad_norm": 2.675889015197754, | |
| "learning_rate": 3.979824895317854e-06, | |
| "loss": 1.4881, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.866974833076528, | |
| "grad_norm": 2.7418212890625, | |
| "learning_rate": 3.977921583555387e-06, | |
| "loss": 1.4541, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.8680020544427324, | |
| "grad_norm": 2.572862386703491, | |
| "learning_rate": 3.97601827179292e-06, | |
| "loss": 1.5191, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.8690292758089369, | |
| "grad_norm": 2.6524274349212646, | |
| "learning_rate": 3.974114960030453e-06, | |
| "loss": 1.4647, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.8700564971751412, | |
| "grad_norm": 2.794415235519409, | |
| "learning_rate": 3.9722116482679866e-06, | |
| "loss": 1.504, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.8710837185413457, | |
| "grad_norm": 2.5947723388671875, | |
| "learning_rate": 3.97030833650552e-06, | |
| "loss": 1.492, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.8721109399075501, | |
| "grad_norm": 2.8539984226226807, | |
| "learning_rate": 3.968405024743053e-06, | |
| "loss": 1.5049, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.8731381612737545, | |
| "grad_norm": 2.522786855697632, | |
| "learning_rate": 3.966501712980587e-06, | |
| "loss": 1.4223, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8731381612737545, | |
| "eval_loss": 1.8691684007644653, | |
| "eval_runtime": 37.1287, | |
| "eval_samples_per_second": 26.933, | |
| "eval_steps_per_second": 1.131, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8741653826399589, | |
| "grad_norm": 2.6483359336853027, | |
| "learning_rate": 3.96459840121812e-06, | |
| "loss": 1.4815, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.8751926040061633, | |
| "grad_norm": 2.581429958343506, | |
| "learning_rate": 3.962695089455653e-06, | |
| "loss": 1.4837, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.8762198253723678, | |
| "grad_norm": 2.5967583656311035, | |
| "learning_rate": 3.960791777693187e-06, | |
| "loss": 1.5289, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.8772470467385721, | |
| "grad_norm": 2.7169225215911865, | |
| "learning_rate": 3.95888846593072e-06, | |
| "loss": 1.5173, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.8782742681047766, | |
| "grad_norm": 2.644656181335449, | |
| "learning_rate": 3.956985154168253e-06, | |
| "loss": 1.5095, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.879301489470981, | |
| "grad_norm": 2.6397511959075928, | |
| "learning_rate": 3.955081842405786e-06, | |
| "loss": 1.5422, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.8803287108371854, | |
| "grad_norm": 2.691540479660034, | |
| "learning_rate": 3.953178530643319e-06, | |
| "loss": 1.5703, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": 2.50526762008667, | |
| "learning_rate": 3.951275218880853e-06, | |
| "loss": 1.5885, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.8823831535695943, | |
| "grad_norm": 2.3846609592437744, | |
| "learning_rate": 3.949371907118386e-06, | |
| "loss": 1.4248, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.8834103749357987, | |
| "grad_norm": 2.7107760906219482, | |
| "learning_rate": 3.9474685953559194e-06, | |
| "loss": 1.5358, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8834103749357987, | |
| "eval_loss": 1.876391887664795, | |
| "eval_runtime": 37.1284, | |
| "eval_samples_per_second": 26.934, | |
| "eval_steps_per_second": 1.131, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.884437596302003, | |
| "grad_norm": 2.6206252574920654, | |
| "learning_rate": 3.945565283593453e-06, | |
| "loss": 1.4907, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.8854648176682075, | |
| "grad_norm": 2.6641664505004883, | |
| "learning_rate": 3.943661971830986e-06, | |
| "loss": 1.4888, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.8864920390344119, | |
| "grad_norm": 2.7342002391815186, | |
| "learning_rate": 3.9417586600685195e-06, | |
| "loss": 1.5421, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.8875192604006163, | |
| "grad_norm": 2.7120890617370605, | |
| "learning_rate": 3.939855348306053e-06, | |
| "loss": 1.5154, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.8885464817668207, | |
| "grad_norm": 2.6350717544555664, | |
| "learning_rate": 3.937952036543586e-06, | |
| "loss": 1.5135, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.8895737031330252, | |
| "grad_norm": 2.570857524871826, | |
| "learning_rate": 3.93604872478112e-06, | |
| "loss": 1.5072, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.8906009244992296, | |
| "grad_norm": 2.855071544647217, | |
| "learning_rate": 3.934145413018653e-06, | |
| "loss": 1.5171, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.891628145865434, | |
| "grad_norm": 2.5592195987701416, | |
| "learning_rate": 3.932242101256186e-06, | |
| "loss": 1.4695, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.8926553672316384, | |
| "grad_norm": 2.6110830307006836, | |
| "learning_rate": 3.93033878949372e-06, | |
| "loss": 1.4802, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.8936825885978429, | |
| "grad_norm": 2.7121548652648926, | |
| "learning_rate": 3.928435477731253e-06, | |
| "loss": 1.4422, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8936825885978429, | |
| "eval_loss": 1.8629941940307617, | |
| "eval_runtime": 37.1091, | |
| "eval_samples_per_second": 26.948, | |
| "eval_steps_per_second": 1.132, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8947098099640473, | |
| "grad_norm": 2.7763099670410156, | |
| "learning_rate": 3.9265321659687864e-06, | |
| "loss": 1.5275, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.8957370313302516, | |
| "grad_norm": 2.596220016479492, | |
| "learning_rate": 3.924628854206319e-06, | |
| "loss": 1.5374, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.8967642526964561, | |
| "grad_norm": 2.575990915298462, | |
| "learning_rate": 3.922725542443852e-06, | |
| "loss": 1.5071, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.8977914740626605, | |
| "grad_norm": 2.7052223682403564, | |
| "learning_rate": 3.920822230681386e-06, | |
| "loss": 1.4656, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.8988186954288649, | |
| "grad_norm": 2.550267219543457, | |
| "learning_rate": 3.918918918918919e-06, | |
| "loss": 1.4837, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8998459167950693, | |
| "grad_norm": 2.6948060989379883, | |
| "learning_rate": 3.917015607156452e-06, | |
| "loss": 1.5156, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.9008731381612738, | |
| "grad_norm": 2.575596809387207, | |
| "learning_rate": 3.915112295393986e-06, | |
| "loss": 1.4881, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.9019003595274782, | |
| "grad_norm": 2.9835500717163086, | |
| "learning_rate": 3.913208983631519e-06, | |
| "loss": 1.5729, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.9029275808936826, | |
| "grad_norm": 2.5961520671844482, | |
| "learning_rate": 3.9113056718690525e-06, | |
| "loss": 1.5469, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 2.518260955810547, | |
| "learning_rate": 3.909402360106586e-06, | |
| "loss": 1.4704, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "eval_loss": 1.8570330142974854, | |
| "eval_runtime": 37.1293, | |
| "eval_samples_per_second": 26.933, | |
| "eval_steps_per_second": 1.131, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9049820236260914, | |
| "grad_norm": 2.740879535675049, | |
| "learning_rate": 3.907499048344119e-06, | |
| "loss": 1.5092, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.9060092449922958, | |
| "grad_norm": 2.5227973461151123, | |
| "learning_rate": 3.905595736581652e-06, | |
| "loss": 1.5252, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.9070364663585002, | |
| "grad_norm": 2.483125925064087, | |
| "learning_rate": 3.903692424819186e-06, | |
| "loss": 1.5216, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.9080636877247047, | |
| "grad_norm": 2.4979538917541504, | |
| "learning_rate": 3.901789113056719e-06, | |
| "loss": 1.4734, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 2.707669496536255, | |
| "learning_rate": 3.899885801294253e-06, | |
| "loss": 1.5347, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.9101181304571135, | |
| "grad_norm": 2.6548409461975098, | |
| "learning_rate": 3.897982489531786e-06, | |
| "loss": 1.5079, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.9111453518233179, | |
| "grad_norm": 2.6678848266601562, | |
| "learning_rate": 3.896079177769319e-06, | |
| "loss": 1.5659, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.9121725731895224, | |
| "grad_norm": 2.570976734161377, | |
| "learning_rate": 3.894175866006853e-06, | |
| "loss": 1.5281, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.9131997945557268, | |
| "grad_norm": 2.5939226150512695, | |
| "learning_rate": 3.892272554244385e-06, | |
| "loss": 1.56, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.9142270159219312, | |
| "grad_norm": 2.4577109813690186, | |
| "learning_rate": 3.890369242481919e-06, | |
| "loss": 1.4702, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9142270159219312, | |
| "eval_loss": 1.8534926176071167, | |
| "eval_runtime": 37.3353, | |
| "eval_samples_per_second": 26.784, | |
| "eval_steps_per_second": 1.125, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9152542372881356, | |
| "grad_norm": 2.5012643337249756, | |
| "learning_rate": 3.888465930719452e-06, | |
| "loss": 1.5411, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.91628145865434, | |
| "grad_norm": 2.470905065536499, | |
| "learning_rate": 3.886562618956985e-06, | |
| "loss": 1.4766, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.9173086800205444, | |
| "grad_norm": 2.4610393047332764, | |
| "learning_rate": 3.884659307194519e-06, | |
| "loss": 1.4925, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.9183359013867488, | |
| "grad_norm": 2.573151111602783, | |
| "learning_rate": 3.882755995432052e-06, | |
| "loss": 1.4389, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.9193631227529533, | |
| "grad_norm": 2.628934144973755, | |
| "learning_rate": 3.8808526836695854e-06, | |
| "loss": 1.5099, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.9203903441191577, | |
| "grad_norm": 2.639920949935913, | |
| "learning_rate": 3.878949371907119e-06, | |
| "loss": 1.4724, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.9214175654853621, | |
| "grad_norm": 2.4775230884552, | |
| "learning_rate": 3.877046060144652e-06, | |
| "loss": 1.4657, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.9224447868515665, | |
| "grad_norm": 2.5242490768432617, | |
| "learning_rate": 3.8751427483821855e-06, | |
| "loss": 1.459, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.923472008217771, | |
| "grad_norm": 2.4444870948791504, | |
| "learning_rate": 3.873239436619718e-06, | |
| "loss": 1.494, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.9244992295839753, | |
| "grad_norm": 2.4326930046081543, | |
| "learning_rate": 3.871336124857251e-06, | |
| "loss": 1.4449, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9244992295839753, | |
| "eval_loss": 1.8844366073608398, | |
| "eval_runtime": 37.432, | |
| "eval_samples_per_second": 26.715, | |
| "eval_steps_per_second": 1.122, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2919, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.805578468425728e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |