| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7190549563430919, | |
| "eval_steps": 10, | |
| "global_step": 700, | |
| "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": 2.7525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002054442732408834, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7605, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030816640986132513, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8008, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004108885464817668, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.809, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005136106831022085, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7841, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0061633281972265025, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7924, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007190549563430919, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008217770929635337, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7953, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009244992295839754, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01027221366204417, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7909, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01027221366204417, | |
| "eval_loss": 2.811410665512085, | |
| "eval_runtime": 37.9307, | |
| "eval_samples_per_second": 26.364, | |
| "eval_steps_per_second": 1.107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011299435028248588, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7592, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012326656394453005, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7394, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01335387776065742, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8111, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014381099126861838, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7786, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015408320493066256, | |
| "grad_norm": 5.814355373382568, | |
| "learning_rate": 1.7123287671232876e-08, | |
| "loss": 2.7711, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016435541859270673, | |
| "grad_norm": 6.2984514236450195, | |
| "learning_rate": 3.424657534246575e-08, | |
| "loss": 2.7517, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01746276322547509, | |
| "grad_norm": 6.235473155975342, | |
| "learning_rate": 5.136986301369863e-08, | |
| "loss": 2.7191, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01848998459167951, | |
| "grad_norm": 6.235473155975342, | |
| "learning_rate": 5.136986301369863e-08, | |
| "loss": 2.806, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019517205957883924, | |
| "grad_norm": 6.621068000793457, | |
| "learning_rate": 6.84931506849315e-08, | |
| "loss": 2.7192, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02054442732408834, | |
| "grad_norm": 6.781496524810791, | |
| "learning_rate": 8.561643835616439e-08, | |
| "loss": 2.7862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02054442732408834, | |
| "eval_loss": 2.8109023571014404, | |
| "eval_runtime": 37.527, | |
| "eval_samples_per_second": 26.647, | |
| "eval_steps_per_second": 1.119, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02157164869029276, | |
| "grad_norm": 6.336451530456543, | |
| "learning_rate": 1.0273972602739726e-07, | |
| "loss": 2.7997, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 6.184426307678223, | |
| "learning_rate": 1.1986301369863014e-07, | |
| "loss": 2.7938, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02362609142270159, | |
| "grad_norm": 6.443874359130859, | |
| "learning_rate": 1.36986301369863e-07, | |
| "loss": 2.7485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02465331278890601, | |
| "grad_norm": 6.17667293548584, | |
| "learning_rate": 1.541095890410959e-07, | |
| "loss": 2.7779, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025680534155110426, | |
| "grad_norm": 5.850281715393066, | |
| "learning_rate": 1.7123287671232878e-07, | |
| "loss": 2.7598, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02670775552131484, | |
| "grad_norm": 5.788112640380859, | |
| "learning_rate": 1.8835616438356165e-07, | |
| "loss": 2.7837, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02773497688751926, | |
| "grad_norm": 5.17655086517334, | |
| "learning_rate": 2.0547945205479452e-07, | |
| "loss": 2.7513, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028762198253723677, | |
| "grad_norm": 4.698268890380859, | |
| "learning_rate": 2.226027397260274e-07, | |
| "loss": 2.7714, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029789419619928096, | |
| "grad_norm": 4.562674522399902, | |
| "learning_rate": 2.397260273972603e-07, | |
| "loss": 2.7759, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030816640986132512, | |
| "grad_norm": 4.138142108917236, | |
| "learning_rate": 2.568493150684932e-07, | |
| "loss": 2.7656, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030816640986132512, | |
| "eval_loss": 2.784187078475952, | |
| "eval_runtime": 36.9691, | |
| "eval_samples_per_second": 27.05, | |
| "eval_steps_per_second": 1.136, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03184386235233693, | |
| "grad_norm": 4.39779806137085, | |
| "learning_rate": 2.73972602739726e-07, | |
| "loss": 2.7377, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03287108371854135, | |
| "grad_norm": 3.9160122871398926, | |
| "learning_rate": 2.910958904109589e-07, | |
| "loss": 2.7753, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 4.828811168670654, | |
| "learning_rate": 3.082191780821918e-07, | |
| "loss": 2.7311, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03492552645095018, | |
| "grad_norm": 4.6300435066223145, | |
| "learning_rate": 3.2534246575342466e-07, | |
| "loss": 2.7287, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.035952747817154594, | |
| "grad_norm": 4.47259521484375, | |
| "learning_rate": 3.4246575342465755e-07, | |
| "loss": 2.7117, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03697996918335902, | |
| "grad_norm": 4.557999610900879, | |
| "learning_rate": 3.595890410958904e-07, | |
| "loss": 2.6291, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03800719054956343, | |
| "grad_norm": 4.3974761962890625, | |
| "learning_rate": 3.767123287671233e-07, | |
| "loss": 2.7421, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03903441191576785, | |
| "grad_norm": 3.6151702404022217, | |
| "learning_rate": 3.938356164383562e-07, | |
| "loss": 2.6744, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.040061633281972264, | |
| "grad_norm": 3.165523052215576, | |
| "learning_rate": 4.1095890410958903e-07, | |
| "loss": 2.6694, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04108885464817668, | |
| "grad_norm": 3.2827563285827637, | |
| "learning_rate": 4.2808219178082193e-07, | |
| "loss": 2.7177, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04108885464817668, | |
| "eval_loss": 2.705791711807251, | |
| "eval_runtime": 36.995, | |
| "eval_samples_per_second": 27.031, | |
| "eval_steps_per_second": 1.135, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.042116076014381096, | |
| "grad_norm": 3.241729736328125, | |
| "learning_rate": 4.452054794520548e-07, | |
| "loss": 2.6703, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04314329738058552, | |
| "grad_norm": 3.401049852371216, | |
| "learning_rate": 4.6232876712328767e-07, | |
| "loss": 2.6036, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.044170518746789934, | |
| "grad_norm": 3.2498552799224854, | |
| "learning_rate": 4.794520547945206e-07, | |
| "loss": 2.6666, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 3.1376283168792725, | |
| "learning_rate": 4.965753424657534e-07, | |
| "loss": 2.6331, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.046224961479198766, | |
| "grad_norm": 2.885286569595337, | |
| "learning_rate": 5.136986301369864e-07, | |
| "loss": 2.6609, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04725218284540318, | |
| "grad_norm": 2.636420249938965, | |
| "learning_rate": 5.308219178082192e-07, | |
| "loss": 2.6462, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.048279404211607604, | |
| "grad_norm": 2.5609490871429443, | |
| "learning_rate": 5.47945205479452e-07, | |
| "loss": 2.6821, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04930662557781202, | |
| "grad_norm": 2.7683653831481934, | |
| "learning_rate": 5.65068493150685e-07, | |
| "loss": 2.61, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.050333846944016436, | |
| "grad_norm": 3.3999135494232178, | |
| "learning_rate": 5.821917808219178e-07, | |
| "loss": 2.6166, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "grad_norm": 2.922145128250122, | |
| "learning_rate": 5.993150684931507e-07, | |
| "loss": 2.5657, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05136106831022085, | |
| "eval_loss": 2.6353814601898193, | |
| "eval_runtime": 37.0591, | |
| "eval_samples_per_second": 26.984, | |
| "eval_steps_per_second": 1.133, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05238828967642527, | |
| "grad_norm": 2.5821900367736816, | |
| "learning_rate": 6.164383561643836e-07, | |
| "loss": 2.5512, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05341551104262968, | |
| "grad_norm": 2.2299063205718994, | |
| "learning_rate": 6.335616438356165e-07, | |
| "loss": 2.6082, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.054442732408834106, | |
| "grad_norm": 2.0938310623168945, | |
| "learning_rate": 6.506849315068493e-07, | |
| "loss": 2.5301, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05546995377503852, | |
| "grad_norm": 2.186629295349121, | |
| "learning_rate": 6.678082191780823e-07, | |
| "loss": 2.5755, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05649717514124294, | |
| "grad_norm": 2.1747493743896484, | |
| "learning_rate": 6.849315068493151e-07, | |
| "loss": 2.5451, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05752439650744735, | |
| "grad_norm": 2.5470354557037354, | |
| "learning_rate": 7.020547945205481e-07, | |
| "loss": 2.5159, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05855161787365177, | |
| "grad_norm": 2.5056023597717285, | |
| "learning_rate": 7.191780821917808e-07, | |
| "loss": 2.5431, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05957883923985619, | |
| "grad_norm": 2.6059749126434326, | |
| "learning_rate": 7.363013698630137e-07, | |
| "loss": 2.4684, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 1.87150239944458, | |
| "learning_rate": 7.534246575342466e-07, | |
| "loss": 2.5269, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.061633281972265024, | |
| "grad_norm": 1.8777480125427246, | |
| "learning_rate": 7.705479452054795e-07, | |
| "loss": 2.5253, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.061633281972265024, | |
| "eval_loss": 2.5705313682556152, | |
| "eval_runtime": 37.0929, | |
| "eval_samples_per_second": 26.959, | |
| "eval_steps_per_second": 1.132, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06266050333846944, | |
| "grad_norm": 1.8500003814697266, | |
| "learning_rate": 7.876712328767124e-07, | |
| "loss": 2.4987, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06368772470467386, | |
| "grad_norm": 1.9473347663879395, | |
| "learning_rate": 8.047945205479453e-07, | |
| "loss": 2.4866, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06471494607087827, | |
| "grad_norm": 2.2350873947143555, | |
| "learning_rate": 8.219178082191781e-07, | |
| "loss": 2.5343, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0657421674370827, | |
| "grad_norm": 2.1791350841522217, | |
| "learning_rate": 8.39041095890411e-07, | |
| "loss": 2.5185, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0667693888032871, | |
| "grad_norm": 1.8400903940200806, | |
| "learning_rate": 8.561643835616439e-07, | |
| "loss": 2.3897, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 1.7193644046783447, | |
| "learning_rate": 8.732876712328768e-07, | |
| "loss": 2.485, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06882383153569595, | |
| "grad_norm": 1.8478909730911255, | |
| "learning_rate": 8.904109589041097e-07, | |
| "loss": 2.4404, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06985105290190036, | |
| "grad_norm": 1.8803719282150269, | |
| "learning_rate": 9.075342465753426e-07, | |
| "loss": 2.4933, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07087827426810478, | |
| "grad_norm": 1.6866114139556885, | |
| "learning_rate": 9.246575342465753e-07, | |
| "loss": 2.4441, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07190549563430919, | |
| "grad_norm": 1.807783842086792, | |
| "learning_rate": 9.417808219178083e-07, | |
| "loss": 2.5477, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07190549563430919, | |
| "eval_loss": 2.5140035152435303, | |
| "eval_runtime": 37.1384, | |
| "eval_samples_per_second": 26.926, | |
| "eval_steps_per_second": 1.131, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07293271700051361, | |
| "grad_norm": 1.7754000425338745, | |
| "learning_rate": 9.589041095890411e-07, | |
| "loss": 2.44, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07395993836671803, | |
| "grad_norm": 1.7819652557373047, | |
| "learning_rate": 9.76027397260274e-07, | |
| "loss": 2.402, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07498715973292244, | |
| "grad_norm": 1.6666278839111328, | |
| "learning_rate": 9.931506849315068e-07, | |
| "loss": 2.4511, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07601438109912687, | |
| "grad_norm": 2.0625369548797607, | |
| "learning_rate": 1.0102739726027399e-06, | |
| "loss": 2.424, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07704160246533127, | |
| "grad_norm": 1.9408000707626343, | |
| "learning_rate": 1.0273972602739727e-06, | |
| "loss": 2.4286, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0780688238315357, | |
| "grad_norm": 1.7670842409133911, | |
| "learning_rate": 1.0445205479452056e-06, | |
| "loss": 2.407, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.07909604519774012, | |
| "grad_norm": 3.045717716217041, | |
| "learning_rate": 1.0616438356164384e-06, | |
| "loss": 2.425, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08012326656394453, | |
| "grad_norm": 1.9278619289398193, | |
| "learning_rate": 1.0787671232876712e-06, | |
| "loss": 2.4306, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08115048793014895, | |
| "grad_norm": 2.405146837234497, | |
| "learning_rate": 1.095890410958904e-06, | |
| "loss": 2.3499, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08217770929635336, | |
| "grad_norm": 2.1083860397338867, | |
| "learning_rate": 1.1130136986301371e-06, | |
| "loss": 2.4115, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08217770929635336, | |
| "eval_loss": 2.4501075744628906, | |
| "eval_runtime": 37.1247, | |
| "eval_samples_per_second": 26.936, | |
| "eval_steps_per_second": 1.131, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08320493066255778, | |
| "grad_norm": 2.181162118911743, | |
| "learning_rate": 1.13013698630137e-06, | |
| "loss": 2.3517, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08423215202876219, | |
| "grad_norm": 2.1833999156951904, | |
| "learning_rate": 1.1472602739726028e-06, | |
| "loss": 2.38, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08525937339496661, | |
| "grad_norm": 2.670384645462036, | |
| "learning_rate": 1.1643835616438357e-06, | |
| "loss": 2.3833, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08628659476117104, | |
| "grad_norm": 2.438676118850708, | |
| "learning_rate": 1.1815068493150685e-06, | |
| "loss": 2.3399, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08731381612737545, | |
| "grad_norm": 2.7584919929504395, | |
| "learning_rate": 1.1986301369863014e-06, | |
| "loss": 2.31, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08834103749357987, | |
| "grad_norm": 2.4129064083099365, | |
| "learning_rate": 1.2157534246575344e-06, | |
| "loss": 2.3758, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.08936825885978428, | |
| "grad_norm": 2.366154193878174, | |
| "learning_rate": 1.2328767123287673e-06, | |
| "loss": 2.3154, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 2.4916300773620605, | |
| "learning_rate": 1.25e-06, | |
| "loss": 2.3022, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09142270159219312, | |
| "grad_norm": 2.4606640338897705, | |
| "learning_rate": 1.267123287671233e-06, | |
| "loss": 2.3103, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09244992295839753, | |
| "grad_norm": 2.4134910106658936, | |
| "learning_rate": 1.284246575342466e-06, | |
| "loss": 2.2672, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09244992295839753, | |
| "eval_loss": 2.3742051124572754, | |
| "eval_runtime": 37.1258, | |
| "eval_samples_per_second": 26.935, | |
| "eval_steps_per_second": 1.131, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09347714432460195, | |
| "grad_norm": 2.302776336669922, | |
| "learning_rate": 1.3013698630136986e-06, | |
| "loss": 2.2798, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.09450436569080636, | |
| "grad_norm": 3.397819757461548, | |
| "learning_rate": 1.3184931506849317e-06, | |
| "loss": 2.2947, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09553158705701079, | |
| "grad_norm": 2.6030948162078857, | |
| "learning_rate": 1.3356164383561645e-06, | |
| "loss": 2.2734, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09655880842321521, | |
| "grad_norm": 2.9380528926849365, | |
| "learning_rate": 1.3527397260273976e-06, | |
| "loss": 2.2635, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.09758602978941962, | |
| "grad_norm": 2.9196345806121826, | |
| "learning_rate": 1.3698630136986302e-06, | |
| "loss": 2.3161, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09861325115562404, | |
| "grad_norm": 2.2380659580230713, | |
| "learning_rate": 1.386986301369863e-06, | |
| "loss": 2.21, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.09964047252182845, | |
| "grad_norm": 2.730910539627075, | |
| "learning_rate": 1.4041095890410961e-06, | |
| "loss": 2.2562, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.10066769388803287, | |
| "grad_norm": 2.994748830795288, | |
| "learning_rate": 1.421232876712329e-06, | |
| "loss": 2.1597, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 2.2228171825408936, | |
| "learning_rate": 1.4383561643835616e-06, | |
| "loss": 2.1835, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1027221366204417, | |
| "grad_norm": 2.715527296066284, | |
| "learning_rate": 1.4554794520547946e-06, | |
| "loss": 2.2074, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1027221366204417, | |
| "eval_loss": 2.3061234951019287, | |
| "eval_runtime": 37.1393, | |
| "eval_samples_per_second": 26.926, | |
| "eval_steps_per_second": 1.131, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10374935798664613, | |
| "grad_norm": 2.7054452896118164, | |
| "learning_rate": 1.4726027397260275e-06, | |
| "loss": 2.2089, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.10477657935285054, | |
| "grad_norm": 2.795694589614868, | |
| "learning_rate": 1.4897260273972605e-06, | |
| "loss": 2.1802, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.10580380071905496, | |
| "grad_norm": 2.634822368621826, | |
| "learning_rate": 1.5068493150684932e-06, | |
| "loss": 2.1428, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.10683102208525937, | |
| "grad_norm": 2.2418437004089355, | |
| "learning_rate": 1.5239726027397262e-06, | |
| "loss": 2.1706, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.10785824345146379, | |
| "grad_norm": 2.471231698989868, | |
| "learning_rate": 1.541095890410959e-06, | |
| "loss": 2.2248, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10888546481766821, | |
| "grad_norm": 2.4154577255249023, | |
| "learning_rate": 1.5582191780821921e-06, | |
| "loss": 2.1873, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.10991268618387262, | |
| "grad_norm": 2.2823996543884277, | |
| "learning_rate": 1.5753424657534248e-06, | |
| "loss": 2.2237, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.11093990755007704, | |
| "grad_norm": 2.8695461750030518, | |
| "learning_rate": 1.5924657534246576e-06, | |
| "loss": 2.1966, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11196712891628145, | |
| "grad_norm": 3.319650650024414, | |
| "learning_rate": 1.6095890410958907e-06, | |
| "loss": 2.066, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 2.815196990966797, | |
| "learning_rate": 1.6267123287671235e-06, | |
| "loss": 2.1355, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "eval_loss": 2.250187635421753, | |
| "eval_runtime": 37.1645, | |
| "eval_samples_per_second": 26.907, | |
| "eval_steps_per_second": 1.13, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1140215716486903, | |
| "grad_norm": 2.9195759296417236, | |
| "learning_rate": 1.6438356164383561e-06, | |
| "loss": 2.0713, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1150487930148947, | |
| "grad_norm": 2.5600695610046387, | |
| "learning_rate": 1.6609589041095892e-06, | |
| "loss": 2.1573, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.11607601438109913, | |
| "grad_norm": 2.7566795349121094, | |
| "learning_rate": 1.678082191780822e-06, | |
| "loss": 2.0909, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.11710323574730354, | |
| "grad_norm": 2.5593106746673584, | |
| "learning_rate": 1.695205479452055e-06, | |
| "loss": 2.144, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.11813045711350796, | |
| "grad_norm": 2.594931125640869, | |
| "learning_rate": 1.7123287671232877e-06, | |
| "loss": 2.0606, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11915767847971238, | |
| "grad_norm": 2.769916534423828, | |
| "learning_rate": 1.7294520547945206e-06, | |
| "loss": 2.1737, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12018489984591679, | |
| "grad_norm": 2.523179054260254, | |
| "learning_rate": 1.7465753424657536e-06, | |
| "loss": 2.1247, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 2.8153676986694336, | |
| "learning_rate": 1.7636986301369865e-06, | |
| "loss": 2.1257, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.12223934257832562, | |
| "grad_norm": 2.5389721393585205, | |
| "learning_rate": 1.7808219178082193e-06, | |
| "loss": 2.1049, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.12326656394453005, | |
| "grad_norm": 2.9753856658935547, | |
| "learning_rate": 1.7979452054794521e-06, | |
| "loss": 2.1871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12326656394453005, | |
| "eval_loss": 2.2089297771453857, | |
| "eval_runtime": 37.897, | |
| "eval_samples_per_second": 26.387, | |
| "eval_steps_per_second": 1.108, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12429378531073447, | |
| "grad_norm": 2.737180471420288, | |
| "learning_rate": 1.8150684931506852e-06, | |
| "loss": 2.1166, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.12532100667693888, | |
| "grad_norm": 2.783801794052124, | |
| "learning_rate": 1.832191780821918e-06, | |
| "loss": 2.0932, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1263482280431433, | |
| "grad_norm": 2.9615402221679688, | |
| "learning_rate": 1.8493150684931507e-06, | |
| "loss": 2.0327, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.12737544940934772, | |
| "grad_norm": 3.053622007369995, | |
| "learning_rate": 1.8664383561643837e-06, | |
| "loss": 2.0665, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.12840267077555212, | |
| "grad_norm": 3.265355348587036, | |
| "learning_rate": 1.8835616438356166e-06, | |
| "loss": 2.0243, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12942989214175654, | |
| "grad_norm": 2.4237143993377686, | |
| "learning_rate": 1.9006849315068496e-06, | |
| "loss": 2.0902, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.13045711350796096, | |
| "grad_norm": 2.926950693130493, | |
| "learning_rate": 1.9178082191780823e-06, | |
| "loss": 2.0057, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1314843348741654, | |
| "grad_norm": 2.5317165851593018, | |
| "learning_rate": 1.9349315068493153e-06, | |
| "loss": 2.0719, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.1325115562403698, | |
| "grad_norm": 2.4999701976776123, | |
| "learning_rate": 1.952054794520548e-06, | |
| "loss": 2.0969, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1335387776065742, | |
| "grad_norm": 2.7063920497894287, | |
| "learning_rate": 1.969178082191781e-06, | |
| "loss": 2.0902, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1335387776065742, | |
| "eval_loss": 2.175224542617798, | |
| "eval_runtime": 37.4519, | |
| "eval_samples_per_second": 26.701, | |
| "eval_steps_per_second": 1.121, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13456599897277863, | |
| "grad_norm": 2.650860071182251, | |
| "learning_rate": 1.9863013698630136e-06, | |
| "loss": 2.0191, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 2.79182505607605, | |
| "learning_rate": 2.0034246575342467e-06, | |
| "loss": 2.0856, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.13662044170518747, | |
| "grad_norm": 2.453162431716919, | |
| "learning_rate": 2.0205479452054797e-06, | |
| "loss": 2.0679, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1376476630713919, | |
| "grad_norm": 2.9630799293518066, | |
| "learning_rate": 2.037671232876713e-06, | |
| "loss": 2.0038, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1386748844375963, | |
| "grad_norm": 3.0807266235351562, | |
| "learning_rate": 2.0547945205479454e-06, | |
| "loss": 2.0367, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1397021058038007, | |
| "grad_norm": 2.9712910652160645, | |
| "learning_rate": 2.071917808219178e-06, | |
| "loss": 2.0571, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.14072932717000514, | |
| "grad_norm": 3.0804853439331055, | |
| "learning_rate": 2.089041095890411e-06, | |
| "loss": 1.9725, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.14175654853620956, | |
| "grad_norm": 2.659608840942383, | |
| "learning_rate": 2.106164383561644e-06, | |
| "loss": 2.0572, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.14278376990241398, | |
| "grad_norm": 2.8093109130859375, | |
| "learning_rate": 2.123287671232877e-06, | |
| "loss": 2.0178, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.14381099126861838, | |
| "grad_norm": 2.8163881301879883, | |
| "learning_rate": 2.14041095890411e-06, | |
| "loss": 2.0085, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14381099126861838, | |
| "eval_loss": 2.147092342376709, | |
| "eval_runtime": 37.2453, | |
| "eval_samples_per_second": 26.849, | |
| "eval_steps_per_second": 1.128, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1448382126348228, | |
| "grad_norm": 3.795241594314575, | |
| "learning_rate": 2.1575342465753425e-06, | |
| "loss": 2.0149, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.14586543400102722, | |
| "grad_norm": 3.3287174701690674, | |
| "learning_rate": 2.1746575342465755e-06, | |
| "loss": 1.9658, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.14689265536723164, | |
| "grad_norm": 2.803213596343994, | |
| "learning_rate": 2.191780821917808e-06, | |
| "loss": 2.0983, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.14791987673343607, | |
| "grad_norm": 3.2640199661254883, | |
| "learning_rate": 2.2089041095890412e-06, | |
| "loss": 1.9865, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.14894709809964046, | |
| "grad_norm": 2.95979380607605, | |
| "learning_rate": 2.2260273972602743e-06, | |
| "loss": 1.9669, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.14997431946584489, | |
| "grad_norm": 3.737175226211548, | |
| "learning_rate": 2.243150684931507e-06, | |
| "loss": 1.9691, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.1510015408320493, | |
| "grad_norm": 2.7248430252075195, | |
| "learning_rate": 2.26027397260274e-06, | |
| "loss": 1.9764, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.15202876219825373, | |
| "grad_norm": 2.929856061935425, | |
| "learning_rate": 2.2773972602739726e-06, | |
| "loss": 1.9967, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.15305598356445815, | |
| "grad_norm": 2.8998641967773438, | |
| "learning_rate": 2.2945205479452057e-06, | |
| "loss": 2.0842, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.15408320493066255, | |
| "grad_norm": 2.9672694206237793, | |
| "learning_rate": 2.3116438356164387e-06, | |
| "loss": 1.9915, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15408320493066255, | |
| "eval_loss": 2.122715473175049, | |
| "eval_runtime": 37.1938, | |
| "eval_samples_per_second": 26.886, | |
| "eval_steps_per_second": 1.129, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15511042629686697, | |
| "grad_norm": 2.8529887199401855, | |
| "learning_rate": 2.3287671232876713e-06, | |
| "loss": 1.9022, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.1561376476630714, | |
| "grad_norm": 2.914121389389038, | |
| "learning_rate": 2.3458904109589044e-06, | |
| "loss": 1.956, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.15716486902927582, | |
| "grad_norm": 3.6286494731903076, | |
| "learning_rate": 2.363013698630137e-06, | |
| "loss": 2.0118, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.15819209039548024, | |
| "grad_norm": 2.789562702178955, | |
| "learning_rate": 2.38013698630137e-06, | |
| "loss": 1.9935, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.15921931176168463, | |
| "grad_norm": 3.367119550704956, | |
| "learning_rate": 2.3972602739726027e-06, | |
| "loss": 1.9519, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16024653312788906, | |
| "grad_norm": 2.9345803260803223, | |
| "learning_rate": 2.4143835616438358e-06, | |
| "loss": 1.9017, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.16127375449409348, | |
| "grad_norm": 2.8674590587615967, | |
| "learning_rate": 2.431506849315069e-06, | |
| "loss": 1.9731, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1623009758602979, | |
| "grad_norm": 3.144766092300415, | |
| "learning_rate": 2.4486301369863015e-06, | |
| "loss": 1.9811, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.1633281972265023, | |
| "grad_norm": 3.845395088195801, | |
| "learning_rate": 2.4657534246575345e-06, | |
| "loss": 1.9523, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.16435541859270672, | |
| "grad_norm": 2.776700973510742, | |
| "learning_rate": 2.482876712328767e-06, | |
| "loss": 1.9687, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16435541859270672, | |
| "eval_loss": 2.0929579734802246, | |
| "eval_runtime": 37.1917, | |
| "eval_samples_per_second": 26.888, | |
| "eval_steps_per_second": 1.129, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16538263995891114, | |
| "grad_norm": 3.4260904788970947, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.9665, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.16640986132511557, | |
| "grad_norm": 3.1217620372772217, | |
| "learning_rate": 2.5171232876712333e-06, | |
| "loss": 1.9361, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.16743708269132, | |
| "grad_norm": 3.342068910598755, | |
| "learning_rate": 2.534246575342466e-06, | |
| "loss": 1.9084, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.16846430405752438, | |
| "grad_norm": 3.6485838890075684, | |
| "learning_rate": 2.551369863013699e-06, | |
| "loss": 1.9542, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 3.1247780323028564, | |
| "learning_rate": 2.568493150684932e-06, | |
| "loss": 1.9717, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.17051874678993323, | |
| "grad_norm": 2.9856860637664795, | |
| "learning_rate": 2.585616438356164e-06, | |
| "loss": 1.9574, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.17154596815613765, | |
| "grad_norm": 3.337902069091797, | |
| "learning_rate": 2.6027397260273973e-06, | |
| "loss": 1.8884, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.17257318952234207, | |
| "grad_norm": 2.844534158706665, | |
| "learning_rate": 2.6198630136986303e-06, | |
| "loss": 1.9545, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.17360041088854647, | |
| "grad_norm": 3.75907564163208, | |
| "learning_rate": 2.6369863013698634e-06, | |
| "loss": 1.9907, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.1746276322547509, | |
| "grad_norm": 2.9321961402893066, | |
| "learning_rate": 2.654109589041096e-06, | |
| "loss": 1.9663, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1746276322547509, | |
| "eval_loss": 2.0753843784332275, | |
| "eval_runtime": 37.2389, | |
| "eval_samples_per_second": 26.854, | |
| "eval_steps_per_second": 1.128, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17565485362095531, | |
| "grad_norm": 2.952523946762085, | |
| "learning_rate": 2.671232876712329e-06, | |
| "loss": 1.9065, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.17668207498715974, | |
| "grad_norm": 2.952463150024414, | |
| "learning_rate": 2.688356164383562e-06, | |
| "loss": 1.8994, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.17770929635336416, | |
| "grad_norm": 3.1352880001068115, | |
| "learning_rate": 2.705479452054795e-06, | |
| "loss": 1.8902, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.17873651771956856, | |
| "grad_norm": 3.5727322101593018, | |
| "learning_rate": 2.7226027397260274e-06, | |
| "loss": 1.8454, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.17976373908577298, | |
| "grad_norm": 3.0562493801116943, | |
| "learning_rate": 2.7397260273972604e-06, | |
| "loss": 1.984, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 3.367924690246582, | |
| "learning_rate": 2.7568493150684935e-06, | |
| "loss": 1.9398, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 3.1982340812683105, | |
| "learning_rate": 2.773972602739726e-06, | |
| "loss": 1.8566, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.18284540318438625, | |
| "grad_norm": 3.8962080478668213, | |
| "learning_rate": 2.791095890410959e-06, | |
| "loss": 1.9459, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.18387262455059064, | |
| "grad_norm": 3.3503036499023438, | |
| "learning_rate": 2.8082191780821922e-06, | |
| "loss": 1.8348, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.18489984591679506, | |
| "grad_norm": 3.276139497756958, | |
| "learning_rate": 2.8253424657534253e-06, | |
| "loss": 1.9849, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18489984591679506, | |
| "eval_loss": 2.0605413913726807, | |
| "eval_runtime": 37.2276, | |
| "eval_samples_per_second": 26.862, | |
| "eval_steps_per_second": 1.128, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1859270672829995, | |
| "grad_norm": 3.3787975311279297, | |
| "learning_rate": 2.842465753424658e-06, | |
| "loss": 1.9517, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.1869542886492039, | |
| "grad_norm": 3.054290294647217, | |
| "learning_rate": 2.8595890410958905e-06, | |
| "loss": 1.9572, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.18798151001540833, | |
| "grad_norm": 3.0737054347991943, | |
| "learning_rate": 2.876712328767123e-06, | |
| "loss": 1.9674, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.18900873138161273, | |
| "grad_norm": 3.2833855152130127, | |
| "learning_rate": 2.8938356164383562e-06, | |
| "loss": 1.8185, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.19003595274781715, | |
| "grad_norm": 2.70452880859375, | |
| "learning_rate": 2.9109589041095893e-06, | |
| "loss": 1.8552, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.19106317411402157, | |
| "grad_norm": 3.2723655700683594, | |
| "learning_rate": 2.9280821917808223e-06, | |
| "loss": 1.8433, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.192090395480226, | |
| "grad_norm": 2.844536066055298, | |
| "learning_rate": 2.945205479452055e-06, | |
| "loss": 1.8488, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.19311761684643042, | |
| "grad_norm": 2.944545269012451, | |
| "learning_rate": 2.962328767123288e-06, | |
| "loss": 1.9131, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.1941448382126348, | |
| "grad_norm": 2.812204122543335, | |
| "learning_rate": 2.979452054794521e-06, | |
| "loss": 1.8977, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.19517205957883924, | |
| "grad_norm": 2.8999950885772705, | |
| "learning_rate": 2.9965753424657533e-06, | |
| "loss": 1.8477, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19517205957883924, | |
| "eval_loss": 2.051161527633667, | |
| "eval_runtime": 37.2363, | |
| "eval_samples_per_second": 26.856, | |
| "eval_steps_per_second": 1.128, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19619928094504366, | |
| "grad_norm": 2.7814741134643555, | |
| "learning_rate": 3.0136986301369864e-06, | |
| "loss": 1.8989, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.19722650231124808, | |
| "grad_norm": 2.93346905708313, | |
| "learning_rate": 3.0308219178082194e-06, | |
| "loss": 1.8748, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1982537236774525, | |
| "grad_norm": 3.00400447845459, | |
| "learning_rate": 3.0479452054794525e-06, | |
| "loss": 1.838, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.1992809450436569, | |
| "grad_norm": 2.949695110321045, | |
| "learning_rate": 3.065068493150685e-06, | |
| "loss": 1.8817, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.20030816640986132, | |
| "grad_norm": 2.8858301639556885, | |
| "learning_rate": 3.082191780821918e-06, | |
| "loss": 1.8333, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.20133538777606574, | |
| "grad_norm": 3.123706102371216, | |
| "learning_rate": 3.099315068493151e-06, | |
| "loss": 1.8533, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.20236260914227017, | |
| "grad_norm": 3.0130505561828613, | |
| "learning_rate": 3.1164383561643843e-06, | |
| "loss": 1.842, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 2.8823280334472656, | |
| "learning_rate": 3.1335616438356165e-06, | |
| "loss": 1.8025, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.20441705187467898, | |
| "grad_norm": 2.920884132385254, | |
| "learning_rate": 3.1506849315068495e-06, | |
| "loss": 1.9488, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.2054442732408834, | |
| "grad_norm": 2.9152207374572754, | |
| "learning_rate": 3.167808219178082e-06, | |
| "loss": 1.8163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2054442732408834, | |
| "eval_loss": 2.033583641052246, | |
| "eval_runtime": 37.127, | |
| "eval_samples_per_second": 26.935, | |
| "eval_steps_per_second": 1.131, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20647149460708783, | |
| "grad_norm": 2.904230833053589, | |
| "learning_rate": 3.184931506849315e-06, | |
| "loss": 1.8207, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.20749871597329225, | |
| "grad_norm": 3.128448486328125, | |
| "learning_rate": 3.2020547945205483e-06, | |
| "loss": 1.8051, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.20852593733949668, | |
| "grad_norm": 3.0049452781677246, | |
| "learning_rate": 3.2191780821917813e-06, | |
| "loss": 1.7823, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.20955315870570107, | |
| "grad_norm": 2.7612497806549072, | |
| "learning_rate": 3.236301369863014e-06, | |
| "loss": 1.7703, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2105803800719055, | |
| "grad_norm": 2.9178879261016846, | |
| "learning_rate": 3.253424657534247e-06, | |
| "loss": 1.7427, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.21160760143810992, | |
| "grad_norm": 2.836967945098877, | |
| "learning_rate": 3.2705479452054796e-06, | |
| "loss": 1.8347, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.21263482280431434, | |
| "grad_norm": 2.8437204360961914, | |
| "learning_rate": 3.2876712328767123e-06, | |
| "loss": 1.8147, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.21366204417051873, | |
| "grad_norm": 3.0728225708007812, | |
| "learning_rate": 3.3047945205479453e-06, | |
| "loss": 1.7823, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.21468926553672316, | |
| "grad_norm": 3.357631206512451, | |
| "learning_rate": 3.3219178082191784e-06, | |
| "loss": 1.8013, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.21571648690292758, | |
| "grad_norm": 2.7996842861175537, | |
| "learning_rate": 3.3390410958904114e-06, | |
| "loss": 1.8279, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.21571648690292758, | |
| "eval_loss": 2.024500846862793, | |
| "eval_runtime": 37.0122, | |
| "eval_samples_per_second": 27.018, | |
| "eval_steps_per_second": 1.135, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.216743708269132, | |
| "grad_norm": 3.3635380268096924, | |
| "learning_rate": 3.356164383561644e-06, | |
| "loss": 1.8509, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.21777092963533642, | |
| "grad_norm": 2.703932523727417, | |
| "learning_rate": 3.373287671232877e-06, | |
| "loss": 1.8984, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.21879815100154082, | |
| "grad_norm": 2.9341695308685303, | |
| "learning_rate": 3.39041095890411e-06, | |
| "loss": 1.8381, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.21982537236774524, | |
| "grad_norm": 3.072448253631592, | |
| "learning_rate": 3.4075342465753424e-06, | |
| "loss": 1.8779, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.22085259373394966, | |
| "grad_norm": 2.850555419921875, | |
| "learning_rate": 3.4246575342465754e-06, | |
| "loss": 1.7656, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2218798151001541, | |
| "grad_norm": 3.0218873023986816, | |
| "learning_rate": 3.4417808219178085e-06, | |
| "loss": 1.829, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.2229070364663585, | |
| "grad_norm": 2.8475091457366943, | |
| "learning_rate": 3.458904109589041e-06, | |
| "loss": 1.8121, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.2239342578325629, | |
| "grad_norm": 2.8760111331939697, | |
| "learning_rate": 3.476027397260274e-06, | |
| "loss": 1.8281, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.22496147919876733, | |
| "grad_norm": 2.976670265197754, | |
| "learning_rate": 3.4931506849315072e-06, | |
| "loss": 1.8274, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 2.912505865097046, | |
| "learning_rate": 3.5102739726027403e-06, | |
| "loss": 1.8316, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 2.0203635692596436, | |
| "eval_runtime": 37.0433, | |
| "eval_samples_per_second": 26.995, | |
| "eval_steps_per_second": 1.134, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22701592193117617, | |
| "grad_norm": 3.1133334636688232, | |
| "learning_rate": 3.527397260273973e-06, | |
| "loss": 1.8277, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.2280431432973806, | |
| "grad_norm": 3.289062261581421, | |
| "learning_rate": 3.5445205479452056e-06, | |
| "loss": 1.7893, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.229070364663585, | |
| "grad_norm": 2.814558267593384, | |
| "learning_rate": 3.5616438356164386e-06, | |
| "loss": 1.8095, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.2300975860297894, | |
| "grad_norm": 3.48117733001709, | |
| "learning_rate": 3.5787671232876712e-06, | |
| "loss": 1.8701, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.23112480739599384, | |
| "grad_norm": 2.922144651412964, | |
| "learning_rate": 3.5958904109589043e-06, | |
| "loss": 1.8479, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23215202876219826, | |
| "grad_norm": 3.552428960800171, | |
| "learning_rate": 3.6130136986301373e-06, | |
| "loss": 1.7822, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.23317925012840268, | |
| "grad_norm": 3.058274269104004, | |
| "learning_rate": 3.6301369863013704e-06, | |
| "loss": 1.8228, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.23420647149460708, | |
| "grad_norm": 3.365823268890381, | |
| "learning_rate": 3.647260273972603e-06, | |
| "loss": 1.8415, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.2352336928608115, | |
| "grad_norm": 2.87333607673645, | |
| "learning_rate": 3.664383561643836e-06, | |
| "loss": 1.8474, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.23626091422701592, | |
| "grad_norm": 3.185807228088379, | |
| "learning_rate": 3.6815068493150687e-06, | |
| "loss": 1.7854, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.23626091422701592, | |
| "eval_loss": 2.0132367610931396, | |
| "eval_runtime": 37.3246, | |
| "eval_samples_per_second": 26.792, | |
| "eval_steps_per_second": 1.125, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.23728813559322035, | |
| "grad_norm": 3.02864933013916, | |
| "learning_rate": 3.6986301369863014e-06, | |
| "loss": 1.8081, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.23831535695942477, | |
| "grad_norm": 2.892451286315918, | |
| "learning_rate": 3.7157534246575344e-06, | |
| "loss": 1.7619, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.23934257832562916, | |
| "grad_norm": 3.24947452545166, | |
| "learning_rate": 3.7328767123287675e-06, | |
| "loss": 1.8729, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.24036979969183359, | |
| "grad_norm": 3.13212513923645, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.7849, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.241397021058038, | |
| "grad_norm": 3.004814863204956, | |
| "learning_rate": 3.767123287671233e-06, | |
| "loss": 1.8217, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 2.845555067062378, | |
| "learning_rate": 3.784246575342466e-06, | |
| "loss": 1.8438, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.24345146379044685, | |
| "grad_norm": 3.1796751022338867, | |
| "learning_rate": 3.8013698630136993e-06, | |
| "loss": 1.7807, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.24447868515665125, | |
| "grad_norm": 2.7663002014160156, | |
| "learning_rate": 3.818493150684932e-06, | |
| "loss": 1.7981, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.24550590652285567, | |
| "grad_norm": 3.0547749996185303, | |
| "learning_rate": 3.8356164383561645e-06, | |
| "loss": 1.7543, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.2465331278890601, | |
| "grad_norm": 2.6994550228118896, | |
| "learning_rate": 3.852739726027397e-06, | |
| "loss": 1.8612, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2465331278890601, | |
| "eval_loss": 2.0076475143432617, | |
| "eval_runtime": 37.3223, | |
| "eval_samples_per_second": 26.794, | |
| "eval_steps_per_second": 1.125, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.24756034925526452, | |
| "grad_norm": 2.769717216491699, | |
| "learning_rate": 3.869863013698631e-06, | |
| "loss": 1.8352, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.24858757062146894, | |
| "grad_norm": 2.7526769638061523, | |
| "learning_rate": 3.886986301369863e-06, | |
| "loss": 1.7775, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.24961479198767333, | |
| "grad_norm": 3.0213067531585693, | |
| "learning_rate": 3.904109589041096e-06, | |
| "loss": 1.7901, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.25064201335387776, | |
| "grad_norm": 2.8562498092651367, | |
| "learning_rate": 3.921232876712329e-06, | |
| "loss": 1.7483, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.2516692347200822, | |
| "grad_norm": 2.812774896621704, | |
| "learning_rate": 3.938356164383562e-06, | |
| "loss": 1.7643, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2526964560862866, | |
| "grad_norm": 3.2509777545928955, | |
| "learning_rate": 3.9554794520547955e-06, | |
| "loss": 1.729, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.253723677452491, | |
| "grad_norm": 3.6394171714782715, | |
| "learning_rate": 3.972602739726027e-06, | |
| "loss": 1.8253, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.25475089881869545, | |
| "grad_norm": 3.1234781742095947, | |
| "learning_rate": 3.989726027397261e-06, | |
| "loss": 1.7457, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.25577812018489987, | |
| "grad_norm": 2.8587522506713867, | |
| "learning_rate": 4.006849315068493e-06, | |
| "loss": 1.804, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.25680534155110424, | |
| "grad_norm": 2.9718286991119385, | |
| "learning_rate": 4.023972602739726e-06, | |
| "loss": 1.8051, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25680534155110424, | |
| "eval_loss": 2.0024874210357666, | |
| "eval_runtime": 37.2884, | |
| "eval_samples_per_second": 26.818, | |
| "eval_steps_per_second": 1.126, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25783256291730866, | |
| "grad_norm": 3.007124423980713, | |
| "learning_rate": 4.0410958904109595e-06, | |
| "loss": 1.7946, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.2588597842835131, | |
| "grad_norm": 3.1715426445007324, | |
| "learning_rate": 4.058219178082192e-06, | |
| "loss": 1.7811, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.2598870056497175, | |
| "grad_norm": 2.814269542694092, | |
| "learning_rate": 4.075342465753426e-06, | |
| "loss": 1.8024, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.26091422701592193, | |
| "grad_norm": 2.841212034225464, | |
| "learning_rate": 4.092465753424658e-06, | |
| "loss": 1.7713, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.26194144838212635, | |
| "grad_norm": 3.0878522396087646, | |
| "learning_rate": 4.109589041095891e-06, | |
| "loss": 1.7579, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2629686697483308, | |
| "grad_norm": 2.946709394454956, | |
| "learning_rate": 4.1267123287671235e-06, | |
| "loss": 1.823, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.2639958911145352, | |
| "grad_norm": 2.8136606216430664, | |
| "learning_rate": 4.143835616438356e-06, | |
| "loss": 1.7731, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.2650231124807396, | |
| "grad_norm": 2.745762825012207, | |
| "learning_rate": 4.16095890410959e-06, | |
| "loss": 1.8445, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.26605033384694404, | |
| "grad_norm": 3.0986413955688477, | |
| "learning_rate": 4.178082191780822e-06, | |
| "loss": 1.8231, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.2670775552131484, | |
| "grad_norm": 2.6990394592285156, | |
| "learning_rate": 4.195205479452055e-06, | |
| "loss": 1.7635, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2670775552131484, | |
| "eval_loss": 1.9839800596237183, | |
| "eval_runtime": 37.1612, | |
| "eval_samples_per_second": 26.91, | |
| "eval_steps_per_second": 1.13, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.26810477657935283, | |
| "grad_norm": 3.281421184539795, | |
| "learning_rate": 4.212328767123288e-06, | |
| "loss": 1.7587, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.26913199794555726, | |
| "grad_norm": 3.1233623027801514, | |
| "learning_rate": 4.229452054794521e-06, | |
| "loss": 1.7673, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.2701592193117617, | |
| "grad_norm": 3.3131625652313232, | |
| "learning_rate": 4.246575342465754e-06, | |
| "loss": 1.7755, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 3.3002350330352783, | |
| "learning_rate": 4.263698630136986e-06, | |
| "loss": 1.7575, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.2722136620441705, | |
| "grad_norm": 2.965397357940674, | |
| "learning_rate": 4.28082191780822e-06, | |
| "loss": 1.7162, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.27324088341037495, | |
| "grad_norm": 2.9904608726501465, | |
| "learning_rate": 4.297945205479452e-06, | |
| "loss": 1.8794, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.27426810477657937, | |
| "grad_norm": 2.707996129989624, | |
| "learning_rate": 4.315068493150685e-06, | |
| "loss": 1.7646, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.2752953261427838, | |
| "grad_norm": 2.8878190517425537, | |
| "learning_rate": 4.3321917808219185e-06, | |
| "loss": 1.7559, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.2763225475089882, | |
| "grad_norm": 3.1676602363586426, | |
| "learning_rate": 4.349315068493151e-06, | |
| "loss": 1.7806, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "grad_norm": 2.9179935455322266, | |
| "learning_rate": 4.3664383561643846e-06, | |
| "loss": 1.7493, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2773497688751926, | |
| "eval_loss": 1.9736579656600952, | |
| "eval_runtime": 37.0983, | |
| "eval_samples_per_second": 26.955, | |
| "eval_steps_per_second": 1.132, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.278376990241397, | |
| "grad_norm": 3.0081794261932373, | |
| "learning_rate": 4.383561643835616e-06, | |
| "loss": 1.7405, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.2794042116076014, | |
| "grad_norm": 3.240462064743042, | |
| "learning_rate": 4.40068493150685e-06, | |
| "loss": 1.8326, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.28043143297380585, | |
| "grad_norm": 3.324059247970581, | |
| "learning_rate": 4.4178082191780825e-06, | |
| "loss": 1.7819, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.2814586543400103, | |
| "grad_norm": 2.8438684940338135, | |
| "learning_rate": 4.434931506849315e-06, | |
| "loss": 1.7435, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.2824858757062147, | |
| "grad_norm": 2.9525997638702393, | |
| "learning_rate": 4.4520547945205486e-06, | |
| "loss": 1.7123, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.2835130970724191, | |
| "grad_norm": 2.972714900970459, | |
| "learning_rate": 4.469178082191781e-06, | |
| "loss": 1.7693, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.28454031843862354, | |
| "grad_norm": 3.4248580932617188, | |
| "learning_rate": 4.486301369863014e-06, | |
| "loss": 1.7502, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.28556753980482796, | |
| "grad_norm": 2.9928481578826904, | |
| "learning_rate": 4.503424657534247e-06, | |
| "loss": 1.8064, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.28659476117103233, | |
| "grad_norm": 2.944093942642212, | |
| "learning_rate": 4.52054794520548e-06, | |
| "loss": 1.7075, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.28762198253723675, | |
| "grad_norm": 3.2028305530548096, | |
| "learning_rate": 4.537671232876713e-06, | |
| "loss": 1.7366, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.28762198253723675, | |
| "eval_loss": 1.9768972396850586, | |
| "eval_runtime": 37.1078, | |
| "eval_samples_per_second": 26.948, | |
| "eval_steps_per_second": 1.132, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2886492039034412, | |
| "grad_norm": 2.8642148971557617, | |
| "learning_rate": 4.554794520547945e-06, | |
| "loss": 1.7909, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.2896764252696456, | |
| "grad_norm": 3.2716004848480225, | |
| "learning_rate": 4.571917808219179e-06, | |
| "loss": 1.7906, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.29070364663585, | |
| "grad_norm": 2.9601588249206543, | |
| "learning_rate": 4.589041095890411e-06, | |
| "loss": 1.7731, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.29173086800205444, | |
| "grad_norm": 3.1850085258483887, | |
| "learning_rate": 4.606164383561644e-06, | |
| "loss": 1.7335, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.29275808936825887, | |
| "grad_norm": 3.128908634185791, | |
| "learning_rate": 4.6232876712328774e-06, | |
| "loss": 1.748, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2937853107344633, | |
| "grad_norm": 3.063014507293701, | |
| "learning_rate": 4.64041095890411e-06, | |
| "loss": 1.7632, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.2948125321006677, | |
| "grad_norm": 3.467817783355713, | |
| "learning_rate": 4.657534246575343e-06, | |
| "loss": 1.7295, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.29583975346687214, | |
| "grad_norm": 2.7431066036224365, | |
| "learning_rate": 4.674657534246575e-06, | |
| "loss": 1.7728, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.2968669748330765, | |
| "grad_norm": 3.271421432495117, | |
| "learning_rate": 4.691780821917809e-06, | |
| "loss": 1.7403, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.2978941961992809, | |
| "grad_norm": 2.908351421356201, | |
| "learning_rate": 4.7089041095890414e-06, | |
| "loss": 1.7983, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2978941961992809, | |
| "eval_loss": 1.955810308456421, | |
| "eval_runtime": 37.0914, | |
| "eval_samples_per_second": 26.96, | |
| "eval_steps_per_second": 1.132, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.29892141756548535, | |
| "grad_norm": 3.046114683151245, | |
| "learning_rate": 4.726027397260274e-06, | |
| "loss": 1.7612, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.29994863893168977, | |
| "grad_norm": 3.275486707687378, | |
| "learning_rate": 4.7431506849315075e-06, | |
| "loss": 1.7548, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.3009758602978942, | |
| "grad_norm": 2.819552183151245, | |
| "learning_rate": 4.76027397260274e-06, | |
| "loss": 1.7645, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.3020030816640986, | |
| "grad_norm": 3.234227418899536, | |
| "learning_rate": 4.777397260273973e-06, | |
| "loss": 1.715, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 2.988713502883911, | |
| "learning_rate": 4.7945205479452054e-06, | |
| "loss": 1.7343, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.30405752439650746, | |
| "grad_norm": 3.195387601852417, | |
| "learning_rate": 4.811643835616439e-06, | |
| "loss": 1.7421, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.3050847457627119, | |
| "grad_norm": 3.617765426635742, | |
| "learning_rate": 4.8287671232876716e-06, | |
| "loss": 1.6661, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.3061119671289163, | |
| "grad_norm": 2.741631269454956, | |
| "learning_rate": 4.845890410958904e-06, | |
| "loss": 1.7188, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.3071391884951207, | |
| "grad_norm": 3.3230361938476562, | |
| "learning_rate": 4.863013698630138e-06, | |
| "loss": 1.721, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.3081664098613251, | |
| "grad_norm": 2.696352005004883, | |
| "learning_rate": 4.88013698630137e-06, | |
| "loss": 1.7137, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3081664098613251, | |
| "eval_loss": 1.9677459001541138, | |
| "eval_runtime": 37.1101, | |
| "eval_samples_per_second": 26.947, | |
| "eval_steps_per_second": 1.132, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3091936312275295, | |
| "grad_norm": 3.162966251373291, | |
| "learning_rate": 4.897260273972603e-06, | |
| "loss": 1.6956, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.31022085259373394, | |
| "grad_norm": 2.6055824756622314, | |
| "learning_rate": 4.914383561643836e-06, | |
| "loss": 1.8174, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.31124807395993837, | |
| "grad_norm": 2.816882610321045, | |
| "learning_rate": 4.931506849315069e-06, | |
| "loss": 1.7444, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.3122752953261428, | |
| "grad_norm": 2.9913320541381836, | |
| "learning_rate": 4.948630136986302e-06, | |
| "loss": 1.7744, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3133025166923472, | |
| "grad_norm": 2.992614507675171, | |
| "learning_rate": 4.965753424657534e-06, | |
| "loss": 1.8155, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.31432973805855163, | |
| "grad_norm": 3.2482688426971436, | |
| "learning_rate": 4.982876712328768e-06, | |
| "loss": 1.6903, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.31535695942475606, | |
| "grad_norm": 2.7701141834259033, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7228, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 3.179245948791504, | |
| "learning_rate": 4.998096688237534e-06, | |
| "loss": 1.6644, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.31741140215716485, | |
| "grad_norm": 2.845163106918335, | |
| "learning_rate": 4.996193376475067e-06, | |
| "loss": 1.772, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.31843862352336927, | |
| "grad_norm": 3.1509721279144287, | |
| "learning_rate": 4.9942900647126005e-06, | |
| "loss": 1.6662, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.31843862352336927, | |
| "eval_loss": 1.9684854745864868, | |
| "eval_runtime": 37.0507, | |
| "eval_samples_per_second": 26.99, | |
| "eval_steps_per_second": 1.134, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3194658448895737, | |
| "grad_norm": 2.8594536781311035, | |
| "learning_rate": 4.992386752950134e-06, | |
| "loss": 1.6587, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3204930662557781, | |
| "grad_norm": 3.358464002609253, | |
| "learning_rate": 4.990483441187667e-06, | |
| "loss": 1.7021, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.32152028762198254, | |
| "grad_norm": 2.6954872608184814, | |
| "learning_rate": 4.9885801294252e-06, | |
| "loss": 1.7301, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.32254750898818696, | |
| "grad_norm": 2.9256083965301514, | |
| "learning_rate": 4.986676817662733e-06, | |
| "loss": 1.7316, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.3235747303543914, | |
| "grad_norm": 2.840461254119873, | |
| "learning_rate": 4.9847735059002665e-06, | |
| "loss": 1.6848, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3246019517205958, | |
| "grad_norm": 2.9138107299804688, | |
| "learning_rate": 4.9828701941378e-06, | |
| "loss": 1.765, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.3256291730868002, | |
| "grad_norm": 2.858368396759033, | |
| "learning_rate": 4.980966882375333e-06, | |
| "loss": 1.7078, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.3266563944530046, | |
| "grad_norm": 2.905238628387451, | |
| "learning_rate": 4.979063570612867e-06, | |
| "loss": 1.6765, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.327683615819209, | |
| "grad_norm": 3.117845296859741, | |
| "learning_rate": 4.9771602588504e-06, | |
| "loss": 1.6419, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.32871083718541344, | |
| "grad_norm": 2.5665884017944336, | |
| "learning_rate": 4.975256947087933e-06, | |
| "loss": 1.7424, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.32871083718541344, | |
| "eval_loss": 1.9528932571411133, | |
| "eval_runtime": 37.2179, | |
| "eval_samples_per_second": 26.869, | |
| "eval_steps_per_second": 1.128, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.32973805855161786, | |
| "grad_norm": 2.499392032623291, | |
| "learning_rate": 4.973353635325467e-06, | |
| "loss": 1.6544, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.3307652799178223, | |
| "grad_norm": 2.8056774139404297, | |
| "learning_rate": 4.971450323563e-06, | |
| "loss": 1.7085, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.3317925012840267, | |
| "grad_norm": 2.850602388381958, | |
| "learning_rate": 4.969547011800533e-06, | |
| "loss": 1.6489, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.33281972265023113, | |
| "grad_norm": 2.783855438232422, | |
| "learning_rate": 4.967643700038067e-06, | |
| "loss": 1.7153, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.33384694401643555, | |
| "grad_norm": 2.7178030014038086, | |
| "learning_rate": 4.9657403882756e-06, | |
| "loss": 1.7104, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.33487416538264, | |
| "grad_norm": 2.7497682571411133, | |
| "learning_rate": 4.9638370765131335e-06, | |
| "loss": 1.6778, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.3359013867488444, | |
| "grad_norm": 2.688120126724243, | |
| "learning_rate": 4.961933764750667e-06, | |
| "loss": 1.6673, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.33692860811504877, | |
| "grad_norm": 2.661578416824341, | |
| "learning_rate": 4.9600304529882e-06, | |
| "loss": 1.7353, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.3379558294812532, | |
| "grad_norm": 2.759965419769287, | |
| "learning_rate": 4.9581271412257335e-06, | |
| "loss": 1.7506, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 2.972900390625, | |
| "learning_rate": 4.956223829463266e-06, | |
| "loss": 1.7114, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "eval_loss": 1.9369672536849976, | |
| "eval_runtime": 37.2876, | |
| "eval_samples_per_second": 26.819, | |
| "eval_steps_per_second": 1.126, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.34001027221366203, | |
| "grad_norm": 2.7194814682006836, | |
| "learning_rate": 4.954320517700799e-06, | |
| "loss": 1.621, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.34103749357986646, | |
| "grad_norm": 2.822052001953125, | |
| "learning_rate": 4.952417205938333e-06, | |
| "loss": 1.7215, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.3420647149460709, | |
| "grad_norm": 2.778348207473755, | |
| "learning_rate": 4.950513894175866e-06, | |
| "loss": 1.7049, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.3430919363122753, | |
| "grad_norm": 2.8513247966766357, | |
| "learning_rate": 4.9486105824133995e-06, | |
| "loss": 1.684, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.3441191576784797, | |
| "grad_norm": 2.5596683025360107, | |
| "learning_rate": 4.946707270650933e-06, | |
| "loss": 1.6992, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.34514637904468415, | |
| "grad_norm": 2.850728750228882, | |
| "learning_rate": 4.944803958888466e-06, | |
| "loss": 1.7095, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.34617360041088857, | |
| "grad_norm": 2.8497488498687744, | |
| "learning_rate": 4.942900647126e-06, | |
| "loss": 1.7361, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.34720082177709294, | |
| "grad_norm": 2.9133079051971436, | |
| "learning_rate": 4.940997335363533e-06, | |
| "loss": 1.6783, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.34822804314329736, | |
| "grad_norm": 2.7611589431762695, | |
| "learning_rate": 4.939094023601066e-06, | |
| "loss": 1.6407, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.3492552645095018, | |
| "grad_norm": 2.7190754413604736, | |
| "learning_rate": 4.9371907118386e-06, | |
| "loss": 1.6886, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3492552645095018, | |
| "eval_loss": 1.9296809434890747, | |
| "eval_runtime": 37.4339, | |
| "eval_samples_per_second": 26.714, | |
| "eval_steps_per_second": 1.122, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3502824858757062, | |
| "grad_norm": 2.863070487976074, | |
| "learning_rate": 4.935287400076133e-06, | |
| "loss": 1.6912, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.35130970724191063, | |
| "grad_norm": 2.5978336334228516, | |
| "learning_rate": 4.933384088313666e-06, | |
| "loss": 1.7107, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.35233692860811505, | |
| "grad_norm": 2.8323776721954346, | |
| "learning_rate": 4.9314807765512e-06, | |
| "loss": 1.6723, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.3533641499743195, | |
| "grad_norm": 2.7128350734710693, | |
| "learning_rate": 4.929577464788733e-06, | |
| "loss": 1.5993, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.3543913713405239, | |
| "grad_norm": 2.618936061859131, | |
| "learning_rate": 4.9276741530262665e-06, | |
| "loss": 1.6769, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3554185927067283, | |
| "grad_norm": 2.9575355052948, | |
| "learning_rate": 4.9257708412638e-06, | |
| "loss": 1.6743, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.35644581407293274, | |
| "grad_norm": 2.756464719772339, | |
| "learning_rate": 4.923867529501332e-06, | |
| "loss": 1.6858, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.3574730354391371, | |
| "grad_norm": 2.6581053733825684, | |
| "learning_rate": 4.921964217738866e-06, | |
| "loss": 1.6515, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.35850025680534153, | |
| "grad_norm": 2.890632390975952, | |
| "learning_rate": 4.920060905976399e-06, | |
| "loss": 1.7378, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.35952747817154596, | |
| "grad_norm": 2.7895255088806152, | |
| "learning_rate": 4.9181575942139325e-06, | |
| "loss": 1.7131, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.35952747817154596, | |
| "eval_loss": 1.9226924180984497, | |
| "eval_runtime": 37.5186, | |
| "eval_samples_per_second": 26.653, | |
| "eval_steps_per_second": 1.119, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3605546995377504, | |
| "grad_norm": 2.7698557376861572, | |
| "learning_rate": 4.916254282451466e-06, | |
| "loss": 1.71, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 2.956592321395874, | |
| "learning_rate": 4.914350970688999e-06, | |
| "loss": 1.7487, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.3626091422701592, | |
| "grad_norm": 2.6062943935394287, | |
| "learning_rate": 4.9124476589265325e-06, | |
| "loss": 1.6486, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 2.588418483734131, | |
| "learning_rate": 4.910544347164066e-06, | |
| "loss": 1.6468, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.36466358500256807, | |
| "grad_norm": 2.4665889739990234, | |
| "learning_rate": 4.908641035401599e-06, | |
| "loss": 1.7264, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3656908063687725, | |
| "grad_norm": 2.701957941055298, | |
| "learning_rate": 4.906737723639133e-06, | |
| "loss": 1.7914, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.3667180277349769, | |
| "grad_norm": 2.68169903755188, | |
| "learning_rate": 4.904834411876665e-06, | |
| "loss": 1.6609, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.3677452491011813, | |
| "grad_norm": 2.633120536804199, | |
| "learning_rate": 4.902931100114199e-06, | |
| "loss": 1.6998, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.3687724704673857, | |
| "grad_norm": 2.549065113067627, | |
| "learning_rate": 4.901027788351733e-06, | |
| "loss": 1.6227, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.3697996918335901, | |
| "grad_norm": 2.6537365913391113, | |
| "learning_rate": 4.899124476589266e-06, | |
| "loss": 1.6678, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3697996918335901, | |
| "eval_loss": 1.9240167140960693, | |
| "eval_runtime": 37.3212, | |
| "eval_samples_per_second": 26.794, | |
| "eval_steps_per_second": 1.125, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.37082691319979455, | |
| "grad_norm": 2.8710854053497314, | |
| "learning_rate": 4.8972211648267994e-06, | |
| "loss": 1.6377, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.371854134565999, | |
| "grad_norm": 2.8168065547943115, | |
| "learning_rate": 4.895317853064333e-06, | |
| "loss": 1.6888, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.3728813559322034, | |
| "grad_norm": 2.7674975395202637, | |
| "learning_rate": 4.893414541301866e-06, | |
| "loss": 1.6532, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.3739085772984078, | |
| "grad_norm": 2.5604195594787598, | |
| "learning_rate": 4.891511229539399e-06, | |
| "loss": 1.6513, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.37493579866461224, | |
| "grad_norm": 2.5669636726379395, | |
| "learning_rate": 4.889607917776932e-06, | |
| "loss": 1.6832, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.37596302003081666, | |
| "grad_norm": 2.650104522705078, | |
| "learning_rate": 4.887704606014465e-06, | |
| "loss": 1.6836, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.37699024139702103, | |
| "grad_norm": 2.702894926071167, | |
| "learning_rate": 4.885801294251999e-06, | |
| "loss": 1.6916, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.37801746276322545, | |
| "grad_norm": 2.991715431213379, | |
| "learning_rate": 4.883897982489532e-06, | |
| "loss": 1.6146, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.3790446841294299, | |
| "grad_norm": 2.725093126296997, | |
| "learning_rate": 4.8819946707270655e-06, | |
| "loss": 1.7124, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.3800719054956343, | |
| "grad_norm": 2.8419744968414307, | |
| "learning_rate": 4.880091358964599e-06, | |
| "loss": 1.7002, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3800719054956343, | |
| "eval_loss": 1.9024126529693604, | |
| "eval_runtime": 37.231, | |
| "eval_samples_per_second": 26.859, | |
| "eval_steps_per_second": 1.128, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3810991268618387, | |
| "grad_norm": 2.3915929794311523, | |
| "learning_rate": 4.878188047202132e-06, | |
| "loss": 1.6096, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.38212634822804314, | |
| "grad_norm": 2.577662944793701, | |
| "learning_rate": 4.876284735439666e-06, | |
| "loss": 1.772, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.38315356959424757, | |
| "grad_norm": 2.6686151027679443, | |
| "learning_rate": 4.874381423677199e-06, | |
| "loss": 1.7375, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.384180790960452, | |
| "grad_norm": 2.4534966945648193, | |
| "learning_rate": 4.8724781119147315e-06, | |
| "loss": 1.6603, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.3852080123266564, | |
| "grad_norm": 2.7308576107025146, | |
| "learning_rate": 4.870574800152265e-06, | |
| "loss": 1.6999, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.38623523369286084, | |
| "grad_norm": 2.551203727722168, | |
| "learning_rate": 4.868671488389798e-06, | |
| "loss": 1.6193, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.3872624550590652, | |
| "grad_norm": 2.78924822807312, | |
| "learning_rate": 4.8667681766273316e-06, | |
| "loss": 1.6359, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.3882896764252696, | |
| "grad_norm": 2.7972333431243896, | |
| "learning_rate": 4.864864864864866e-06, | |
| "loss": 1.6057, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.38931689779147405, | |
| "grad_norm": 2.721069097518921, | |
| "learning_rate": 4.862961553102399e-06, | |
| "loss": 1.6661, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.39034411915767847, | |
| "grad_norm": 2.817729949951172, | |
| "learning_rate": 4.8610582413399325e-06, | |
| "loss": 1.7053, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.39034411915767847, | |
| "eval_loss": 1.9177663326263428, | |
| "eval_runtime": 37.2158, | |
| "eval_samples_per_second": 26.87, | |
| "eval_steps_per_second": 1.129, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3913713405238829, | |
| "grad_norm": 2.800873279571533, | |
| "learning_rate": 4.859154929577465e-06, | |
| "loss": 1.6584, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.3923985618900873, | |
| "grad_norm": 2.6885769367218018, | |
| "learning_rate": 4.857251617814998e-06, | |
| "loss": 1.661, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.39342578325629174, | |
| "grad_norm": 2.56797456741333, | |
| "learning_rate": 4.855348306052532e-06, | |
| "loss": 1.7058, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.39445300462249616, | |
| "grad_norm": 2.5235650539398193, | |
| "learning_rate": 4.853444994290065e-06, | |
| "loss": 1.6977, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.3954802259887006, | |
| "grad_norm": 2.713711738586426, | |
| "learning_rate": 4.8515416825275985e-06, | |
| "loss": 1.6449, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.396507447354905, | |
| "grad_norm": 2.7639107704162598, | |
| "learning_rate": 4.849638370765132e-06, | |
| "loss": 1.7169, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.3975346687211094, | |
| "grad_norm": 2.4775755405426025, | |
| "learning_rate": 4.847735059002665e-06, | |
| "loss": 1.6423, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.3985618900873138, | |
| "grad_norm": 2.574907064437866, | |
| "learning_rate": 4.8458317472401985e-06, | |
| "loss": 1.5911, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.3995891114535182, | |
| "grad_norm": 2.667907953262329, | |
| "learning_rate": 4.843928435477732e-06, | |
| "loss": 1.6883, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.40061633281972264, | |
| "grad_norm": 2.592353343963623, | |
| "learning_rate": 4.842025123715265e-06, | |
| "loss": 1.639, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.40061633281972264, | |
| "eval_loss": 1.9100708961486816, | |
| "eval_runtime": 37.2379, | |
| "eval_samples_per_second": 26.854, | |
| "eval_steps_per_second": 1.128, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.40164355418592707, | |
| "grad_norm": 2.8238866329193115, | |
| "learning_rate": 4.840121811952798e-06, | |
| "loss": 1.6835, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.4026707755521315, | |
| "grad_norm": 2.769272804260254, | |
| "learning_rate": 4.838218500190331e-06, | |
| "loss": 1.6651, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.4036979969183359, | |
| "grad_norm": 2.749093532562256, | |
| "learning_rate": 4.8363151884278645e-06, | |
| "loss": 1.6815, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.40472521828454033, | |
| "grad_norm": 2.7952616214752197, | |
| "learning_rate": 4.834411876665398e-06, | |
| "loss": 1.6622, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.40575243965074476, | |
| "grad_norm": 2.5004849433898926, | |
| "learning_rate": 4.832508564902931e-06, | |
| "loss": 1.6768, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 2.938015937805176, | |
| "learning_rate": 4.830605253140465e-06, | |
| "loss": 1.6171, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.40780688238315355, | |
| "grad_norm": 2.737666130065918, | |
| "learning_rate": 4.828701941377998e-06, | |
| "loss": 1.6572, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.40883410374935797, | |
| "grad_norm": 2.6246249675750732, | |
| "learning_rate": 4.826798629615531e-06, | |
| "loss": 1.609, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.4098613251155624, | |
| "grad_norm": 2.6501305103302, | |
| "learning_rate": 4.824895317853065e-06, | |
| "loss": 1.6235, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.4108885464817668, | |
| "grad_norm": 2.89320707321167, | |
| "learning_rate": 4.822992006090598e-06, | |
| "loss": 1.6494, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4108885464817668, | |
| "eval_loss": 1.8916113376617432, | |
| "eval_runtime": 37.1849, | |
| "eval_samples_per_second": 26.893, | |
| "eval_steps_per_second": 1.129, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41191576784797124, | |
| "grad_norm": 2.4857001304626465, | |
| "learning_rate": 4.821088694328131e-06, | |
| "loss": 1.594, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.41294298921417566, | |
| "grad_norm": 2.903836250305176, | |
| "learning_rate": 4.819185382565665e-06, | |
| "loss": 1.6319, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.4139702105803801, | |
| "grad_norm": 2.69596266746521, | |
| "learning_rate": 4.817282070803198e-06, | |
| "loss": 1.6843, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.4149974319465845, | |
| "grad_norm": 2.5105295181274414, | |
| "learning_rate": 4.8153787590407315e-06, | |
| "loss": 1.6725, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.41602465331278893, | |
| "grad_norm": 2.7997353076934814, | |
| "learning_rate": 4.813475447278265e-06, | |
| "loss": 1.6017, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.41705187467899335, | |
| "grad_norm": 2.6215803623199463, | |
| "learning_rate": 4.811572135515798e-06, | |
| "loss": 1.6824, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.4180790960451977, | |
| "grad_norm": 2.76534104347229, | |
| "learning_rate": 4.809668823753332e-06, | |
| "loss": 1.6111, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.41910631741140214, | |
| "grad_norm": 2.6977133750915527, | |
| "learning_rate": 4.807765511990864e-06, | |
| "loss": 1.6165, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.42013353877760656, | |
| "grad_norm": 2.6771748065948486, | |
| "learning_rate": 4.8058622002283975e-06, | |
| "loss": 1.648, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.421160760143811, | |
| "grad_norm": 2.746731996536255, | |
| "learning_rate": 4.803958888465931e-06, | |
| "loss": 1.6946, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.421160760143811, | |
| "eval_loss": 1.878269076347351, | |
| "eval_runtime": 37.0935, | |
| "eval_samples_per_second": 26.959, | |
| "eval_steps_per_second": 1.132, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4221879815100154, | |
| "grad_norm": 2.688074827194214, | |
| "learning_rate": 4.802055576703464e-06, | |
| "loss": 1.6545, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.42321520287621983, | |
| "grad_norm": 2.7336084842681885, | |
| "learning_rate": 4.8001522649409976e-06, | |
| "loss": 1.7305, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 2.6902427673339844, | |
| "learning_rate": 4.798248953178531e-06, | |
| "loss": 1.612, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.4252696456086287, | |
| "grad_norm": 2.5339174270629883, | |
| "learning_rate": 4.796345641416064e-06, | |
| "loss": 1.5947, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.4262968669748331, | |
| "grad_norm": 2.6804542541503906, | |
| "learning_rate": 4.794442329653598e-06, | |
| "loss": 1.634, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.42732408834103747, | |
| "grad_norm": 2.5764853954315186, | |
| "learning_rate": 4.792539017891131e-06, | |
| "loss": 1.6947, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.4283513097072419, | |
| "grad_norm": 2.4067094326019287, | |
| "learning_rate": 4.790635706128664e-06, | |
| "loss": 1.616, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.4293785310734463, | |
| "grad_norm": 2.576206684112549, | |
| "learning_rate": 4.788732394366197e-06, | |
| "loss": 1.6529, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.43040575243965074, | |
| "grad_norm": 2.57826828956604, | |
| "learning_rate": 4.786829082603731e-06, | |
| "loss": 1.5771, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.43143297380585516, | |
| "grad_norm": 2.5002858638763428, | |
| "learning_rate": 4.7849257708412645e-06, | |
| "loss": 1.5814, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.43143297380585516, | |
| "eval_loss": 1.8940727710723877, | |
| "eval_runtime": 37.0932, | |
| "eval_samples_per_second": 26.959, | |
| "eval_steps_per_second": 1.132, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4324601951720596, | |
| "grad_norm": 2.618067502975464, | |
| "learning_rate": 4.783022459078798e-06, | |
| "loss": 1.6645, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.433487416538264, | |
| "grad_norm": 2.5745837688446045, | |
| "learning_rate": 4.781119147316331e-06, | |
| "loss": 1.602, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.4345146379044684, | |
| "grad_norm": 2.8009719848632812, | |
| "learning_rate": 4.7792158355538645e-06, | |
| "loss": 1.6269, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.43554185927067285, | |
| "grad_norm": 2.8486008644104004, | |
| "learning_rate": 4.777312523791398e-06, | |
| "loss": 1.6402, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.43656908063687727, | |
| "grad_norm": 2.5588459968566895, | |
| "learning_rate": 4.77540921202893e-06, | |
| "loss": 1.6122, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.43759630200308164, | |
| "grad_norm": 3.1455588340759277, | |
| "learning_rate": 4.773505900266464e-06, | |
| "loss": 1.6542, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.43862352336928606, | |
| "grad_norm": 2.6221370697021484, | |
| "learning_rate": 4.771602588503997e-06, | |
| "loss": 1.6339, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.4396507447354905, | |
| "grad_norm": 3.006816864013672, | |
| "learning_rate": 4.7696992767415305e-06, | |
| "loss": 1.6381, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.4406779661016949, | |
| "grad_norm": 2.7317590713500977, | |
| "learning_rate": 4.767795964979064e-06, | |
| "loss": 1.6689, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.44170518746789933, | |
| "grad_norm": 2.9259109497070312, | |
| "learning_rate": 4.765892653216597e-06, | |
| "loss": 1.6793, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.44170518746789933, | |
| "eval_loss": 1.8887399435043335, | |
| "eval_runtime": 37.1334, | |
| "eval_samples_per_second": 26.93, | |
| "eval_steps_per_second": 1.131, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.44273240883410375, | |
| "grad_norm": 2.8546087741851807, | |
| "learning_rate": 4.763989341454131e-06, | |
| "loss": 1.6706, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.4437596302003082, | |
| "grad_norm": 2.6085422039031982, | |
| "learning_rate": 4.762086029691664e-06, | |
| "loss": 1.5855, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.4447868515665126, | |
| "grad_norm": 2.622277021408081, | |
| "learning_rate": 4.760182717929197e-06, | |
| "loss": 1.6068, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.445814072932717, | |
| "grad_norm": 2.5327494144439697, | |
| "learning_rate": 4.758279406166731e-06, | |
| "loss": 1.6303, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.44684129429892144, | |
| "grad_norm": 2.7626633644104004, | |
| "learning_rate": 4.756376094404263e-06, | |
| "loss": 1.5567, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.4478685156651258, | |
| "grad_norm": 2.613476514816284, | |
| "learning_rate": 4.7544727826417966e-06, | |
| "loss": 1.6345, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.44889573703133023, | |
| "grad_norm": 2.58027720451355, | |
| "learning_rate": 4.75256947087933e-06, | |
| "loss": 1.675, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.44992295839753466, | |
| "grad_norm": 2.6709048748016357, | |
| "learning_rate": 4.750666159116863e-06, | |
| "loss": 1.6335, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.4509501797637391, | |
| "grad_norm": 2.7493093013763428, | |
| "learning_rate": 4.7487628473543975e-06, | |
| "loss": 1.6061, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 2.725672960281372, | |
| "learning_rate": 4.746859535591931e-06, | |
| "loss": 1.5515, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "eval_loss": 1.8779852390289307, | |
| "eval_runtime": 37.3135, | |
| "eval_samples_per_second": 26.8, | |
| "eval_steps_per_second": 1.126, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4530046224961479, | |
| "grad_norm": 2.784477472305298, | |
| "learning_rate": 4.744956223829464e-06, | |
| "loss": 1.6146, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.45403184386235235, | |
| "grad_norm": 2.758119821548462, | |
| "learning_rate": 4.743052912066997e-06, | |
| "loss": 1.5945, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.45505906522855677, | |
| "grad_norm": 2.9006264209747314, | |
| "learning_rate": 4.74114960030453e-06, | |
| "loss": 1.6461, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.4560862865947612, | |
| "grad_norm": 2.8473031520843506, | |
| "learning_rate": 4.7392462885420635e-06, | |
| "loss": 1.6565, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.4571135079609656, | |
| "grad_norm": 2.715806722640991, | |
| "learning_rate": 4.737342976779597e-06, | |
| "loss": 1.5414, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.45814072932717, | |
| "grad_norm": 2.6588337421417236, | |
| "learning_rate": 4.73543966501713e-06, | |
| "loss": 1.6284, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.4591679506933744, | |
| "grad_norm": 3.1152243614196777, | |
| "learning_rate": 4.7335363532546636e-06, | |
| "loss": 1.6237, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.4601951720595788, | |
| "grad_norm": 2.545490264892578, | |
| "learning_rate": 4.731633041492197e-06, | |
| "loss": 1.6149, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.46122239342578325, | |
| "grad_norm": 3.0324277877807617, | |
| "learning_rate": 4.72972972972973e-06, | |
| "loss": 1.6277, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.4622496147919877, | |
| "grad_norm": 2.885970115661621, | |
| "learning_rate": 4.727826417967264e-06, | |
| "loss": 1.6625, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4622496147919877, | |
| "eval_loss": 1.8651624917984009, | |
| "eval_runtime": 37.3486, | |
| "eval_samples_per_second": 26.775, | |
| "eval_steps_per_second": 1.125, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4632768361581921, | |
| "grad_norm": 2.7258739471435547, | |
| "learning_rate": 4.725923106204797e-06, | |
| "loss": 1.6263, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.4643040575243965, | |
| "grad_norm": 2.631122589111328, | |
| "learning_rate": 4.72401979444233e-06, | |
| "loss": 1.6081, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.46533127889060094, | |
| "grad_norm": 2.5882441997528076, | |
| "learning_rate": 4.722116482679863e-06, | |
| "loss": 1.6237, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.46635850025680536, | |
| "grad_norm": 2.66310715675354, | |
| "learning_rate": 4.720213170917396e-06, | |
| "loss": 1.6306, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.46738572162300973, | |
| "grad_norm": 2.6906657218933105, | |
| "learning_rate": 4.71830985915493e-06, | |
| "loss": 1.6492, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.46841294298921415, | |
| "grad_norm": 2.6957409381866455, | |
| "learning_rate": 4.716406547392463e-06, | |
| "loss": 1.5993, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.4694401643554186, | |
| "grad_norm": 2.904311418533325, | |
| "learning_rate": 4.714503235629996e-06, | |
| "loss": 1.6633, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.470467385721623, | |
| "grad_norm": 2.6853256225585938, | |
| "learning_rate": 4.71259992386753e-06, | |
| "loss": 1.5824, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.4714946070878274, | |
| "grad_norm": 2.4767656326293945, | |
| "learning_rate": 4.710696612105063e-06, | |
| "loss": 1.6145, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.47252182845403184, | |
| "grad_norm": 2.5569417476654053, | |
| "learning_rate": 4.708793300342596e-06, | |
| "loss": 1.6116, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.47252182845403184, | |
| "eval_loss": 1.8785003423690796, | |
| "eval_runtime": 37.401, | |
| "eval_samples_per_second": 26.737, | |
| "eval_steps_per_second": 1.123, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.47354904982023627, | |
| "grad_norm": 2.6568074226379395, | |
| "learning_rate": 4.70688998858013e-06, | |
| "loss": 1.6097, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 2.6002280712127686, | |
| "learning_rate": 4.704986676817663e-06, | |
| "loss": 1.6025, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.4756034925526451, | |
| "grad_norm": 2.6055355072021484, | |
| "learning_rate": 4.7030833650551965e-06, | |
| "loss": 1.6322, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.47663071391884954, | |
| "grad_norm": 2.6288487911224365, | |
| "learning_rate": 4.70118005329273e-06, | |
| "loss": 1.594, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.4776579352850539, | |
| "grad_norm": 2.6981899738311768, | |
| "learning_rate": 4.699276741530263e-06, | |
| "loss": 1.6707, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4786851566512583, | |
| "grad_norm": 2.6832222938537598, | |
| "learning_rate": 4.697373429767797e-06, | |
| "loss": 1.6435, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.47971237801746275, | |
| "grad_norm": 2.563159227371216, | |
| "learning_rate": 4.69547011800533e-06, | |
| "loss": 1.6249, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.48073959938366717, | |
| "grad_norm": 2.545778751373291, | |
| "learning_rate": 4.693566806242863e-06, | |
| "loss": 1.6309, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.4817668207498716, | |
| "grad_norm": 2.555227518081665, | |
| "learning_rate": 4.691663494480397e-06, | |
| "loss": 1.6128, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.482794042116076, | |
| "grad_norm": 2.612576723098755, | |
| "learning_rate": 4.689760182717929e-06, | |
| "loss": 1.6484, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.482794042116076, | |
| "eval_loss": 1.8684974908828735, | |
| "eval_runtime": 37.2607, | |
| "eval_samples_per_second": 26.838, | |
| "eval_steps_per_second": 1.127, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.48382126348228044, | |
| "grad_norm": 2.4981396198272705, | |
| "learning_rate": 4.6878568709554626e-06, | |
| "loss": 1.5393, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 2.793700695037842, | |
| "learning_rate": 4.685953559192996e-06, | |
| "loss": 1.608, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.4858757062146893, | |
| "grad_norm": 2.7605607509613037, | |
| "learning_rate": 4.684050247430529e-06, | |
| "loss": 1.6236, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.4869029275808937, | |
| "grad_norm": 2.413719892501831, | |
| "learning_rate": 4.682146935668063e-06, | |
| "loss": 1.5555, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.4879301489470981, | |
| "grad_norm": 2.9032249450683594, | |
| "learning_rate": 4.680243623905596e-06, | |
| "loss": 1.6042, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4889573703133025, | |
| "grad_norm": 2.5445175170898438, | |
| "learning_rate": 4.678340312143129e-06, | |
| "loss": 1.6265, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.4899845916795069, | |
| "grad_norm": 2.6955716609954834, | |
| "learning_rate": 4.676437000380663e-06, | |
| "loss": 1.5879, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.49101181304571134, | |
| "grad_norm": 2.8399500846862793, | |
| "learning_rate": 4.674533688618196e-06, | |
| "loss": 1.7009, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.49203903441191577, | |
| "grad_norm": 2.635035991668701, | |
| "learning_rate": 4.6726303768557295e-06, | |
| "loss": 1.6381, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.4930662557781202, | |
| "grad_norm": 2.7609052658081055, | |
| "learning_rate": 4.670727065093263e-06, | |
| "loss": 1.5492, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4930662557781202, | |
| "eval_loss": 1.8574503660202026, | |
| "eval_runtime": 37.2173, | |
| "eval_samples_per_second": 26.869, | |
| "eval_steps_per_second": 1.129, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4940934771443246, | |
| "grad_norm": 2.593766927719116, | |
| "learning_rate": 4.668823753330796e-06, | |
| "loss": 1.5693, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.49512069851052903, | |
| "grad_norm": 2.8000242710113525, | |
| "learning_rate": 4.6669204415683295e-06, | |
| "loss": 1.5998, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.49614791987673346, | |
| "grad_norm": 2.522688627243042, | |
| "learning_rate": 4.665017129805863e-06, | |
| "loss": 1.6653, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 2.854534864425659, | |
| "learning_rate": 4.663113818043396e-06, | |
| "loss": 1.6393, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.49820236260914225, | |
| "grad_norm": 2.5333967208862305, | |
| "learning_rate": 4.66121050628093e-06, | |
| "loss": 1.606, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.49922958397534667, | |
| "grad_norm": 2.565260171890259, | |
| "learning_rate": 4.659307194518463e-06, | |
| "loss": 1.6471, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.5002568053415511, | |
| "grad_norm": 2.570220947265625, | |
| "learning_rate": 4.6574038827559955e-06, | |
| "loss": 1.6023, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.5012840267077555, | |
| "grad_norm": 2.460740089416504, | |
| "learning_rate": 4.655500570993529e-06, | |
| "loss": 1.6208, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.50231124807396, | |
| "grad_norm": 2.6339426040649414, | |
| "learning_rate": 4.653597259231062e-06, | |
| "loss": 1.6533, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.5033384694401644, | |
| "grad_norm": 2.681044578552246, | |
| "learning_rate": 4.651693947468596e-06, | |
| "loss": 1.5437, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5033384694401644, | |
| "eval_loss": 1.8701337575912476, | |
| "eval_runtime": 37.1714, | |
| "eval_samples_per_second": 26.902, | |
| "eval_steps_per_second": 1.13, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5043656908063687, | |
| "grad_norm": 2.6900649070739746, | |
| "learning_rate": 4.649790635706129e-06, | |
| "loss": 1.6816, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.5053929121725732, | |
| "grad_norm": 2.6106340885162354, | |
| "learning_rate": 4.647887323943662e-06, | |
| "loss": 1.5784, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.5064201335387776, | |
| "grad_norm": 3.0704469680786133, | |
| "learning_rate": 4.645984012181196e-06, | |
| "loss": 1.6065, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.507447354904982, | |
| "grad_norm": 2.648425817489624, | |
| "learning_rate": 4.644080700418729e-06, | |
| "loss": 1.5134, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 2.509066343307495, | |
| "learning_rate": 4.642177388656262e-06, | |
| "loss": 1.6324, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5095017976373909, | |
| "grad_norm": 2.8628857135772705, | |
| "learning_rate": 4.640274076893796e-06, | |
| "loss": 1.5957, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.5105290190035953, | |
| "grad_norm": 2.83579683303833, | |
| "learning_rate": 4.638370765131328e-06, | |
| "loss": 1.6556, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.5115562403697997, | |
| "grad_norm": 2.6618151664733887, | |
| "learning_rate": 4.636467453368862e-06, | |
| "loss": 1.5738, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.5125834617360041, | |
| "grad_norm": 2.936943769454956, | |
| "learning_rate": 4.634564141606396e-06, | |
| "loss": 1.5597, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.5136106831022085, | |
| "grad_norm": 2.8520913124084473, | |
| "learning_rate": 4.632660829843929e-06, | |
| "loss": 1.6316, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5136106831022085, | |
| "eval_loss": 1.8548446893692017, | |
| "eval_runtime": 37.1878, | |
| "eval_samples_per_second": 26.891, | |
| "eval_steps_per_second": 1.129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.514637904468413, | |
| "grad_norm": 2.446373462677002, | |
| "learning_rate": 4.630757518081463e-06, | |
| "loss": 1.5533, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.5156651258346173, | |
| "grad_norm": 2.8339035511016846, | |
| "learning_rate": 4.628854206318996e-06, | |
| "loss": 1.6904, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.5166923472008218, | |
| "grad_norm": 2.664249897003174, | |
| "learning_rate": 4.626950894556529e-06, | |
| "loss": 1.5926, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.5177195685670262, | |
| "grad_norm": 2.681185483932495, | |
| "learning_rate": 4.625047582794062e-06, | |
| "loss": 1.6348, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.5187467899332306, | |
| "grad_norm": 2.468263864517212, | |
| "learning_rate": 4.623144271031595e-06, | |
| "loss": 1.5477, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.519774011299435, | |
| "grad_norm": 2.539066791534424, | |
| "learning_rate": 4.6212409592691286e-06, | |
| "loss": 1.5615, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.5208012326656395, | |
| "grad_norm": 2.822235345840454, | |
| "learning_rate": 4.619337647506662e-06, | |
| "loss": 1.6398, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.5218284540318439, | |
| "grad_norm": 2.6063523292541504, | |
| "learning_rate": 4.617434335744195e-06, | |
| "loss": 1.5992, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.5228556753980482, | |
| "grad_norm": 2.624810218811035, | |
| "learning_rate": 4.615531023981729e-06, | |
| "loss": 1.5708, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.5238828967642527, | |
| "grad_norm": 2.6324198246002197, | |
| "learning_rate": 4.613627712219262e-06, | |
| "loss": 1.5865, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5238828967642527, | |
| "eval_loss": 1.8442509174346924, | |
| "eval_runtime": 36.9899, | |
| "eval_samples_per_second": 27.034, | |
| "eval_steps_per_second": 1.135, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5249101181304571, | |
| "grad_norm": 2.5496973991394043, | |
| "learning_rate": 4.611724400456795e-06, | |
| "loss": 1.6048, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.5259373394966615, | |
| "grad_norm": 2.4150168895721436, | |
| "learning_rate": 4.609821088694329e-06, | |
| "loss": 1.6009, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.5269645608628659, | |
| "grad_norm": 2.8799378871917725, | |
| "learning_rate": 4.607917776931862e-06, | |
| "loss": 1.5761, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.5279917822290704, | |
| "grad_norm": 2.749016761779785, | |
| "learning_rate": 4.606014465169395e-06, | |
| "loss": 1.6202, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.5290190035952748, | |
| "grad_norm": 2.6993141174316406, | |
| "learning_rate": 4.604111153406928e-06, | |
| "loss": 1.632, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5300462249614792, | |
| "grad_norm": 2.9027445316314697, | |
| "learning_rate": 4.602207841644461e-06, | |
| "loss": 1.5352, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.5310734463276836, | |
| "grad_norm": 2.874267816543579, | |
| "learning_rate": 4.600304529881995e-06, | |
| "loss": 1.642, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.5321006676938881, | |
| "grad_norm": 2.6057357788085938, | |
| "learning_rate": 4.598401218119528e-06, | |
| "loss": 1.6179, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.5331278890600925, | |
| "grad_norm": 2.658812999725342, | |
| "learning_rate": 4.5964979063570614e-06, | |
| "loss": 1.6285, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.5341551104262968, | |
| "grad_norm": 2.667215585708618, | |
| "learning_rate": 4.594594594594596e-06, | |
| "loss": 1.5694, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5341551104262968, | |
| "eval_loss": 1.8490455150604248, | |
| "eval_runtime": 37.0914, | |
| "eval_samples_per_second": 26.96, | |
| "eval_steps_per_second": 1.132, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5351823317925013, | |
| "grad_norm": 2.5979607105255127, | |
| "learning_rate": 4.592691282832128e-06, | |
| "loss": 1.6091, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.5362095531587057, | |
| "grad_norm": 2.552816152572632, | |
| "learning_rate": 4.5907879710696615e-06, | |
| "loss": 1.6145, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.5372367745249101, | |
| "grad_norm": 2.575045347213745, | |
| "learning_rate": 4.588884659307195e-06, | |
| "loss": 1.5444, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.5382639958911145, | |
| "grad_norm": 2.650202751159668, | |
| "learning_rate": 4.586981347544728e-06, | |
| "loss": 1.6181, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.539291217257319, | |
| "grad_norm": 2.7869739532470703, | |
| "learning_rate": 4.585078035782262e-06, | |
| "loss": 1.563, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5403184386235234, | |
| "grad_norm": 2.6828651428222656, | |
| "learning_rate": 4.583174724019795e-06, | |
| "loss": 1.6004, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.5413456599897278, | |
| "grad_norm": 2.552387237548828, | |
| "learning_rate": 4.581271412257328e-06, | |
| "loss": 1.5351, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 2.785661458969116, | |
| "learning_rate": 4.579368100494862e-06, | |
| "loss": 1.5264, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.5434001027221366, | |
| "grad_norm": 2.832939863204956, | |
| "learning_rate": 4.577464788732395e-06, | |
| "loss": 1.6261, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.544427324088341, | |
| "grad_norm": 2.641766309738159, | |
| "learning_rate": 4.575561476969928e-06, | |
| "loss": 1.6019, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.544427324088341, | |
| "eval_loss": 1.8477164506912231, | |
| "eval_runtime": 37.1444, | |
| "eval_samples_per_second": 26.922, | |
| "eval_steps_per_second": 1.131, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 3.0502524375915527, | |
| "learning_rate": 4.573658165207461e-06, | |
| "loss": 1.6436, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.5464817668207499, | |
| "grad_norm": 2.64772891998291, | |
| "learning_rate": 4.571754853444994e-06, | |
| "loss": 1.6085, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.5475089881869543, | |
| "grad_norm": 2.549692392349243, | |
| "learning_rate": 4.569851541682528e-06, | |
| "loss": 1.5977, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.5485362095531587, | |
| "grad_norm": 2.719322681427002, | |
| "learning_rate": 4.567948229920061e-06, | |
| "loss": 1.5659, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.5495634309193631, | |
| "grad_norm": 2.5005698204040527, | |
| "learning_rate": 4.566044918157594e-06, | |
| "loss": 1.5301, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5505906522855676, | |
| "grad_norm": 2.7379472255706787, | |
| "learning_rate": 4.564141606395128e-06, | |
| "loss": 1.5721, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.551617873651772, | |
| "grad_norm": 2.6673905849456787, | |
| "learning_rate": 4.562238294632661e-06, | |
| "loss": 1.6105, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.5526450950179764, | |
| "grad_norm": 2.6745669841766357, | |
| "learning_rate": 4.5603349828701945e-06, | |
| "loss": 1.577, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.5536723163841808, | |
| "grad_norm": 2.593475341796875, | |
| "learning_rate": 4.558431671107728e-06, | |
| "loss": 1.6084, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "grad_norm": 2.6577041149139404, | |
| "learning_rate": 4.556528359345261e-06, | |
| "loss": 1.6417, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5546995377503852, | |
| "eval_loss": 1.839761734008789, | |
| "eval_runtime": 37.1765, | |
| "eval_samples_per_second": 26.899, | |
| "eval_steps_per_second": 1.13, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5557267591165896, | |
| "grad_norm": 2.6834933757781982, | |
| "learning_rate": 4.5546250475827946e-06, | |
| "loss": 1.5803, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.556753980482794, | |
| "grad_norm": 2.464665174484253, | |
| "learning_rate": 4.552721735820328e-06, | |
| "loss": 1.5324, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.5577812018489985, | |
| "grad_norm": 2.4488964080810547, | |
| "learning_rate": 4.550818424057861e-06, | |
| "loss": 1.5767, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.5588084232152029, | |
| "grad_norm": 2.763124465942383, | |
| "learning_rate": 4.548915112295395e-06, | |
| "loss": 1.5903, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.5598356445814073, | |
| "grad_norm": 2.7473502159118652, | |
| "learning_rate": 4.547011800532928e-06, | |
| "loss": 1.5966, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5608628659476117, | |
| "grad_norm": 3.050267219543457, | |
| "learning_rate": 4.545108488770461e-06, | |
| "loss": 1.5492, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.5618900873138162, | |
| "grad_norm": 2.910439968109131, | |
| "learning_rate": 4.543205177007995e-06, | |
| "loss": 1.6357, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.5629173086800205, | |
| "grad_norm": 2.5621109008789062, | |
| "learning_rate": 4.541301865245527e-06, | |
| "loss": 1.5693, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.5639445300462249, | |
| "grad_norm": 2.7492010593414307, | |
| "learning_rate": 4.539398553483061e-06, | |
| "loss": 1.615, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "grad_norm": 2.6651856899261475, | |
| "learning_rate": 4.537495241720594e-06, | |
| "loss": 1.5804, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "eval_loss": 1.8344007730484009, | |
| "eval_runtime": 37.1218, | |
| "eval_samples_per_second": 26.938, | |
| "eval_steps_per_second": 1.131, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5659989727786338, | |
| "grad_norm": 2.5933356285095215, | |
| "learning_rate": 4.535591929958127e-06, | |
| "loss": 1.6108, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.5670261941448382, | |
| "grad_norm": 2.660522222518921, | |
| "learning_rate": 4.533688618195661e-06, | |
| "loss": 1.5977, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.5680534155110426, | |
| "grad_norm": 2.5636332035064697, | |
| "learning_rate": 4.531785306433194e-06, | |
| "loss": 1.5802, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.5690806368772471, | |
| "grad_norm": 2.759533166885376, | |
| "learning_rate": 4.529881994670727e-06, | |
| "loss": 1.5656, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.5701078582434514, | |
| "grad_norm": 2.6530680656433105, | |
| "learning_rate": 4.527978682908261e-06, | |
| "loss": 1.5693, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.5711350796096559, | |
| "grad_norm": 2.688427448272705, | |
| "learning_rate": 4.526075371145794e-06, | |
| "loss": 1.5769, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.5721623009758603, | |
| "grad_norm": 2.5163164138793945, | |
| "learning_rate": 4.5241720593833275e-06, | |
| "loss": 1.593, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.5731895223420647, | |
| "grad_norm": 2.612612724304199, | |
| "learning_rate": 4.52226874762086e-06, | |
| "loss": 1.5854, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.5742167437082691, | |
| "grad_norm": 2.647853374481201, | |
| "learning_rate": 4.520365435858393e-06, | |
| "loss": 1.6085, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.5752439650744735, | |
| "grad_norm": 2.7160937786102295, | |
| "learning_rate": 4.518462124095928e-06, | |
| "loss": 1.6353, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5752439650744735, | |
| "eval_loss": 1.8585809469223022, | |
| "eval_runtime": 37.328, | |
| "eval_samples_per_second": 26.79, | |
| "eval_steps_per_second": 1.125, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.576271186440678, | |
| "grad_norm": 2.9025261402130127, | |
| "learning_rate": 4.516558812333461e-06, | |
| "loss": 1.5903, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.5772984078068824, | |
| "grad_norm": 2.5665547847747803, | |
| "learning_rate": 4.514655500570994e-06, | |
| "loss": 1.5775, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.5783256291730868, | |
| "grad_norm": 2.591381311416626, | |
| "learning_rate": 4.512752188808528e-06, | |
| "loss": 1.6387, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.5793528505392912, | |
| "grad_norm": 2.7540411949157715, | |
| "learning_rate": 4.510848877046061e-06, | |
| "loss": 1.6432, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.5803800719054957, | |
| "grad_norm": 2.6911778450012207, | |
| "learning_rate": 4.5089455652835936e-06, | |
| "loss": 1.6078, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5814072932717, | |
| "grad_norm": 2.609619140625, | |
| "learning_rate": 4.507042253521127e-06, | |
| "loss": 1.5709, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.5824345146379045, | |
| "grad_norm": 2.4930672645568848, | |
| "learning_rate": 4.50513894175866e-06, | |
| "loss": 1.5305, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.5834617360041089, | |
| "grad_norm": 2.490992307662964, | |
| "learning_rate": 4.503235629996194e-06, | |
| "loss": 1.61, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.5844889573703133, | |
| "grad_norm": 2.7229626178741455, | |
| "learning_rate": 4.501332318233727e-06, | |
| "loss": 1.5996, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.5855161787365177, | |
| "grad_norm": 2.5289995670318604, | |
| "learning_rate": 4.49942900647126e-06, | |
| "loss": 1.5624, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5855161787365177, | |
| "eval_loss": 1.867126226425171, | |
| "eval_runtime": 37.4117, | |
| "eval_samples_per_second": 26.73, | |
| "eval_steps_per_second": 1.123, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5865434001027221, | |
| "grad_norm": 2.6244945526123047, | |
| "learning_rate": 4.497525694708794e-06, | |
| "loss": 1.6154, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 2.4343698024749756, | |
| "learning_rate": 4.495622382946327e-06, | |
| "loss": 1.5967, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.588597842835131, | |
| "grad_norm": 2.5899314880371094, | |
| "learning_rate": 4.4937190711838605e-06, | |
| "loss": 1.5601, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.5896250642013354, | |
| "grad_norm": 2.829028367996216, | |
| "learning_rate": 4.491815759421394e-06, | |
| "loss": 1.6315, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.5906522855675398, | |
| "grad_norm": 2.748849868774414, | |
| "learning_rate": 4.489912447658926e-06, | |
| "loss": 1.5591, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5916795069337443, | |
| "grad_norm": 2.7016541957855225, | |
| "learning_rate": 4.48800913589646e-06, | |
| "loss": 1.5575, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.5927067282999486, | |
| "grad_norm": 2.6260931491851807, | |
| "learning_rate": 4.486105824133993e-06, | |
| "loss": 1.5823, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.593733949666153, | |
| "grad_norm": 2.797224998474121, | |
| "learning_rate": 4.4842025123715264e-06, | |
| "loss": 1.5902, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.5947611710323575, | |
| "grad_norm": 2.671342611312866, | |
| "learning_rate": 4.48229920060906e-06, | |
| "loss": 1.551, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.5957883923985619, | |
| "grad_norm": 2.626988172531128, | |
| "learning_rate": 4.480395888846594e-06, | |
| "loss": 1.5312, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5957883923985619, | |
| "eval_loss": 1.8685871362686157, | |
| "eval_runtime": 37.388, | |
| "eval_samples_per_second": 26.747, | |
| "eval_steps_per_second": 1.123, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5968156137647663, | |
| "grad_norm": 2.8422539234161377, | |
| "learning_rate": 4.478492577084127e-06, | |
| "loss": 1.6393, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.5978428351309707, | |
| "grad_norm": 2.6877822875976562, | |
| "learning_rate": 4.47658926532166e-06, | |
| "loss": 1.5376, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.5988700564971752, | |
| "grad_norm": 2.736452341079712, | |
| "learning_rate": 4.474685953559193e-06, | |
| "loss": 1.5798, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.5998972778633795, | |
| "grad_norm": 2.732513904571533, | |
| "learning_rate": 4.472782641796727e-06, | |
| "loss": 1.6897, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.600924499229584, | |
| "grad_norm": 2.8732001781463623, | |
| "learning_rate": 4.47087933003426e-06, | |
| "loss": 1.533, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.6019517205957884, | |
| "grad_norm": 2.6099846363067627, | |
| "learning_rate": 4.468976018271793e-06, | |
| "loss": 1.5481, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.6029789419619929, | |
| "grad_norm": 2.754856586456299, | |
| "learning_rate": 4.467072706509327e-06, | |
| "loss": 1.5497, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.6040061633281972, | |
| "grad_norm": 2.6755611896514893, | |
| "learning_rate": 4.46516939474686e-06, | |
| "loss": 1.5882, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.6050333846944016, | |
| "grad_norm": 2.632248640060425, | |
| "learning_rate": 4.463266082984393e-06, | |
| "loss": 1.5481, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 2.6425793170928955, | |
| "learning_rate": 4.461362771221927e-06, | |
| "loss": 1.6607, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "eval_loss": 1.863004446029663, | |
| "eval_runtime": 37.2064, | |
| "eval_samples_per_second": 26.877, | |
| "eval_steps_per_second": 1.129, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6070878274268104, | |
| "grad_norm": 2.6340153217315674, | |
| "learning_rate": 4.45945945945946e-06, | |
| "loss": 1.5474, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.6081150487930149, | |
| "grad_norm": 2.7601606845855713, | |
| "learning_rate": 4.457556147696993e-06, | |
| "loss": 1.5569, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.6091422701592193, | |
| "grad_norm": 2.8151822090148926, | |
| "learning_rate": 4.455652835934526e-06, | |
| "loss": 1.6441, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 2.757577419281006, | |
| "learning_rate": 4.453749524172059e-06, | |
| "loss": 1.6339, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.6111967128916281, | |
| "grad_norm": 2.6828997135162354, | |
| "learning_rate": 4.451846212409593e-06, | |
| "loss": 1.5885, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6122239342578326, | |
| "grad_norm": 2.6645700931549072, | |
| "learning_rate": 4.449942900647126e-06, | |
| "loss": 1.5866, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.613251155624037, | |
| "grad_norm": 2.572789430618286, | |
| "learning_rate": 4.4480395888846595e-06, | |
| "loss": 1.5255, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.6142783769902413, | |
| "grad_norm": 2.6281981468200684, | |
| "learning_rate": 4.446136277122193e-06, | |
| "loss": 1.5905, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.6153055983564458, | |
| "grad_norm": 2.6164042949676514, | |
| "learning_rate": 4.444232965359726e-06, | |
| "loss": 1.5274, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.6163328197226502, | |
| "grad_norm": 2.606343984603882, | |
| "learning_rate": 4.4423296535972596e-06, | |
| "loss": 1.5846, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6163328197226502, | |
| "eval_loss": 1.8634170293807983, | |
| "eval_runtime": 37.1568, | |
| "eval_samples_per_second": 26.913, | |
| "eval_steps_per_second": 1.13, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6173600410888547, | |
| "grad_norm": 2.8743226528167725, | |
| "learning_rate": 4.440426341834793e-06, | |
| "loss": 1.538, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.618387262455059, | |
| "grad_norm": 2.5392212867736816, | |
| "learning_rate": 4.438523030072326e-06, | |
| "loss": 1.585, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.6194144838212635, | |
| "grad_norm": 2.715684413909912, | |
| "learning_rate": 4.43661971830986e-06, | |
| "loss": 1.6028, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.6204417051874679, | |
| "grad_norm": 2.514934778213501, | |
| "learning_rate": 4.434716406547393e-06, | |
| "loss": 1.5525, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.6214689265536724, | |
| "grad_norm": 2.685807943344116, | |
| "learning_rate": 4.432813094784926e-06, | |
| "loss": 1.5456, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6224961479198767, | |
| "grad_norm": 2.848557949066162, | |
| "learning_rate": 4.43090978302246e-06, | |
| "loss": 1.6017, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.6235233692860811, | |
| "grad_norm": 2.6820950508117676, | |
| "learning_rate": 4.429006471259993e-06, | |
| "loss": 1.573, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.6245505906522856, | |
| "grad_norm": 2.493544340133667, | |
| "learning_rate": 4.4271031594975265e-06, | |
| "loss": 1.5576, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.6255778120184899, | |
| "grad_norm": 2.6240968704223633, | |
| "learning_rate": 4.425199847735059e-06, | |
| "loss": 1.5312, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.6266050333846944, | |
| "grad_norm": 2.516113042831421, | |
| "learning_rate": 4.423296535972592e-06, | |
| "loss": 1.5284, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6266050333846944, | |
| "eval_loss": 1.8370482921600342, | |
| "eval_runtime": 36.9401, | |
| "eval_samples_per_second": 27.071, | |
| "eval_steps_per_second": 1.137, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6276322547508988, | |
| "grad_norm": 2.8341944217681885, | |
| "learning_rate": 4.421393224210126e-06, | |
| "loss": 1.5609, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.6286594761171033, | |
| "grad_norm": 2.5433242321014404, | |
| "learning_rate": 4.419489912447659e-06, | |
| "loss": 1.5253, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.6296866974833076, | |
| "grad_norm": 2.6761138439178467, | |
| "learning_rate": 4.4175866006851924e-06, | |
| "loss": 1.6171, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.6307139188495121, | |
| "grad_norm": 2.570707321166992, | |
| "learning_rate": 4.415683288922726e-06, | |
| "loss": 1.5766, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.6317411402157165, | |
| "grad_norm": 2.5421109199523926, | |
| "learning_rate": 4.413779977160259e-06, | |
| "loss": 1.5616, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 2.6767091751098633, | |
| "learning_rate": 4.4118766653977925e-06, | |
| "loss": 1.5531, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.6337955829481253, | |
| "grad_norm": 2.7730000019073486, | |
| "learning_rate": 4.409973353635326e-06, | |
| "loss": 1.6224, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.6348228043143297, | |
| "grad_norm": 2.7248494625091553, | |
| "learning_rate": 4.408070041872859e-06, | |
| "loss": 1.5752, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.6358500256805342, | |
| "grad_norm": 2.5071568489074707, | |
| "learning_rate": 4.406166730110393e-06, | |
| "loss": 1.5178, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.6368772470467385, | |
| "grad_norm": 2.5583243370056152, | |
| "learning_rate": 4.404263418347925e-06, | |
| "loss": 1.5298, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6368772470467385, | |
| "eval_loss": 1.833156943321228, | |
| "eval_runtime": 37.1108, | |
| "eval_samples_per_second": 26.946, | |
| "eval_steps_per_second": 1.132, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.637904468412943, | |
| "grad_norm": 2.492332696914673, | |
| "learning_rate": 4.402360106585459e-06, | |
| "loss": 1.5443, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.6389316897791474, | |
| "grad_norm": 2.5734798908233643, | |
| "learning_rate": 4.400456794822993e-06, | |
| "loss": 1.5362, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.6399589111453519, | |
| "grad_norm": 2.7597742080688477, | |
| "learning_rate": 4.398553483060526e-06, | |
| "loss": 1.56, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.6409861325115562, | |
| "grad_norm": 2.6911630630493164, | |
| "learning_rate": 4.396650171298059e-06, | |
| "loss": 1.5138, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.6420133538777607, | |
| "grad_norm": 2.596557378768921, | |
| "learning_rate": 4.394746859535593e-06, | |
| "loss": 1.5381, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6430405752439651, | |
| "grad_norm": 2.5787081718444824, | |
| "learning_rate": 4.392843547773125e-06, | |
| "loss": 1.5284, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.6440677966101694, | |
| "grad_norm": 2.5975289344787598, | |
| "learning_rate": 4.390940236010659e-06, | |
| "loss": 1.5359, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.6450950179763739, | |
| "grad_norm": 2.5175442695617676, | |
| "learning_rate": 4.389036924248192e-06, | |
| "loss": 1.5608, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.6461222393425783, | |
| "grad_norm": 2.535139322280884, | |
| "learning_rate": 4.387133612485725e-06, | |
| "loss": 1.5856, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.6471494607087828, | |
| "grad_norm": 2.5596396923065186, | |
| "learning_rate": 4.385230300723259e-06, | |
| "loss": 1.5467, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6471494607087828, | |
| "eval_loss": 1.835809588432312, | |
| "eval_runtime": 37.1073, | |
| "eval_samples_per_second": 26.949, | |
| "eval_steps_per_second": 1.132, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6481766820749871, | |
| "grad_norm": 2.691441297531128, | |
| "learning_rate": 4.383326988960792e-06, | |
| "loss": 1.5516, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.6492039034411916, | |
| "grad_norm": 2.534902811050415, | |
| "learning_rate": 4.3814236771983255e-06, | |
| "loss": 1.5215, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.650231124807396, | |
| "grad_norm": 2.626211643218994, | |
| "learning_rate": 4.379520365435859e-06, | |
| "loss": 1.5811, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.6512583461736005, | |
| "grad_norm": 2.6646480560302734, | |
| "learning_rate": 4.377617053673392e-06, | |
| "loss": 1.5674, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.6522855675398048, | |
| "grad_norm": 2.5728375911712646, | |
| "learning_rate": 4.3757137419109256e-06, | |
| "loss": 1.5655, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6533127889060092, | |
| "grad_norm": 2.72817325592041, | |
| "learning_rate": 4.373810430148459e-06, | |
| "loss": 1.6283, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.6543400102722137, | |
| "grad_norm": 2.5395050048828125, | |
| "learning_rate": 4.3719071183859914e-06, | |
| "loss": 1.5191, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.655367231638418, | |
| "grad_norm": 2.964163064956665, | |
| "learning_rate": 4.370003806623525e-06, | |
| "loss": 1.5839, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.6563944530046225, | |
| "grad_norm": 2.517214298248291, | |
| "learning_rate": 4.368100494861058e-06, | |
| "loss": 1.5278, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.6574216743708269, | |
| "grad_norm": 2.765145778656006, | |
| "learning_rate": 4.3661971830985915e-06, | |
| "loss": 1.5718, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6574216743708269, | |
| "eval_loss": 1.8324981927871704, | |
| "eval_runtime": 37.0883, | |
| "eval_samples_per_second": 26.963, | |
| "eval_steps_per_second": 1.132, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6584488957370314, | |
| "grad_norm": 2.463439464569092, | |
| "learning_rate": 4.364293871336126e-06, | |
| "loss": 1.5378, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.6594761171032357, | |
| "grad_norm": 2.7756192684173584, | |
| "learning_rate": 4.362390559573659e-06, | |
| "loss": 1.5601, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.6605033384694402, | |
| "grad_norm": 2.4134342670440674, | |
| "learning_rate": 4.3604872478111925e-06, | |
| "loss": 1.5252, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.6615305598356446, | |
| "grad_norm": 2.4549670219421387, | |
| "learning_rate": 4.358583936048725e-06, | |
| "loss": 1.4602, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.662557781201849, | |
| "grad_norm": 2.6815311908721924, | |
| "learning_rate": 4.356680624286258e-06, | |
| "loss": 1.5865, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.6635850025680534, | |
| "grad_norm": 2.5216286182403564, | |
| "learning_rate": 4.354777312523792e-06, | |
| "loss": 1.5432, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.6646122239342578, | |
| "grad_norm": 2.5547335147857666, | |
| "learning_rate": 4.352874000761325e-06, | |
| "loss": 1.59, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.6656394453004623, | |
| "grad_norm": 2.587646484375, | |
| "learning_rate": 4.3509706889988584e-06, | |
| "loss": 1.5351, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.530768871307373, | |
| "learning_rate": 4.349067377236392e-06, | |
| "loss": 1.603, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.6676938880328711, | |
| "grad_norm": 2.727213144302368, | |
| "learning_rate": 4.347164065473925e-06, | |
| "loss": 1.6032, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6676938880328711, | |
| "eval_loss": 1.8441001176834106, | |
| "eval_runtime": 37.0797, | |
| "eval_samples_per_second": 26.969, | |
| "eval_steps_per_second": 1.133, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6687211093990755, | |
| "grad_norm": 2.750441312789917, | |
| "learning_rate": 4.3452607537114585e-06, | |
| "loss": 1.6172, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.66974833076528, | |
| "grad_norm": 2.571692705154419, | |
| "learning_rate": 4.343357441948992e-06, | |
| "loss": 1.528, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.6707755521314843, | |
| "grad_norm": 2.5415565967559814, | |
| "learning_rate": 4.341454130186525e-06, | |
| "loss": 1.5629, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.6718027734976888, | |
| "grad_norm": 2.4970591068267822, | |
| "learning_rate": 4.339550818424058e-06, | |
| "loss": 1.5299, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.6728299948638932, | |
| "grad_norm": 2.5283010005950928, | |
| "learning_rate": 4.337647506661591e-06, | |
| "loss": 1.5149, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.6738572162300975, | |
| "grad_norm": 2.5205166339874268, | |
| "learning_rate": 4.3357441948991245e-06, | |
| "loss": 1.5486, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.674884437596302, | |
| "grad_norm": 2.4621481895446777, | |
| "learning_rate": 4.333840883136658e-06, | |
| "loss": 1.5769, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.6759116589625064, | |
| "grad_norm": 2.5954174995422363, | |
| "learning_rate": 4.331937571374191e-06, | |
| "loss": 1.5242, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.6769388803287109, | |
| "grad_norm": 2.553523063659668, | |
| "learning_rate": 4.3300342596117246e-06, | |
| "loss": 1.5339, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 2.5289323329925537, | |
| "learning_rate": 4.328130947849258e-06, | |
| "loss": 1.5371, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "eval_loss": 1.8562791347503662, | |
| "eval_runtime": 37.1299, | |
| "eval_samples_per_second": 26.932, | |
| "eval_steps_per_second": 1.131, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6789933230611197, | |
| "grad_norm": 2.537010908126831, | |
| "learning_rate": 4.326227636086791e-06, | |
| "loss": 1.5005, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.6800205444273241, | |
| "grad_norm": 2.6716437339782715, | |
| "learning_rate": 4.324324324324325e-06, | |
| "loss": 1.5501, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.6810477657935285, | |
| "grad_norm": 2.4969863891601562, | |
| "learning_rate": 4.322421012561858e-06, | |
| "loss": 1.5474, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.6820749871597329, | |
| "grad_norm": 2.6803722381591797, | |
| "learning_rate": 4.320517700799391e-06, | |
| "loss": 1.5397, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.6831022085259374, | |
| "grad_norm": 2.6370725631713867, | |
| "learning_rate": 4.318614389036925e-06, | |
| "loss": 1.6274, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.6841294298921418, | |
| "grad_norm": 2.6329426765441895, | |
| "learning_rate": 4.316711077274458e-06, | |
| "loss": 1.6015, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.6851566512583461, | |
| "grad_norm": 2.6113548278808594, | |
| "learning_rate": 4.3148077655119915e-06, | |
| "loss": 1.5015, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.6861838726245506, | |
| "grad_norm": 2.718801498413086, | |
| "learning_rate": 4.312904453749525e-06, | |
| "loss": 1.597, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.687211093990755, | |
| "grad_norm": 2.638871908187866, | |
| "learning_rate": 4.311001141987058e-06, | |
| "loss": 1.5528, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.6882383153569595, | |
| "grad_norm": 2.74849534034729, | |
| "learning_rate": 4.3090978302245916e-06, | |
| "loss": 1.5627, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6882383153569595, | |
| "eval_loss": 1.8493062257766724, | |
| "eval_runtime": 37.2964, | |
| "eval_samples_per_second": 26.812, | |
| "eval_steps_per_second": 1.126, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6892655367231638, | |
| "grad_norm": 2.6839728355407715, | |
| "learning_rate": 4.307194518462124e-06, | |
| "loss": 1.552, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.6902927580893683, | |
| "grad_norm": 2.844496488571167, | |
| "learning_rate": 4.3052912066996574e-06, | |
| "loss": 1.6218, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.6913199794555727, | |
| "grad_norm": 2.4792141914367676, | |
| "learning_rate": 4.303387894937191e-06, | |
| "loss": 1.592, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.6923472008217771, | |
| "grad_norm": 2.4852263927459717, | |
| "learning_rate": 4.301484583174724e-06, | |
| "loss": 1.5165, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.6933744221879815, | |
| "grad_norm": 2.5438406467437744, | |
| "learning_rate": 4.2995812714122575e-06, | |
| "loss": 1.5109, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6944016435541859, | |
| "grad_norm": 2.5431931018829346, | |
| "learning_rate": 4.297677959649791e-06, | |
| "loss": 1.5345, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.6954288649203904, | |
| "grad_norm": 2.650897979736328, | |
| "learning_rate": 4.295774647887324e-06, | |
| "loss": 1.5607, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.6964560862865947, | |
| "grad_norm": 2.721167802810669, | |
| "learning_rate": 4.293871336124858e-06, | |
| "loss": 1.5764, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.6974833076527992, | |
| "grad_norm": 2.5402960777282715, | |
| "learning_rate": 4.291968024362391e-06, | |
| "loss": 1.5505, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.6985105290190036, | |
| "grad_norm": 2.6878864765167236, | |
| "learning_rate": 4.290064712599924e-06, | |
| "loss": 1.5821, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6985105290190036, | |
| "eval_loss": 1.8400572538375854, | |
| "eval_runtime": 37.3885, | |
| "eval_samples_per_second": 26.746, | |
| "eval_steps_per_second": 1.123, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.699537750385208, | |
| "grad_norm": 2.6703765392303467, | |
| "learning_rate": 4.288161400837458e-06, | |
| "loss": 1.5794, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.7005649717514124, | |
| "grad_norm": 2.626725196838379, | |
| "learning_rate": 4.286258089074991e-06, | |
| "loss": 1.4986, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.7015921931176169, | |
| "grad_norm": 2.6062862873077393, | |
| "learning_rate": 4.284354777312524e-06, | |
| "loss": 1.5606, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.7026194144838213, | |
| "grad_norm": 2.6359503269195557, | |
| "learning_rate": 4.282451465550058e-06, | |
| "loss": 1.5174, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.7036466358500256, | |
| "grad_norm": 2.8453221321105957, | |
| "learning_rate": 4.280548153787591e-06, | |
| "loss": 1.543, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7046738572162301, | |
| "grad_norm": 2.5195140838623047, | |
| "learning_rate": 4.2786448420251245e-06, | |
| "loss": 1.5462, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.7057010785824345, | |
| "grad_norm": 2.757230281829834, | |
| "learning_rate": 4.276741530262658e-06, | |
| "loss": 1.5033, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.706728299948639, | |
| "grad_norm": 2.708148241043091, | |
| "learning_rate": 4.27483821850019e-06, | |
| "loss": 1.5286, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.7077555213148433, | |
| "grad_norm": 2.6836555004119873, | |
| "learning_rate": 4.272934906737724e-06, | |
| "loss": 1.5973, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.7087827426810478, | |
| "grad_norm": 2.6970176696777344, | |
| "learning_rate": 4.271031594975257e-06, | |
| "loss": 1.5844, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7087827426810478, | |
| "eval_loss": 1.8414137363433838, | |
| "eval_runtime": 37.3847, | |
| "eval_samples_per_second": 26.749, | |
| "eval_steps_per_second": 1.123, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7098099640472522, | |
| "grad_norm": 2.69212007522583, | |
| "learning_rate": 4.2691282832127905e-06, | |
| "loss": 1.5817, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.7108371854134566, | |
| "grad_norm": 2.6203925609588623, | |
| "learning_rate": 4.267224971450324e-06, | |
| "loss": 1.5411, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.711864406779661, | |
| "grad_norm": 2.418916940689087, | |
| "learning_rate": 4.265321659687857e-06, | |
| "loss": 1.483, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.7128916281458655, | |
| "grad_norm": 2.784196615219116, | |
| "learning_rate": 4.2634183479253906e-06, | |
| "loss": 1.5286, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.7139188495120699, | |
| "grad_norm": 2.675043821334839, | |
| "learning_rate": 4.261515036162924e-06, | |
| "loss": 1.5067, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.7149460708782742, | |
| "grad_norm": 2.7075769901275635, | |
| "learning_rate": 4.259611724400457e-06, | |
| "loss": 1.5316, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.7159732922444787, | |
| "grad_norm": 2.911898612976074, | |
| "learning_rate": 4.257708412637991e-06, | |
| "loss": 1.5203, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.7170005136106831, | |
| "grad_norm": 2.748126983642578, | |
| "learning_rate": 4.255805100875523e-06, | |
| "loss": 1.465, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.7180277349768875, | |
| "grad_norm": 2.6017746925354004, | |
| "learning_rate": 4.2539017891130565e-06, | |
| "loss": 1.4956, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.7190549563430919, | |
| "grad_norm": 3.0877811908721924, | |
| "learning_rate": 4.25199847735059e-06, | |
| "loss": 1.587, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7190549563430919, | |
| "eval_loss": 1.8209773302078247, | |
| "eval_runtime": 37.1796, | |
| "eval_samples_per_second": 26.896, | |
| "eval_steps_per_second": 1.13, | |
| "step": 700 | |
| } | |
| ], | |
| "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": 2.182116586553344e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |