| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00684931506849315, | |
| "grad_norm": 8.315443992614746, | |
| "learning_rate": 1.3698630136986302e-06, | |
| "loss": 1.7877, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03424657534246575, | |
| "grad_norm": 7.738222599029541, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 1.7409, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 7.3871989250183105, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 1.6148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10273972602739725, | |
| "grad_norm": 4.8537421226501465, | |
| "learning_rate": 2.0547945205479453e-05, | |
| "loss": 1.3419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 2.9443578720092773, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 1.1536, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17123287671232876, | |
| "grad_norm": 1.285714864730835, | |
| "learning_rate": 3.424657534246575e-05, | |
| "loss": 1.0747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 0.9238005876541138, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 0.9979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23972602739726026, | |
| "grad_norm": 0.6104592680931091, | |
| "learning_rate": 4.794520547945205e-05, | |
| "loss": 0.9327, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.6212075352668762, | |
| "learning_rate": 5.479452054794521e-05, | |
| "loss": 0.8795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3082191780821918, | |
| "grad_norm": 0.4866364002227783, | |
| "learning_rate": 6.164383561643835e-05, | |
| "loss": 0.859, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 0.33247315883636475, | |
| "learning_rate": 6.84931506849315e-05, | |
| "loss": 0.831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3767123287671233, | |
| "grad_norm": 0.33287501335144043, | |
| "learning_rate": 7.534246575342466e-05, | |
| "loss": 0.8186, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 0.40740513801574707, | |
| "learning_rate": 8.219178082191781e-05, | |
| "loss": 0.8011, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4452054794520548, | |
| "grad_norm": 0.766364574432373, | |
| "learning_rate": 8.904109589041096e-05, | |
| "loss": 0.7926, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 0.7360146045684814, | |
| "learning_rate": 9.58904109589041e-05, | |
| "loss": 0.7767, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5136986301369864, | |
| "grad_norm": 0.3070668578147888, | |
| "learning_rate": 0.00010273972602739728, | |
| "loss": 0.7761, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.7730902433395386, | |
| "learning_rate": 0.00010958904109589041, | |
| "loss": 0.778, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5821917808219178, | |
| "grad_norm": 0.4104633033275604, | |
| "learning_rate": 0.00011643835616438356, | |
| "loss": 0.7555, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 0.2929731011390686, | |
| "learning_rate": 0.0001232876712328767, | |
| "loss": 0.7522, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6506849315068494, | |
| "grad_norm": 0.33198031783103943, | |
| "learning_rate": 0.00013013698630136988, | |
| "loss": 0.7533, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 0.35038191080093384, | |
| "learning_rate": 0.000136986301369863, | |
| "loss": 0.7433, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7191780821917808, | |
| "grad_norm": 0.380381315946579, | |
| "learning_rate": 0.00014383561643835618, | |
| "loss": 0.7446, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 0.3344345986843109, | |
| "learning_rate": 0.00015068493150684933, | |
| "loss": 0.7325, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7876712328767124, | |
| "grad_norm": 0.5609772205352783, | |
| "learning_rate": 0.00015753424657534247, | |
| "loss": 0.7339, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.5873807668685913, | |
| "learning_rate": 0.00016438356164383562, | |
| "loss": 0.7253, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8561643835616438, | |
| "grad_norm": 0.5051682591438293, | |
| "learning_rate": 0.00017123287671232877, | |
| "loss": 0.7272, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 0.3545282483100891, | |
| "learning_rate": 0.00017808219178082192, | |
| "loss": 0.7126, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9246575342465754, | |
| "grad_norm": 0.40065136551856995, | |
| "learning_rate": 0.0001849315068493151, | |
| "loss": 0.7165, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 0.6324636936187744, | |
| "learning_rate": 0.0001917808219178082, | |
| "loss": 0.7096, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9931506849315068, | |
| "grad_norm": 0.8474305868148804, | |
| "learning_rate": 0.00019863013698630139, | |
| "loss": 0.7127, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7009907960891724, | |
| "eval_runtime": 0.6831, | |
| "eval_samples_per_second": 8.783, | |
| "eval_steps_per_second": 1.464, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.0273972602739727, | |
| "grad_norm": 0.34465500712394714, | |
| "learning_rate": 0.00019999542705801296, | |
| "loss": 0.7106, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0616438356164384, | |
| "grad_norm": 0.32777366042137146, | |
| "learning_rate": 0.00019997685019798912, | |
| "loss": 0.6947, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.34322458505630493, | |
| "learning_rate": 0.00019994398626371643, | |
| "loss": 0.6952, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.13013698630137, | |
| "grad_norm": 0.2865244150161743, | |
| "learning_rate": 0.00019989683995157677, | |
| "loss": 0.6965, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.1643835616438356, | |
| "grad_norm": 0.2771136462688446, | |
| "learning_rate": 0.0001998354179989585, | |
| "loss": 0.6933, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1986301369863013, | |
| "grad_norm": 0.3072766661643982, | |
| "learning_rate": 0.00019975972918329356, | |
| "loss": 0.6938, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.2328767123287672, | |
| "grad_norm": 0.2912730872631073, | |
| "learning_rate": 0.00019966978432080316, | |
| "loss": 0.6913, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2671232876712328, | |
| "grad_norm": 0.33161672949790955, | |
| "learning_rate": 0.00019956559626495212, | |
| "loss": 0.6856, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.3013698630136985, | |
| "grad_norm": 0.40179818868637085, | |
| "learning_rate": 0.00019944717990461207, | |
| "loss": 0.6863, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3356164383561644, | |
| "grad_norm": 0.32012802362442017, | |
| "learning_rate": 0.00019931455216193382, | |
| "loss": 0.6828, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "grad_norm": 0.9038059115409851, | |
| "learning_rate": 0.000199167731989929, | |
| "loss": 0.6874, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.404109589041096, | |
| "grad_norm": 0.8754851222038269, | |
| "learning_rate": 0.00019900674036976173, | |
| "loss": 0.6794, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.4383561643835616, | |
| "grad_norm": 0.39323532581329346, | |
| "learning_rate": 0.00019883160030775016, | |
| "loss": 0.6799, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4726027397260273, | |
| "grad_norm": 0.44316402077674866, | |
| "learning_rate": 0.00019864233683207906, | |
| "loss": 0.6801, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.5068493150684932, | |
| "grad_norm": 0.3385327160358429, | |
| "learning_rate": 0.00019843897698922284, | |
| "loss": 0.6759, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.541095890410959, | |
| "grad_norm": 0.26804545521736145, | |
| "learning_rate": 0.00019822154984008088, | |
| "loss": 0.6704, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.5753424657534247, | |
| "grad_norm": 0.26624366641044617, | |
| "learning_rate": 0.0001979900864558242, | |
| "loss": 0.6747, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.6095890410958904, | |
| "grad_norm": 0.2834051549434662, | |
| "learning_rate": 0.00019774461991345577, | |
| "loss": 0.6674, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 0.36631157994270325, | |
| "learning_rate": 0.00019748518529108316, | |
| "loss": 0.6702, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.678082191780822, | |
| "grad_norm": 0.2652304768562317, | |
| "learning_rate": 0.00019721181966290613, | |
| "loss": 0.6704, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.7123287671232876, | |
| "grad_norm": 0.46855708956718445, | |
| "learning_rate": 0.00019692456209391846, | |
| "loss": 0.6782, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7465753424657535, | |
| "grad_norm": 0.27823150157928467, | |
| "learning_rate": 0.0001966234536343253, | |
| "loss": 0.665, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.7808219178082192, | |
| "grad_norm": 0.32231074571609497, | |
| "learning_rate": 0.00019630853731367713, | |
| "loss": 0.6651, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8150684931506849, | |
| "grad_norm": 0.24578699469566345, | |
| "learning_rate": 0.00019597985813472052, | |
| "loss": 0.6665, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "grad_norm": 0.31806036829948425, | |
| "learning_rate": 0.0001956374630669672, | |
| "loss": 0.6672, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8835616438356164, | |
| "grad_norm": 0.31710395216941833, | |
| "learning_rate": 0.00019528140103998177, | |
| "loss": 0.6609, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.9178082191780823, | |
| "grad_norm": 0.28619030117988586, | |
| "learning_rate": 0.00019491172293638968, | |
| "loss": 0.6631, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.952054794520548, | |
| "grad_norm": 0.3997630774974823, | |
| "learning_rate": 0.0001945284815846057, | |
| "loss": 0.6575, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.9863013698630136, | |
| "grad_norm": 0.30261415243148804, | |
| "learning_rate": 0.00019413173175128473, | |
| "loss": 0.6581, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.6853089332580566, | |
| "eval_runtime": 0.6813, | |
| "eval_samples_per_second": 8.806, | |
| "eval_steps_per_second": 1.468, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.0205479452054793, | |
| "grad_norm": 0.2559691071510315, | |
| "learning_rate": 0.00019372153013349523, | |
| "loss": 0.6464, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.0547945205479454, | |
| "grad_norm": 0.25488296151161194, | |
| "learning_rate": 0.00019329793535061723, | |
| "loss": 0.6446, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.089041095890411, | |
| "grad_norm": 0.27149608731269836, | |
| "learning_rate": 0.0001928610079359652, | |
| "loss": 0.6391, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.1232876712328768, | |
| "grad_norm": 0.27013513445854187, | |
| "learning_rate": 0.00019241081032813772, | |
| "loss": 0.6451, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.1575342465753424, | |
| "grad_norm": 0.287147581577301, | |
| "learning_rate": 0.00019194740686209464, | |
| "loss": 0.642, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 0.41998761892318726, | |
| "learning_rate": 0.0001914708637599636, | |
| "loss": 0.6395, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.2260273972602738, | |
| "grad_norm": 0.2858888506889343, | |
| "learning_rate": 0.00019098124912157632, | |
| "loss": 0.6389, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.26027397260274, | |
| "grad_norm": 0.34377697110176086, | |
| "learning_rate": 0.00019047863291473717, | |
| "loss": 0.6422, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.2945205479452055, | |
| "grad_norm": 0.2444482445716858, | |
| "learning_rate": 0.00018996308696522433, | |
| "loss": 0.6355, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.328767123287671, | |
| "grad_norm": 0.308186411857605, | |
| "learning_rate": 0.0001894346849465257, | |
| "loss": 0.6403, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.363013698630137, | |
| "grad_norm": 0.25512081384658813, | |
| "learning_rate": 0.00018889350236931055, | |
| "loss": 0.6417, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.3972602739726026, | |
| "grad_norm": 0.3035546839237213, | |
| "learning_rate": 0.00018833961657063885, | |
| "loss": 0.6366, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.4315068493150687, | |
| "grad_norm": 0.31536582112312317, | |
| "learning_rate": 0.0001877731067029096, | |
| "loss": 0.6376, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.4657534246575343, | |
| "grad_norm": 0.45909973978996277, | |
| "learning_rate": 0.00018719405372254948, | |
| "loss": 0.635, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.39519354701042175, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6384, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.5342465753424657, | |
| "grad_norm": 0.29281747341156006, | |
| "learning_rate": 0.00018599865120011192, | |
| "loss": 0.6316, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.5684931506849313, | |
| "grad_norm": 0.24112151563167572, | |
| "learning_rate": 0.00018538247248562674, | |
| "loss": 0.6363, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 0.2908940017223358, | |
| "learning_rate": 0.00018475409228928312, | |
| "loss": 0.6346, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.636986301369863, | |
| "grad_norm": 0.30711865425109863, | |
| "learning_rate": 0.0001841136004090144, | |
| "loss": 0.6453, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.671232876712329, | |
| "grad_norm": 0.24229027330875397, | |
| "learning_rate": 0.00018346108837355972, | |
| "loss": 0.6373, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.7054794520547945, | |
| "grad_norm": 0.28023508191108704, | |
| "learning_rate": 0.00018279664942938447, | |
| "loss": 0.6366, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 0.36763280630111694, | |
| "learning_rate": 0.00018212037852735486, | |
| "loss": 0.6461, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.7739726027397262, | |
| "grad_norm": 0.3579126000404358, | |
| "learning_rate": 0.0001814323723091692, | |
| "loss": 0.6433, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.808219178082192, | |
| "grad_norm": 0.30816444754600525, | |
| "learning_rate": 0.00018073272909354727, | |
| "loss": 0.6319, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.8424657534246576, | |
| "grad_norm": 0.4557536542415619, | |
| "learning_rate": 0.00018002154886218033, | |
| "loss": 0.6384, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 2.8767123287671232, | |
| "grad_norm": 0.4224196672439575, | |
| "learning_rate": 0.00017929893324544332, | |
| "loss": 0.6355, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.910958904109589, | |
| "grad_norm": 0.285664826631546, | |
| "learning_rate": 0.00017856498550787144, | |
| "loss": 0.6408, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.9452054794520546, | |
| "grad_norm": 0.29482561349868774, | |
| "learning_rate": 0.00017781981053340337, | |
| "loss": 0.6351, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.9794520547945207, | |
| "grad_norm": 0.31438663601875305, | |
| "learning_rate": 0.00017706351481039284, | |
| "loss": 0.6323, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.6891189813613892, | |
| "eval_runtime": 0.6806, | |
| "eval_samples_per_second": 8.815, | |
| "eval_steps_per_second": 1.469, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 3.0136986301369864, | |
| "grad_norm": 0.235789492726326, | |
| "learning_rate": 0.00017629620641639103, | |
| "loss": 0.6314, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.047945205479452, | |
| "grad_norm": 0.2618357241153717, | |
| "learning_rate": 0.00017551799500270198, | |
| "loss": 0.6064, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.0821917808219177, | |
| "grad_norm": 0.24724790453910828, | |
| "learning_rate": 0.00017472899177871297, | |
| "loss": 0.6096, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.1164383561643834, | |
| "grad_norm": 0.25246715545654297, | |
| "learning_rate": 0.00017392930949600217, | |
| "loss": 0.6088, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.1506849315068495, | |
| "grad_norm": 0.24573026597499847, | |
| "learning_rate": 0.00017311906243222614, | |
| "loss": 0.6184, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.184931506849315, | |
| "grad_norm": 0.2606354057788849, | |
| "learning_rate": 0.00017229836637478902, | |
| "loss": 0.6113, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 3.219178082191781, | |
| "grad_norm": 0.3043690025806427, | |
| "learning_rate": 0.00017146733860429612, | |
| "loss": 0.6092, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.2534246575342465, | |
| "grad_norm": 0.26179400086402893, | |
| "learning_rate": 0.00017062609787779403, | |
| "loss": 0.6173, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.287671232876712, | |
| "grad_norm": 0.2980283498764038, | |
| "learning_rate": 0.00016977476441179992, | |
| "loss": 0.6173, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.3219178082191783, | |
| "grad_norm": 0.2769377529621124, | |
| "learning_rate": 0.0001689134598651219, | |
| "loss": 0.6181, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 3.356164383561644, | |
| "grad_norm": 0.31351810693740845, | |
| "learning_rate": 0.0001680423073214737, | |
| "loss": 0.6223, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.3904109589041096, | |
| "grad_norm": 0.2710462510585785, | |
| "learning_rate": 0.00016716143127188548, | |
| "loss": 0.6171, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.4246575342465753, | |
| "grad_norm": 0.2538503110408783, | |
| "learning_rate": 0.00016627095759691362, | |
| "loss": 0.6132, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.458904109589041, | |
| "grad_norm": 0.2977152168750763, | |
| "learning_rate": 0.0001653710135486518, | |
| "loss": 0.613, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.493150684931507, | |
| "grad_norm": 0.2564401626586914, | |
| "learning_rate": 0.00016446172773254629, | |
| "loss": 0.6124, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.5273972602739727, | |
| "grad_norm": 0.2717874050140381, | |
| "learning_rate": 0.00016354323008901776, | |
| "loss": 0.6104, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 3.5616438356164384, | |
| "grad_norm": 0.3490482270717621, | |
| "learning_rate": 0.0001626156518748922, | |
| "loss": 0.625, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.595890410958904, | |
| "grad_norm": 0.2741421163082123, | |
| "learning_rate": 0.00016167912564464383, | |
| "loss": 0.6094, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.6301369863013697, | |
| "grad_norm": 0.269045352935791, | |
| "learning_rate": 0.0001607337852314527, | |
| "loss": 0.6053, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.6643835616438354, | |
| "grad_norm": 0.30331557989120483, | |
| "learning_rate": 0.0001597797657280792, | |
| "loss": 0.6173, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 3.6986301369863015, | |
| "grad_norm": 0.27356013655662537, | |
| "learning_rate": 0.00015881720346755905, | |
| "loss": 0.6095, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.732876712328767, | |
| "grad_norm": 0.2557332515716553, | |
| "learning_rate": 0.00015784623600372042, | |
| "loss": 0.6128, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 3.767123287671233, | |
| "grad_norm": 0.26268497109413147, | |
| "learning_rate": 0.00015686700209152738, | |
| "loss": 0.614, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.8013698630136985, | |
| "grad_norm": 0.240408256649971, | |
| "learning_rate": 0.00015587964166725095, | |
| "loss": 0.62, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 3.8356164383561646, | |
| "grad_norm": 0.2302975207567215, | |
| "learning_rate": 0.00015488429582847192, | |
| "loss": 0.6076, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.8698630136986303, | |
| "grad_norm": 0.24237115681171417, | |
| "learning_rate": 0.00015388110681391725, | |
| "loss": 0.6193, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 3.904109589041096, | |
| "grad_norm": 0.23819388449192047, | |
| "learning_rate": 0.0001528702179831338, | |
| "loss": 0.6047, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.9383561643835616, | |
| "grad_norm": 0.2723640203475952, | |
| "learning_rate": 0.00015185177379600152, | |
| "loss": 0.611, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.9726027397260273, | |
| "grad_norm": 0.24371425807476044, | |
| "learning_rate": 0.00015082591979208976, | |
| "loss": 0.6067, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.7035120725631714, | |
| "eval_runtime": 0.6811, | |
| "eval_samples_per_second": 8.81, | |
| "eval_steps_per_second": 1.468, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 4.006849315068493, | |
| "grad_norm": 0.28401726484298706, | |
| "learning_rate": 0.000149792802569859, | |
| "loss": 0.6113, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 4.041095890410959, | |
| "grad_norm": 0.2556915581226349, | |
| "learning_rate": 0.00014875256976571135, | |
| "loss": 0.5917, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.075342465753424, | |
| "grad_norm": 0.2777804434299469, | |
| "learning_rate": 0.0001477053700328929, | |
| "loss": 0.591, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 4.109589041095891, | |
| "grad_norm": 0.24701425433158875, | |
| "learning_rate": 0.00014665135302025035, | |
| "loss": 0.59, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.1438356164383565, | |
| "grad_norm": 0.24922576546669006, | |
| "learning_rate": 0.00014559066935084588, | |
| "loss": 0.5878, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 4.178082191780822, | |
| "grad_norm": 0.2835874557495117, | |
| "learning_rate": 0.00014452347060043237, | |
| "loss": 0.5827, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.212328767123288, | |
| "grad_norm": 0.2816501557826996, | |
| "learning_rate": 0.00014344990927579268, | |
| "loss": 0.5902, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.2465753424657535, | |
| "grad_norm": 0.27082914113998413, | |
| "learning_rate": 0.0001423701387929459, | |
| "loss": 0.5943, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.280821917808219, | |
| "grad_norm": 0.26985329389572144, | |
| "learning_rate": 0.0001412843134552235, | |
| "loss": 0.601, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.315068493150685, | |
| "grad_norm": 0.2813054621219635, | |
| "learning_rate": 0.00014019258843121893, | |
| "loss": 0.5896, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.3493150684931505, | |
| "grad_norm": 0.24405089020729065, | |
| "learning_rate": 0.0001390951197326134, | |
| "loss": 0.591, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 4.383561643835616, | |
| "grad_norm": 0.2506767511367798, | |
| "learning_rate": 0.00013799206419188103, | |
| "loss": 0.5957, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.417808219178082, | |
| "grad_norm": 0.28518110513687134, | |
| "learning_rate": 0.00013688357943987732, | |
| "loss": 0.5847, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 4.4520547945205475, | |
| "grad_norm": 0.25432756543159485, | |
| "learning_rate": 0.0001357698238833126, | |
| "loss": 0.5985, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.486301369863014, | |
| "grad_norm": 0.24484550952911377, | |
| "learning_rate": 0.0001346509566821153, | |
| "loss": 0.5928, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 4.52054794520548, | |
| "grad_norm": 0.2853868305683136, | |
| "learning_rate": 0.00013352713772668765, | |
| "loss": 0.5968, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.554794520547945, | |
| "grad_norm": 0.25753411650657654, | |
| "learning_rate": 0.00013239852761505626, | |
| "loss": 0.5945, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 4.589041095890411, | |
| "grad_norm": 0.2740824818611145, | |
| "learning_rate": 0.00013126528762992247, | |
| "loss": 0.5944, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.623287671232877, | |
| "grad_norm": 0.24608436226844788, | |
| "learning_rate": 0.00013012757971561415, | |
| "loss": 0.596, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.657534246575342, | |
| "grad_norm": 0.24703024327754974, | |
| "learning_rate": 0.00012898556645494325, | |
| "loss": 0.6013, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.691780821917808, | |
| "grad_norm": 0.26772698760032654, | |
| "learning_rate": 0.0001278394110459724, | |
| "loss": 0.5945, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 4.726027397260274, | |
| "grad_norm": 0.24686093628406525, | |
| "learning_rate": 0.0001266892772786929, | |
| "loss": 0.5904, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.760273972602739, | |
| "grad_norm": 0.27200302481651306, | |
| "learning_rate": 0.0001255353295116187, | |
| "loss": 0.5915, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 4.794520547945205, | |
| "grad_norm": 0.2462131232023239, | |
| "learning_rate": 0.00012437773264829897, | |
| "loss": 0.5896, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.828767123287671, | |
| "grad_norm": 0.25482824444770813, | |
| "learning_rate": 0.00012321665211375256, | |
| "loss": 0.5921, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 4.863013698630137, | |
| "grad_norm": 0.2556120455265045, | |
| "learning_rate": 0.00012205225383082843, | |
| "loss": 0.5944, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.897260273972603, | |
| "grad_norm": 0.2709575593471527, | |
| "learning_rate": 0.00012088470419649432, | |
| "loss": 0.5975, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 4.931506849315069, | |
| "grad_norm": 0.29646211862564087, | |
| "learning_rate": 0.00011971417005805818, | |
| "loss": 0.6007, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.965753424657534, | |
| "grad_norm": 0.2482611984014511, | |
| "learning_rate": 0.0001185408186893251, | |
| "loss": 0.5927, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.24462343752384186, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.591, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7225574254989624, | |
| "eval_runtime": 0.6804, | |
| "eval_samples_per_second": 8.818, | |
| "eval_steps_per_second": 1.47, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.034246575342466, | |
| "grad_norm": 0.25259608030319214, | |
| "learning_rate": 0.00011618633534519141, | |
| "loss": 0.5762, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 5.068493150684931, | |
| "grad_norm": 0.24844078719615936, | |
| "learning_rate": 0.00011500553983446527, | |
| "loss": 0.5762, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.102739726027397, | |
| "grad_norm": 0.2850824296474457, | |
| "learning_rate": 0.00011382259997470899, | |
| "loss": 0.5744, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 5.136986301369863, | |
| "grad_norm": 0.27126604318618774, | |
| "learning_rate": 0.00011263768481255264, | |
| "loss": 0.5713, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.171232876712328, | |
| "grad_norm": 0.25230973958969116, | |
| "learning_rate": 0.00011145096367690444, | |
| "loss": 0.5755, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 5.205479452054795, | |
| "grad_norm": 0.24937325716018677, | |
| "learning_rate": 0.00011026260615475333, | |
| "loss": 0.5752, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.239726027397261, | |
| "grad_norm": 0.26235413551330566, | |
| "learning_rate": 0.00010907278206693395, | |
| "loss": 0.5793, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 5.273972602739726, | |
| "grad_norm": 0.2632244825363159, | |
| "learning_rate": 0.00010788166144385888, | |
| "loss": 0.576, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.308219178082192, | |
| "grad_norm": 0.2701359689235687, | |
| "learning_rate": 0.00010668941450122055, | |
| "loss": 0.5812, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.342465753424658, | |
| "grad_norm": 0.2537064552307129, | |
| "learning_rate": 0.0001054962116156667, | |
| "loss": 0.5754, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.376712328767123, | |
| "grad_norm": 0.2470828741788864, | |
| "learning_rate": 0.00010430222330045304, | |
| "loss": 0.5707, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 5.410958904109589, | |
| "grad_norm": 0.2509852945804596, | |
| "learning_rate": 0.0001031076201810762, | |
| "loss": 0.5762, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.445205479452055, | |
| "grad_norm": 0.2670098543167114, | |
| "learning_rate": 0.00010191257297089052, | |
| "loss": 0.5763, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 5.47945205479452, | |
| "grad_norm": 0.25170961022377014, | |
| "learning_rate": 0.00010071725244671282, | |
| "loss": 0.5704, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.513698630136986, | |
| "grad_norm": 0.2560670077800751, | |
| "learning_rate": 9.952182942441733e-05, | |
| "loss": 0.5796, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 5.5479452054794525, | |
| "grad_norm": 0.25187042355537415, | |
| "learning_rate": 9.83264747345259e-05, | |
| "loss": 0.5722, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.582191780821918, | |
| "grad_norm": 0.2625672519207001, | |
| "learning_rate": 9.713135919779515e-05, | |
| "loss": 0.5762, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 5.616438356164384, | |
| "grad_norm": 0.25329843163490295, | |
| "learning_rate": 9.593665360080599e-05, | |
| "loss": 0.5744, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.6506849315068495, | |
| "grad_norm": 0.25838255882263184, | |
| "learning_rate": 9.474252867155732e-05, | |
| "loss": 0.5759, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 5.684931506849315, | |
| "grad_norm": 0.28136056661605835, | |
| "learning_rate": 9.354915505506839e-05, | |
| "loss": 0.5768, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.719178082191781, | |
| "grad_norm": 0.24633042514324188, | |
| "learning_rate": 9.235670328899293e-05, | |
| "loss": 0.5794, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 5.7534246575342465, | |
| "grad_norm": 0.2591402232646942, | |
| "learning_rate": 9.116534377924883e-05, | |
| "loss": 0.578, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.787671232876712, | |
| "grad_norm": 0.27811384201049805, | |
| "learning_rate": 8.997524677566627e-05, | |
| "loss": 0.5818, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 5.821917808219178, | |
| "grad_norm": 0.2641887962818146, | |
| "learning_rate": 8.878658234765858e-05, | |
| "loss": 0.5756, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.8561643835616435, | |
| "grad_norm": 0.26102420687675476, | |
| "learning_rate": 8.759952035991844e-05, | |
| "loss": 0.5817, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 5.890410958904109, | |
| "grad_norm": 0.25208574533462524, | |
| "learning_rate": 8.641423044814374e-05, | |
| "loss": 0.5792, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.924657534246576, | |
| "grad_norm": 0.2486419528722763, | |
| "learning_rate": 8.5230881994796e-05, | |
| "loss": 0.5743, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 5.958904109589041, | |
| "grad_norm": 0.2543000280857086, | |
| "learning_rate": 8.404964410489485e-05, | |
| "loss": 0.575, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.993150684931507, | |
| "grad_norm": 0.2586722671985626, | |
| "learning_rate": 8.287068558185225e-05, | |
| "loss": 0.5752, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.725889801979065, | |
| "eval_runtime": 0.6823, | |
| "eval_samples_per_second": 8.794, | |
| "eval_steps_per_second": 1.466, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 6.027397260273973, | |
| "grad_norm": 0.2684203088283539, | |
| "learning_rate": 8.169417490335007e-05, | |
| "loss": 0.5647, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.061643835616438, | |
| "grad_norm": 0.2663749158382416, | |
| "learning_rate": 8.052028019726371e-05, | |
| "loss": 0.5576, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 6.095890410958904, | |
| "grad_norm": 0.2585398256778717, | |
| "learning_rate": 7.934916921763628e-05, | |
| "loss": 0.5512, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.13013698630137, | |
| "grad_norm": 0.2593580484390259, | |
| "learning_rate": 7.818100932070546e-05, | |
| "loss": 0.5513, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 6.164383561643835, | |
| "grad_norm": 0.2640758454799652, | |
| "learning_rate": 7.701596744098818e-05, | |
| "loss": 0.561, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.198630136986301, | |
| "grad_norm": 0.29837489128112793, | |
| "learning_rate": 7.585421006742463e-05, | |
| "loss": 0.5576, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 6.232876712328767, | |
| "grad_norm": 0.2711084485054016, | |
| "learning_rate": 7.469590321958662e-05, | |
| "loss": 0.5632, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.267123287671233, | |
| "grad_norm": 0.27940109372138977, | |
| "learning_rate": 7.354121242395254e-05, | |
| "loss": 0.5597, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 6.301369863013699, | |
| "grad_norm": 0.2598007321357727, | |
| "learning_rate": 7.239030269025311e-05, | |
| "loss": 0.5634, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.335616438356165, | |
| "grad_norm": 0.27142032980918884, | |
| "learning_rate": 7.124333848789091e-05, | |
| "loss": 0.5684, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 6.36986301369863, | |
| "grad_norm": 0.2744521200656891, | |
| "learning_rate": 7.010048372243698e-05, | |
| "loss": 0.566, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.404109589041096, | |
| "grad_norm": 0.2650752067565918, | |
| "learning_rate": 6.8961901712208e-05, | |
| "loss": 0.5633, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 6.438356164383562, | |
| "grad_norm": 0.2859334349632263, | |
| "learning_rate": 6.782775516492771e-05, | |
| "loss": 0.5622, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.472602739726027, | |
| "grad_norm": 0.2793692946434021, | |
| "learning_rate": 6.669820615447522e-05, | |
| "loss": 0.5618, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 6.506849315068493, | |
| "grad_norm": 0.2735882103443146, | |
| "learning_rate": 6.5573416097724e-05, | |
| "loss": 0.5674, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.541095890410959, | |
| "grad_norm": 0.26911288499832153, | |
| "learning_rate": 6.445354573147484e-05, | |
| "loss": 0.5641, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 6.575342465753424, | |
| "grad_norm": 0.2591806948184967, | |
| "learning_rate": 6.333875508948593e-05, | |
| "loss": 0.5689, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.609589041095891, | |
| "grad_norm": 0.25813576579093933, | |
| "learning_rate": 6.22292034796035e-05, | |
| "loss": 0.5609, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 6.6438356164383565, | |
| "grad_norm": 0.26337507367134094, | |
| "learning_rate": 6.112504946099604e-05, | |
| "loss": 0.5577, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.678082191780822, | |
| "grad_norm": 0.2651839852333069, | |
| "learning_rate": 6.0026450821495536e-05, | |
| "loss": 0.5593, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 6.712328767123288, | |
| "grad_norm": 0.274582177400589, | |
| "learning_rate": 5.8933564555049105e-05, | |
| "loss": 0.5597, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.7465753424657535, | |
| "grad_norm": 0.26564931869506836, | |
| "learning_rate": 5.784654683928391e-05, | |
| "loss": 0.5645, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 6.780821917808219, | |
| "grad_norm": 0.2597637176513672, | |
| "learning_rate": 5.6765553013188766e-05, | |
| "loss": 0.5592, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.815068493150685, | |
| "grad_norm": 0.2663344144821167, | |
| "learning_rate": 5.5690737554915604e-05, | |
| "loss": 0.5657, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 6.8493150684931505, | |
| "grad_norm": 0.2605944275856018, | |
| "learning_rate": 5.462225405970401e-05, | |
| "loss": 0.5604, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.883561643835616, | |
| "grad_norm": 0.2578333914279938, | |
| "learning_rate": 5.3560255217931785e-05, | |
| "loss": 0.5713, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 6.917808219178082, | |
| "grad_norm": 0.2837528586387634, | |
| "learning_rate": 5.2504892793295e-05, | |
| "loss": 0.5609, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 6.9520547945205475, | |
| "grad_norm": 0.26841509342193604, | |
| "learning_rate": 5.145631760112022e-05, | |
| "loss": 0.5696, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 6.986301369863014, | |
| "grad_norm": 0.27431559562683105, | |
| "learning_rate": 5.041467948681269e-05, | |
| "loss": 0.5603, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7421818971633911, | |
| "eval_runtime": 0.6796, | |
| "eval_samples_per_second": 8.829, | |
| "eval_steps_per_second": 1.471, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 7.02054794520548, | |
| "grad_norm": 0.2642446458339691, | |
| "learning_rate": 4.9380127304442634e-05, | |
| "loss": 0.5559, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 7.054794520547945, | |
| "grad_norm": 0.25995686650276184, | |
| "learning_rate": 4.835280889547351e-05, | |
| "loss": 0.5473, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.089041095890411, | |
| "grad_norm": 0.26262959837913513, | |
| "learning_rate": 4.733287106763481e-05, | |
| "loss": 0.5516, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 7.123287671232877, | |
| "grad_norm": 0.2740737199783325, | |
| "learning_rate": 4.6320459573942856e-05, | |
| "loss": 0.5395, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.157534246575342, | |
| "grad_norm": 0.2638036012649536, | |
| "learning_rate": 4.531571909187197e-05, | |
| "loss": 0.5507, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 7.191780821917808, | |
| "grad_norm": 0.2760368585586548, | |
| "learning_rate": 4.431879320267972e-05, | |
| "loss": 0.5516, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.226027397260274, | |
| "grad_norm": 0.26356157660484314, | |
| "learning_rate": 4.332982437088825e-05, | |
| "loss": 0.5528, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 7.260273972602739, | |
| "grad_norm": 0.27334779500961304, | |
| "learning_rate": 4.2348953923925916e-05, | |
| "loss": 0.547, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.294520547945205, | |
| "grad_norm": 0.2645105719566345, | |
| "learning_rate": 4.137632203193086e-05, | |
| "loss": 0.5449, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 7.328767123287671, | |
| "grad_norm": 0.2697451114654541, | |
| "learning_rate": 4.041206768772022e-05, | |
| "loss": 0.5484, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.363013698630137, | |
| "grad_norm": 0.2794542610645294, | |
| "learning_rate": 3.9456328686927525e-05, | |
| "loss": 0.5527, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 7.397260273972603, | |
| "grad_norm": 0.27488037943840027, | |
| "learning_rate": 3.850924160831115e-05, | |
| "loss": 0.5473, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.431506849315069, | |
| "grad_norm": 0.2687772810459137, | |
| "learning_rate": 3.757094179423672e-05, | |
| "loss": 0.5505, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 7.465753424657534, | |
| "grad_norm": 0.2724910080432892, | |
| "learning_rate": 3.6641563331336125e-05, | |
| "loss": 0.5615, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 0.26319825649261475, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.5571, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 7.534246575342466, | |
| "grad_norm": 0.270577609539032, | |
| "learning_rate": 3.4810100412128747e-05, | |
| "loss": 0.5428, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.568493150684931, | |
| "grad_norm": 0.2661505341529846, | |
| "learning_rate": 3.3908277678877445e-05, | |
| "loss": 0.5515, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 7.602739726027397, | |
| "grad_norm": 0.2684604823589325, | |
| "learning_rate": 3.3015899705509734e-05, | |
| "loss": 0.5513, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.636986301369863, | |
| "grad_norm": 0.2670838534832001, | |
| "learning_rate": 3.21330940162508e-05, | |
| "loss": 0.5553, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 7.671232876712329, | |
| "grad_norm": 0.26764294505119324, | |
| "learning_rate": 3.125998676740987e-05, | |
| "loss": 0.5553, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.705479452054795, | |
| "grad_norm": 0.2651881277561188, | |
| "learning_rate": 3.0396702729352023e-05, | |
| "loss": 0.5502, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 7.739726027397261, | |
| "grad_norm": 0.27107974886894226, | |
| "learning_rate": 2.9543365268667867e-05, | |
| "loss": 0.5522, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.773972602739726, | |
| "grad_norm": 0.2676118314266205, | |
| "learning_rate": 2.8700096330544012e-05, | |
| "loss": 0.5506, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 7.808219178082192, | |
| "grad_norm": 0.2681746184825897, | |
| "learning_rate": 2.7867016421336776e-05, | |
| "loss": 0.5473, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.842465753424658, | |
| "grad_norm": 0.27224835753440857, | |
| "learning_rate": 2.7044244591351232e-05, | |
| "loss": 0.5493, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 7.876712328767123, | |
| "grad_norm": 0.2668222486972809, | |
| "learning_rate": 2.6231898417828603e-05, | |
| "loss": 0.55, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 7.910958904109589, | |
| "grad_norm": 0.2646133005619049, | |
| "learning_rate": 2.5430093988143778e-05, | |
| "loss": 0.5532, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 7.945205479452055, | |
| "grad_norm": 0.26807960867881775, | |
| "learning_rate": 2.4638945883216235e-05, | |
| "loss": 0.555, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 7.97945205479452, | |
| "grad_norm": 0.2676006853580475, | |
| "learning_rate": 2.385856716113587e-05, | |
| "loss": 0.5632, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.7482503652572632, | |
| "eval_runtime": 0.6829, | |
| "eval_samples_per_second": 8.786, | |
| "eval_steps_per_second": 1.464, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 8.013698630136986, | |
| "grad_norm": 0.2698109447956085, | |
| "learning_rate": 2.3089069341006565e-05, | |
| "loss": 0.5524, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.047945205479452, | |
| "grad_norm": 0.26906144618988037, | |
| "learning_rate": 2.2330562387009745e-05, | |
| "loss": 0.5412, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 8.082191780821917, | |
| "grad_norm": 0.2829205095767975, | |
| "learning_rate": 2.1583154692689976e-05, | |
| "loss": 0.5406, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.116438356164384, | |
| "grad_norm": 0.27515366673469543, | |
| "learning_rate": 2.08469530654652e-05, | |
| "loss": 0.5447, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 8.150684931506849, | |
| "grad_norm": 0.26556894183158875, | |
| "learning_rate": 2.0122062711363532e-05, | |
| "loss": 0.5426, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.184931506849315, | |
| "grad_norm": 0.2701828181743622, | |
| "learning_rate": 1.9408587219988805e-05, | |
| "loss": 0.5375, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 8.219178082191782, | |
| "grad_norm": 0.2658767104148865, | |
| "learning_rate": 1.8706628549717452e-05, | |
| "loss": 0.5402, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.253424657534246, | |
| "grad_norm": 0.28211283683776855, | |
| "learning_rate": 1.8016287013128018e-05, | |
| "loss": 0.5416, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 8.287671232876713, | |
| "grad_norm": 0.281766802072525, | |
| "learning_rate": 1.7337661262666294e-05, | |
| "loss": 0.546, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.321917808219178, | |
| "grad_norm": 0.2836877405643463, | |
| "learning_rate": 1.6670848276547334e-05, | |
| "loss": 0.5415, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 8.356164383561644, | |
| "grad_norm": 0.2742989659309387, | |
| "learning_rate": 1.601594334489702e-05, | |
| "loss": 0.5483, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.39041095890411, | |
| "grad_norm": 0.2683957517147064, | |
| "learning_rate": 1.5373040056134814e-05, | |
| "loss": 0.5433, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 8.424657534246576, | |
| "grad_norm": 0.2692102789878845, | |
| "learning_rate": 1.474223028359939e-05, | |
| "loss": 0.5465, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.45890410958904, | |
| "grad_norm": 0.2703090310096741, | |
| "learning_rate": 1.4123604172419713e-05, | |
| "loss": 0.5405, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 8.493150684931507, | |
| "grad_norm": 0.27296507358551025, | |
| "learning_rate": 1.3517250126632986e-05, | |
| "loss": 0.5424, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.527397260273972, | |
| "grad_norm": 0.26967960596084595, | |
| "learning_rate": 1.292325479655131e-05, | |
| "loss": 0.5428, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 8.561643835616438, | |
| "grad_norm": 0.27562007308006287, | |
| "learning_rate": 1.2341703066379074e-05, | |
| "loss": 0.546, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.595890410958905, | |
| "grad_norm": 0.2698553204536438, | |
| "learning_rate": 1.1772678042082607e-05, | |
| "loss": 0.5463, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 8.63013698630137, | |
| "grad_norm": 0.27123743295669556, | |
| "learning_rate": 1.1216261039514087e-05, | |
| "loss": 0.5423, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.664383561643836, | |
| "grad_norm": 0.27804234623908997, | |
| "learning_rate": 1.0672531572791178e-05, | |
| "loss": 0.5481, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 8.698630136986301, | |
| "grad_norm": 0.26643478870391846, | |
| "learning_rate": 1.0141567342934132e-05, | |
| "loss": 0.5415, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.732876712328768, | |
| "grad_norm": 0.2655141353607178, | |
| "learning_rate": 9.623444226762035e-06, | |
| "loss": 0.5439, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 8.767123287671232, | |
| "grad_norm": 0.26757049560546875, | |
| "learning_rate": 9.118236266049707e-06, | |
| "loss": 0.5495, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.801369863013699, | |
| "grad_norm": 0.2669236958026886, | |
| "learning_rate": 8.626015656946895e-06, | |
| "loss": 0.5473, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 8.835616438356164, | |
| "grad_norm": 0.2733878791332245, | |
| "learning_rate": 8.146852739661105e-06, | |
| "loss": 0.5449, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.86986301369863, | |
| "grad_norm": 0.27196043729782104, | |
| "learning_rate": 7.6808159884057e-06, | |
| "loss": 0.5451, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 8.904109589041095, | |
| "grad_norm": 0.27573108673095703, | |
| "learning_rate": 7.2279720016148244e-06, | |
| "loss": 0.5422, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.938356164383562, | |
| "grad_norm": 0.2723158299922943, | |
| "learning_rate": 6.788385492426053e-06, | |
| "loss": 0.548, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 8.972602739726028, | |
| "grad_norm": 0.2763724625110626, | |
| "learning_rate": 6.36211927943271e-06, | |
| "loss": 0.5497, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.7569636106491089, | |
| "eval_runtime": 0.6815, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.467, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 9.006849315068493, | |
| "grad_norm": 0.26691538095474243, | |
| "learning_rate": 5.949234277706861e-06, | |
| "loss": 0.5373, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 9.04109589041096, | |
| "grad_norm": 0.26734665036201477, | |
| "learning_rate": 5.549789490094304e-06, | |
| "loss": 0.5391, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.075342465753424, | |
| "grad_norm": 0.2708768844604492, | |
| "learning_rate": 5.163841998782837e-06, | |
| "loss": 0.5492, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 9.10958904109589, | |
| "grad_norm": 0.2653951942920685, | |
| "learning_rate": 4.79144695714504e-06, | |
| "loss": 0.5358, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.143835616438356, | |
| "grad_norm": 0.27374231815338135, | |
| "learning_rate": 4.432657581856525e-06, | |
| "loss": 0.5426, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 9.178082191780822, | |
| "grad_norm": 0.2698308229446411, | |
| "learning_rate": 4.087525145291204e-06, | |
| "loss": 0.54, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.212328767123287, | |
| "grad_norm": 0.2661896049976349, | |
| "learning_rate": 3.7560989681941992e-06, | |
| "loss": 0.5396, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 9.246575342465754, | |
| "grad_norm": 0.26976555585861206, | |
| "learning_rate": 3.4384264126337328e-06, | |
| "loss": 0.5421, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.280821917808218, | |
| "grad_norm": 0.26978161931037903, | |
| "learning_rate": 3.1345528752329212e-06, | |
| "loss": 0.5419, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 9.315068493150685, | |
| "grad_norm": 0.2713252902030945, | |
| "learning_rate": 2.8445217806824077e-06, | |
| "loss": 0.5367, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.349315068493151, | |
| "grad_norm": 0.27367061376571655, | |
| "learning_rate": 2.5683745755348044e-06, | |
| "loss": 0.5384, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 9.383561643835616, | |
| "grad_norm": 0.2732658386230469, | |
| "learning_rate": 2.30615072228183e-06, | |
| "loss": 0.5452, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.417808219178083, | |
| "grad_norm": 0.2684633731842041, | |
| "learning_rate": 2.057887693714988e-06, | |
| "loss": 0.5354, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 9.452054794520548, | |
| "grad_norm": 0.2733153700828552, | |
| "learning_rate": 1.8236209675705274e-06, | |
| "loss": 0.5406, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.486301369863014, | |
| "grad_norm": 0.265996515750885, | |
| "learning_rate": 1.6033840214595308e-06, | |
| "loss": 0.5394, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 9.520547945205479, | |
| "grad_norm": 0.26887837052345276, | |
| "learning_rate": 1.397208328083921e-06, | |
| "loss": 0.5407, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.554794520547945, | |
| "grad_norm": 0.26908043026924133, | |
| "learning_rate": 1.205123350738746e-06, | |
| "loss": 0.5366, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 9.58904109589041, | |
| "grad_norm": 0.2689751088619232, | |
| "learning_rate": 1.0271565391018922e-06, | |
| "loss": 0.5381, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.623287671232877, | |
| "grad_norm": 0.2709926664829254, | |
| "learning_rate": 8.633333253113995e-07, | |
| "loss": 0.5383, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 9.657534246575342, | |
| "grad_norm": 0.26522693037986755, | |
| "learning_rate": 7.136771203310245e-07, | |
| "loss": 0.5417, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.691780821917808, | |
| "grad_norm": 0.2700962722301483, | |
| "learning_rate": 5.782093106048159e-07, | |
| "loss": 0.5441, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 9.726027397260275, | |
| "grad_norm": 0.2700207531452179, | |
| "learning_rate": 4.569492550008603e-07, | |
| "loss": 0.5373, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.76027397260274, | |
| "grad_norm": 0.26531684398651123, | |
| "learning_rate": 3.49914282044872e-07, | |
| "loss": 0.5395, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 9.794520547945206, | |
| "grad_norm": 0.2695051431655884, | |
| "learning_rate": 2.5711968744382974e-07, | |
| "loss": 0.536, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.82876712328767, | |
| "grad_norm": 0.2686808407306671, | |
| "learning_rate": 1.7857873190019192e-07, | |
| "loss": 0.544, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 9.863013698630137, | |
| "grad_norm": 0.27493226528167725, | |
| "learning_rate": 1.143026392168789e-07, | |
| "loss": 0.5456, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.897260273972602, | |
| "grad_norm": 0.27204445004463196, | |
| "learning_rate": 6.430059469334504e-08, | |
| "loss": 0.5423, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 9.931506849315069, | |
| "grad_norm": 0.27562659978866577, | |
| "learning_rate": 2.8579743813006432e-08, | |
| "loss": 0.5435, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 9.965753424657533, | |
| "grad_norm": 0.27623289823532104, | |
| "learning_rate": 7.145191222035497e-09, | |
| "loss": 0.5455, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.26718658208847046, | |
| "learning_rate": 0.0, | |
| "loss": 0.5353, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.7579952478408813, | |
| "eval_runtime": 0.6696, | |
| "eval_samples_per_second": 8.961, | |
| "eval_steps_per_second": 1.493, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1460, | |
| "total_flos": 8.183666472539652e+18, | |
| "train_loss": 0.6181400966970888, | |
| "train_runtime": 11966.6323, | |
| "train_samples_per_second": 15.569, | |
| "train_steps_per_second": 0.122 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1460, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.183666472539652e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |