| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 730, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 2.7397260273972604e-06, | |
| "loss": 3.0538, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 3.0804, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 3.036, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 3.0119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 1.84375, | |
| "learning_rate": 5.479452054794521e-05, | |
| "loss": 2.7939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 6.84931506849315e-05, | |
| "loss": 2.5661, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 7.25, | |
| "learning_rate": 8.219178082191781e-05, | |
| "loss": 2.3942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 9.58904109589041e-05, | |
| "loss": 2.2555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 0.00010958904109589041, | |
| "loss": 2.1131, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 0.0001232876712328767, | |
| "loss": 1.9336, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 0.000136986301369863, | |
| "loss": 1.7804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 0.00015068493150684933, | |
| "loss": 1.6514, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 0.00016438356164383562, | |
| "loss": 1.5682, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 0.00017808219178082192, | |
| "loss": 1.5013, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 0.0001917808219178082, | |
| "loss": 1.4358, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.546966075897217, | |
| "eval_runtime": 0.552, | |
| "eval_samples_per_second": 18.116, | |
| "eval_steps_per_second": 1.812, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0273972602739727, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 0.00019999542705801296, | |
| "loss": 1.3872, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.326171875, | |
| "learning_rate": 0.00019994398626371643, | |
| "loss": 1.3485, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1643835616438356, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 0.0001998354179989585, | |
| "loss": 1.3316, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.2328767123287672, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 0.00019966978432080316, | |
| "loss": 1.3049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3013698630136985, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 0.00019944717990461207, | |
| "loss": 1.2894, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 0.000199167731989929, | |
| "loss": 1.2703, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4383561643835616, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 0.00019883160030775016, | |
| "loss": 1.2547, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.5068493150684932, | |
| "grad_norm": 0.291015625, | |
| "learning_rate": 0.00019843897698922284, | |
| "loss": 1.2613, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.5753424657534247, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 0.0001979900864558242, | |
| "loss": 1.2388, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 0.00019748518529108316, | |
| "loss": 1.2528, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7123287671232876, | |
| "grad_norm": 0.419921875, | |
| "learning_rate": 0.00019692456209391846, | |
| "loss": 1.2373, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.7808219178082192, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 0.00019630853731367713, | |
| "loss": 1.2241, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "grad_norm": 0.33984375, | |
| "learning_rate": 0.0001956374630669672, | |
| "loss": 1.2263, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.9178082191780823, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 0.00019491172293638968, | |
| "loss": 1.212, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.9863013698630136, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 0.00019413173175128473, | |
| "loss": 1.2092, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.5063788890838623, | |
| "eval_runtime": 0.5512, | |
| "eval_samples_per_second": 18.144, | |
| "eval_steps_per_second": 1.814, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.0547945205479454, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 0.00019329793535061723, | |
| "loss": 1.1791, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.1232876712328768, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 0.00019241081032813772, | |
| "loss": 1.1745, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 0.0001914708637599636, | |
| "loss": 1.1783, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.26027397260274, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 0.00019047863291473717, | |
| "loss": 1.156, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.328767123287671, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 0.0001894346849465257, | |
| "loss": 1.1642, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.3972602739726026, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 0.00018833961657063885, | |
| "loss": 1.176, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.4657534246575343, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.00018719405372254948, | |
| "loss": 1.16, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.5342465753424657, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 0.00018599865120011192, | |
| "loss": 1.1653, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 0.3125, | |
| "learning_rate": 0.00018475409228928312, | |
| "loss": 1.1616, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.671232876712329, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 0.00018346108837355972, | |
| "loss": 1.1549, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 0.00018212037852735486, | |
| "loss": 1.1518, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.808219178082192, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.00018073272909354727, | |
| "loss": 1.1516, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.8767123287671232, | |
| "grad_norm": 0.375, | |
| "learning_rate": 0.00017929893324544332, | |
| "loss": 1.154, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.9452054794520546, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 0.00017781981053340337, | |
| "loss": 1.1501, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.4999959468841553, | |
| "eval_runtime": 0.5406, | |
| "eval_samples_per_second": 18.499, | |
| "eval_steps_per_second": 1.85, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 3.0136986301369864, | |
| "grad_norm": 0.353515625, | |
| "learning_rate": 0.00017629620641639103, | |
| "loss": 1.1368, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0821917808219177, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 0.00017472899177871297, | |
| "loss": 1.118, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.1506849315068495, | |
| "grad_norm": 0.353515625, | |
| "learning_rate": 0.00017311906243222614, | |
| "loss": 1.1122, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.219178082191781, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 0.00017146733860429612, | |
| "loss": 1.1205, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.287671232876712, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 0.00016977476441179992, | |
| "loss": 1.1197, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.356164383561644, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 0.0001680423073214737, | |
| "loss": 1.1155, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.4246575342465753, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 0.00016627095759691362, | |
| "loss": 1.1255, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.493150684931507, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 0.00016446172773254629, | |
| "loss": 1.1113, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.5616438356164384, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 0.0001626156518748922, | |
| "loss": 1.1073, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6301369863013697, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 0.0001607337852314527, | |
| "loss": 1.1155, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.6986301369863015, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 0.00015881720346755905, | |
| "loss": 1.1239, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.767123287671233, | |
| "grad_norm": 0.416015625, | |
| "learning_rate": 0.00015686700209152738, | |
| "loss": 1.1185, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.8356164383561646, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 0.00015488429582847192, | |
| "loss": 1.1125, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.904109589041096, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 0.0001528702179831338, | |
| "loss": 1.0925, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.9726027397260273, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 0.00015082591979208976, | |
| "loss": 1.0995, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.506415843963623, | |
| "eval_runtime": 0.5555, | |
| "eval_samples_per_second": 18.001, | |
| "eval_steps_per_second": 1.8, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 4.041095890410959, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 0.00014875256976571135, | |
| "loss": 1.0993, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.109589041095891, | |
| "grad_norm": 0.375, | |
| "learning_rate": 0.00014665135302025035, | |
| "loss": 1.0789, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.178082191780822, | |
| "grad_norm": 0.3984375, | |
| "learning_rate": 0.00014452347060043237, | |
| "loss": 1.0724, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.2465753424657535, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 0.0001423701387929459, | |
| "loss": 1.0874, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.315068493150685, | |
| "grad_norm": 0.357421875, | |
| "learning_rate": 0.00014019258843121893, | |
| "loss": 1.0913, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.383561643835616, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 0.00013799206419188103, | |
| "loss": 1.085, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.4520547945205475, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 0.0001357698238833126, | |
| "loss": 1.0733, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.52054794520548, | |
| "grad_norm": 0.44140625, | |
| "learning_rate": 0.00013352713772668765, | |
| "loss": 1.0799, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.589041095890411, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 0.00013126528762992247, | |
| "loss": 1.0774, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.657534246575342, | |
| "grad_norm": 0.34375, | |
| "learning_rate": 0.00012898556645494325, | |
| "loss": 1.0742, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.726027397260274, | |
| "grad_norm": 0.408203125, | |
| "learning_rate": 0.0001266892772786929, | |
| "loss": 1.0806, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.794520547945205, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 0.00012437773264829897, | |
| "loss": 1.0892, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.863013698630137, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 0.00012205225383082843, | |
| "loss": 1.0805, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.931506849315069, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 0.00011971417005805818, | |
| "loss": 1.0786, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.37890625, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.0809, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.5177359580993652, | |
| "eval_runtime": 0.545, | |
| "eval_samples_per_second": 18.35, | |
| "eval_steps_per_second": 1.835, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.068493150684931, | |
| "grad_norm": 0.388671875, | |
| "learning_rate": 0.00011500553983446527, | |
| "loss": 1.0503, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.136986301369863, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 0.00011263768481255264, | |
| "loss": 1.0578, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.205479452054795, | |
| "grad_norm": 0.41015625, | |
| "learning_rate": 0.00011026260615475333, | |
| "loss": 1.0601, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.273972602739726, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 0.00010788166144385888, | |
| "loss": 1.0519, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.342465753424658, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 0.0001054962116156667, | |
| "loss": 1.0555, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.410958904109589, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 0.0001031076201810762, | |
| "loss": 1.0673, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 5.47945205479452, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 0.00010071725244671282, | |
| "loss": 1.0495, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.5479452054794525, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 9.83264747345259e-05, | |
| "loss": 1.054, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 5.616438356164384, | |
| "grad_norm": 0.408203125, | |
| "learning_rate": 9.593665360080599e-05, | |
| "loss": 1.0631, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.684931506849315, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 9.354915505506839e-05, | |
| "loss": 1.0599, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.7534246575342465, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 9.116534377924883e-05, | |
| "loss": 1.0554, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.821917808219178, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 8.878658234765858e-05, | |
| "loss": 1.0503, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.890410958904109, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 8.641423044814374e-05, | |
| "loss": 1.0632, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.958904109589041, | |
| "grad_norm": 0.431640625, | |
| "learning_rate": 8.404964410489485e-05, | |
| "loss": 1.0583, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.541933536529541, | |
| "eval_runtime": 0.5507, | |
| "eval_samples_per_second": 18.16, | |
| "eval_steps_per_second": 1.816, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 6.027397260273973, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 8.169417490335007e-05, | |
| "loss": 1.0504, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.095890410958904, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 7.934916921763628e-05, | |
| "loss": 1.0301, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 6.164383561643835, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 7.701596744098818e-05, | |
| "loss": 1.0358, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.232876712328767, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 7.469590321958662e-05, | |
| "loss": 1.0316, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 6.301369863013699, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 7.239030269025311e-05, | |
| "loss": 1.0415, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.36986301369863, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 7.010048372243698e-05, | |
| "loss": 1.0336, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 6.438356164383562, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 6.782775516492771e-05, | |
| "loss": 1.0496, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.506849315068493, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 6.5573416097724e-05, | |
| "loss": 1.04, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 6.575342465753424, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 6.333875508948593e-05, | |
| "loss": 1.0461, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.6438356164383565, | |
| "grad_norm": 0.4296875, | |
| "learning_rate": 6.112504946099604e-05, | |
| "loss": 1.0439, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 6.712328767123288, | |
| "grad_norm": 0.42578125, | |
| "learning_rate": 5.8933564555049105e-05, | |
| "loss": 1.0358, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.780821917808219, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 5.6765553013188766e-05, | |
| "loss": 1.045, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 6.8493150684931505, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 5.462225405970401e-05, | |
| "loss": 1.0329, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.917808219178082, | |
| "grad_norm": 0.388671875, | |
| "learning_rate": 5.2504892793295e-05, | |
| "loss": 1.0442, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 6.986301369863014, | |
| "grad_norm": 0.37109375, | |
| "learning_rate": 5.041467948681269e-05, | |
| "loss": 1.04, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.5487561225891113, | |
| "eval_runtime": 0.5536, | |
| "eval_samples_per_second": 18.064, | |
| "eval_steps_per_second": 1.806, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 7.054794520547945, | |
| "grad_norm": 0.384765625, | |
| "learning_rate": 4.835280889547351e-05, | |
| "loss": 1.0298, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 7.123287671232877, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 4.6320459573942856e-05, | |
| "loss": 1.0213, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.191780821917808, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 4.431879320267972e-05, | |
| "loss": 1.0334, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.260273972602739, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 4.2348953923925916e-05, | |
| "loss": 1.0208, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.328767123287671, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 4.041206768772022e-05, | |
| "loss": 1.0323, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 7.397260273972603, | |
| "grad_norm": 0.41015625, | |
| "learning_rate": 3.850924160831115e-05, | |
| "loss": 1.0295, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.465753424657534, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 3.6641563331336125e-05, | |
| "loss": 1.0266, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 7.534246575342466, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 3.4810100412128747e-05, | |
| "loss": 1.0218, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.602739726027397, | |
| "grad_norm": 0.375, | |
| "learning_rate": 3.3015899705509734e-05, | |
| "loss": 1.0369, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 7.671232876712329, | |
| "grad_norm": 0.40234375, | |
| "learning_rate": 3.125998676740987e-05, | |
| "loss": 1.0308, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.739726027397261, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 2.9543365268667867e-05, | |
| "loss": 1.0225, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 7.808219178082192, | |
| "grad_norm": 0.36328125, | |
| "learning_rate": 2.7867016421336776e-05, | |
| "loss": 1.0236, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.876712328767123, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 2.6231898417828603e-05, | |
| "loss": 1.0272, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 7.945205479452055, | |
| "grad_norm": 0.37890625, | |
| "learning_rate": 2.4638945883216235e-05, | |
| "loss": 1.0248, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.557366132736206, | |
| "eval_runtime": 0.554, | |
| "eval_samples_per_second": 18.051, | |
| "eval_steps_per_second": 1.805, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 8.013698630136986, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 2.3089069341006565e-05, | |
| "loss": 1.0197, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 8.082191780821917, | |
| "grad_norm": 0.359375, | |
| "learning_rate": 2.1583154692689976e-05, | |
| "loss": 1.0234, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.150684931506849, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 2.0122062711363532e-05, | |
| "loss": 1.0212, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 8.219178082191782, | |
| "grad_norm": 0.357421875, | |
| "learning_rate": 1.8706628549717452e-05, | |
| "loss": 1.0168, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.287671232876713, | |
| "grad_norm": 0.37109375, | |
| "learning_rate": 1.7337661262666294e-05, | |
| "loss": 1.0172, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 8.356164383561644, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 1.601594334489702e-05, | |
| "loss": 1.0167, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.424657534246576, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 1.474223028359939e-05, | |
| "loss": 1.0271, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 8.493150684931507, | |
| "grad_norm": 0.369140625, | |
| "learning_rate": 1.3517250126632986e-05, | |
| "loss": 1.0233, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.561643835616438, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 1.2341703066379074e-05, | |
| "loss": 1.0209, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 8.63013698630137, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 1.1216261039514087e-05, | |
| "loss": 1.0143, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.698630136986301, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 1.0141567342934132e-05, | |
| "loss": 1.0231, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 8.767123287671232, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 9.118236266049707e-06, | |
| "loss": 1.014, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.835616438356164, | |
| "grad_norm": 0.375, | |
| "learning_rate": 8.146852739661105e-06, | |
| "loss": 1.016, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 8.904109589041095, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 7.2279720016148244e-06, | |
| "loss": 1.0274, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.972602739726028, | |
| "grad_norm": 0.392578125, | |
| "learning_rate": 6.36211927943271e-06, | |
| "loss": 1.021, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.5613903999328613, | |
| "eval_runtime": 0.5421, | |
| "eval_samples_per_second": 18.447, | |
| "eval_steps_per_second": 1.845, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 9.04109589041096, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 5.549789490094304e-06, | |
| "loss": 1.0166, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.10958904109589, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 4.79144695714504e-06, | |
| "loss": 1.0251, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 9.178082191780822, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 4.087525145291204e-06, | |
| "loss": 1.0213, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.246575342465754, | |
| "grad_norm": 0.404296875, | |
| "learning_rate": 3.4384264126337328e-06, | |
| "loss": 1.0181, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 9.315068493150685, | |
| "grad_norm": 0.357421875, | |
| "learning_rate": 2.8445217806824077e-06, | |
| "loss": 1.0202, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.383561643835616, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 2.30615072228183e-06, | |
| "loss": 1.0139, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 9.452054794520548, | |
| "grad_norm": 0.359375, | |
| "learning_rate": 1.8236209675705274e-06, | |
| "loss": 1.0292, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.520547945205479, | |
| "grad_norm": 0.36328125, | |
| "learning_rate": 1.397208328083921e-06, | |
| "loss": 1.016, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 9.58904109589041, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 1.0271565391018922e-06, | |
| "loss": 1.0206, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.657534246575342, | |
| "grad_norm": 0.369140625, | |
| "learning_rate": 7.136771203310245e-07, | |
| "loss": 1.0181, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 9.726027397260275, | |
| "grad_norm": 0.359375, | |
| "learning_rate": 4.569492550008603e-07, | |
| "loss": 1.0123, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.794520547945206, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 2.5711968744382974e-07, | |
| "loss": 1.0101, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 9.863013698630137, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 1.143026392168789e-07, | |
| "loss": 1.0103, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.931506849315069, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 2.8579743813006432e-08, | |
| "loss": 1.0282, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.36328125, | |
| "learning_rate": 0.0, | |
| "loss": 1.0179, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.5617620944976807, | |
| "eval_runtime": 0.5453, | |
| "eval_samples_per_second": 18.339, | |
| "eval_steps_per_second": 1.834, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 730, | |
| "total_flos": 4.287825372721971e+17, | |
| "train_loss": 1.1969801510850044, | |
| "train_runtime": 3891.9077, | |
| "train_samples_per_second": 9.003, | |
| "train_steps_per_second": 0.188 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 730, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.287825372721971e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |