| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8316831683168315, | |
| "eval_steps": 13, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0919, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "eval_loss": 2.079954147338867, | |
| "eval_runtime": 13.8908, | |
| "eval_samples_per_second": 8.999, | |
| "eval_steps_per_second": 4.535, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0814, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": 1.1953125, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0499, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 1.0859375, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0153, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8982, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13861386138613863, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8226, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7074, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6317, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21782178217821782, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 0.0001999863304992469, | |
| "loss": 1.5801, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 1.5721, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.25742574257425743, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 0.00019987699691483048, | |
| "loss": 1.5479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25742574257425743, | |
| "eval_loss": 1.5341482162475586, | |
| "eval_runtime": 13.8795, | |
| "eval_samples_per_second": 9.006, | |
| "eval_steps_per_second": 4.539, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.27722772277227725, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 1.534, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 1.4804, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 1.4805, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.33663366336633666, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 0.00019933092663536382, | |
| "loss": 1.3809, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": 0.3125, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 1.3837, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37623762376237624, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 0.00019889478706014687, | |
| "loss": 1.3673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 1.366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "grad_norm": 0.34375, | |
| "learning_rate": 0.00019835050748723824, | |
| "loss": 1.3318, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.43564356435643564, | |
| "grad_norm": 0.341796875, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 1.2741, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.45544554455445546, | |
| "grad_norm": 0.326171875, | |
| "learning_rate": 0.00019769868307835994, | |
| "loss": 1.2978, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.291015625, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.2733, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 1.2302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "grad_norm": 0.318359375, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.2083, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "eval_loss": 1.224540114402771, | |
| "eval_runtime": 13.8695, | |
| "eval_samples_per_second": 9.013, | |
| "eval_steps_per_second": 4.542, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 0.00019607536761368484, | |
| "loss": 1.1761, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 1.1751, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5742574257425742, | |
| "grad_norm": 0.310546875, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.2002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 1.1544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6138613861386139, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 0.00019403193901161613, | |
| "loss": 1.1384, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 0.236328125, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 1.0999, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "grad_norm": 0.326171875, | |
| "learning_rate": 0.00019285540384897073, | |
| "loss": 1.1576, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6732673267326733, | |
| "grad_norm": 0.310546875, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 1.091, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.693069306930693, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 1.056, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 1.1068, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7326732673267327, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 0.00019019912301329592, | |
| "loss": 1.0583, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7524752475247525, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 1.0671, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7722772277227723, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 0.0001887222819443612, | |
| "loss": 1.0851, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7722772277227723, | |
| "eval_loss": 1.060703158378601, | |
| "eval_runtime": 13.878, | |
| "eval_samples_per_second": 9.007, | |
| "eval_steps_per_second": 4.54, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 1.0343, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8118811881188119, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 0.00018714842436272773, | |
| "loss": 0.9789, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "grad_norm": 0.248046875, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 1.0174, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8514851485148515, | |
| "grad_norm": 0.2294921875, | |
| "learning_rate": 0.0001854792712585539, | |
| "loss": 1.0004, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": 0.228515625, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 1.0281, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8910891089108911, | |
| "grad_norm": 0.220703125, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 0.9992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9108910891089109, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.9635, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9306930693069307, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 0.00018186248146866927, | |
| "loss": 1.006, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 0.2451171875, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9891, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9702970297029703, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 0.0001799187996894925, | |
| "loss": 0.9809, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": 0.212890625, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.9646, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.00990099009901, | |
| "grad_norm": 0.2451171875, | |
| "learning_rate": 0.00017788772787621126, | |
| "loss": 0.9553, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0297029702970297, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.9432, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0297029702970297, | |
| "eval_loss": 0.9755253195762634, | |
| "eval_runtime": 13.879, | |
| "eval_samples_per_second": 9.006, | |
| "eval_steps_per_second": 4.539, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0495049504950495, | |
| "grad_norm": 0.2021484375, | |
| "learning_rate": 0.0001757714869760335, | |
| "loss": 0.9631, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.0693069306930694, | |
| "grad_norm": 0.3046875, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.9539, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0198019801980198, | |
| "grad_norm": 0.232421875, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 0.9559, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0396039603960396, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.9111, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0594059405940595, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 0.00017129284482913972, | |
| "loss": 0.9503, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.0792079207920793, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.911, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.099009900990099, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 0.0001689353409118566, | |
| "loss": 0.9041, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.118811881188119, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.9117, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 0.0001665024572113848, | |
| "loss": 0.9351, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.1584158415841583, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.9438, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.1782178217821782, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 0.00016399685405033167, | |
| "loss": 0.9075, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.198019801980198, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.8983, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.2178217821782178, | |
| "grad_norm": 0.2021484375, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 0.9007, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.2178217821782178, | |
| "eval_loss": 0.9333999156951904, | |
| "eval_runtime": 13.8668, | |
| "eval_samples_per_second": 9.014, | |
| "eval_steps_per_second": 4.543, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.2376237623762376, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.9108, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.2574257425742574, | |
| "grad_norm": 0.232421875, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.9177, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.2772277227722773, | |
| "grad_norm": 0.271484375, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.9, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.297029702970297, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 0.0001560715057351673, | |
| "loss": 0.9096, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.316831683168317, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.8946, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.3366336633663367, | |
| "grad_norm": 0.31640625, | |
| "learning_rate": 0.0001533031728727994, | |
| "loss": 0.8995, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.3564356435643563, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.922, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.3762376237623761, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 0.0001504765537734844, | |
| "loss": 0.885, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.396039603960396, | |
| "grad_norm": 0.248046875, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.895, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4158415841584158, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 0.892, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.4356435643564356, | |
| "grad_norm": 0.216796875, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.8277, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.4554455445544554, | |
| "grad_norm": 0.23828125, | |
| "learning_rate": 0.00014466088068528068, | |
| "loss": 0.8687, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.4752475247524752, | |
| "grad_norm": 0.228515625, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.8765, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.4752475247524752, | |
| "eval_loss": 0.9083698391914368, | |
| "eval_runtime": 13.8834, | |
| "eval_samples_per_second": 9.004, | |
| "eval_steps_per_second": 4.538, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.495049504950495, | |
| "grad_norm": 0.228515625, | |
| "learning_rate": 0.00014167818604952906, | |
| "loss": 0.8797, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.5148514851485149, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.905, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.5346534653465347, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 0.00013864991692924523, | |
| "loss": 0.8575, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.5544554455445545, | |
| "grad_norm": 0.2451171875, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.8957, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.5742574257425743, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 0.00013557938469225167, | |
| "loss": 0.8792, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.5940594059405941, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.889, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.613861386138614, | |
| "grad_norm": 0.228515625, | |
| "learning_rate": 0.00013246994692046836, | |
| "loss": 0.8657, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.6336633663366338, | |
| "grad_norm": 0.20703125, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8784, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.6534653465346536, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 0.0001293250037384465, | |
| "loss": 0.8822, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.6732673267326734, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.9092, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.693069306930693, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 0.00012614799409538198, | |
| "loss": 0.8813, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.7128712871287128, | |
| "grad_norm": 0.2294921875, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.8975, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.7326732673267327, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 0.00012294239200467516, | |
| "loss": 0.8789, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.7326732673267327, | |
| "eval_loss": 0.8891416788101196, | |
| "eval_runtime": 13.872, | |
| "eval_samples_per_second": 9.011, | |
| "eval_steps_per_second": 4.542, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.7524752475247525, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.9184, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.7722772277227723, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 0.00011971170274514802, | |
| "loss": 0.8854, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.7920792079207921, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.8688, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.811881188118812, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 0.00011645945902807341, | |
| "loss": 0.8281, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.8316831683168315, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.8488, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.8514851485148514, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 0.00011318921713420691, | |
| "loss": 0.8742, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.8712871287128712, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.8586, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.891089108910891, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 0.0001099045530250463, | |
| "loss": 0.8776, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.9108910891089108, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.8563, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9306930693069306, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 0.00010660905843256994, | |
| "loss": 0.8381, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.9504950495049505, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 0.847, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.9702970297029703, | |
| "grad_norm": 0.23828125, | |
| "learning_rate": 0.00010330633693173082, | |
| "loss": 0.8512, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.99009900990099, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 0.8304, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.99009900990099, | |
| "eval_loss": 0.8779018521308899, | |
| "eval_runtime": 13.8827, | |
| "eval_samples_per_second": 9.004, | |
| "eval_steps_per_second": 4.538, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.00990099009901, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8523, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.0297029702970297, | |
| "grad_norm": 0.2392578125, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 0.8109, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.0495049504950495, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 9.669366306826919e-05, | |
| "loss": 0.8394, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.0693069306930694, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 0.8524, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.01980198019802, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 9.339094156743007e-05, | |
| "loss": 0.8391, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.0396039603960396, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.8317, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0594059405940595, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 9.009544697495374e-05, | |
| "loss": 0.833, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.0792079207920793, | |
| "grad_norm": 0.2041015625, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 0.8408, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.099009900990099, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 8.681078286579311e-05, | |
| "loss": 0.8459, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.118811881188119, | |
| "grad_norm": 0.2021484375, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 0.8177, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.1386138613861387, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 8.35405409719266e-05, | |
| "loss": 0.8451, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.1584158415841586, | |
| "grad_norm": 0.2294921875, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 0.8543, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.1782178217821784, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 8.028829725485199e-05, | |
| "loss": 0.8194, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.1782178217821784, | |
| "eval_loss": 0.8713971972465515, | |
| "eval_runtime": 13.8976, | |
| "eval_samples_per_second": 8.994, | |
| "eval_steps_per_second": 4.533, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.198019801980198, | |
| "grad_norm": 0.2333984375, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 0.808, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.217821782178218, | |
| "grad_norm": 0.2470703125, | |
| "learning_rate": 7.705760799532485e-05, | |
| "loss": 0.8073, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.237623762376238, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.8392, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.2574257425742577, | |
| "grad_norm": 0.25, | |
| "learning_rate": 7.385200590461803e-05, | |
| "loss": 0.8574, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.2772277227722775, | |
| "grad_norm": 0.271484375, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 0.8338, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.297029702970297, | |
| "grad_norm": 0.294921875, | |
| "learning_rate": 7.067499626155354e-05, | |
| "loss": 0.8788, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.3168316831683167, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.8297, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.3366336633663365, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 6.753005307953167e-05, | |
| "loss": 0.8125, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.3564356435643563, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 0.814, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.376237623762376, | |
| "grad_norm": 0.27734375, | |
| "learning_rate": 6.442061530774834e-05, | |
| "loss": 0.8335, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.396039603960396, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 0.8512, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.4158415841584158, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 6.135008307075481e-05, | |
| "loss": 0.8297, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.4356435643564356, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.848, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.4356435643564356, | |
| "eval_loss": 0.8665071129798889, | |
| "eval_runtime": 13.8735, | |
| "eval_samples_per_second": 9.01, | |
| "eval_steps_per_second": 4.541, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.4554455445544554, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 5.832181395047098e-05, | |
| "loss": 0.8203, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.4752475247524752, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 0.8519, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.495049504950495, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 5.533911931471936e-05, | |
| "loss": 0.83, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.514851485148515, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 0.842, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.5346534653465347, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 5.240526069629265e-05, | |
| "loss": 0.8419, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.5544554455445545, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 0.8458, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.5742574257425743, | |
| "grad_norm": 0.203125, | |
| "learning_rate": 4.952344622651566e-05, | |
| "loss": 0.8133, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.594059405940594, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 0.8103, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.613861386138614, | |
| "grad_norm": 0.20703125, | |
| "learning_rate": 4.669682712720065e-05, | |
| "loss": 0.8105, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.633663366336634, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.8305, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.6534653465346536, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 4.392849426483274e-05, | |
| "loss": 0.7881, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.6732673267326734, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 0.8204, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.693069306930693, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.8354, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.693069306930693, | |
| "eval_loss": 0.8626759648323059, | |
| "eval_runtime": 13.8585, | |
| "eval_samples_per_second": 9.02, | |
| "eval_steps_per_second": 4.546, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.7128712871287126, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 0.8441, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.7326732673267324, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 3.857872873103322e-05, | |
| "loss": 0.8084, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.7524752475247523, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 0.8184, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.772277227722772, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 3.600314594966834e-05, | |
| "loss": 0.8302, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.792079207920792, | |
| "grad_norm": 0.2041015625, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 0.8503, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.8118811881188117, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 3.349754278861517e-05, | |
| "loss": 0.8273, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.8316831683168315, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.8332, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.1227070440800256e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |