| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9977595220313666, | |
| "eval_steps": 20, | |
| "global_step": 334, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5435, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3967, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8e-05, | |
| "loss": 1.368, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0507, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0016, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9427, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019999949852874652, | |
| "loss": 0.9023, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019999799412001546, | |
| "loss": 0.8257, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001999954867888952, | |
| "loss": 0.9064, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019999197656053288, | |
| "loss": 0.8408, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019998746347013398, | |
| "loss": 0.9058, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001999819475629623, | |
| "loss": 0.8419, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019997542889433915, | |
| "loss": 0.8535, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019996790752964305, | |
| "loss": 0.8121, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019995938354430898, | |
| "loss": 0.7725, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019994985702382758, | |
| "loss": 0.7661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.517298698425293, | |
| "eval_runtime": 15.7157, | |
| "eval_samples_per_second": 37.097, | |
| "eval_steps_per_second": 18.58, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001999393280637444, | |
| "loss": 0.7878, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019992779676965885, | |
| "loss": 0.7435, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019991526325722315, | |
| "loss": 0.8219, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019990172765214128, | |
| "loss": 0.7624, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019988719009016753, | |
| "loss": 0.7527, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019987165071710527, | |
| "loss": 0.7699, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019985510968880557, | |
| "loss": 0.7536, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019983756717116536, | |
| "loss": 0.7863, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000199819023340126, | |
| "loss": 0.7166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001997994783816715, | |
| "loss": 0.7459, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019977893249182652, | |
| "loss": 0.7376, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019975738587665456, | |
| "loss": 0.7624, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019973483875225574, | |
| "loss": 0.7329, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019971129134476473, | |
| "loss": 0.7512, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001996867438903486, | |
| "loss": 0.7211, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019966119663520412, | |
| "loss": 0.7467, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019963464983555556, | |
| "loss": 0.7186, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001996071037576521, | |
| "loss": 0.7244, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019957855867776508, | |
| "loss": 0.7071, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019954901488218515, | |
| "loss": 0.7681, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.2323185205459595, | |
| "eval_runtime": 15.7174, | |
| "eval_samples_per_second": 37.093, | |
| "eval_steps_per_second": 18.578, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001995184726672197, | |
| "loss": 0.708, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 0.7443, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000199454394214426, | |
| "loss": 0.7079, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001994208586192678, | |
| "loss": 0.6812, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001993863258900577, | |
| "loss": 0.6792, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019935079637313906, | |
| "loss": 0.6553, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001993142704248525, | |
| "loss": 0.6936, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019927674841153237, | |
| "loss": 0.74, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019923823070950282, | |
| "loss": 0.7154, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001991987177050743, | |
| "loss": 0.6902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001991582097945395, | |
| "loss": 0.7009, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019911670738416947, | |
| "loss": 0.699, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019907421089020955, | |
| "loss": 0.681, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019903072073887507, | |
| "loss": 0.7097, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019898623736634737, | |
| "loss": 0.6861, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000198940761218769, | |
| "loss": 0.7279, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019889429275223957, | |
| "loss": 0.6784, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019884683243281116, | |
| "loss": 0.7, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019879838073648341, | |
| "loss": 0.6634, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019874893814919906, | |
| "loss": 0.6647, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.1306297779083252, | |
| "eval_runtime": 15.73, | |
| "eval_samples_per_second": 37.063, | |
| "eval_steps_per_second": 18.563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019869850516683875, | |
| "loss": 0.7377, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019864708229521636, | |
| "loss": 0.6794, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019859467005007368, | |
| "loss": 0.6744, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001985412689570754, | |
| "loss": 0.6921, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019848687955180386, | |
| "loss": 0.7389, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019843150237975344, | |
| "loss": 0.6795, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019837513799632534, | |
| "loss": 0.6917, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019831778696682194, | |
| "loss": 0.66, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019825944986644114, | |
| "loss": 0.6926, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019820012728027044, | |
| "loss": 0.7265, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019813981980328129, | |
| "loss": 0.733, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.6543, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019801625260611685, | |
| "loss": 0.673, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019795299412524945, | |
| "loss": 0.6773, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001978887532321671, | |
| "loss": 0.6469, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000197823530571169, | |
| "loss": 0.7272, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00019775732679640093, | |
| "loss": 0.7015, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001976901425718487, | |
| "loss": 0.6973, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019762197857133148, | |
| "loss": 0.6831, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019755283547849494, | |
| "loss": 0.6742, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.0846511125564575, | |
| "eval_runtime": 15.6885, | |
| "eval_samples_per_second": 37.161, | |
| "eval_steps_per_second": 18.612, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001974827139868046, | |
| "loss": 0.683, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001974116147995387, | |
| "loss": 0.7063, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019733953862978123, | |
| "loss": 0.6963, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019726648620041468, | |
| "loss": 0.7179, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019719245824411296, | |
| "loss": 0.7315, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001971174555033339, | |
| "loss": 0.6839, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019704147873031186, | |
| "loss": 0.6917, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019696452868705024, | |
| "loss": 0.6828, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019688660614531367, | |
| "loss": 0.6965, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019680771188662044, | |
| "loss": 0.6522, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019672784670223464, | |
| "loss": 0.6939, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001966470113931582, | |
| "loss": 0.7037, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019656520677012264, | |
| "loss": 0.6903, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019648243365358146, | |
| "loss": 0.706, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001963986928737014, | |
| "loss": 0.6253, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00019631398527035422, | |
| "loss": 0.732, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001962283116931086, | |
| "loss": 0.6935, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00019614167300122126, | |
| "loss": 0.731, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001960540700636284, | |
| "loss": 0.6916, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001959655037589372, | |
| "loss": 0.6995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.0572510957717896, | |
| "eval_runtime": 15.7086, | |
| "eval_samples_per_second": 37.113, | |
| "eval_steps_per_second": 18.588, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001958759749754167, | |
| "loss": 0.7313, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00019578548461098914, | |
| "loss": 0.7337, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001956940335732209, | |
| "loss": 0.6721, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019560162277931325, | |
| "loss": 0.6907, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001955082531560934, | |
| "loss": 0.6599, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019541392564000488, | |
| "loss": 0.6941, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019531864117709855, | |
| "loss": 0.7037, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019522240072302274, | |
| "loss": 0.6819, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019512520524301387, | |
| "loss": 0.6729, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019502705571188672, | |
| "loss": 0.713, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019492795311402473, | |
| "loss": 0.6638, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001948278984433699, | |
| "loss": 0.647, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019472689270341303, | |
| "loss": 0.614, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001946249369071837, | |
| "loss": 0.6783, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001945220320772399, | |
| "loss": 0.7093, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019441817924565786, | |
| "loss": 0.7179, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019431337945402185, | |
| "loss": 0.7241, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001942076337534135, | |
| "loss": 0.7168, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019410094320440138, | |
| "loss": 0.7127, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019399330887703037, | |
| "loss": 0.6883, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.0412259101867676, | |
| "eval_runtime": 15.6448, | |
| "eval_samples_per_second": 37.265, | |
| "eval_steps_per_second": 18.664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019388473185081087, | |
| "loss": 0.6663, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019377521321470805, | |
| "loss": 0.7319, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019366475406713086, | |
| "loss": 0.6942, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019355335551592105, | |
| "loss": 0.6847, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.000193441018678342, | |
| "loss": 0.6732, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019332774468106768, | |
| "loss": 0.6661, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019321353466017108, | |
| "loss": 0.7044, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019309838976111311, | |
| "loss": 0.6794, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019298231113873087, | |
| "loss": 0.7275, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019286529995722623, | |
| "loss": 0.685, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019274735739015404, | |
| "loss": 0.6825, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019262848462041045, | |
| "loss": 0.6857, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.000192508682840221, | |
| "loss": 0.7139, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6413, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019226629706398186, | |
| "loss": 0.7257, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001921437154989221, | |
| "loss": 0.6365, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019202020978537207, | |
| "loss": 0.66, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019189578116202307, | |
| "loss": 0.6525, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019177043087682265, | |
| "loss": 0.6438, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019164416018696207, | |
| "loss": 0.6437, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.0374538898468018, | |
| "eval_runtime": 15.6903, | |
| "eval_samples_per_second": 37.157, | |
| "eval_steps_per_second": 18.61, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019151697035886382, | |
| "loss": 0.6878, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019138886266816866, | |
| "loss": 0.7072, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019125983839972317, | |
| "loss": 0.69, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019112989884756653, | |
| "loss": 0.7666, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019099904531491774, | |
| "loss": 0.689, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001908672791141625, | |
| "loss": 0.7394, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001907346015668401, | |
| "loss": 0.6882, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019060101400362998, | |
| "loss": 0.6394, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019046651776433862, | |
| "loss": 0.6932, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019033111419788597, | |
| "loss": 0.6676, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019019480466229201, | |
| "loss": 0.6818, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.000190057590524663, | |
| "loss": 0.6695, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001899194731611778, | |
| "loss": 0.7082, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00018978045395707418, | |
| "loss": 0.6626, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00018964053430663483, | |
| "loss": 0.6708, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001894997156131734, | |
| "loss": 0.7864, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00018935799928902045, | |
| "loss": 0.6899, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001892153867555092, | |
| "loss": 0.6574, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00018907187944296137, | |
| "loss": 0.7157, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018892747879067286, | |
| "loss": 0.6331, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.0186299085617065, | |
| "eval_runtime": 15.6809, | |
| "eval_samples_per_second": 37.179, | |
| "eval_steps_per_second": 18.621, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001887821862468991, | |
| "loss": 0.7219, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018863600326884082, | |
| "loss": 0.7203, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00018848893132262926, | |
| "loss": 0.6722, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00018834097188331143, | |
| "loss": 0.7223, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001881921264348355, | |
| "loss": 0.659, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018804239647003573, | |
| "loss": 0.6763, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018789178349061753, | |
| "loss": 0.649, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018774028900714256, | |
| "loss": 0.6762, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018758791453901336, | |
| "loss": 0.6547, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 0.6516, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001872805317705159, | |
| "loss": 0.6479, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001871255265530201, | |
| "loss": 0.6986, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00018696964751658404, | |
| "loss": 0.7402, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00018681289622458485, | |
| "loss": 0.6629, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00018665527424914787, | |
| "loss": 0.6761, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018649678317113084, | |
| "loss": 0.6746, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001863374245801082, | |
| "loss": 0.67, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018617720007435497, | |
| "loss": 0.7406, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018601611126083087, | |
| "loss": 0.6735, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000185854159755164, | |
| "loss": 0.6686, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.0153461694717407, | |
| "eval_runtime": 15.6769, | |
| "eval_samples_per_second": 37.189, | |
| "eval_steps_per_second": 18.626, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018569134718163496, | |
| "loss": 0.6416, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018552767517316022, | |
| "loss": 0.6456, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018536314537127586, | |
| "loss": 0.6794, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018519775942612128, | |
| "loss": 0.6754, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018503151899642236, | |
| "loss": 0.6251, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018486442574947511, | |
| "loss": 0.7354, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018469648136112867, | |
| "loss": 0.6457, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001845276875157687, | |
| "loss": 0.6823, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018435804590630043, | |
| "loss": 0.6891, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001841875582341317, | |
| "loss": 0.6731, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018401622620915583, | |
| "loss": 0.6857, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001838440515497345, | |
| "loss": 0.6807, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001836710359826806, | |
| "loss": 0.6622, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018349718124324076, | |
| "loss": 0.6628, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018332248907507807, | |
| "loss": 0.724, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.675, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018297059946921355, | |
| "loss": 0.677, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018279340556076216, | |
| "loss": 0.6555, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001826153812820534, | |
| "loss": 0.6273, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001824365284185684, | |
| "loss": 0.6767, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.004173994064331, | |
| "eval_runtime": 15.726, | |
| "eval_samples_per_second": 37.072, | |
| "eval_steps_per_second": 18.568, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018225684876409863, | |
| "loss": 0.6719, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018207634412072764, | |
| "loss": 0.6522, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001818950162988133, | |
| "loss": 0.6957, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018171286711696934, | |
| "loss": 0.7013, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018152989840204735, | |
| "loss": 0.6603, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001813461119891184, | |
| "loss": 0.6788, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001811615097214545, | |
| "loss": 0.6795, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018097609345051025, | |
| "loss": 0.6458, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018078986503590428, | |
| "loss": 0.6741, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018060282634540053, | |
| "loss": 0.6537, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001804149792548895, | |
| "loss": 0.6501, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018022632564836948, | |
| "loss": 0.673, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00018003686741792772, | |
| "loss": 0.6746, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001798466064637214, | |
| "loss": 0.6329, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00017965554469395837, | |
| "loss": 0.69, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017946368402487845, | |
| "loss": 0.6513, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017927102638073383, | |
| "loss": 0.6758, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017907757369376985, | |
| "loss": 0.6776, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017888332790420584, | |
| "loss": 0.6487, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017868829096021527, | |
| "loss": 0.7037, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.002336025238037, | |
| "eval_runtime": 17.4124, | |
| "eval_samples_per_second": 33.482, | |
| "eval_steps_per_second": 16.77, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017849246481790664, | |
| "loss": 0.71, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017829585144130356, | |
| "loss": 0.6695, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00017809845280232514, | |
| "loss": 0.6645, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001779002708807662, | |
| "loss": 0.6983, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001777013076642776, | |
| "loss": 0.6785, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001775015651483459, | |
| "loss": 0.6791, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001773010453362737, | |
| "loss": 0.695, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00017709975023915949, | |
| "loss": 0.6352, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00017689768187587732, | |
| "loss": 0.6911, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001766948422730567, | |
| "loss": 0.7189, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017649123346506223, | |
| "loss": 0.6838, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001762868574939732, | |
| "loss": 0.7209, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00017608171640956313, | |
| "loss": 0.6719, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001758758122692791, | |
| "loss": 0.6624, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001756691471382213, | |
| "loss": 0.637, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00017546172308912213, | |
| "loss": 0.653, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001752535422023256, | |
| "loss": 0.6368, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00017504460656576627, | |
| "loss": 0.6713, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00017483491827494847, | |
| "loss": 0.6614, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001746244794329252, | |
| "loss": 0.6994, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.0014034509658813, | |
| "eval_runtime": 15.6575, | |
| "eval_samples_per_second": 37.235, | |
| "eval_steps_per_second": 18.649, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00017441329215027706, | |
| "loss": 0.6644, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001742013585450911, | |
| "loss": 0.6374, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017398868074293948, | |
| "loss": 0.6627, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017377526087685832, | |
| "loss": 0.6936, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017356110108732617, | |
| "loss": 0.6419, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001733462035222426, | |
| "loss": 0.6402, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001731305703369066, | |
| "loss": 0.7028, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001729142036939951, | |
| "loss": 0.6146, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001726971057635411, | |
| "loss": 0.6702, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000172479278722912, | |
| "loss": 0.6971, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00017226072475678782, | |
| "loss": 0.6289, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001720414460571392, | |
| "loss": 0.6786, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001718214448232054, | |
| "loss": 0.6599, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001716007232614723, | |
| "loss": 0.656, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00017137928358565028, | |
| "loss": 0.7092, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.000171157128016652, | |
| "loss": 0.6596, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017093425878257005, | |
| "loss": 0.6937, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7027, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017048638826729163, | |
| "loss": 0.6776, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001702613914779789, | |
| "loss": 0.7012, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.9995876550674438, | |
| "eval_runtime": 15.664, | |
| "eval_samples_per_second": 37.219, | |
| "eval_steps_per_second": 18.641, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00017003569000730498, | |
| "loss": 0.6786, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001698092861189259, | |
| "loss": 0.7071, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016958218208354252, | |
| "loss": 0.6556, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016935438017887772, | |
| "loss": 0.6418, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001691258826896536, | |
| "loss": 0.6726, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00016889669190756868, | |
| "loss": 0.6514, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016866681013127466, | |
| "loss": 0.6914, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016843623966635366, | |
| "loss": 0.6884, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016820498282529479, | |
| "loss": 0.6624, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001679730419274713, | |
| "loss": 0.7241, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00016774041929911698, | |
| "loss": 0.6923, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001675071172733031, | |
| "loss": 0.6817, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016727313818991487, | |
| "loss": 0.7042, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016703848439562785, | |
| "loss": 0.66, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016680315824388483, | |
| "loss": 0.662, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016656716209487174, | |
| "loss": 0.6174, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00016633049831549424, | |
| "loss": 0.6684, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0001660931692793541, | |
| "loss": 0.6581, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00016585517736672498, | |
| "loss": 0.6835, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.000165616524964529, | |
| "loss": 0.6599, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.9926242828369141, | |
| "eval_runtime": 15.669, | |
| "eval_samples_per_second": 37.207, | |
| "eval_steps_per_second": 18.636, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016537721446631252, | |
| "loss": 0.6619, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016513724827222227, | |
| "loss": 0.6557, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00016489662878898113, | |
| "loss": 0.6577, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00016465535842986434, | |
| "loss": 0.6423, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00016441343961467471, | |
| "loss": 0.6472, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.000164170874769719, | |
| "loss": 0.6434, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00016392766632778312, | |
| "loss": 0.6461, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00016368381672810786, | |
| "loss": 0.6857, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00016343932841636456, | |
| "loss": 0.6927, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001631942038446304, | |
| "loss": 0.6263, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00016294844547136395, | |
| "loss": 0.6857, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00016270205576138032, | |
| "loss": 0.682, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001624550371858267, | |
| "loss": 0.6964, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016220739222215738, | |
| "loss": 0.6261, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016195912335410895, | |
| "loss": 0.6848, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016171023307167545, | |
| "loss": 0.635, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001614607238710833, | |
| "loss": 0.6941, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001612105982547663, | |
| "loss": 0.6339, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001609598587313406, | |
| "loss": 0.6298, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00016070850781557948, | |
| "loss": 0.6401, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.9913042187690735, | |
| "eval_runtime": 15.6715, | |
| "eval_samples_per_second": 37.201, | |
| "eval_steps_per_second": 18.633, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00016045654802838812, | |
| "loss": 0.6483, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001602039818967783, | |
| "loss": 0.6352, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015995081195384315, | |
| "loss": 0.6344, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00015969704073873157, | |
| "loss": 0.6317, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000159442670796623, | |
| "loss": 0.6979, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001591877046787017, | |
| "loss": 0.6429, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015893214494213132, | |
| "loss": 0.6493, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015867599415002895, | |
| "loss": 0.6765, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015841925487143987, | |
| "loss": 0.6871, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00015816192968131138, | |
| "loss": 0.6389, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00015790402116046726, | |
| "loss": 0.6002, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001576455318955816, | |
| "loss": 0.6025, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001573864644791532, | |
| "loss": 0.6692, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015712682150947923, | |
| "loss": 0.7079, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015686660559062945, | |
| "loss": 0.6622, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015660581933241993, | |
| "loss": 0.6402, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00015634446535038688, | |
| "loss": 0.7251, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00015608254626576048, | |
| "loss": 0.6806, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00015582006470543855, | |
| "loss": 0.6475, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.6665, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.9910463094711304, | |
| "eval_runtime": 15.7019, | |
| "eval_samples_per_second": 37.129, | |
| "eval_steps_per_second": 18.596, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015529342469347958, | |
| "loss": 0.6674, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015502927152373914, | |
| "loss": 0.6873, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015476456644204328, | |
| "loss": 0.6425, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0001544993121032318, | |
| "loss": 0.6565, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015423351116765317, | |
| "loss": 0.6886, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000153967166301138, | |
| "loss": 0.6904, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015370028017497217, | |
| "loss": 0.6281, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015343285546587013, | |
| "loss": 0.6836, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015316489485594782, | |
| "loss": 0.697, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015289640103269625, | |
| "loss": 0.656, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015262737668895405, | |
| "loss": 0.6649, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015235782452288068, | |
| "loss": 0.6775, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015208774723792943, | |
| "loss": 0.6637, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001518171475428202, | |
| "loss": 0.7175, | |
| "step": 334 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1002, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4.735056607476449e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |