| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.40216550657385924, |
| "eval_steps": 65, |
| "global_step": 130, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 2.7493, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 2.3529411764705884e-05, |
| "loss": 2.6209, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 2.6323, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 4.705882352941177e-05, |
| "loss": 2.7371, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 5.882352941176471e-05, |
| "loss": 2.7399, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 7.058823529411765e-05, |
| "loss": 2.6775, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 8.23529411764706e-05, |
| "loss": 2.6392, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 9.411764705882353e-05, |
| "loss": 2.6636, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00010588235294117647, |
| "loss": 2.6269, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00011764705882352942, |
| "loss": 2.6557, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00012941176470588237, |
| "loss": 2.5117, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0001411764705882353, |
| "loss": 2.54, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00015294117647058822, |
| "loss": 2.4645, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0001647058823529412, |
| "loss": 2.4728, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00017647058823529413, |
| "loss": 2.5242, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00018823529411764707, |
| "loss": 2.4592, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0002, |
| "loss": 2.364, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019999472984871732, |
| "loss": 2.3955, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019997891995035912, |
| "loss": 2.3193, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.0001999525719713366, |
| "loss": 2.3536, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.0001999156886888064, |
| "loss": 2.4059, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019986827399037812, |
| "loss": 2.4518, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019981033287370443, |
| "loss": 2.3709, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019974187144595432, |
| "loss": 2.4401, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00019966289692316944, |
| "loss": 2.3015, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00019957341762950344, |
| "loss": 2.3688, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00019947344299634464, |
| "loss": 2.2737, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00019936298356132176, |
| "loss": 2.2844, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0001992420509671936, |
| "loss": 2.2693, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00019911065796062135, |
| "loss": 2.2691, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019896881839082556, |
| "loss": 2.2378, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019881654720812594, |
| "loss": 2.1501, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019865386046236596, |
| "loss": 2.0803, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019848077530122083, |
| "loss": 2.1133, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0001982973099683902, |
| "loss": 2.0154, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019810348380167527, |
| "loss": 1.962, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019789931723094046, |
| "loss": 1.9794, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0001976848317759601, |
| "loss": 2.017, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00019746005004415005, |
| "loss": 1.9816, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00019722499572818496, |
| "loss": 1.9713, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019697969360350098, |
| "loss": 1.9338, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019672416952568416, |
| "loss": 1.983, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019645845042774553, |
| "loss": 1.821, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00019618256431728194, |
| "loss": 1.9501, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00019589654027352414, |
| "loss": 1.9909, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0001956004084442718, |
| "loss": 1.8494, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019529420004271567, |
| "loss": 1.8093, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0001949779473441478, |
| "loss": 1.7693, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019465168368255946, |
| "loss": 1.7823, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019431544344712776, |
| "loss": 1.7239, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00019396926207859084, |
| "loss": 2.2562, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00019361317606551238, |
| "loss": 2.201, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00019324722294043558, |
| "loss": 2.2162, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00019287144127592704, |
| "loss": 2.2388, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0001924858706805112, |
| "loss": 2.2686, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0001920905517944954, |
| "loss": 2.213, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00019168552628568631, |
| "loss": 2.1732, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00019127083684499806, |
| "loss": 2.2206, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00019084652718195238, |
| "loss": 2.0658, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0001904126420200716, |
| "loss": 2.1432, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00018996922709216455, |
| "loss": 2.0427, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00018951632913550626, |
| "loss": 2.1674, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00018905399588691163, |
| "loss": 2.1218, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018858227607770398, |
| "loss": 2.1721, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018810121942857845, |
| "loss": 2.1525, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 2.053250789642334, |
| "eval_runtime": 25.1667, |
| "eval_samples_per_second": 3.457, |
| "eval_steps_per_second": 0.437, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018761087664436138, |
| "loss": 2.1132, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00018711129940866575, |
| "loss": 2.127, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 2.1563, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00018608465317843678, |
| "loss": 2.0825, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00018555769239552233, |
| "loss": 2.1625, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00018502171357296144, |
| "loss": 2.1801, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00018447677320454367, |
| "loss": 2.1931, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00018392292872863267, |
| "loss": 2.1354, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00018336023852211195, |
| "loss": 2.2592, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00018278876189423179, |
| "loss": 2.1984, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018220855908035783, |
| "loss": 2.1576, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0001816196912356222, |
| "loss": 2.158, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018102222042847737, |
| "loss": 2.1722, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018041620963415417, |
| "loss": 2.144, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.000179801722728024, |
| "loss": 2.1204, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00017917882447886582, |
| "loss": 2.1186, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00017854758054203988, |
| "loss": 2.1699, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00017790805745256704, |
| "loss": 2.0864, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0001772603226181159, |
| "loss": 2.1616, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0001766044443118978, |
| "loss": 2.0011, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00017594049166547073, |
| "loss": 1.9033, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00017526853466145244, |
| "loss": 1.8434, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00017458864412614434, |
| "loss": 1.9592, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00017390089172206592, |
| "loss": 1.892, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00017320534994040148, |
| "loss": 1.8285, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00017250209209335927, |
| "loss": 1.8733, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0001717911923064442, |
| "loss": 1.8142, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00017107272551064473, |
| "loss": 1.7412, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00017034676743453499, |
| "loss": 1.721, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0001696133945962927, |
| "loss": 1.6415, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0001688726842956339, |
| "loss": 1.7964, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0001681247146056654, |
| "loss": 1.5657, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00016736956436465573, |
| "loss": 1.6301, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00016660731316772505, |
| "loss": 1.738, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0001658380413584558, |
| "loss": 1.5882, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0001650618300204242, |
| "loss": 2.1436, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00016427876096865394, |
| "loss": 2.1338, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0001634889167409923, |
| "loss": 2.1798, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0001626923805894107, |
| "loss": 2.1958, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00016188923647122947, |
| "loss": 2.0973, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0001610795690402688, |
| "loss": 2.2179, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00016026346363792567, |
| "loss": 2.1803, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00015944100628417868, |
| "loss": 2.1251, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00015861228366852148, |
| "loss": 2.0697, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00015777738314082514, |
| "loss": 2.1803, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00015693639270213136, |
| "loss": 2.112, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.000156089400995377, |
| "loss": 2.1563, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0001552364972960506, |
| "loss": 2.1587, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00015437777150278267, |
| "loss": 2.1726, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00015351331412787004, |
| "loss": 2.0995, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0001526432162877356, |
| "loss": 2.0481, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00015176756969332425, |
| "loss": 2.0404, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0001508864666404365, |
| "loss": 2.1471, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 2.1167, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00014910826320828084, |
| "loss": 2.1705, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0001482113502570349, |
| "loss": 2.0837, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00014730935568360102, |
| "loss": 2.1088, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00014640237456093634, |
| "loss": 2.046, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00014549050248759547, |
| "loss": 2.1104, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00014457383557765386, |
| "loss": 2.0926, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00014365247045057734, |
| "loss": 2.094, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0001427265042210381, |
| "loss": 2.0852, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00014179603448867835, |
| "loss": 2.0501, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00014086115932782314, |
| "loss": 2.1239, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.0001399219772771431, |
| "loss": 2.0143, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.9829031229019165, |
| "eval_runtime": 25.1483, |
| "eval_samples_per_second": 3.459, |
| "eval_steps_per_second": 0.437, |
| "step": 130 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 323, |
| "num_train_epochs": 1, |
| "save_steps": 65, |
| "total_flos": 7.631867476426752e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
