| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.20108275328692962, |
| "eval_steps": 65, |
| "global_step": 65, |
| "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 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 323, |
| "num_train_epochs": 1, |
| "save_steps": 65, |
| "total_flos": 3.793060461625344e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
