| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9945652173913043, |
| "eval_steps": 500, |
| "global_step": 61, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016304347826086956, |
| "grad_norm": 45.78702163696289, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 4.8845, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03260869565217391, |
| "grad_norm": 45.26464080810547, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 4.8307, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.04891304347826087, |
| "grad_norm": 45.96015167236328, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 4.8322, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06521739130434782, |
| "grad_norm": 45.86792755126953, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 4.8841, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.08152173913043478, |
| "grad_norm": 44.19926071166992, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 4.8013, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.09782608695652174, |
| "grad_norm": 45.76038360595703, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 4.8112, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.11413043478260869, |
| "grad_norm": 45.73483657836914, |
| "learning_rate": 3.5000000000000004e-07, |
| "loss": 4.8235, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13043478260869565, |
| "grad_norm": 46.2863655090332, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 4.895, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.14673913043478262, |
| "grad_norm": 44.06720733642578, |
| "learning_rate": 4.5000000000000003e-07, |
| "loss": 4.7696, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.16304347826086957, |
| "grad_norm": 43.8859977722168, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 4.7098, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1793478260869565, |
| "grad_norm": 44.059043884277344, |
| "learning_rate": 5.5e-07, |
| "loss": 4.7519, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.1956521739130435, |
| "grad_norm": 43.980201721191406, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 4.7465, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.21195652173913043, |
| "grad_norm": 40.88735580444336, |
| "learning_rate": 6.5e-07, |
| "loss": 4.5416, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.22826086956521738, |
| "grad_norm": 39.40138244628906, |
| "learning_rate": 7.000000000000001e-07, |
| "loss": 4.5273, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.24456521739130435, |
| "grad_norm": 37.21616744995117, |
| "learning_rate": 7.5e-07, |
| "loss": 4.4206, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 35.060447692871094, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 4.3318, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.27717391304347827, |
| "grad_norm": 30.492183685302734, |
| "learning_rate": 8.500000000000001e-07, |
| "loss": 4.0841, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.29347826086956524, |
| "grad_norm": 28.49239730834961, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 4.0979, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.30978260869565216, |
| "grad_norm": 24.898632049560547, |
| "learning_rate": 9.500000000000001e-07, |
| "loss": 3.8752, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.32608695652173914, |
| "grad_norm": 22.521434783935547, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 3.77, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3423913043478261, |
| "grad_norm": 20.311031341552734, |
| "learning_rate": 1.0500000000000001e-06, |
| "loss": 3.5973, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.358695652173913, |
| "grad_norm": 19.707839965820312, |
| "learning_rate": 1.1e-06, |
| "loss": 3.6102, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 18.431489944458008, |
| "learning_rate": 1.1500000000000002e-06, |
| "loss": 3.4147, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.391304347826087, |
| "grad_norm": 17.78904151916504, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 3.2665, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.4076086956521739, |
| "grad_norm": 18.014617919921875, |
| "learning_rate": 1.25e-06, |
| "loss": 3.1941, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.42391304347826086, |
| "grad_norm": 17.8990478515625, |
| "learning_rate": 1.3e-06, |
| "loss": 3.0377, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.44021739130434784, |
| "grad_norm": 18.60847282409668, |
| "learning_rate": 1.3500000000000002e-06, |
| "loss": 2.8489, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.45652173913043476, |
| "grad_norm": 18.562536239624023, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 2.6229, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.47282608695652173, |
| "grad_norm": 19.00884246826172, |
| "learning_rate": 1.45e-06, |
| "loss": 2.4521, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.4891304347826087, |
| "grad_norm": 20.419940948486328, |
| "learning_rate": 1.5e-06, |
| "loss": 2.3907, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5054347826086957, |
| "grad_norm": 21.181713104248047, |
| "learning_rate": 1.5500000000000002e-06, |
| "loss": 2.2032, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 20.592416763305664, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 2.004, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.5380434782608695, |
| "grad_norm": 20.40924835205078, |
| "learning_rate": 1.6500000000000003e-06, |
| "loss": 1.8373, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.5543478260869565, |
| "grad_norm": 18.38524627685547, |
| "learning_rate": 1.7000000000000002e-06, |
| "loss": 1.6218, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.5706521739130435, |
| "grad_norm": 18.922391891479492, |
| "learning_rate": 1.75e-06, |
| "loss": 1.4708, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5869565217391305, |
| "grad_norm": 20.200698852539062, |
| "learning_rate": 1.8000000000000001e-06, |
| "loss": 1.3044, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6032608695652174, |
| "grad_norm": 20.70162582397461, |
| "learning_rate": 1.85e-06, |
| "loss": 1.1445, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6195652173913043, |
| "grad_norm": 18.18869400024414, |
| "learning_rate": 1.9000000000000002e-06, |
| "loss": 0.9504, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.6358695652173914, |
| "grad_norm": 15.211593627929688, |
| "learning_rate": 1.9500000000000004e-06, |
| "loss": 0.8083, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 12.71890640258789, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.6981, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6684782608695652, |
| "grad_norm": 10.869053840637207, |
| "learning_rate": 2.05e-06, |
| "loss": 0.6018, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.6847826086956522, |
| "grad_norm": 9.5787353515625, |
| "learning_rate": 2.1000000000000002e-06, |
| "loss": 0.4899, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.7010869565217391, |
| "grad_norm": 9.319293975830078, |
| "learning_rate": 2.15e-06, |
| "loss": 0.3986, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.717391304347826, |
| "grad_norm": 9.404044151306152, |
| "learning_rate": 2.2e-06, |
| "loss": 0.3084, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.7336956521739131, |
| "grad_norm": 7.995025634765625, |
| "learning_rate": 2.25e-06, |
| "loss": 0.2373, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 4.505397319793701, |
| "learning_rate": 2.3000000000000004e-06, |
| "loss": 0.1527, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.7663043478260869, |
| "grad_norm": 2.5063579082489014, |
| "learning_rate": 2.35e-06, |
| "loss": 0.1097, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 1.5846028327941895, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.102, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.7989130434782609, |
| "grad_norm": 1.1286852359771729, |
| "learning_rate": 2.4500000000000003e-06, |
| "loss": 0.093, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.8152173913043478, |
| "grad_norm": 1.0311343669891357, |
| "learning_rate": 2.5e-06, |
| "loss": 0.0778, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8315217391304348, |
| "grad_norm": 0.6458576917648315, |
| "learning_rate": 2.55e-06, |
| "loss": 0.0883, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.8478260869565217, |
| "grad_norm": 0.727554202079773, |
| "learning_rate": 2.6e-06, |
| "loss": 0.0852, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.8641304347826086, |
| "grad_norm": 0.619137167930603, |
| "learning_rate": 2.6500000000000005e-06, |
| "loss": 0.0697, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.8804347826086957, |
| "grad_norm": 0.38241881132125854, |
| "learning_rate": 2.7000000000000004e-06, |
| "loss": 0.0665, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.8967391304347826, |
| "grad_norm": 0.541621744632721, |
| "learning_rate": 2.7500000000000004e-06, |
| "loss": 0.0658, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.9130434782608695, |
| "grad_norm": 0.3869657516479492, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 0.0728, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.9293478260869565, |
| "grad_norm": 0.3768727481365204, |
| "learning_rate": 2.85e-06, |
| "loss": 0.0741, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.9456521739130435, |
| "grad_norm": 0.31400591135025024, |
| "learning_rate": 2.9e-06, |
| "loss": 0.0682, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.9619565217391305, |
| "grad_norm": 0.3604981303215027, |
| "learning_rate": 2.95e-06, |
| "loss": 0.0652, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.9782608695652174, |
| "grad_norm": 0.4383264482021332, |
| "learning_rate": 3e-06, |
| "loss": 0.0703, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9945652173913043, |
| "grad_norm": 0.310332328081131, |
| "learning_rate": 3.05e-06, |
| "loss": 0.0664, |
| "step": 61 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 366, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 61, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3664872324451533e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
