| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 13, |
| "global_step": 66, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 2.6548092365264893, |
| "learning_rate": 0.0, |
| "loss": 1.6435546875, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 2.1871001720428467, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 1.658203125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 2.062452554702759, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 1.6513671875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 2.1208860874176025, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.79296875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 2.061913013458252, |
| "learning_rate": 5.714285714285714e-05, |
| "loss": 1.7509765625, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 1.7802969217300415, |
| "learning_rate": 7.142857142857143e-05, |
| "loss": 1.5673828125, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 1.2095720767974854, |
| "learning_rate": 8.571428571428571e-05, |
| "loss": 1.306640625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.9277960658073425, |
| "learning_rate": 0.0001, |
| "loss": 1.5087890625, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4090909090909091, |
| "grad_norm": 0.422941118478775, |
| "learning_rate": 9.99362213054543e-05, |
| "loss": 1.28564453125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 0.4278399646282196, |
| "learning_rate": 9.974506600945618e-05, |
| "loss": 1.15869140625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.5854852199554443, |
| "learning_rate": 9.942707596246052e-05, |
| "loss": 1.2158203125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.6278713941574097, |
| "learning_rate": 9.8983152541804e-05, |
| "loss": 1.11083984375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5909090909090909, |
| "grad_norm": 0.5748578906059265, |
| "learning_rate": 9.841455409665323e-05, |
| "loss": 1.12744140625, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 0.512302577495575, |
| "learning_rate": 9.772289238107715e-05, |
| "loss": 1.142822265625, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "eval_loss": 1.291748046875, |
| "eval_runtime": 2.5876, |
| "eval_samples_per_second": 0.773, |
| "eval_steps_per_second": 0.386, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 0.4575030207633972, |
| "learning_rate": 9.691012798535524e-05, |
| "loss": 1.03515625, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.43149498105049133, |
| "learning_rate": 9.59785647784711e-05, |
| "loss": 1.15673828125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7727272727272727, |
| "grad_norm": 0.3845219016075134, |
| "learning_rate": 9.493084337754573e-05, |
| "loss": 1.15966796875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 0.3182738125324249, |
| "learning_rate": 9.376993366272128e-05, |
| "loss": 1.005126953125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8636363636363636, |
| "grad_norm": 0.26902279257774353, |
| "learning_rate": 9.249912635871318e-05, |
| "loss": 0.90478515625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.2571004629135132, |
| "learning_rate": 9.112202370689337e-05, |
| "loss": 1.18798828125, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9545454545454546, |
| "grad_norm": 0.22165662050247192, |
| "learning_rate": 8.964252925434579e-05, |
| "loss": 1.18212890625, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.22131846845149994, |
| "learning_rate": 8.806483678883803e-05, |
| "loss": 1.0927734375, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0454545454545454, |
| "grad_norm": 0.22180692851543427, |
| "learning_rate": 8.639341845107433e-05, |
| "loss": 0.904296875, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "grad_norm": 0.1869996339082718, |
| "learning_rate": 8.463301205792675e-05, |
| "loss": 1.0166015625, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.1363636363636362, |
| "grad_norm": 0.1848447024822235, |
| "learning_rate": 8.278860767257865e-05, |
| "loss": 1.04736328125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 0.18901988863945007, |
| "learning_rate": 8.086543345964832e-05, |
| "loss": 1.13818359375, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.2272727272727273, |
| "grad_norm": 0.18062233924865723, |
| "learning_rate": 7.886894086538841e-05, |
| "loss": 1.14208984375, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2272727272727273, |
| "eval_loss": 1.1639404296875, |
| "eval_runtime": 2.5708, |
| "eval_samples_per_second": 0.778, |
| "eval_steps_per_second": 0.389, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.15816649794578552, |
| "learning_rate": 7.680478916496926e-05, |
| "loss": 1.048828125, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.3181818181818181, |
| "grad_norm": 0.14896328747272491, |
| "learning_rate": 7.46788294206485e-05, |
| "loss": 0.94775390625, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 0.1636885106563568, |
| "learning_rate": 7.249708789629944e-05, |
| "loss": 1.25439453125, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4090909090909092, |
| "grad_norm": 0.14491912722587585, |
| "learning_rate": 7.026574897531137e-05, |
| "loss": 1.07958984375, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "grad_norm": 0.14638982713222504, |
| "learning_rate": 6.799113763028295e-05, |
| "loss": 0.95654296875, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.1446317881345749, |
| "learning_rate": 6.567970149420018e-05, |
| "loss": 1.0166015625, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 0.1534801572561264, |
| "learning_rate": 6.333799258392015e-05, |
| "loss": 0.9140625, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5909090909090908, |
| "grad_norm": 0.13671812415122986, |
| "learning_rate": 6.097264872776749e-05, |
| "loss": 0.966796875, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "grad_norm": 0.10513126850128174, |
| "learning_rate": 5.859037474988874e-05, |
| "loss": 1.013671875, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.6818181818181817, |
| "grad_norm": 0.10856485366821289, |
| "learning_rate": 5.6197923464699875e-05, |
| "loss": 0.8955078125, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 0.10285820811986923, |
| "learning_rate": 5.3802076535300135e-05, |
| "loss": 1.03466796875, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.7727272727272727, |
| "grad_norm": 0.11110834032297134, |
| "learning_rate": 5.140962525011126e-05, |
| "loss": 1.033203125, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.12622413039207458, |
| "learning_rate": 4.902735127223252e-05, |
| "loss": 0.872802734375, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "eval_loss": 1.1239013671875, |
| "eval_runtime": 2.5733, |
| "eval_samples_per_second": 0.777, |
| "eval_steps_per_second": 0.389, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8636363636363638, |
| "grad_norm": 0.14194338023662567, |
| "learning_rate": 4.6662007416079864e-05, |
| "loss": 0.77783203125, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 0.1279911994934082, |
| "learning_rate": 4.432029850579983e-05, |
| "loss": 1.11865234375, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.9545454545454546, |
| "grad_norm": 0.1066598892211914, |
| "learning_rate": 4.2008862369717074e-05, |
| "loss": 1.10205078125, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.10433182120323181, |
| "learning_rate": 3.973425102468864e-05, |
| "loss": 0.99658203125, |
| "step": 44 |
| }, |
| { |
| "epoch": 2.0454545454545454, |
| "grad_norm": 0.13041560351848602, |
| "learning_rate": 3.750291210370057e-05, |
| "loss": 0.7978515625, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.090909090909091, |
| "grad_norm": 0.09705521911382675, |
| "learning_rate": 3.5321170579351516e-05, |
| "loss": 0.93994140625, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.1363636363636362, |
| "grad_norm": 0.09956496208906174, |
| "learning_rate": 3.319521083503075e-05, |
| "loss": 0.984375, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.09361614286899567, |
| "learning_rate": 3.113105913461159e-05, |
| "loss": 1.08203125, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.227272727272727, |
| "grad_norm": 0.10508329421281815, |
| "learning_rate": 2.9134566540351693e-05, |
| "loss": 1.0947265625, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 0.09553074091672897, |
| "learning_rate": 2.721139232742137e-05, |
| "loss": 0.98388671875, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.3181818181818183, |
| "grad_norm": 0.10687677562236786, |
| "learning_rate": 2.5366987942073267e-05, |
| "loss": 0.8876953125, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.1090177521109581, |
| "learning_rate": 2.3606581548925695e-05, |
| "loss": 1.20703125, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.409090909090909, |
| "grad_norm": 0.11122502386569977, |
| "learning_rate": 2.1935163211161985e-05, |
| "loss": 1.0263671875, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.409090909090909, |
| "eval_loss": 1.099853515625, |
| "eval_runtime": 2.5655, |
| "eval_samples_per_second": 0.78, |
| "eval_steps_per_second": 0.39, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.4545454545454546, |
| "grad_norm": 0.10583138465881348, |
| "learning_rate": 2.0357470745654214e-05, |
| "loss": 0.89794921875, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.1000722348690033, |
| "learning_rate": 1.8877976293106646e-05, |
| "loss": 0.9599609375, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.10857231914997101, |
| "learning_rate": 1.7500873641286825e-05, |
| "loss": 0.8583984375, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.590909090909091, |
| "grad_norm": 0.0891537070274353, |
| "learning_rate": 1.6230066337278724e-05, |
| "loss": 0.923828125, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.6363636363636362, |
| "grad_norm": 0.08360682427883148, |
| "learning_rate": 1.5069156622454287e-05, |
| "loss": 0.983642578125, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.6818181818181817, |
| "grad_norm": 0.08480792492628098, |
| "learning_rate": 1.4021435221528906e-05, |
| "loss": 0.86181640625, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.07951804250478745, |
| "learning_rate": 1.3089872014644771e-05, |
| "loss": 1.0068359375, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.7727272727272725, |
| "grad_norm": 0.08608327805995941, |
| "learning_rate": 1.2277107618922843e-05, |
| "loss": 1.00048828125, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.8181818181818183, |
| "grad_norm": 0.1031343936920166, |
| "learning_rate": 1.1585445903346783e-05, |
| "loss": 0.836669921875, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.8636363636363638, |
| "grad_norm": 0.1224270910024643, |
| "learning_rate": 1.1016847458196001e-05, |
| "loss": 0.7412109375, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 0.10332220047712326, |
| "learning_rate": 1.0572924037539496e-05, |
| "loss": 1.10009765625, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.9545454545454546, |
| "grad_norm": 0.08486974984407425, |
| "learning_rate": 1.0254933990543831e-05, |
| "loss": 1.078125, |
| "step": 65 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.08661636710166931, |
| "learning_rate": 1.0063778694545714e-05, |
| "loss": 0.97265625, |
| "step": 66 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.0919189453125, |
| "eval_runtime": 2.5707, |
| "eval_samples_per_second": 0.778, |
| "eval_steps_per_second": 0.389, |
| "step": 66 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 66, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.339633585618944e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
