| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0973936899862826, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.8683, | |
| "eval_samples_per_second": 31.633, | |
| "eval_steps_per_second": 8.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07681755829903979, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0877914951989026, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10973936899862825, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12071330589849108, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14266117969821673, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15363511659807957, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1646090534979424, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1755829903978052, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18655692729766804, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2085048010973937, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2194787379972565, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23045267489711935, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24142661179698216, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.252400548696845, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26337448559670784, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27434842249657065, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28532235939643347, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30727023319615915, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31824417009602196, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3292181069958848, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3401920438957476, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3511659807956104, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.36213991769547327, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3731138545953361, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3840877914951989, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4060356652949246, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4170096021947874, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4279835390946502, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.438957475994513, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4499314128943759, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4609053497942387, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4718792866941015, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4828532235939643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.50480109739369, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5157750342935528, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5267489711934157, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5377229080932785, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5486968449931413, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5486968449931413, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3325, | |
| "eval_samples_per_second": 35.545, | |
| "eval_steps_per_second": 9.002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5596707818930041, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5706447187928669, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5816186556927297, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6035665294924554, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6145404663923183, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6255144032921811, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6364883401920439, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6474622770919067, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6584362139917695, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6694101508916324, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6803840877914952, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.691358024691358, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7023319615912208, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7133058984910837, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7242798353909465, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7352537722908093, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7462277091906722, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.757201646090535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7681755829903978, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7791495198902606, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8010973936899863, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8120713305898491, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.823045267489712, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8340192043895748, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8449931412894376, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8559670781893004, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8669410150891632, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.877914951989026, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8998628257887518, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9108367626886146, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9218106995884774, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9327846364883402, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.943758573388203, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9547325102880658, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9657064471879286, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.9766803840877915, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9986282578875172, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.00960219478738, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0205761316872428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.0315500685871055, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0425240054869684, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0534979423868314, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.064471879286694, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.075445816186557, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.0864197530864197, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.0973936899862826, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0973936899862826, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.3294, | |
| "eval_samples_per_second": 35.571, | |
| "eval_steps_per_second": 9.008, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6117212556230656e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |