| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.36363636363636365, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036363636363636364, | |
| "grad_norm": 6.489499568939209, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.6819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036363636363636364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 66.4136, | |
| "eval_samples_per_second": 6.987, | |
| "eval_steps_per_second": 1.747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007272727272727273, | |
| "grad_norm": 6.3966569900512695, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.7032, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01090909090909091, | |
| "grad_norm": 5.9107489585876465, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.5685, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014545454545454545, | |
| "grad_norm": 6.378429412841797, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.9957, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 6.892773151397705, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.5134, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02181818181818182, | |
| "grad_norm": 6.415897369384766, | |
| "learning_rate": 3e-06, | |
| "loss": 2.5895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025454545454545455, | |
| "grad_norm": 5.840323448181152, | |
| "learning_rate": 3.5e-06, | |
| "loss": 2.278, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 6.8785529136657715, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.8814, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03272727272727273, | |
| "grad_norm": 6.929254531860352, | |
| "learning_rate": 4.5e-06, | |
| "loss": 2.7498, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 6.886597633361816, | |
| "learning_rate": 5e-06, | |
| "loss": 2.428, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 6.729462623596191, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 2.4775, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04363636363636364, | |
| "grad_norm": 6.443943023681641, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 2.4983, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04727272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 35.9766, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05090909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06545454545454546, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07636363636363637, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08363636363636363, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09454545454545454, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09818181818181818, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10545454545454545, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12363636363636364, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12727272727272726, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13090909090909092, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13454545454545455, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13818181818181818, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14909090909090908, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15272727272727274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15636363636363637, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16363636363636364, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16727272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1709090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1781818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "eval_loss": NaN, | |
| "eval_runtime": 65.6699, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 1.766, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18545454545454546, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1890909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.19272727272727272, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.19636363636363635, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.20363636363636364, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.20727272727272728, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2109090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.21454545454545454, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22181818181818183, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.22545454545454546, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2290909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.23636363636363636, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.24363636363636362, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.24727272727272728, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2509090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2545454545454545, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2581818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.26181818181818184, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.26545454545454544, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2690909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.27636363636363637, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.28363636363636363, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2872727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.29454545454545455, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.29818181818181816, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3018181818181818, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3054545454545455, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3090909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.31272727272727274, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.31636363636363635, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3236363636363636, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.32727272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.33090909090909093, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.33454545454545453, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3381818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3418181818181818, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.34545454545454546, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3527272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3563636363636364, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "eval_loss": NaN, | |
| "eval_runtime": 65.6965, | |
| "eval_samples_per_second": 7.063, | |
| "eval_steps_per_second": 1.766, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.7509941635907584e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |