| { | |
| "best_metric": 0.8117169737815857, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.5154639175257731, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005154639175257732, | |
| "grad_norm": 0.35949328541755676, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.7545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005154639175257732, | |
| "eval_loss": 1.1052348613739014, | |
| "eval_runtime": 30.1244, | |
| "eval_samples_per_second": 10.855, | |
| "eval_steps_per_second": 1.361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 0.45567527413368225, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.7432, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015463917525773196, | |
| "grad_norm": 0.5274704694747925, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.8322, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 0.5776087045669556, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.7875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02577319587628866, | |
| "grad_norm": 0.6656889915466309, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.8479, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "grad_norm": 0.6724861860275269, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9279, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03608247422680412, | |
| "grad_norm": 0.785415530204773, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.8712, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 0.7006766200065613, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.7866, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04639175257731959, | |
| "grad_norm": 0.9407919645309448, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.8717, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05154639175257732, | |
| "grad_norm": 0.6719709038734436, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05670103092783505, | |
| "grad_norm": 0.6967365145683289, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.8185, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": 0.666429877281189, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.9746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06701030927835051, | |
| "grad_norm": 0.687868595123291, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.8567, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07216494845360824, | |
| "grad_norm": 0.7461718916893005, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.8906, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07731958762886598, | |
| "grad_norm": 0.7825281023979187, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.8898, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 0.8114840984344482, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.9206, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08762886597938144, | |
| "grad_norm": 0.8150220513343811, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.8875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09278350515463918, | |
| "grad_norm": 0.7087549567222595, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.9555, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0979381443298969, | |
| "grad_norm": 0.8564397692680359, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.9177, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "grad_norm": 0.7236621975898743, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.8545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10824742268041238, | |
| "grad_norm": 0.8788579106330872, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.9195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1134020618556701, | |
| "grad_norm": 0.8592295050621033, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.9803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11855670103092783, | |
| "grad_norm": 0.8085874915122986, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.9333, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 1.5814393758773804, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.9284, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "grad_norm": 0.925155758857727, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 1.0185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13402061855670103, | |
| "grad_norm": 1.0410577058792114, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.8878, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13917525773195877, | |
| "grad_norm": 1.2917616367340088, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.9616, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14432989690721648, | |
| "grad_norm": 0.9885799884796143, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.8762, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14948453608247422, | |
| "grad_norm": 1.0929198265075684, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 1.0202, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15463917525773196, | |
| "grad_norm": 1.0404047966003418, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.9885, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15979381443298968, | |
| "grad_norm": 1.0854883193969727, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.9228, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 1.257588267326355, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.9343, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17010309278350516, | |
| "grad_norm": 1.0686402320861816, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.9171, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17525773195876287, | |
| "grad_norm": 1.2666049003601074, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.9904, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18041237113402062, | |
| "grad_norm": 1.3324109315872192, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 1.0908, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18556701030927836, | |
| "grad_norm": 1.1834466457366943, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.905, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19072164948453607, | |
| "grad_norm": 1.5354310274124146, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 1.0866, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1958762886597938, | |
| "grad_norm": 1.3238235712051392, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 1.0469, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20103092783505155, | |
| "grad_norm": 1.776808261871338, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 1.1054, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 1.812841534614563, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.9541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.211340206185567, | |
| "grad_norm": 1.7133516073226929, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.9837, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21649484536082475, | |
| "grad_norm": 2.0302529335021973, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 1.0123, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22164948453608246, | |
| "grad_norm": 1.8799409866333008, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 1.1035, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2268041237113402, | |
| "grad_norm": 2.289742946624756, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 1.1235, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23195876288659795, | |
| "grad_norm": 2.045342445373535, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 1.0909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23711340206185566, | |
| "grad_norm": 2.1356890201568604, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 1.1785, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2422680412371134, | |
| "grad_norm": 2.7677886486053467, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 1.2987, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 3.38108491897583, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 1.2262, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.25257731958762886, | |
| "grad_norm": 0.44239917397499084, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.7028, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.25773195876288657, | |
| "grad_norm": 0.610641598701477, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.7112, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25773195876288657, | |
| "eval_loss": 0.852555513381958, | |
| "eval_runtime": 29.9863, | |
| "eval_samples_per_second": 10.905, | |
| "eval_steps_per_second": 1.367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26288659793814434, | |
| "grad_norm": 0.7899359464645386, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.783, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.26804123711340205, | |
| "grad_norm": 0.7177944779396057, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.7351, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.27319587628865977, | |
| "grad_norm": 0.7365036010742188, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.6999, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.27835051546391754, | |
| "grad_norm": 0.739840030670166, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.6864, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.28350515463917525, | |
| "grad_norm": 0.7644721865653992, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.8022, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 0.7222386002540588, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.7589, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.29381443298969073, | |
| "grad_norm": 0.6763759851455688, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.7278, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.29896907216494845, | |
| "grad_norm": 0.849905252456665, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.8218, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.30412371134020616, | |
| "grad_norm": 0.7614359259605408, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.7381, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.30927835051546393, | |
| "grad_norm": 0.6714977025985718, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.6973, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31443298969072164, | |
| "grad_norm": 0.6945096254348755, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.7788, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.31958762886597936, | |
| "grad_norm": 0.7656300663948059, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.7903, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3247422680412371, | |
| "grad_norm": 0.7429731488227844, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.8319, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 0.7177958488464355, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.7017, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.33505154639175255, | |
| "grad_norm": 0.6787317991256714, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.7736, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3402061855670103, | |
| "grad_norm": 0.7011315226554871, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.7023, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.34536082474226804, | |
| "grad_norm": 0.6774159669876099, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.7007, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.35051546391752575, | |
| "grad_norm": 0.7961472868919373, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.7179, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3556701030927835, | |
| "grad_norm": 0.7200611233711243, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.8084, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.36082474226804123, | |
| "grad_norm": 0.9225122332572937, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.8685, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36597938144329895, | |
| "grad_norm": 0.7724214792251587, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.7963, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3711340206185567, | |
| "grad_norm": 0.709747314453125, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.7898, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.37628865979381443, | |
| "grad_norm": 0.8793331384658813, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.8988, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.38144329896907214, | |
| "grad_norm": 0.7961267232894897, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.7907, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3865979381443299, | |
| "grad_norm": 0.8463252186775208, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.8535, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3917525773195876, | |
| "grad_norm": 0.9485563635826111, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.8272, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.39690721649484534, | |
| "grad_norm": 0.9562703371047974, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.8414, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.4020618556701031, | |
| "grad_norm": 0.9790942668914795, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.8585, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4072164948453608, | |
| "grad_norm": 0.9100154638290405, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.8219, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 0.9290817975997925, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.8056, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4175257731958763, | |
| "grad_norm": 1.1186609268188477, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.8711, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.422680412371134, | |
| "grad_norm": 0.9763901233673096, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.8513, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.42783505154639173, | |
| "grad_norm": 1.0024268627166748, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.8448, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.4329896907216495, | |
| "grad_norm": 1.1477421522140503, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.9141, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.4381443298969072, | |
| "grad_norm": 1.1041942834854126, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.83, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.44329896907216493, | |
| "grad_norm": 1.0946459770202637, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.8241, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4484536082474227, | |
| "grad_norm": 1.2004777193069458, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.8111, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.4536082474226804, | |
| "grad_norm": 1.2121765613555908, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.7956, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.4587628865979381, | |
| "grad_norm": 1.216789722442627, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.8099, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.4639175257731959, | |
| "grad_norm": 1.7433570623397827, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.8918, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4690721649484536, | |
| "grad_norm": 1.6635973453521729, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.8888, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.4742268041237113, | |
| "grad_norm": 1.456506609916687, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.8422, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4793814432989691, | |
| "grad_norm": 1.6814242601394653, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.8215, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4845360824742268, | |
| "grad_norm": 1.8594515323638916, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.8137, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4896907216494845, | |
| "grad_norm": 2.3002114295959473, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.9984, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 3.094780445098877, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 1.1265, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.3856060802936554, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.7213, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5051546391752577, | |
| "grad_norm": 0.4723763167858124, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.686, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5103092783505154, | |
| "grad_norm": 1.0411378145217896, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.9629, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5154639175257731, | |
| "grad_norm": 0.4399566054344177, | |
| "learning_rate": 0.0, | |
| "loss": 0.6826, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5154639175257731, | |
| "eval_loss": 0.8117169737815857, | |
| "eval_runtime": 29.5641, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 1.387, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.719705479770276e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |