| { |
| "best_metric": 0.971350908279419, |
| "best_model_checkpoint": "./fine_tuned_models/health/Llama-3.1-8B-Instruct/checkpoint-2500", |
| "epoch": 2.5669135802469136, |
| "eval_steps": 100, |
| "global_step": 2600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.019753086419753086, |
| "grad_norm": 1.1160211563110352, |
| "learning_rate": 1.9736842105263157e-06, |
| "loss": 2.0627, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03950617283950617, |
| "grad_norm": 1.0905706882476807, |
| "learning_rate": 3.9473684210526315e-06, |
| "loss": 2.0246, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05925925925925926, |
| "grad_norm": 0.9707510471343994, |
| "learning_rate": 5.921052631578948e-06, |
| "loss": 1.9243, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.0528677701950073, |
| "learning_rate": 7.894736842105263e-06, |
| "loss": 1.6172, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "grad_norm": 0.7791302800178528, |
| "learning_rate": 9.868421052631579e-06, |
| "loss": 1.3386, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "eval_loss": 1.2289670705795288, |
| "eval_runtime": 404.6369, |
| "eval_samples_per_second": 4.448, |
| "eval_steps_per_second": 1.112, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.6323535442352295, |
| "learning_rate": 1.1842105263157895e-05, |
| "loss": 1.1669, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1382716049382716, |
| "grad_norm": 0.6384269595146179, |
| "learning_rate": 1.3815789473684211e-05, |
| "loss": 1.1764, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.6977917551994324, |
| "learning_rate": 1.5789473684210526e-05, |
| "loss": 1.1308, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.6905924081802368, |
| "learning_rate": 1.7763157894736842e-05, |
| "loss": 1.1127, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7211576700210571, |
| "learning_rate": 1.9736842105263158e-05, |
| "loss": 1.1204, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "eval_loss": 1.10204017162323, |
| "eval_runtime": 403.0411, |
| "eval_samples_per_second": 4.466, |
| "eval_steps_per_second": 1.117, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21728395061728395, |
| "grad_norm": 0.7831864953041077, |
| "learning_rate": 2.1710526315789474e-05, |
| "loss": 1.0875, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.8442113399505615, |
| "learning_rate": 2.368421052631579e-05, |
| "loss": 1.0855, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.25679012345679014, |
| "grad_norm": 0.8692957162857056, |
| "learning_rate": 2.5657894736842107e-05, |
| "loss": 1.0797, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.8785028457641602, |
| "learning_rate": 2.7631578947368423e-05, |
| "loss": 1.1142, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.8870799541473389, |
| "learning_rate": 2.9605263157894735e-05, |
| "loss": 1.0707, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "eval_loss": 1.074904203414917, |
| "eval_runtime": 403.0664, |
| "eval_samples_per_second": 4.466, |
| "eval_steps_per_second": 1.116, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.9721025228500366, |
| "learning_rate": 2.9997461206762896e-05, |
| "loss": 1.0471, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3358024691358025, |
| "grad_norm": 0.9425962567329407, |
| "learning_rate": 2.998714883211034e-05, |
| "loss": 1.0614, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.0400207042694092, |
| "learning_rate": 2.9968909651554313e-05, |
| "loss": 1.0386, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.37530864197530867, |
| "grad_norm": 1.033016562461853, |
| "learning_rate": 2.994275331192262e-05, |
| "loss": 1.0591, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.202338695526123, |
| "learning_rate": 2.9908693647482852e-05, |
| "loss": 1.081, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 1.05765700340271, |
| "eval_runtime": 402.7051, |
| "eval_samples_per_second": 4.47, |
| "eval_steps_per_second": 1.117, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4148148148148148, |
| "grad_norm": 1.0287129878997803, |
| "learning_rate": 2.9866748672625354e-05, |
| "loss": 1.1013, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.114308476448059, |
| "learning_rate": 2.9816940572335275e-05, |
| "loss": 1.0684, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.454320987654321, |
| "grad_norm": 1.1122310161590576, |
| "learning_rate": 2.9759295690458793e-05, |
| "loss": 1.0675, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.0627741813659668, |
| "learning_rate": 2.9693844515769658e-05, |
| "loss": 1.0327, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "grad_norm": 1.0726803541183472, |
| "learning_rate": 2.9620621665843482e-05, |
| "loss": 1.0413, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "eval_loss": 1.0474056005477905, |
| "eval_runtime": 403.0908, |
| "eval_samples_per_second": 4.465, |
| "eval_steps_per_second": 1.116, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.2839173078536987, |
| "learning_rate": 2.953966586874827e-05, |
| "loss": 1.0507, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 1.0455371141433716, |
| "learning_rate": 2.9451019942560854e-05, |
| "loss": 1.0484, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 1.0756592750549316, |
| "learning_rate": 2.9354730772720152e-05, |
| "loss": 1.0612, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5728395061728395, |
| "grad_norm": 1.1546605825424194, |
| "learning_rate": 2.9250849287229115e-05, |
| "loss": 1.0338, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 1.062068223953247, |
| "learning_rate": 2.9139430429718557e-05, |
| "loss": 1.05, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "eval_loss": 1.0370533466339111, |
| "eval_runtime": 402.7813, |
| "eval_samples_per_second": 4.469, |
| "eval_steps_per_second": 1.117, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6123456790123457, |
| "grad_norm": 1.0931472778320312, |
| "learning_rate": 2.90205331303871e-05, |
| "loss": 1.0282, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.1314401626586914, |
| "learning_rate": 2.889422027483259e-05, |
| "loss": 1.0185, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.6518518518518519, |
| "grad_norm": 1.1147228479385376, |
| "learning_rate": 2.876055867079146e-05, |
| "loss": 1.0552, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 1.2712368965148926, |
| "learning_rate": 2.8619619012803674e-05, |
| "loss": 1.0241, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "grad_norm": 1.1172308921813965, |
| "learning_rate": 2.847147584482188e-05, |
| "loss": 1.018, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "eval_loss": 1.0282899141311646, |
| "eval_runtime": 403.0768, |
| "eval_samples_per_second": 4.466, |
| "eval_steps_per_second": 1.116, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 1.1631219387054443, |
| "learning_rate": 2.8316207520784622e-05, |
| "loss": 1.037, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.7308641975308642, |
| "grad_norm": 1.0679621696472168, |
| "learning_rate": 2.81538961631744e-05, |
| "loss": 0.9998, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 1.098596215248108, |
| "learning_rate": 2.7984627619582507e-05, |
| "loss": 1.0164, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.7703703703703704, |
| "grad_norm": 1.1393965482711792, |
| "learning_rate": 2.7808491417303672e-05, |
| "loss": 1.0407, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 1.34330153465271, |
| "learning_rate": 2.7625580715984452e-05, |
| "loss": 1.0432, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 1.0187339782714844, |
| "eval_runtime": 402.8401, |
| "eval_samples_per_second": 4.468, |
| "eval_steps_per_second": 1.117, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8098765432098766, |
| "grad_norm": 1.1482850313186646, |
| "learning_rate": 2.7435992258350444e-05, |
| "loss": 1.0214, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 1.0984679460525513, |
| "learning_rate": 2.7239826319038413e-05, |
| "loss": 1.0104, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.8493827160493828, |
| "grad_norm": 1.1276164054870605, |
| "learning_rate": 2.703718665156033e-05, |
| "loss": 1.0151, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 1.1957815885543823, |
| "learning_rate": 2.6828180433427437e-05, |
| "loss": 1.0254, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 1.1888211965560913, |
| "learning_rate": 2.6612918209463323e-05, |
| "loss": 1.0056, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "eval_loss": 1.0113353729248047, |
| "eval_runtime": 403.2634, |
| "eval_samples_per_second": 4.464, |
| "eval_steps_per_second": 1.116, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 1.1143324375152588, |
| "learning_rate": 2.6391513833336013e-05, |
| "loss": 1.038, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.928395061728395, |
| "grad_norm": 1.1294788122177124, |
| "learning_rate": 2.616408440733997e-05, |
| "loss": 1.0346, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 1.1774975061416626, |
| "learning_rate": 2.5930750220459893e-05, |
| "loss": 1.004, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.9679012345679012, |
| "grad_norm": 1.1493123769760132, |
| "learning_rate": 2.569163468474906e-05, |
| "loss": 0.9974, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 1.2377318143844604, |
| "learning_rate": 2.5446864270055825e-05, |
| "loss": 0.9987, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "eval_loss": 1.0076097249984741, |
| "eval_runtime": 402.948, |
| "eval_samples_per_second": 4.467, |
| "eval_steps_per_second": 1.117, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0069135802469136, |
| "grad_norm": 1.225941777229309, |
| "learning_rate": 2.5196568437132855e-05, |
| "loss": 0.9939, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.0266666666666666, |
| "grad_norm": 1.240697979927063, |
| "learning_rate": 2.4940879569164453e-05, |
| "loss": 0.9806, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.0464197530864197, |
| "grad_norm": 1.2726426124572754, |
| "learning_rate": 2.467993290174819e-05, |
| "loss": 0.9758, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.066172839506173, |
| "grad_norm": 1.3213516473770142, |
| "learning_rate": 2.4413866451367836e-05, |
| "loss": 0.9822, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.085925925925926, |
| "grad_norm": 1.2369683980941772, |
| "learning_rate": 2.414282094239555e-05, |
| "loss": 0.9467, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.085925925925926, |
| "eval_loss": 1.0044056177139282, |
| "eval_runtime": 402.972, |
| "eval_samples_per_second": 4.467, |
| "eval_steps_per_second": 1.117, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.105679012345679, |
| "grad_norm": 1.1692577600479126, |
| "learning_rate": 2.386693973266173e-05, |
| "loss": 0.9586, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.125432098765432, |
| "grad_norm": 1.1815599203109741, |
| "learning_rate": 2.3586368737632124e-05, |
| "loss": 0.9711, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.145185185185185, |
| "grad_norm": 1.2383053302764893, |
| "learning_rate": 2.3301256353232112e-05, |
| "loss": 0.9668, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.1649382716049383, |
| "grad_norm": 1.4748594760894775, |
| "learning_rate": 2.3011753377359084e-05, |
| "loss": 0.977, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.1846913580246914, |
| "grad_norm": 1.3367607593536377, |
| "learning_rate": 2.2718012930124407e-05, |
| "loss": 0.9461, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.1846913580246914, |
| "eval_loss": 0.9985090494155884, |
| "eval_runtime": 402.6419, |
| "eval_samples_per_second": 4.47, |
| "eval_steps_per_second": 1.118, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.2044444444444444, |
| "grad_norm": 1.3120101690292358, |
| "learning_rate": 2.2420190372867144e-05, |
| "loss": 0.9728, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.2241975308641975, |
| "grad_norm": 1.4451560974121094, |
| "learning_rate": 2.2118443225982365e-05, |
| "loss": 0.962, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.2439506172839505, |
| "grad_norm": 1.2705769538879395, |
| "learning_rate": 2.1812931085607537e-05, |
| "loss": 0.9425, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.2637037037037038, |
| "grad_norm": 1.3269940614700317, |
| "learning_rate": 2.1503815539211034e-05, |
| "loss": 0.9519, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.2834567901234568, |
| "grad_norm": 1.2251733541488647, |
| "learning_rate": 2.119126008012741e-05, |
| "loss": 0.9671, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2834567901234568, |
| "eval_loss": 0.9977313280105591, |
| "eval_runtime": 402.6952, |
| "eval_samples_per_second": 4.47, |
| "eval_steps_per_second": 1.117, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.3032098765432099, |
| "grad_norm": 1.3956445455551147, |
| "learning_rate": 2.0875430021084665e-05, |
| "loss": 0.9742, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.322962962962963, |
| "grad_norm": 1.2852596044540405, |
| "learning_rate": 2.0556492406769176e-05, |
| "loss": 0.9635, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.342716049382716, |
| "grad_norm": 1.3903273344039917, |
| "learning_rate": 2.0234615925474648e-05, |
| "loss": 0.9622, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.3624691358024692, |
| "grad_norm": 1.457078456878662, |
| "learning_rate": 1.9909970819881708e-05, |
| "loss": 0.9833, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.3822222222222222, |
| "grad_norm": 1.2986372709274292, |
| "learning_rate": 1.9582728797015385e-05, |
| "loss": 0.9495, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.3822222222222222, |
| "eval_loss": 0.9925122857093811, |
| "eval_runtime": 402.5025, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.4019753086419753, |
| "grad_norm": 1.342713475227356, |
| "learning_rate": 1.9253062937428073e-05, |
| "loss": 0.9609, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.4217283950617283, |
| "grad_norm": 1.2822914123535156, |
| "learning_rate": 1.892114760365605e-05, |
| "loss": 0.9658, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.4414814814814814, |
| "grad_norm": 1.331895351409912, |
| "learning_rate": 1.8587158347997932e-05, |
| "loss": 0.9769, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.4612345679012346, |
| "grad_norm": 1.3801404237747192, |
| "learning_rate": 1.8251271819663863e-05, |
| "loss": 0.98, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.4809876543209877, |
| "grad_norm": 1.337031364440918, |
| "learning_rate": 1.7913665671344526e-05, |
| "loss": 0.9716, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.4809876543209877, |
| "eval_loss": 0.9894294738769531, |
| "eval_runtime": 402.6051, |
| "eval_samples_per_second": 4.471, |
| "eval_steps_per_second": 1.118, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.5007407407407407, |
| "grad_norm": 1.551279067993164, |
| "learning_rate": 1.7574518465249413e-05, |
| "loss": 0.9772, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.520493827160494, |
| "grad_norm": 1.3463525772094727, |
| "learning_rate": 1.7234009578664066e-05, |
| "loss": 0.9477, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.5402469135802468, |
| "grad_norm": 1.3253049850463867, |
| "learning_rate": 1.6892319109076183e-05, |
| "loss": 0.9641, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 1.4334008693695068, |
| "learning_rate": 1.654962777892081e-05, |
| "loss": 0.9584, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.579753086419753, |
| "grad_norm": 1.412903904914856, |
| "learning_rate": 1.6206116839995033e-05, |
| "loss": 0.9779, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.579753086419753, |
| "eval_loss": 0.9848657846450806, |
| "eval_runtime": 402.5392, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.5995061728395061, |
| "grad_norm": 1.251621961593628, |
| "learning_rate": 1.5861967977592642e-05, |
| "loss": 0.942, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.6192592592592594, |
| "grad_norm": 1.3814697265625, |
| "learning_rate": 1.5517363214409528e-05, |
| "loss": 0.9469, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.6390123456790122, |
| "grad_norm": 1.388342022895813, |
| "learning_rate": 1.5172484814270635e-05, |
| "loss": 0.9716, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.6587654320987655, |
| "grad_norm": 1.318664312362671, |
| "learning_rate": 1.4827515185729368e-05, |
| "loss": 0.98, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.6785185185185185, |
| "grad_norm": 1.364259958267212, |
| "learning_rate": 1.4482636785590474e-05, |
| "loss": 0.9628, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.6785185185185185, |
| "eval_loss": 0.9820418357849121, |
| "eval_runtime": 402.744, |
| "eval_samples_per_second": 4.469, |
| "eval_steps_per_second": 1.117, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.6982716049382716, |
| "grad_norm": 1.346475601196289, |
| "learning_rate": 1.413803202240736e-05, |
| "loss": 0.995, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.7180246913580248, |
| "grad_norm": 1.350071907043457, |
| "learning_rate": 1.3793883160004971e-05, |
| "loss": 0.9792, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.7377777777777776, |
| "grad_norm": 1.3962644338607788, |
| "learning_rate": 1.3450372221079193e-05, |
| "loss": 0.9885, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.757530864197531, |
| "grad_norm": 1.4300681352615356, |
| "learning_rate": 1.3107680890923821e-05, |
| "loss": 0.9433, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.777283950617284, |
| "grad_norm": 1.604736566543579, |
| "learning_rate": 1.2765990421335937e-05, |
| "loss": 0.966, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.777283950617284, |
| "eval_loss": 0.9798233509063721, |
| "eval_runtime": 402.6875, |
| "eval_samples_per_second": 4.47, |
| "eval_steps_per_second": 1.117, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.797037037037037, |
| "grad_norm": 1.3228657245635986, |
| "learning_rate": 1.2425481534750591e-05, |
| "loss": 1.0006, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.8167901234567903, |
| "grad_norm": 1.5004771947860718, |
| "learning_rate": 1.2086334328655478e-05, |
| "loss": 0.9622, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.836543209876543, |
| "grad_norm": 1.412369966506958, |
| "learning_rate": 1.1748728180336137e-05, |
| "loss": 0.9764, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.8562962962962963, |
| "grad_norm": 1.4217263460159302, |
| "learning_rate": 1.141284165200207e-05, |
| "loss": 0.9396, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.8760493827160494, |
| "grad_norm": 1.3855938911437988, |
| "learning_rate": 1.1078852396343955e-05, |
| "loss": 0.9449, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.8760493827160494, |
| "eval_loss": 0.9764742255210876, |
| "eval_runtime": 402.9468, |
| "eval_samples_per_second": 4.467, |
| "eval_steps_per_second": 1.117, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.8958024691358024, |
| "grad_norm": 1.3269942998886108, |
| "learning_rate": 1.0746937062571928e-05, |
| "loss": 0.9488, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.9155555555555557, |
| "grad_norm": 1.3707290887832642, |
| "learning_rate": 1.0417271202984614e-05, |
| "loss": 0.9477, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.9353086419753085, |
| "grad_norm": 1.4749308824539185, |
| "learning_rate": 1.0090029180118293e-05, |
| "loss": 0.9367, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.9550617283950618, |
| "grad_norm": 1.537101149559021, |
| "learning_rate": 9.765384074525358e-06, |
| "loss": 0.919, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.9748148148148148, |
| "grad_norm": 1.251558780670166, |
| "learning_rate": 9.443507593230829e-06, |
| "loss": 0.9454, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.9748148148148148, |
| "eval_loss": 0.9748017191886902, |
| "eval_runtime": 403.0506, |
| "eval_samples_per_second": 4.466, |
| "eval_steps_per_second": 1.116, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.9945679012345678, |
| "grad_norm": 1.4743434190750122, |
| "learning_rate": 9.124569978915336e-06, |
| "loss": 0.9237, |
| "step": 2020 |
| }, |
| { |
| "epoch": 2.013827160493827, |
| "grad_norm": 1.2874201536178589, |
| "learning_rate": 8.808739919872588e-06, |
| "loss": 0.8969, |
| "step": 2040 |
| }, |
| { |
| "epoch": 2.0335802469135804, |
| "grad_norm": 1.4540894031524658, |
| "learning_rate": 8.496184460788969e-06, |
| "loss": 0.9179, |
| "step": 2060 |
| }, |
| { |
| "epoch": 2.0533333333333332, |
| "grad_norm": 1.5025060176849365, |
| "learning_rate": 8.187068914392464e-06, |
| "loss": 0.9091, |
| "step": 2080 |
| }, |
| { |
| "epoch": 2.0730864197530865, |
| "grad_norm": 1.4199432134628296, |
| "learning_rate": 7.881556774017635e-06, |
| "loss": 0.9209, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.0730864197530865, |
| "eval_loss": 0.9763918519020081, |
| "eval_runtime": 402.9594, |
| "eval_samples_per_second": 4.467, |
| "eval_steps_per_second": 1.117, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.0928395061728393, |
| "grad_norm": 1.5283966064453125, |
| "learning_rate": 7.579809627132857e-06, |
| "loss": 0.9488, |
| "step": 2120 |
| }, |
| { |
| "epoch": 2.1125925925925926, |
| "grad_norm": 1.4568904638290405, |
| "learning_rate": 7.281987069875591e-06, |
| "loss": 0.9094, |
| "step": 2140 |
| }, |
| { |
| "epoch": 2.132345679012346, |
| "grad_norm": 1.4240208864212036, |
| "learning_rate": 6.988246622640921e-06, |
| "loss": 0.9166, |
| "step": 2160 |
| }, |
| { |
| "epoch": 2.1520987654320987, |
| "grad_norm": 1.5284944772720337, |
| "learning_rate": 6.698743646767891e-06, |
| "loss": 0.9205, |
| "step": 2180 |
| }, |
| { |
| "epoch": 2.171851851851852, |
| "grad_norm": 1.4134441614151, |
| "learning_rate": 6.413631262367882e-06, |
| "loss": 0.9121, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.171851851851852, |
| "eval_loss": 0.9747745990753174, |
| "eval_runtime": 402.9155, |
| "eval_samples_per_second": 4.467, |
| "eval_steps_per_second": 1.117, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.1916049382716047, |
| "grad_norm": 1.4537668228149414, |
| "learning_rate": 6.1330602673382725e-06, |
| "loss": 0.8968, |
| "step": 2220 |
| }, |
| { |
| "epoch": 2.211358024691358, |
| "grad_norm": 1.4549959897994995, |
| "learning_rate": 5.857179057604451e-06, |
| "loss": 0.8984, |
| "step": 2240 |
| }, |
| { |
| "epoch": 2.2311111111111113, |
| "grad_norm": 1.5467361211776733, |
| "learning_rate": 5.586133548632161e-06, |
| "loss": 0.9044, |
| "step": 2260 |
| }, |
| { |
| "epoch": 2.250864197530864, |
| "grad_norm": 1.5347260236740112, |
| "learning_rate": 5.320067098251815e-06, |
| "loss": 0.9008, |
| "step": 2280 |
| }, |
| { |
| "epoch": 2.2706172839506173, |
| "grad_norm": 1.5415095090866089, |
| "learning_rate": 5.0591204308355465e-06, |
| "loss": 0.92, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.2706172839506173, |
| "eval_loss": 0.9742743372917175, |
| "eval_runtime": 402.5831, |
| "eval_samples_per_second": 4.471, |
| "eval_steps_per_second": 1.118, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.29037037037037, |
| "grad_norm": 1.4806352853775024, |
| "learning_rate": 4.803431562867145e-06, |
| "loss": 0.9074, |
| "step": 2320 |
| }, |
| { |
| "epoch": 2.3101234567901234, |
| "grad_norm": 1.5135067701339722, |
| "learning_rate": 4.5531357299441774e-06, |
| "loss": 0.9279, |
| "step": 2340 |
| }, |
| { |
| "epoch": 2.3298765432098767, |
| "grad_norm": 1.5284662246704102, |
| "learning_rate": 4.3083653152509434e-06, |
| "loss": 0.918, |
| "step": 2360 |
| }, |
| { |
| "epoch": 2.3496296296296295, |
| "grad_norm": 1.5032851696014404, |
| "learning_rate": 4.069249779540108e-06, |
| "loss": 0.8999, |
| "step": 2380 |
| }, |
| { |
| "epoch": 2.3693827160493828, |
| "grad_norm": 1.510326862335205, |
| "learning_rate": 3.835915592660032e-06, |
| "loss": 0.8842, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.3693827160493828, |
| "eval_loss": 0.9732682108879089, |
| "eval_runtime": 402.6779, |
| "eval_samples_per_second": 4.47, |
| "eval_steps_per_second": 1.118, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.389135802469136, |
| "grad_norm": 1.5141196250915527, |
| "learning_rate": 3.6084861666639856e-06, |
| "loss": 0.8984, |
| "step": 2420 |
| }, |
| { |
| "epoch": 2.408888888888889, |
| "grad_norm": 1.5734765529632568, |
| "learning_rate": 3.387081790536677e-06, |
| "loss": 0.9365, |
| "step": 2440 |
| }, |
| { |
| "epoch": 2.428641975308642, |
| "grad_norm": 1.4879003763198853, |
| "learning_rate": 3.171819566572563e-06, |
| "loss": 0.8829, |
| "step": 2460 |
| }, |
| { |
| "epoch": 2.448395061728395, |
| "grad_norm": 1.4807547330856323, |
| "learning_rate": 2.962813348439669e-06, |
| "loss": 0.9212, |
| "step": 2480 |
| }, |
| { |
| "epoch": 2.468148148148148, |
| "grad_norm": 1.492896556854248, |
| "learning_rate": 2.7601736809615883e-06, |
| "loss": 0.9079, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.468148148148148, |
| "eval_loss": 0.971350908279419, |
| "eval_runtime": 402.7891, |
| "eval_samples_per_second": 4.469, |
| "eval_steps_per_second": 1.117, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.487901234567901, |
| "grad_norm": 1.49791419506073, |
| "learning_rate": 2.564007741649559e-06, |
| "loss": 0.9271, |
| "step": 2520 |
| }, |
| { |
| "epoch": 2.5076543209876543, |
| "grad_norm": 1.5255753993988037, |
| "learning_rate": 2.374419284015552e-06, |
| "loss": 0.9105, |
| "step": 2540 |
| }, |
| { |
| "epoch": 2.5274074074074075, |
| "grad_norm": 1.4556204080581665, |
| "learning_rate": 2.191508582696329e-06, |
| "loss": 0.9169, |
| "step": 2560 |
| }, |
| { |
| "epoch": 2.5471604938271604, |
| "grad_norm": 1.5181186199188232, |
| "learning_rate": 2.0153723804174945e-06, |
| "loss": 0.8952, |
| "step": 2580 |
| }, |
| { |
| "epoch": 2.5669135802469136, |
| "grad_norm": 1.5350087881088257, |
| "learning_rate": 1.8461038368256027e-06, |
| "loss": 0.909, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.5669135802469136, |
| "eval_loss": 0.9715363383293152, |
| "eval_runtime": 402.7586, |
| "eval_samples_per_second": 4.469, |
| "eval_steps_per_second": 1.117, |
| "step": 2600 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 3036, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.8563300999472087e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
