| { | |
| "best_metric": 0.9849200248718262, | |
| "best_model_checkpoint": "/kaggle/working/LLaMA-Factory/output/dolphin-2.9-llama3-8b-GER/checkpoint-300", | |
| "epoch": 0.35335689045936397, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.5445218086242676, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.2105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.4362960457801819, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9311, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.5098525881767273, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.3604, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.0830402374267578, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5808, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5936903953552246, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.248, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.7212775945663452, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.2712, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.4733128845691681, | |
| "learning_rate": 1.75e-05, | |
| "loss": 1.3005, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6236618757247925, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3398, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5326029658317566, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.0476, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5021428465843201, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1245, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.46588796377182007, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 1.1041, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.936045229434967, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3201, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5649005770683289, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.1596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5679148435592651, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.2501, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.8638319373130798, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.237, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5722486972808838, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2616, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5802999138832092, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.9578, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.2806150913238525, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.3815, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5839210748672485, | |
| "learning_rate": 4.75e-05, | |
| "loss": 1.2619, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7132797837257385, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2842, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7936571836471558, | |
| "learning_rate": 5.25e-05, | |
| "loss": 1.3991, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7268731594085693, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.2217, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6649657487869263, | |
| "learning_rate": 5.7499999999999995e-05, | |
| "loss": 1.2485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.45912331342697144, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1452, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.49475613236427307, | |
| "learning_rate": 6.25e-05, | |
| "loss": 1.256, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6027999520301819, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.2267, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.48380520939826965, | |
| "learning_rate": 6.750000000000001e-05, | |
| "loss": 1.202, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6623361706733704, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3924, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6632773280143738, | |
| "learning_rate": 7.25e-05, | |
| "loss": 1.2443, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.5974243879318237, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0591, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.7902927398681641, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.0192, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.7081462144851685, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0955, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4744333326816559, | |
| "learning_rate": 8.25e-05, | |
| "loss": 1.0564, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.703999400138855, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.1022, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.5378603339195251, | |
| "learning_rate": 8.75e-05, | |
| "loss": 1.063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6105419397354126, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9748, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6250177025794983, | |
| "learning_rate": 9.250000000000001e-05, | |
| "loss": 0.9951, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6306005716323853, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.9875, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.8635210990905762, | |
| "learning_rate": 9.75e-05, | |
| "loss": 1.1825, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.5938963890075684, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.5765062570571899, | |
| "learning_rate": 0.0001025, | |
| "loss": 1.1031, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.5162666440010071, | |
| "learning_rate": 0.000105, | |
| "loss": 1.0831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.8675170540809631, | |
| "learning_rate": 0.0001075, | |
| "loss": 1.0034, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.44026264548301697, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.9607, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.4922897219657898, | |
| "learning_rate": 0.00011250000000000001, | |
| "loss": 1.0251, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.5505048632621765, | |
| "learning_rate": 0.00011499999999999999, | |
| "loss": 0.6948, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5226988792419434, | |
| "learning_rate": 0.00011750000000000001, | |
| "loss": 1.2259, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5105571150779724, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1239, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 2.0914857387542725, | |
| "learning_rate": 0.00012250000000000002, | |
| "loss": 1.4032, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.4611998498439789, | |
| "learning_rate": 0.000125, | |
| "loss": 1.1481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5243968367576599, | |
| "learning_rate": 0.0001275, | |
| "loss": 1.0514, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.48045778274536133, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 1.1552, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5543797612190247, | |
| "learning_rate": 0.0001325, | |
| "loss": 1.035, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5148913264274597, | |
| "learning_rate": 0.00013500000000000003, | |
| "loss": 0.9244, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5708130598068237, | |
| "learning_rate": 0.0001375, | |
| "loss": 1.2272, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.7507888078689575, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1196, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.5411068201065063, | |
| "learning_rate": 0.00014250000000000002, | |
| "loss": 1.1444, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.7314138412475586, | |
| "learning_rate": 0.000145, | |
| "loss": 1.3451, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.5134022831916809, | |
| "learning_rate": 0.0001475, | |
| "loss": 0.8021, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.7859703302383423, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.952, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.4740566611289978, | |
| "learning_rate": 0.0001525, | |
| "loss": 0.8878, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.8245677947998047, | |
| "learning_rate": 0.000155, | |
| "loss": 1.4341, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.5067218542098999, | |
| "learning_rate": 0.0001575, | |
| "loss": 0.8404, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.40824806690216064, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0943, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.428151935338974, | |
| "learning_rate": 0.00016250000000000002, | |
| "loss": 1.0819, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.437532901763916, | |
| "learning_rate": 0.000165, | |
| "loss": 1.0461, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.4619809091091156, | |
| "learning_rate": 0.0001675, | |
| "loss": 1.0232, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.3247042894363403, | |
| "learning_rate": 0.00017, | |
| "loss": 1.218, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5896454453468323, | |
| "learning_rate": 0.00017250000000000002, | |
| "loss": 1.1953, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5605736970901489, | |
| "learning_rate": 0.000175, | |
| "loss": 1.2542, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.36923155188560486, | |
| "learning_rate": 0.0001775, | |
| "loss": 0.7096, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.6809273362159729, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1959, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.42645493149757385, | |
| "learning_rate": 0.0001825, | |
| "loss": 1.1829, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.7621450424194336, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.1599, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.5299301743507385, | |
| "learning_rate": 0.0001875, | |
| "loss": 1.0546, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.484611451625824, | |
| "learning_rate": 0.00019, | |
| "loss": 1.0854, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.4027417004108429, | |
| "learning_rate": 0.00019250000000000002, | |
| "loss": 0.7812, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.7537221908569336, | |
| "learning_rate": 0.000195, | |
| "loss": 0.9719, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.45811474323272705, | |
| "learning_rate": 0.00019750000000000003, | |
| "loss": 0.9684, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.5426852107048035, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9451, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.48964977264404297, | |
| "learning_rate": 0.000199739921976593, | |
| "loss": 1.0807, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.6225113272666931, | |
| "learning_rate": 0.00019947984395318597, | |
| "loss": 1.1913, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.47157713770866394, | |
| "learning_rate": 0.00019921976592977893, | |
| "loss": 1.0392, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.42048129439353943, | |
| "learning_rate": 0.0001989596879063719, | |
| "loss": 0.8439, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.4129664897918701, | |
| "learning_rate": 0.0001986996098829649, | |
| "loss": 1.1025, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5610629320144653, | |
| "learning_rate": 0.00019843953185955788, | |
| "loss": 0.9368, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.4288642406463623, | |
| "learning_rate": 0.00019817945383615086, | |
| "loss": 0.9711, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.572507917881012, | |
| "learning_rate": 0.0001979193758127438, | |
| "loss": 0.9739, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5115912556648254, | |
| "learning_rate": 0.0001976592977893368, | |
| "loss": 0.9356, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.608063280582428, | |
| "learning_rate": 0.00019739921976592978, | |
| "loss": 1.2459, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.0171502828598022, | |
| "learning_rate": 0.00019713914174252276, | |
| "loss": 1.0629, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.514552116394043, | |
| "learning_rate": 0.00019687906371911574, | |
| "loss": 0.9646, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.4363428056240082, | |
| "learning_rate": 0.00019661898569570872, | |
| "loss": 0.8659, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.4470008611679077, | |
| "learning_rate": 0.0001963589076723017, | |
| "loss": 1.0338, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.5710871815681458, | |
| "learning_rate": 0.0001960988296488947, | |
| "loss": 0.946, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.6456964612007141, | |
| "learning_rate": 0.00019583875162548767, | |
| "loss": 1.0956, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.45742425322532654, | |
| "learning_rate": 0.00019557867360208065, | |
| "loss": 0.7985, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.9953218698501587, | |
| "learning_rate": 0.0001953185955786736, | |
| "loss": 0.9476, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5075244307518005, | |
| "learning_rate": 0.0001950585175552666, | |
| "loss": 1.1704, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.7076822519302368, | |
| "learning_rate": 0.00019479843953185957, | |
| "loss": 1.2054, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.0368528366088867, | |
| "eval_runtime": 547.1826, | |
| "eval_samples_per_second": 2.76, | |
| "eval_steps_per_second": 1.38, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.7408495545387268, | |
| "learning_rate": 0.00019453836150845255, | |
| "loss": 1.3149, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5010321736335754, | |
| "learning_rate": 0.00019427828348504554, | |
| "loss": 0.8483, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5388755798339844, | |
| "learning_rate": 0.0001940182054616385, | |
| "loss": 1.034, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.32918357849121094, | |
| "learning_rate": 0.00019375812743823147, | |
| "loss": 1.0762, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.4812282919883728, | |
| "learning_rate": 0.00019349804941482446, | |
| "loss": 1.0797, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.6160157918930054, | |
| "learning_rate": 0.00019323797139141744, | |
| "loss": 0.9488, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.41306182742118835, | |
| "learning_rate": 0.00019297789336801042, | |
| "loss": 1.0742, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.5411396026611328, | |
| "learning_rate": 0.00019271781534460338, | |
| "loss": 1.1162, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.45688003301620483, | |
| "learning_rate": 0.00019245773732119636, | |
| "loss": 0.8042, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.4660446047782898, | |
| "learning_rate": 0.00019219765929778934, | |
| "loss": 0.8234, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.6277762055397034, | |
| "learning_rate": 0.00019193758127438232, | |
| "loss": 1.0324, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.6119320392608643, | |
| "learning_rate": 0.0001916775032509753, | |
| "loss": 0.6912, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.5463618040084839, | |
| "learning_rate": 0.00019141742522756826, | |
| "loss": 1.1297, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.4918029010295868, | |
| "learning_rate": 0.00019115734720416124, | |
| "loss": 1.0857, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4734187424182892, | |
| "learning_rate": 0.00019089726918075422, | |
| "loss": 1.0246, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.5416173934936523, | |
| "learning_rate": 0.0001906371911573472, | |
| "loss": 1.0262, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.486284464597702, | |
| "learning_rate": 0.0001903771131339402, | |
| "loss": 1.2198, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4003067910671234, | |
| "learning_rate": 0.00019011703511053317, | |
| "loss": 0.8525, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.38142916560173035, | |
| "learning_rate": 0.00018985695708712615, | |
| "loss": 1.1475, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.42364147305488586, | |
| "learning_rate": 0.00018959687906371913, | |
| "loss": 0.8207, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.384432852268219, | |
| "learning_rate": 0.00018933680104031212, | |
| "loss": 0.9451, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.38188567757606506, | |
| "learning_rate": 0.0001890767230169051, | |
| "loss": 0.921, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4212167263031006, | |
| "learning_rate": 0.00018881664499349805, | |
| "loss": 0.8532, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.7674171924591064, | |
| "learning_rate": 0.00018855656697009104, | |
| "loss": 1.1751, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4111984074115753, | |
| "learning_rate": 0.00018829648894668402, | |
| "loss": 0.906, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.6682639718055725, | |
| "learning_rate": 0.000188036410923277, | |
| "loss": 1.1284, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.3887438178062439, | |
| "learning_rate": 0.00018777633289986998, | |
| "loss": 1.0324, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.5829350352287292, | |
| "learning_rate": 0.00018751625487646294, | |
| "loss": 1.038, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.5861855149269104, | |
| "learning_rate": 0.00018725617685305592, | |
| "loss": 0.9453, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.40044718980789185, | |
| "learning_rate": 0.0001869960988296489, | |
| "loss": 1.1971, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4322098195552826, | |
| "learning_rate": 0.00018673602080624188, | |
| "loss": 0.9792, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.4132952392101288, | |
| "learning_rate": 0.00018647594278283487, | |
| "loss": 0.9597, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.4141194224357605, | |
| "learning_rate": 0.00018621586475942782, | |
| "loss": 1.0785, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5526332855224609, | |
| "learning_rate": 0.0001859557867360208, | |
| "loss": 1.0762, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.6953147053718567, | |
| "learning_rate": 0.00018569570871261379, | |
| "loss": 1.1048, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.4306538701057434, | |
| "learning_rate": 0.00018543563068920677, | |
| "loss": 0.9798, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.32605746388435364, | |
| "learning_rate": 0.00018517555266579975, | |
| "loss": 0.9825, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.48711439967155457, | |
| "learning_rate": 0.0001849154746423927, | |
| "loss": 0.9685, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.7728849649429321, | |
| "learning_rate": 0.0001846553966189857, | |
| "loss": 1.2843, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.38121744990348816, | |
| "learning_rate": 0.00018439531859557867, | |
| "loss": 0.8289, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.5053502321243286, | |
| "learning_rate": 0.00018413524057217165, | |
| "loss": 1.0824, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.44003796577453613, | |
| "learning_rate": 0.00018387516254876463, | |
| "loss": 1.0957, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.35713884234428406, | |
| "learning_rate": 0.00018361508452535762, | |
| "loss": 0.7869, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.6612699627876282, | |
| "learning_rate": 0.0001833550065019506, | |
| "loss": 1.1621, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.4270091950893402, | |
| "learning_rate": 0.00018309492847854358, | |
| "loss": 0.8964, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.42207202315330505, | |
| "learning_rate": 0.00018283485045513656, | |
| "loss": 1.1403, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.48486125469207764, | |
| "learning_rate": 0.00018257477243172954, | |
| "loss": 0.9993, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.4205480217933655, | |
| "learning_rate": 0.0001823146944083225, | |
| "loss": 1.0404, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3420919179916382, | |
| "learning_rate": 0.00018205461638491548, | |
| "loss": 1.1434, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.6411290168762207, | |
| "learning_rate": 0.00018179453836150846, | |
| "loss": 1.2055, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.7193886637687683, | |
| "learning_rate": 0.00018153446033810145, | |
| "loss": 0.9436, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.34661969542503357, | |
| "learning_rate": 0.00018127438231469443, | |
| "loss": 0.8158, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.4028843939304352, | |
| "learning_rate": 0.00018101430429128738, | |
| "loss": 0.9863, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3898251950740814, | |
| "learning_rate": 0.00018075422626788037, | |
| "loss": 0.9215, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3827955424785614, | |
| "learning_rate": 0.00018049414824447335, | |
| "loss": 0.9513, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3840239644050598, | |
| "learning_rate": 0.00018023407022106633, | |
| "loss": 0.8303, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.42413073778152466, | |
| "learning_rate": 0.0001799739921976593, | |
| "loss": 0.8909, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.47216784954071045, | |
| "learning_rate": 0.00017971391417425227, | |
| "loss": 1.0413, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.35447853803634644, | |
| "learning_rate": 0.00017945383615084525, | |
| "loss": 0.9781, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.46554017066955566, | |
| "learning_rate": 0.00017919375812743823, | |
| "loss": 0.7186, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3696407973766327, | |
| "learning_rate": 0.00017893368010403121, | |
| "loss": 1.0137, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.5633952617645264, | |
| "learning_rate": 0.0001786736020806242, | |
| "loss": 1.0944, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3334963917732239, | |
| "learning_rate": 0.00017841352405721715, | |
| "loss": 1.2606, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.4501505494117737, | |
| "learning_rate": 0.00017815344603381013, | |
| "loss": 0.7306, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.44553884863853455, | |
| "learning_rate": 0.00017789336801040312, | |
| "loss": 0.871, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.474342405796051, | |
| "learning_rate": 0.0001776332899869961, | |
| "loss": 0.7593, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.7258349061012268, | |
| "learning_rate": 0.00017737321196358908, | |
| "loss": 1.4035, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.43586501479148865, | |
| "learning_rate": 0.00017711313394018206, | |
| "loss": 1.1679, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.4580634832382202, | |
| "learning_rate": 0.00017685305591677504, | |
| "loss": 0.9496, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.40509316325187683, | |
| "learning_rate": 0.00017659297789336803, | |
| "loss": 0.9515, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3496972620487213, | |
| "learning_rate": 0.000176332899869961, | |
| "loss": 1.1846, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.6468595862388611, | |
| "learning_rate": 0.000176072821846554, | |
| "loss": 1.0307, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3840126693248749, | |
| "learning_rate": 0.00017581274382314695, | |
| "loss": 1.0248, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.4715554118156433, | |
| "learning_rate": 0.00017555266579973993, | |
| "loss": 1.1017, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.38534194231033325, | |
| "learning_rate": 0.0001752925877763329, | |
| "loss": 1.0073, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.3881916403770447, | |
| "learning_rate": 0.0001750325097529259, | |
| "loss": 0.8961, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.49220091104507446, | |
| "learning_rate": 0.00017477243172951887, | |
| "loss": 1.0184, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.38170936703681946, | |
| "learning_rate": 0.00017451235370611186, | |
| "loss": 1.0939, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.3692156672477722, | |
| "learning_rate": 0.0001742522756827048, | |
| "loss": 1.085, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.43161171674728394, | |
| "learning_rate": 0.0001739921976592978, | |
| "loss": 0.9098, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.3874380886554718, | |
| "learning_rate": 0.00017373211963589078, | |
| "loss": 1.0108, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.37556958198547363, | |
| "learning_rate": 0.00017347204161248376, | |
| "loss": 1.0344, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.4288795292377472, | |
| "learning_rate": 0.00017321196358907674, | |
| "loss": 0.9329, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.6587222218513489, | |
| "learning_rate": 0.0001729518855656697, | |
| "loss": 1.0312, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.6700361371040344, | |
| "learning_rate": 0.00017269180754226268, | |
| "loss": 1.035, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.5208828449249268, | |
| "learning_rate": 0.00017243172951885566, | |
| "loss": 1.0334, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.5774813294410706, | |
| "learning_rate": 0.00017217165149544864, | |
| "loss": 1.0366, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.3492725193500519, | |
| "learning_rate": 0.00017191157347204162, | |
| "loss": 1.0225, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.3714265525341034, | |
| "learning_rate": 0.00017165149544863458, | |
| "loss": 1.0355, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.4425973892211914, | |
| "learning_rate": 0.00017139141742522756, | |
| "loss": 0.974, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.43257299065589905, | |
| "learning_rate": 0.00017113133940182054, | |
| "loss": 0.8614, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.37084296345710754, | |
| "learning_rate": 0.00017087126137841353, | |
| "loss": 0.7135, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.6695109009742737, | |
| "learning_rate": 0.0001706111833550065, | |
| "loss": 0.7722, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.5144183039665222, | |
| "learning_rate": 0.0001703511053315995, | |
| "loss": 0.9364, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.58673095703125, | |
| "learning_rate": 0.00017009102730819247, | |
| "loss": 1.1141, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.4033479392528534, | |
| "learning_rate": 0.00016983094928478545, | |
| "loss": 1.0002, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.38111910223960876, | |
| "learning_rate": 0.00016957087126137844, | |
| "loss": 0.9318, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.4174363613128662, | |
| "learning_rate": 0.00016931079323797142, | |
| "loss": 0.9381, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.3726828098297119, | |
| "learning_rate": 0.00016905071521456437, | |
| "loss": 1.0405, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.5414443612098694, | |
| "learning_rate": 0.00016879063719115736, | |
| "loss": 1.0667, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.0012115240097046, | |
| "eval_runtime": 546.9226, | |
| "eval_samples_per_second": 2.761, | |
| "eval_steps_per_second": 1.38, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.523889422416687, | |
| "learning_rate": 0.00016853055916775034, | |
| "loss": 1.0408, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.47460106015205383, | |
| "learning_rate": 0.00016827048114434332, | |
| "loss": 1.0327, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.5161871314048767, | |
| "learning_rate": 0.0001680104031209363, | |
| "loss": 0.9104, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.3816511631011963, | |
| "learning_rate": 0.00016775032509752926, | |
| "loss": 0.6875, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.3574850261211395, | |
| "learning_rate": 0.00016749024707412224, | |
| "loss": 0.8079, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.37416210770606995, | |
| "learning_rate": 0.00016723016905071522, | |
| "loss": 0.7479, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.648332417011261, | |
| "learning_rate": 0.0001669700910273082, | |
| "loss": 1.0868, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.37010350823402405, | |
| "learning_rate": 0.0001667100130039012, | |
| "loss": 0.8634, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.5206050872802734, | |
| "learning_rate": 0.00016644993498049414, | |
| "loss": 0.8827, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.4001045525074005, | |
| "learning_rate": 0.00016618985695708712, | |
| "loss": 1.1029, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.3948250114917755, | |
| "learning_rate": 0.0001659297789336801, | |
| "loss": 0.7248, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.4833560287952423, | |
| "learning_rate": 0.0001656697009102731, | |
| "loss": 0.7379, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.4951235055923462, | |
| "learning_rate": 0.00016540962288686607, | |
| "loss": 1.0003, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.7607774138450623, | |
| "learning_rate": 0.00016514954486345903, | |
| "loss": 0.8599, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.3604733347892761, | |
| "learning_rate": 0.000164889466840052, | |
| "loss": 1.0301, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.3514990508556366, | |
| "learning_rate": 0.000164629388816645, | |
| "loss": 1.072, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.8136312365531921, | |
| "learning_rate": 0.00016436931079323797, | |
| "loss": 1.0795, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4305706024169922, | |
| "learning_rate": 0.00016410923276983095, | |
| "loss": 0.8288, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4228506088256836, | |
| "learning_rate": 0.00016384915474642394, | |
| "loss": 0.863, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.3303283751010895, | |
| "learning_rate": 0.00016358907672301692, | |
| "loss": 0.8992, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4840926229953766, | |
| "learning_rate": 0.0001633289986996099, | |
| "loss": 0.9309, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.3939206600189209, | |
| "learning_rate": 0.00016306892067620288, | |
| "loss": 1.0456, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4611961245536804, | |
| "learning_rate": 0.00016280884265279587, | |
| "loss": 1.1839, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4443643093109131, | |
| "learning_rate": 0.00016254876462938882, | |
| "loss": 0.8566, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.38910534977912903, | |
| "learning_rate": 0.0001622886866059818, | |
| "loss": 0.9426, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.6585952043533325, | |
| "learning_rate": 0.00016202860858257478, | |
| "loss": 1.0632, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.2883739173412323, | |
| "learning_rate": 0.00016176853055916777, | |
| "loss": 0.8594, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.4793940484523773, | |
| "learning_rate": 0.00016150845253576075, | |
| "loss": 0.9258, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.45249128341674805, | |
| "learning_rate": 0.0001612483745123537, | |
| "loss": 0.875, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.7601549029350281, | |
| "learning_rate": 0.00016098829648894669, | |
| "loss": 1.0903, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.4474358856678009, | |
| "learning_rate": 0.00016072821846553967, | |
| "loss": 0.8636, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.4709658920764923, | |
| "learning_rate": 0.00016046814044213265, | |
| "loss": 1.01, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.49074116349220276, | |
| "learning_rate": 0.00016020806241872563, | |
| "loss": 1.129, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.40011027455329895, | |
| "learning_rate": 0.0001599479843953186, | |
| "loss": 0.9789, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.36765021085739136, | |
| "learning_rate": 0.00015968790637191157, | |
| "loss": 0.9647, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.4226991832256317, | |
| "learning_rate": 0.00015942782834850455, | |
| "loss": 1.0593, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.5633476376533508, | |
| "learning_rate": 0.00015916775032509753, | |
| "loss": 1.139, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.4227031171321869, | |
| "learning_rate": 0.00015890767230169052, | |
| "loss": 0.9766, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.7903754711151123, | |
| "learning_rate": 0.00015864759427828347, | |
| "loss": 1.0215, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.5319734811782837, | |
| "learning_rate": 0.00015838751625487645, | |
| "loss": 1.0351, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.38870692253112793, | |
| "learning_rate": 0.00015812743823146944, | |
| "loss": 1.1089, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.5061522126197815, | |
| "learning_rate": 0.00015786736020806242, | |
| "loss": 0.9956, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.6587597131729126, | |
| "learning_rate": 0.0001576072821846554, | |
| "loss": 0.9433, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.500415027141571, | |
| "learning_rate": 0.00015734720416124838, | |
| "loss": 0.9071, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.49865788221359253, | |
| "learning_rate": 0.00015708712613784136, | |
| "loss": 1.013, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.472517192363739, | |
| "learning_rate": 0.00015682704811443435, | |
| "loss": 1.0552, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.5091108083724976, | |
| "learning_rate": 0.00015656697009102733, | |
| "loss": 0.9919, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.39484265446662903, | |
| "learning_rate": 0.0001563068920676203, | |
| "loss": 0.9945, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.47099944949150085, | |
| "learning_rate": 0.00015604681404421327, | |
| "loss": 0.847, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.4681323766708374, | |
| "learning_rate": 0.00015578673602080625, | |
| "loss": 0.8998, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.35557135939598083, | |
| "learning_rate": 0.00015552665799739923, | |
| "loss": 0.7108, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.7873208522796631, | |
| "learning_rate": 0.0001552665799739922, | |
| "loss": 1.1322, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.45806723833084106, | |
| "learning_rate": 0.0001550065019505852, | |
| "loss": 0.9095, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.639227032661438, | |
| "learning_rate": 0.00015474642392717815, | |
| "loss": 1.1761, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.6849457621574402, | |
| "learning_rate": 0.00015448634590377113, | |
| "loss": 1.1391, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.5833932757377625, | |
| "learning_rate": 0.00015422626788036411, | |
| "loss": 1.0434, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.684618353843689, | |
| "learning_rate": 0.0001539661898569571, | |
| "loss": 0.9719, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.4258657991886139, | |
| "learning_rate": 0.00015370611183355008, | |
| "loss": 1.1534, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.5763025879859924, | |
| "learning_rate": 0.00015344603381014303, | |
| "loss": 0.9974, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.5415167808532715, | |
| "learning_rate": 0.00015318595578673602, | |
| "loss": 1.0696, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.43196481466293335, | |
| "learning_rate": 0.000152925877763329, | |
| "loss": 0.8191, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.3914147913455963, | |
| "learning_rate": 0.00015266579973992198, | |
| "loss": 0.8465, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.4838383197784424, | |
| "learning_rate": 0.00015240572171651496, | |
| "loss": 1.0027, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.3581622540950775, | |
| "learning_rate": 0.00015214564369310792, | |
| "loss": 1.1247, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.9383752942085266, | |
| "learning_rate": 0.0001518855656697009, | |
| "loss": 1.2207, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.5058914422988892, | |
| "learning_rate": 0.00015162548764629388, | |
| "loss": 1.0036, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.4513028860092163, | |
| "learning_rate": 0.0001513654096228869, | |
| "loss": 1.0949, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.5779305696487427, | |
| "learning_rate": 0.00015110533159947987, | |
| "loss": 1.0035, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.6758905649185181, | |
| "learning_rate": 0.00015084525357607283, | |
| "loss": 1.0163, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.5109132528305054, | |
| "learning_rate": 0.0001505851755526658, | |
| "loss": 0.7357, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.42248305678367615, | |
| "learning_rate": 0.0001503250975292588, | |
| "loss": 1.0664, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.7441749572753906, | |
| "learning_rate": 0.00015006501950585178, | |
| "loss": 0.9483, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.5364653468132019, | |
| "learning_rate": 0.00014980494148244476, | |
| "loss": 1.1671, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.3390597701072693, | |
| "learning_rate": 0.0001495448634590377, | |
| "loss": 0.9616, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.3810036778450012, | |
| "learning_rate": 0.0001492847854356307, | |
| "loss": 0.9419, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.39790648221969604, | |
| "learning_rate": 0.00014902470741222368, | |
| "loss": 0.947, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.5461649894714355, | |
| "learning_rate": 0.00014876462938881666, | |
| "loss": 1.0065, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.376022607088089, | |
| "learning_rate": 0.00014850455136540964, | |
| "loss": 0.8626, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.47341254353523254, | |
| "learning_rate": 0.0001482444733420026, | |
| "loss": 0.9812, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.5151678323745728, | |
| "learning_rate": 0.00014798439531859558, | |
| "loss": 0.9688, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.4801676273345947, | |
| "learning_rate": 0.00014772431729518856, | |
| "loss": 0.9348, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.43506500124931335, | |
| "learning_rate": 0.00014746423927178154, | |
| "loss": 1.0792, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.5347827076911926, | |
| "learning_rate": 0.00014720416124837452, | |
| "loss": 1.1285, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.5323308706283569, | |
| "learning_rate": 0.00014694408322496748, | |
| "loss": 1.047, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.364046573638916, | |
| "learning_rate": 0.00014668400520156046, | |
| "loss": 1.0206, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.41780295968055725, | |
| "learning_rate": 0.00014642392717815344, | |
| "loss": 1.011, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.6010937690734863, | |
| "learning_rate": 0.00014616384915474643, | |
| "loss": 0.9836, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.3574303090572357, | |
| "learning_rate": 0.0001459037711313394, | |
| "loss": 0.9051, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.3346600830554962, | |
| "learning_rate": 0.0001456436931079324, | |
| "loss": 1.0333, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.48559319972991943, | |
| "learning_rate": 0.00014538361508452537, | |
| "loss": 0.8363, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.4872112274169922, | |
| "learning_rate": 0.00014512353706111836, | |
| "loss": 0.9565, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.37863266468048096, | |
| "learning_rate": 0.00014486345903771134, | |
| "loss": 0.9869, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.6248475909233093, | |
| "learning_rate": 0.00014460338101430432, | |
| "loss": 1.1117, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.40380629897117615, | |
| "learning_rate": 0.00014434330299089727, | |
| "loss": 0.895, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.4236217439174652, | |
| "learning_rate": 0.00014408322496749026, | |
| "loss": 0.8849, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.35017380118370056, | |
| "learning_rate": 0.00014382314694408324, | |
| "loss": 0.8472, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.5927186608314514, | |
| "learning_rate": 0.00014356306892067622, | |
| "loss": 1.0073, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.7567859292030334, | |
| "learning_rate": 0.0001433029908972692, | |
| "loss": 0.9784, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.4356285035610199, | |
| "learning_rate": 0.00014304291287386216, | |
| "loss": 0.8339, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.3144444525241852, | |
| "learning_rate": 0.00014278283485045514, | |
| "loss": 1.0751, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.9849200248718262, | |
| "eval_runtime": 546.1357, | |
| "eval_samples_per_second": 2.765, | |
| "eval_steps_per_second": 1.382, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 849, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.4054359796233011e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |