| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.971724787935909, | |
| "eval_steps": 500, | |
| "global_step": 792, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03770028275212064, | |
| "grad_norm": 2.8582637310028076, | |
| "learning_rate": 4.9995083170283816e-05, | |
| "loss": 2.995, | |
| "num_input_tokens_seen": 57008, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07540056550424128, | |
| "grad_norm": 2.4749696254730225, | |
| "learning_rate": 4.998033461515242e-05, | |
| "loss": 2.7127, | |
| "num_input_tokens_seen": 117936, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11310084825636192, | |
| "grad_norm": 2.3738160133361816, | |
| "learning_rate": 4.9955760135896534e-05, | |
| "loss": 2.6302, | |
| "num_input_tokens_seen": 176288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15080113100848255, | |
| "grad_norm": 2.2132370471954346, | |
| "learning_rate": 4.992136939879856e-05, | |
| "loss": 2.5818, | |
| "num_input_tokens_seen": 229712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1885014137606032, | |
| "grad_norm": 2.444084882736206, | |
| "learning_rate": 4.9877175931330346e-05, | |
| "loss": 2.4913, | |
| "num_input_tokens_seen": 288784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22620169651272384, | |
| "grad_norm": 2.190948009490967, | |
| "learning_rate": 4.982319711683221e-05, | |
| "loss": 2.4694, | |
| "num_input_tokens_seen": 347712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2639019792648445, | |
| "grad_norm": 1.9827752113342285, | |
| "learning_rate": 4.975945418767529e-05, | |
| "loss": 2.4525, | |
| "num_input_tokens_seen": 404272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3016022620169651, | |
| "grad_norm": 2.3744397163391113, | |
| "learning_rate": 4.968597221690986e-05, | |
| "loss": 2.4745, | |
| "num_input_tokens_seen": 461632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3393025447690858, | |
| "grad_norm": 2.5817763805389404, | |
| "learning_rate": 4.96027801084029e-05, | |
| "loss": 2.4637, | |
| "num_input_tokens_seen": 518016, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3770028275212064, | |
| "grad_norm": 2.2218539714813232, | |
| "learning_rate": 4.950991058546893e-05, | |
| "loss": 2.5011, | |
| "num_input_tokens_seen": 579312, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41470311027332707, | |
| "grad_norm": 2.5139260292053223, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 2.4397, | |
| "num_input_tokens_seen": 636448, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4524033930254477, | |
| "grad_norm": 2.589820623397827, | |
| "learning_rate": 4.929528920808854e-05, | |
| "loss": 2.4109, | |
| "num_input_tokens_seen": 693504, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49010367577756836, | |
| "grad_norm": 2.8880276679992676, | |
| "learning_rate": 4.917362177418342e-05, | |
| "loss": 2.4228, | |
| "num_input_tokens_seen": 752160, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.527803958529689, | |
| "grad_norm": 2.480609178543091, | |
| "learning_rate": 4.904244573372733e-05, | |
| "loss": 2.4391, | |
| "num_input_tokens_seen": 811296, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5655042412818096, | |
| "grad_norm": 2.6764094829559326, | |
| "learning_rate": 4.8901812684340564e-05, | |
| "loss": 2.4552, | |
| "num_input_tokens_seen": 867696, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6032045240339302, | |
| "grad_norm": 2.666821002960205, | |
| "learning_rate": 4.8751777943523634e-05, | |
| "loss": 2.3658, | |
| "num_input_tokens_seen": 924944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6409048067860509, | |
| "grad_norm": 2.884999990463257, | |
| "learning_rate": 4.8592400526898314e-05, | |
| "loss": 2.359, | |
| "num_input_tokens_seen": 978768, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6786050895381716, | |
| "grad_norm": 2.58659291267395, | |
| "learning_rate": 4.842374312499405e-05, | |
| "loss": 2.4228, | |
| "num_input_tokens_seen": 1034544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7163053722902922, | |
| "grad_norm": 2.6272594928741455, | |
| "learning_rate": 4.824587207858888e-05, | |
| "loss": 2.32, | |
| "num_input_tokens_seen": 1091776, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7540056550424128, | |
| "grad_norm": 2.6761183738708496, | |
| "learning_rate": 4.805885735261454e-05, | |
| "loss": 2.3393, | |
| "num_input_tokens_seen": 1153056, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7917059377945335, | |
| "grad_norm": 2.721721887588501, | |
| "learning_rate": 4.786277250863599e-05, | |
| "loss": 2.2595, | |
| "num_input_tokens_seen": 1211808, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8294062205466541, | |
| "grad_norm": 2.718644618988037, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 2.3171, | |
| "num_input_tokens_seen": 1273600, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8671065032987747, | |
| "grad_norm": 2.6614394187927246, | |
| "learning_rate": 4.744370452107789e-05, | |
| "loss": 2.2949, | |
| "num_input_tokens_seen": 1331392, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9048067860508954, | |
| "grad_norm": 2.851165771484375, | |
| "learning_rate": 4.722088621637309e-05, | |
| "loss": 2.3818, | |
| "num_input_tokens_seen": 1387664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.942507068803016, | |
| "grad_norm": 2.692765235900879, | |
| "learning_rate": 4.698932740657479e-05, | |
| "loss": 2.2494, | |
| "num_input_tokens_seen": 1445968, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9802073515551367, | |
| "grad_norm": 2.7365992069244385, | |
| "learning_rate": 4.6749119174501975e-05, | |
| "loss": 2.3593, | |
| "num_input_tokens_seen": 1497744, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0179076343072573, | |
| "grad_norm": 2.6355655193328857, | |
| "learning_rate": 4.6500356005192514e-05, | |
| "loss": 2.1892, | |
| "num_input_tokens_seen": 1549008, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.055607917059378, | |
| "grad_norm": 2.8112802505493164, | |
| "learning_rate": 4.6243135748737864e-05, | |
| "loss": 2.1753, | |
| "num_input_tokens_seen": 1605152, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0933081998114986, | |
| "grad_norm": 3.1792027950286865, | |
| "learning_rate": 4.597755958179406e-05, | |
| "loss": 2.1186, | |
| "num_input_tokens_seen": 1663456, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.1310084825636193, | |
| "grad_norm": 3.5244438648223877, | |
| "learning_rate": 4.570373196778427e-05, | |
| "loss": 2.0526, | |
| "num_input_tokens_seen": 1722320, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1687087653157398, | |
| "grad_norm": 4.0647783279418945, | |
| "learning_rate": 4.5421760615808474e-05, | |
| "loss": 2.1589, | |
| "num_input_tokens_seen": 1771664, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.2064090480678604, | |
| "grad_norm": 3.4753596782684326, | |
| "learning_rate": 4.513175643827647e-05, | |
| "loss": 2.0505, | |
| "num_input_tokens_seen": 1829824, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.244109330819981, | |
| "grad_norm": 3.573631525039673, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 2.0924, | |
| "num_input_tokens_seen": 1882384, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2818096135721018, | |
| "grad_norm": 3.39180588722229, | |
| "learning_rate": 4.4528109009727336e-05, | |
| "loss": 2.0184, | |
| "num_input_tokens_seen": 1939456, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3195098963242224, | |
| "grad_norm": 4.136682987213135, | |
| "learning_rate": 4.42147032012394e-05, | |
| "loss": 2.1524, | |
| "num_input_tokens_seen": 1996320, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3572101790763431, | |
| "grad_norm": 3.9565956592559814, | |
| "learning_rate": 4.389373935885646e-05, | |
| "loss": 2.1253, | |
| "num_input_tokens_seen": 2056560, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3949104618284638, | |
| "grad_norm": 3.7363975048065186, | |
| "learning_rate": 4.356534373254316e-05, | |
| "loss": 2.0752, | |
| "num_input_tokens_seen": 2118496, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4326107445805842, | |
| "grad_norm": 4.311358451843262, | |
| "learning_rate": 4.322964549552943e-05, | |
| "loss": 2.0574, | |
| "num_input_tokens_seen": 2178352, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4703110273327051, | |
| "grad_norm": 3.684499502182007, | |
| "learning_rate": 4.288677669350066e-05, | |
| "loss": 2.0481, | |
| "num_input_tokens_seen": 2233440, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.5080113100848256, | |
| "grad_norm": 4.71754264831543, | |
| "learning_rate": 4.2536872192658036e-05, | |
| "loss": 2.0859, | |
| "num_input_tokens_seen": 2289648, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5457115928369463, | |
| "grad_norm": 4.160897731781006, | |
| "learning_rate": 4.218006962666934e-05, | |
| "loss": 2.0877, | |
| "num_input_tokens_seen": 2346224, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.583411875589067, | |
| "grad_norm": 3.895419120788574, | |
| "learning_rate": 4.181650934253132e-05, | |
| "loss": 2.0488, | |
| "num_input_tokens_seen": 2407392, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.6211121583411876, | |
| "grad_norm": 4.271753787994385, | |
| "learning_rate": 4.144633434536467e-05, | |
| "loss": 2.0074, | |
| "num_input_tokens_seen": 2462400, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6588124410933083, | |
| "grad_norm": 4.415102958679199, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 2.0844, | |
| "num_input_tokens_seen": 2518304, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6965127238454287, | |
| "grad_norm": 4.525811672210693, | |
| "learning_rate": 4.06867251845213e-05, | |
| "loss": 2.0943, | |
| "num_input_tokens_seen": 2583168, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7342130065975496, | |
| "grad_norm": 4.545309543609619, | |
| "learning_rate": 4.0297589810356165e-05, | |
| "loss": 2.0858, | |
| "num_input_tokens_seen": 2643552, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.77191328934967, | |
| "grad_norm": 4.468845844268799, | |
| "learning_rate": 3.9902437184657784e-05, | |
| "loss": 2.044, | |
| "num_input_tokens_seen": 2705600, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.8096135721017907, | |
| "grad_norm": 4.4386138916015625, | |
| "learning_rate": 3.9501422739279956e-05, | |
| "loss": 2.1083, | |
| "num_input_tokens_seen": 2765856, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.8473138548539114, | |
| "grad_norm": 3.7564873695373535, | |
| "learning_rate": 3.909470421180201e-05, | |
| "loss": 2.0431, | |
| "num_input_tokens_seen": 2824192, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.885014137606032, | |
| "grad_norm": 4.3798418045043945, | |
| "learning_rate": 3.8682441583483314e-05, | |
| "loss": 2.0978, | |
| "num_input_tokens_seen": 2880208, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9227144203581528, | |
| "grad_norm": 4.044529914855957, | |
| "learning_rate": 3.8264797016335205e-05, | |
| "loss": 2.096, | |
| "num_input_tokens_seen": 2939856, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.9604147031102732, | |
| "grad_norm": 4.19630241394043, | |
| "learning_rate": 3.7841934789335164e-05, | |
| "loss": 1.9965, | |
| "num_input_tokens_seen": 2995552, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.998114985862394, | |
| "grad_norm": 4.908398151397705, | |
| "learning_rate": 3.741402123380828e-05, | |
| "loss": 2.1569, | |
| "num_input_tokens_seen": 3055504, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.0358152686145146, | |
| "grad_norm": 4.20371150970459, | |
| "learning_rate": 3.6981224668001424e-05, | |
| "loss": 1.7904, | |
| "num_input_tokens_seen": 3110576, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0735155513666355, | |
| "grad_norm": 5.414203643798828, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 1.7416, | |
| "num_input_tokens_seen": 3171440, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.111215834118756, | |
| "grad_norm": 5.226822853088379, | |
| "learning_rate": 3.610166531514436e-05, | |
| "loss": 1.7513, | |
| "num_input_tokens_seen": 3219792, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.1489161168708764, | |
| "grad_norm": 5.410066604614258, | |
| "learning_rate": 3.565524849957921e-05, | |
| "loss": 1.7565, | |
| "num_input_tokens_seen": 3275792, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.1866163996229973, | |
| "grad_norm": 5.878467082977295, | |
| "learning_rate": 3.520464048061758e-05, | |
| "loss": 1.7417, | |
| "num_input_tokens_seen": 3333136, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.2243166823751177, | |
| "grad_norm": 5.918631553649902, | |
| "learning_rate": 3.47500185032913e-05, | |
| "loss": 1.7726, | |
| "num_input_tokens_seen": 3390080, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.2620169651272386, | |
| "grad_norm": 6.060715675354004, | |
| "learning_rate": 3.4291561391508185e-05, | |
| "loss": 1.7763, | |
| "num_input_tokens_seen": 3446208, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.299717247879359, | |
| "grad_norm": 6.188582897186279, | |
| "learning_rate": 3.3829449477712324e-05, | |
| "loss": 1.7327, | |
| "num_input_tokens_seen": 3508240, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.3374175306314795, | |
| "grad_norm": 6.416080951690674, | |
| "learning_rate": 3.336386453195088e-05, | |
| "loss": 1.7441, | |
| "num_input_tokens_seen": 3569856, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.3751178133836004, | |
| "grad_norm": 6.098644733428955, | |
| "learning_rate": 3.2894989690375626e-05, | |
| "loss": 1.7355, | |
| "num_input_tokens_seen": 3631984, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.412818096135721, | |
| "grad_norm": 7.12858772277832, | |
| "learning_rate": 3.2423009383206876e-05, | |
| "loss": 1.7182, | |
| "num_input_tokens_seen": 3688192, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.4505183788878417, | |
| "grad_norm": 6.329550266265869, | |
| "learning_rate": 3.194810926218861e-05, | |
| "loss": 1.7332, | |
| "num_input_tokens_seen": 3746720, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.488218661639962, | |
| "grad_norm": 6.534445762634277, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 1.6908, | |
| "num_input_tokens_seen": 3802432, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.525918944392083, | |
| "grad_norm": 6.304942607879639, | |
| "learning_rate": 3.099029785459328e-05, | |
| "loss": 1.7756, | |
| "num_input_tokens_seen": 3856800, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.5636192271442035, | |
| "grad_norm": 6.389725208282471, | |
| "learning_rate": 3.0507763319663517e-05, | |
| "loss": 1.7737, | |
| "num_input_tokens_seen": 3916320, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.6013195098963244, | |
| "grad_norm": 6.7536940574646, | |
| "learning_rate": 3.002306232598497e-05, | |
| "loss": 1.7446, | |
| "num_input_tokens_seen": 3974864, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.639019792648445, | |
| "grad_norm": 6.574880599975586, | |
| "learning_rate": 2.9536385528937567e-05, | |
| "loss": 1.7283, | |
| "num_input_tokens_seen": 4032656, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.6767200754005653, | |
| "grad_norm": 5.760074138641357, | |
| "learning_rate": 2.9047924361076345e-05, | |
| "loss": 1.7573, | |
| "num_input_tokens_seen": 4092800, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.7144203581526862, | |
| "grad_norm": 6.087067604064941, | |
| "learning_rate": 2.8557870956832132e-05, | |
| "loss": 1.6758, | |
| "num_input_tokens_seen": 4144592, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.7521206409048067, | |
| "grad_norm": 7.485050201416016, | |
| "learning_rate": 2.8066418076936167e-05, | |
| "loss": 1.7087, | |
| "num_input_tokens_seen": 4200000, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.7898209236569276, | |
| "grad_norm": 7.791069984436035, | |
| "learning_rate": 2.7573759032598366e-05, | |
| "loss": 1.7527, | |
| "num_input_tokens_seen": 4262288, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.827521206409048, | |
| "grad_norm": 6.225643634796143, | |
| "learning_rate": 2.7080087609469062e-05, | |
| "loss": 1.786, | |
| "num_input_tokens_seen": 4317040, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.8652214891611685, | |
| "grad_norm": 5.990758895874023, | |
| "learning_rate": 2.6585597991414114e-05, | |
| "loss": 1.677, | |
| "num_input_tokens_seen": 4376576, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.9029217719132894, | |
| "grad_norm": 6.876400470733643, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 1.7027, | |
| "num_input_tokens_seen": 4429024, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.9406220546654103, | |
| "grad_norm": 6.724515914916992, | |
| "learning_rate": 2.5594942438652688e-05, | |
| "loss": 1.7717, | |
| "num_input_tokens_seen": 4494400, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.9783223374175307, | |
| "grad_norm": 7.128418922424316, | |
| "learning_rate": 2.509916617471903e-05, | |
| "loss": 1.8441, | |
| "num_input_tokens_seen": 4554576, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.016022620169651, | |
| "grad_norm": 5.73885440826416, | |
| "learning_rate": 2.46033509041298e-05, | |
| "loss": 1.604, | |
| "num_input_tokens_seen": 4612352, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.053722902921772, | |
| "grad_norm": 6.931432247161865, | |
| "learning_rate": 2.410769165402549e-05, | |
| "loss": 1.4357, | |
| "num_input_tokens_seen": 4674960, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.0914231856738925, | |
| "grad_norm": 10.487885475158691, | |
| "learning_rate": 2.3612383390176503e-05, | |
| "loss": 1.4401, | |
| "num_input_tokens_seen": 4732736, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.1291234684260134, | |
| "grad_norm": 7.611717700958252, | |
| "learning_rate": 2.3117620940294048e-05, | |
| "loss": 1.4433, | |
| "num_input_tokens_seen": 4795856, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 3.166823751178134, | |
| "grad_norm": 7.033103942871094, | |
| "learning_rate": 2.2623598917395438e-05, | |
| "loss": 1.4739, | |
| "num_input_tokens_seen": 4854976, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.2045240339302543, | |
| "grad_norm": 7.760231971740723, | |
| "learning_rate": 2.213051164325366e-05, | |
| "loss": 1.4327, | |
| "num_input_tokens_seen": 4906032, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.242224316682375, | |
| "grad_norm": 9.03538990020752, | |
| "learning_rate": 2.1638553071961708e-05, | |
| "loss": 1.4281, | |
| "num_input_tokens_seen": 4954352, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.2799245994344957, | |
| "grad_norm": 8.354065895080566, | |
| "learning_rate": 2.1147916713641367e-05, | |
| "loss": 1.4006, | |
| "num_input_tokens_seen": 5012208, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.3176248821866166, | |
| "grad_norm": 8.750741004943848, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 1.4065, | |
| "num_input_tokens_seen": 5067616, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.355325164938737, | |
| "grad_norm": 8.950455665588379, | |
| "learning_rate": 2.017138200005236e-05, | |
| "loss": 1.4158, | |
| "num_input_tokens_seen": 5131488, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.3930254476908575, | |
| "grad_norm": 9.109482765197754, | |
| "learning_rate": 1.9685867761175584e-05, | |
| "loss": 1.5139, | |
| "num_input_tokens_seen": 5189216, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.4307257304429783, | |
| "grad_norm": 8.112481117248535, | |
| "learning_rate": 1.9202443816963425e-05, | |
| "loss": 1.4692, | |
| "num_input_tokens_seen": 5246032, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.468426013195099, | |
| "grad_norm": 9.428106307983398, | |
| "learning_rate": 1.872130032047302e-05, | |
| "loss": 1.3873, | |
| "num_input_tokens_seen": 5309648, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.5061262959472197, | |
| "grad_norm": 8.657079696655273, | |
| "learning_rate": 1.824262652775568e-05, | |
| "loss": 1.5167, | |
| "num_input_tokens_seen": 5371392, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 3.54382657869934, | |
| "grad_norm": 8.85914134979248, | |
| "learning_rate": 1.7766610723413684e-05, | |
| "loss": 1.4093, | |
| "num_input_tokens_seen": 5430528, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.581526861451461, | |
| "grad_norm": 8.869074821472168, | |
| "learning_rate": 1.7293440146539196e-05, | |
| "loss": 1.497, | |
| "num_input_tokens_seen": 5486048, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.6192271442035815, | |
| "grad_norm": 7.58018159866333, | |
| "learning_rate": 1.682330091706446e-05, | |
| "loss": 1.5024, | |
| "num_input_tokens_seen": 5551520, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.6569274269557024, | |
| "grad_norm": 9.567265510559082, | |
| "learning_rate": 1.6356377962552238e-05, | |
| "loss": 1.3976, | |
| "num_input_tokens_seen": 5607968, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 3.694627709707823, | |
| "grad_norm": 10.099461555480957, | |
| "learning_rate": 1.589285494545514e-05, | |
| "loss": 1.4343, | |
| "num_input_tokens_seen": 5666240, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.7323279924599433, | |
| "grad_norm": 8.967694282531738, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 1.4647, | |
| "num_input_tokens_seen": 5724272, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.770028275212064, | |
| "grad_norm": 8.292475700378418, | |
| "learning_rate": 1.4976736614834664e-05, | |
| "loss": 1.3874, | |
| "num_input_tokens_seen": 5782144, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.8077285579641846, | |
| "grad_norm": 9.741270065307617, | |
| "learning_rate": 1.4524501653137787e-05, | |
| "loss": 1.4405, | |
| "num_input_tokens_seen": 5835968, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.8454288407163055, | |
| "grad_norm": 9.290925025939941, | |
| "learning_rate": 1.4076387190766017e-05, | |
| "loss": 1.4689, | |
| "num_input_tokens_seen": 5894032, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.883129123468426, | |
| "grad_norm": 9.894857406616211, | |
| "learning_rate": 1.363256949191972e-05, | |
| "loss": 1.3515, | |
| "num_input_tokens_seen": 5948928, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 3.9208294062205464, | |
| "grad_norm": 9.370462417602539, | |
| "learning_rate": 1.3193223130682936e-05, | |
| "loss": 1.4372, | |
| "num_input_tokens_seen": 6004016, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.9585296889726673, | |
| "grad_norm": 8.76706314086914, | |
| "learning_rate": 1.2758520922355226e-05, | |
| "loss": 1.4051, | |
| "num_input_tokens_seen": 6054192, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.9962299717247878, | |
| "grad_norm": 9.206894874572754, | |
| "learning_rate": 1.2328633855475429e-05, | |
| "loss": 1.4304, | |
| "num_input_tokens_seen": 6111840, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.033930254476909, | |
| "grad_norm": 8.561943054199219, | |
| "learning_rate": 1.1903731024563966e-05, | |
| "loss": 1.1746, | |
| "num_input_tokens_seen": 6169584, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 4.071630537229029, | |
| "grad_norm": 9.77757453918457, | |
| "learning_rate": 1.148397956361007e-05, | |
| "loss": 1.172, | |
| "num_input_tokens_seen": 6232800, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.10933081998115, | |
| "grad_norm": 11.026362419128418, | |
| "learning_rate": 1.106954458033026e-05, | |
| "loss": 1.1709, | |
| "num_input_tokens_seen": 6294496, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 4.147031102733271, | |
| "grad_norm": 9.075161933898926, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 1.247, | |
| "num_input_tokens_seen": 6348976, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.184731385485391, | |
| "grad_norm": 10.577301025390625, | |
| "learning_rate": 1.025727395745095e-05, | |
| "loss": 1.2236, | |
| "num_input_tokens_seen": 6402624, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 4.222431668237512, | |
| "grad_norm": 10.635506629943848, | |
| "learning_rate": 9.859757821558337e-06, | |
| "loss": 1.1751, | |
| "num_input_tokens_seen": 6462992, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.260131950989632, | |
| "grad_norm": 10.660634994506836, | |
| "learning_rate": 9.468197045077976e-06, | |
| "loss": 1.1056, | |
| "num_input_tokens_seen": 6514944, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 4.297832233741753, | |
| "grad_norm": 11.758869171142578, | |
| "learning_rate": 9.082745647022797e-06, | |
| "loss": 1.1612, | |
| "num_input_tokens_seen": 6577440, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.335532516493874, | |
| "grad_norm": 10.878021240234375, | |
| "learning_rate": 8.703555243303835e-06, | |
| "loss": 1.146, | |
| "num_input_tokens_seen": 6631296, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.3732327992459945, | |
| "grad_norm": 11.381221771240234, | |
| "learning_rate": 8.330774987092712e-06, | |
| "loss": 1.1462, | |
| "num_input_tokens_seen": 6686784, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.410933081998115, | |
| "grad_norm": 10.535365104675293, | |
| "learning_rate": 7.96455151015272e-06, | |
| "loss": 1.2129, | |
| "num_input_tokens_seen": 6743712, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 4.448633364750235, | |
| "grad_norm": 10.050437927246094, | |
| "learning_rate": 7.605028865161809e-06, | |
| "loss": 1.2495, | |
| "num_input_tokens_seen": 6802416, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.486333647502356, | |
| "grad_norm": 10.320448875427246, | |
| "learning_rate": 7.25234846904993e-06, | |
| "loss": 1.1615, | |
| "num_input_tokens_seen": 6860880, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 4.524033930254477, | |
| "grad_norm": 10.299652099609375, | |
| "learning_rate": 6.906649047373246e-06, | |
| "loss": 1.2619, | |
| "num_input_tokens_seen": 6921424, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.561734213006598, | |
| "grad_norm": 11.873618125915527, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 1.1949, | |
| "num_input_tokens_seen": 6973504, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 4.599434495758718, | |
| "grad_norm": 11.657974243164062, | |
| "learning_rate": 6.2367342463579475e-06, | |
| "loss": 1.1891, | |
| "num_input_tokens_seen": 7027984, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.6371347785108386, | |
| "grad_norm": 10.802141189575195, | |
| "learning_rate": 5.912782375579412e-06, | |
| "loss": 1.1821, | |
| "num_input_tokens_seen": 7082720, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.674835061262959, | |
| "grad_norm": 11.281312942504883, | |
| "learning_rate": 5.596338392706077e-06, | |
| "loss": 1.2011, | |
| "num_input_tokens_seen": 7139760, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.71253534401508, | |
| "grad_norm": 9.546773910522461, | |
| "learning_rate": 5.2875267698322325e-06, | |
| "loss": 1.2479, | |
| "num_input_tokens_seen": 7196832, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.750235626767201, | |
| "grad_norm": 10.804587364196777, | |
| "learning_rate": 4.986468976890993e-06, | |
| "loss": 1.1982, | |
| "num_input_tokens_seen": 7255552, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.787935909519321, | |
| "grad_norm": 11.141725540161133, | |
| "learning_rate": 4.693283433874565e-06, | |
| "loss": 1.1955, | |
| "num_input_tokens_seen": 7310144, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 4.825636192271442, | |
| "grad_norm": 11.219179153442383, | |
| "learning_rate": 4.408085464254183e-06, | |
| "loss": 1.2429, | |
| "num_input_tokens_seen": 7363600, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.863336475023563, | |
| "grad_norm": 9.999290466308594, | |
| "learning_rate": 4.130987249617993e-06, | |
| "loss": 1.2139, | |
| "num_input_tokens_seen": 7425056, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 4.9010367577756835, | |
| "grad_norm": 10.23133373260498, | |
| "learning_rate": 3.8620977855448935e-06, | |
| "loss": 1.2122, | |
| "num_input_tokens_seen": 7488432, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.938737040527804, | |
| "grad_norm": 10.697420120239258, | |
| "learning_rate": 3.601522838731461e-06, | |
| "loss": 1.1634, | |
| "num_input_tokens_seen": 7549248, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 4.976437323279924, | |
| "grad_norm": 11.005745887756348, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 1.2289, | |
| "num_input_tokens_seen": 7607168, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.014137606032045, | |
| "grad_norm": 10.609835624694824, | |
| "learning_rate": 3.1057231709272077e-06, | |
| "loss": 1.1895, | |
| "num_input_tokens_seen": 7666560, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 5.051837888784166, | |
| "grad_norm": 10.383188247680664, | |
| "learning_rate": 2.8706934709395892e-06, | |
| "loss": 1.0644, | |
| "num_input_tokens_seen": 7722432, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.089538171536287, | |
| "grad_norm": 11.61797046661377, | |
| "learning_rate": 2.6443682535072177e-06, | |
| "loss": 0.9969, | |
| "num_input_tokens_seen": 7775296, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 5.127238454288407, | |
| "grad_norm": 10.594493865966797, | |
| "learning_rate": 2.4268365428344736e-06, | |
| "loss": 1.0552, | |
| "num_input_tokens_seen": 7834752, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.1649387370405275, | |
| "grad_norm": 13.08285140991211, | |
| "learning_rate": 2.21818390423168e-06, | |
| "loss": 0.9982, | |
| "num_input_tokens_seen": 7885680, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 5.202639019792649, | |
| "grad_norm": 11.088661193847656, | |
| "learning_rate": 2.0184924104583613e-06, | |
| "loss": 1.041, | |
| "num_input_tokens_seen": 7936032, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.240339302544769, | |
| "grad_norm": 11.851099967956543, | |
| "learning_rate": 1.8278406094401623e-06, | |
| "loss": 1.0186, | |
| "num_input_tokens_seen": 7988256, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 5.27803958529689, | |
| "grad_norm": 11.964996337890625, | |
| "learning_rate": 1.6463034933723337e-06, | |
| "loss": 1.0888, | |
| "num_input_tokens_seen": 8043264, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.31573986804901, | |
| "grad_norm": 10.263463973999023, | |
| "learning_rate": 1.4739524692218314e-06, | |
| "loss": 1.0506, | |
| "num_input_tokens_seen": 8096480, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 5.353440150801131, | |
| "grad_norm": 10.614130020141602, | |
| "learning_rate": 1.3108553306396265e-06, | |
| "loss": 1.1435, | |
| "num_input_tokens_seen": 8156224, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.391140433553252, | |
| "grad_norm": 12.183756828308105, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 1.0799, | |
| "num_input_tokens_seen": 8216272, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 5.4288407163053725, | |
| "grad_norm": 11.565719604492188, | |
| "learning_rate": 1.0126756596375686e-06, | |
| "loss": 1.0618, | |
| "num_input_tokens_seen": 8270896, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.466540999057493, | |
| "grad_norm": 10.969958305358887, | |
| "learning_rate": 8.777104151110826e-07, | |
| "loss": 1.0932, | |
| "num_input_tokens_seen": 8337264, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 5.504241281809613, | |
| "grad_norm": 12.142751693725586, | |
| "learning_rate": 7.522335858048707e-07, | |
| "loss": 1.064, | |
| "num_input_tokens_seen": 8401616, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.541941564561734, | |
| "grad_norm": 12.45744800567627, | |
| "learning_rate": 6.362945275751736e-07, | |
| "loss": 1.0762, | |
| "num_input_tokens_seen": 8456976, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 5.579641847313855, | |
| "grad_norm": 12.17725944519043, | |
| "learning_rate": 5.299388446305343e-07, | |
| "loss": 1.061, | |
| "num_input_tokens_seen": 8513616, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.617342130065976, | |
| "grad_norm": 10.246589660644531, | |
| "learning_rate": 4.3320837159353813e-07, | |
| "loss": 1.0795, | |
| "num_input_tokens_seen": 8575136, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 5.655042412818096, | |
| "grad_norm": 10.445602416992188, | |
| "learning_rate": 3.4614115704533767e-07, | |
| "loss": 1.0228, | |
| "num_input_tokens_seen": 8637744, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.6927426955702165, | |
| "grad_norm": 11.284125328063965, | |
| "learning_rate": 2.687714485593462e-07, | |
| "loss": 1.0506, | |
| "num_input_tokens_seen": 8693904, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 5.730442978322337, | |
| "grad_norm": 12.569458961486816, | |
| "learning_rate": 2.011296792301165e-07, | |
| "loss": 1.1141, | |
| "num_input_tokens_seen": 8756224, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.768143261074458, | |
| "grad_norm": 10.610177040100098, | |
| "learning_rate": 1.4324245570256633e-07, | |
| "loss": 1.1412, | |
| "num_input_tokens_seen": 8813120, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 5.805843543826579, | |
| "grad_norm": 11.221631050109863, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 1.0902, | |
| "num_input_tokens_seen": 8866160, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.843543826578699, | |
| "grad_norm": 11.644889831542969, | |
| "learning_rate": 5.681887909952388e-08, | |
| "loss": 1.1053, | |
| "num_input_tokens_seen": 8925888, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.88124410933082, | |
| "grad_norm": 12.60010814666748, | |
| "learning_rate": 2.831652042480093e-08, | |
| "loss": 1.0414, | |
| "num_input_tokens_seen": 8983424, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.918944392082941, | |
| "grad_norm": 11.038966178894043, | |
| "learning_rate": 9.636682981720158e-09, | |
| "loss": 1.1207, | |
| "num_input_tokens_seen": 9042928, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 5.956644674835061, | |
| "grad_norm": 11.58209228515625, | |
| "learning_rate": 7.867144166728846e-10, | |
| "loss": 1.0952, | |
| "num_input_tokens_seen": 9103184, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.971724787935909, | |
| "num_input_tokens_seen": 9124912, | |
| "step": 792, | |
| "total_flos": 3.904530641814815e+17, | |
| "train_loss": 1.665087498799719, | |
| "train_runtime": 5809.5562, | |
| "train_samples_per_second": 4.383, | |
| "train_steps_per_second": 0.136 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 792, | |
| "num_input_tokens_seen": 9124912, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.904530641814815e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |