Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4bb90f7c3c35b0a30556a1532a617726d7a65eca66b2e014c65e0198205099
+oid sha256:a070fd06e7f656cc4a901b2628ffb72e33f67fdd59838bc5158cd27a0ec65f4a
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccef6dd3ca464f248361b5ec334ad7aeabdc315ba1db9cab86c7fe84f4bff91
+oid sha256:52a39fbbd55460e4f0afdd173a755e3d6b503674400c281994eb92bf2de76bc4
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f863895a52affd34dd681fcffd42e8e15e601fcf3b3bebde0e4adff905bdab
+oid sha256:ea09b521e0a291535b94877c18faa3549e8e46ec71a88a9831903ceac6064891
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e719b167ff43e9abd6ac3524929ca0116687c819063666f828a4fa1f09f850
+oid sha256:71db70ac78ee8e946078797e4d5d2c61002adf573a7b55bb62a17f4ebef915bd
 size 1089994880

trainer_log.jsonl

@@ -184,3 +184,94 @@
 {"current_steps": 184, "total_steps": 276, "loss": 0.4351, "lr": 2.4225765795467267e-05, "epoch": 1.9918809201623815, "percentage": 66.67, "elapsed_time": "11:07:29", "remaining_time": "5:33:44"}
 {"current_steps": 185, "total_steps": 276, "loss": 0.6835, "lr": 2.376140015780372e-05, "epoch": 2.002706359945873, "percentage": 67.03, "elapsed_time": "11:12:40", "remaining_time": "5:30:52"}
 {"current_steps": 186, "total_steps": 276, "loss": 0.405, "lr": 2.3299640308597487e-05, "epoch": 2.013531799729364, "percentage": 67.39, "elapsed_time": "11:16:17", "remaining_time": "5:27:14"}
+{"current_steps": 187, "total_steps": 276, "loss": 0.4038, "lr": 2.2840560345892518e-05, "epoch": 2.024357239512855, "percentage": 67.75, "elapsed_time": "11:19:53", "remaining_time": "5:23:35"}
+{"current_steps": 188, "total_steps": 276, "loss": 0.4047, "lr": 2.2384233937694626e-05, "epoch": 2.0351826792963466, "percentage": 68.12, "elapsed_time": "11:23:31", "remaining_time": "5:19:56"}
+{"current_steps": 189, "total_steps": 276, "loss": 0.3982, "lr": 2.1930734310150116e-05, "epoch": 2.0460081190798376, "percentage": 68.48, "elapsed_time": "11:27:07", "remaining_time": "5:16:17"}
+{"current_steps": 190, "total_steps": 276, "loss": 0.4031, "lr": 2.1480134235795173e-05, "epoch": 2.0568335588633286, "percentage": 68.84, "elapsed_time": "11:30:44", "remaining_time": "5:12:39"}
+{"current_steps": 191, "total_steps": 276, "loss": 0.4084, "lr": 2.10325060218782e-05, "epoch": 2.06765899864682, "percentage": 69.2, "elapsed_time": "11:34:21", "remaining_time": "5:09:00"}
+{"current_steps": 192, "total_steps": 276, "loss": 0.4116, "lr": 2.0587921498756768e-05, "epoch": 2.078484438430311, "percentage": 69.57, "elapsed_time": "11:37:58", "remaining_time": "5:05:21"}
+{"current_steps": 193, "total_steps": 276, "loss": 0.4042, "lr": 2.014645200837105e-05, "epoch": 2.089309878213802, "percentage": 69.93, "elapsed_time": "11:41:35", "remaining_time": "5:01:43"}
+{"current_steps": 194, "total_steps": 276, "loss": 0.3962, "lr": 1.9708168392795718e-05, "epoch": 2.1001353179972937, "percentage": 70.29, "elapsed_time": "11:45:12", "remaining_time": "4:58:04"}
+{"current_steps": 195, "total_steps": 276, "loss": 0.4059, "lr": 1.9273140982871936e-05, "epoch": 2.1109607577807847, "percentage": 70.65, "elapsed_time": "11:48:49", "remaining_time": "4:54:26"}
+{"current_steps": 196, "total_steps": 276, "loss": 0.4042, "lr": 1.8841439586921515e-05, "epoch": 2.121786197564276, "percentage": 71.01, "elapsed_time": "11:52:25", "remaining_time": "4:50:47"}
+{"current_steps": 197, "total_steps": 276, "loss": 0.3995, "lr": 1.841313347954482e-05, "epoch": 2.1326116373477673, "percentage": 71.38, "elapsed_time": "11:56:01", "remaining_time": "4:47:08"}
+{"current_steps": 198, "total_steps": 276, "loss": 0.3986, "lr": 1.7988291390504348e-05, "epoch": 2.1434370771312583, "percentage": 71.74, "elapsed_time": "11:59:37", "remaining_time": "4:43:29"}
+{"current_steps": 199, "total_steps": 276, "loss": 0.4054, "lr": 1.7566981493695828e-05, "epoch": 2.15426251691475, "percentage": 72.1, "elapsed_time": "12:03:14", "remaining_time": "4:39:50"}
+{"current_steps": 200, "total_steps": 276, "loss": 0.4077, "lr": 1.71492713962083e-05, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "12:06:50", "remaining_time": "4:36:11"}
+{"current_steps": 201, "total_steps": 276, "loss": 0.4037, "lr": 1.673522812747544e-05, "epoch": 2.175913396481732, "percentage": 72.83, "elapsed_time": "12:10:26", "remaining_time": "4:32:33"}
+{"current_steps": 202, "total_steps": 276, "loss": 0.4004, "lr": 1.6324918128519306e-05, "epoch": 2.1867388362652234, "percentage": 73.19, "elapsed_time": "12:14:03", "remaining_time": "4:28:54"}
+{"current_steps": 203, "total_steps": 276, "loss": 0.4072, "lr": 1.5918407241288678e-05, "epoch": 2.1975642760487144, "percentage": 73.55, "elapsed_time": "12:17:40", "remaining_time": "4:25:16"}
+{"current_steps": 204, "total_steps": 276, "loss": 0.4054, "lr": 1.5515760698093485e-05, "epoch": 2.208389715832206, "percentage": 73.91, "elapsed_time": "12:21:17", "remaining_time": "4:21:38"}
+{"current_steps": 205, "total_steps": 276, "loss": 0.4028, "lr": 1.511704311113705e-05, "epoch": 2.219215155615697, "percentage": 74.28, "elapsed_time": "12:24:54", "remaining_time": "4:17:59"}
+{"current_steps": 206, "total_steps": 276, "loss": 0.4039, "lr": 1.4722318462147844e-05, "epoch": 2.230040595399188, "percentage": 74.64, "elapsed_time": "12:28:30", "remaining_time": "4:14:20"}
+{"current_steps": 207, "total_steps": 276, "loss": 0.4078, "lr": 1.4331650092112406e-05, "epoch": 2.2408660351826795, "percentage": 75.0, "elapsed_time": "12:32:06", "remaining_time": "4:10:42"}
+{"current_steps": 208, "total_steps": 276, "loss": 0.3986, "lr": 1.394510069111112e-05, "epoch": 2.2516914749661705, "percentage": 75.36, "elapsed_time": "12:35:43", "remaining_time": "4:07:03"}
+{"current_steps": 209, "total_steps": 276, "loss": 0.4038, "lr": 1.3562732288258377e-05, "epoch": 2.2625169147496615, "percentage": 75.72, "elapsed_time": "12:39:20", "remaining_time": "4:03:25"}
+{"current_steps": 210, "total_steps": 276, "loss": 0.3993, "lr": 1.3184606241748857e-05, "epoch": 2.273342354533153, "percentage": 76.09, "elapsed_time": "12:42:57", "remaining_time": "3:59:47"}
+{"current_steps": 211, "total_steps": 276, "loss": 0.4004, "lr": 1.2810783229011486e-05, "epoch": 2.284167794316644, "percentage": 76.45, "elapsed_time": "12:46:35", "remaining_time": "3:56:09"}
+{"current_steps": 212, "total_steps": 276, "loss": 0.4006, "lr": 1.2441323236972536e-05, "epoch": 2.2949932341001356, "percentage": 76.81, "elapsed_time": "12:50:11", "remaining_time": "3:52:30"}
+{"current_steps": 213, "total_steps": 276, "loss": 0.4081, "lr": 1.2076285552429642e-05, "epoch": 2.3058186738836266, "percentage": 77.17, "elapsed_time": "12:53:47", "remaining_time": "3:48:52"}
+{"current_steps": 214, "total_steps": 276, "loss": 0.4028, "lr": 1.1715728752538103e-05, "epoch": 2.3166441136671176, "percentage": 77.54, "elapsed_time": "12:57:23", "remaining_time": "3:45:13"}
+{"current_steps": 215, "total_steps": 276, "loss": 0.4037, "lr": 1.1359710695411086e-05, "epoch": 2.3274695534506087, "percentage": 77.9, "elapsed_time": "13:00:59", "remaining_time": "3:41:35"}
+{"current_steps": 216, "total_steps": 276, "loss": 0.4095, "lr": 1.100828851083521e-05, "epoch": 2.3382949932341, "percentage": 78.26, "elapsed_time": "13:04:36", "remaining_time": "3:37:56"}
+{"current_steps": 217, "total_steps": 276, "loss": 0.4031, "lr": 1.0661518591102973e-05, "epoch": 2.349120433017591, "percentage": 78.62, "elapsed_time": "13:08:13", "remaining_time": "3:34:18"}
+{"current_steps": 218, "total_steps": 276, "loss": 0.4106, "lr": 1.0319456581963578e-05, "epoch": 2.3599458728010827, "percentage": 78.99, "elapsed_time": "13:11:49", "remaining_time": "3:30:40"}
+{"current_steps": 219, "total_steps": 276, "loss": 0.4075, "lr": 9.982157373693502e-06, "epoch": 2.3707713125845737, "percentage": 79.35, "elapsed_time": "13:15:26", "remaining_time": "3:27:02"}
+{"current_steps": 220, "total_steps": 276, "loss": 0.3955, "lr": 9.649675092288366e-06, "epoch": 2.381596752368065, "percentage": 79.71, "elapsed_time": "13:19:03", "remaining_time": "3:23:23"}
+{"current_steps": 221, "total_steps": 276, "loss": 0.4029, "lr": 9.322063090777331e-06, "epoch": 2.3924221921515563, "percentage": 80.07, "elapsed_time": "13:22:40", "remaining_time": "3:19:45"}
+{"current_steps": 222, "total_steps": 276, "loss": 0.4087, "lr": 8.99937394066165e-06, "epoch": 2.4032476319350473, "percentage": 80.43, "elapsed_time": "13:26:17", "remaining_time": "3:16:07"}
+{"current_steps": 223, "total_steps": 276, "loss": 0.4085, "lr": 8.681659423478587e-06, "epoch": 2.414073071718539, "percentage": 80.8, "elapsed_time": "13:29:54", "remaining_time": "3:12:29"}
+{"current_steps": 224, "total_steps": 276, "loss": 0.4048, "lr": 8.368970522492064e-06, "epoch": 2.42489851150203, "percentage": 81.16, "elapsed_time": "13:33:30", "remaining_time": "3:08:50"}
+{"current_steps": 225, "total_steps": 276, "loss": 0.4033, "lr": 8.06135741451146e-06, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "13:37:07", "remaining_time": "3:05:12"}
+{"current_steps": 226, "total_steps": 276, "loss": 0.4062, "lr": 7.758869461839808e-06, "epoch": 2.4465493910690124, "percentage": 81.88, "elapsed_time": "13:40:44", "remaining_time": "3:01:34"}
+{"current_steps": 227, "total_steps": 276, "loss": 0.4, "lr": 7.461555204352655e-06, "epoch": 2.4573748308525034, "percentage": 82.25, "elapsed_time": "13:44:20", "remaining_time": "2:57:56"}
+{"current_steps": 228, "total_steps": 276, "loss": 0.4017, "lr": 7.169462351708958e-06, "epoch": 2.4682002706359945, "percentage": 82.61, "elapsed_time": "13:47:56", "remaining_time": "2:54:18"}
+{"current_steps": 229, "total_steps": 276, "loss": 0.3982, "lr": 6.882637775695147e-06, "epoch": 2.479025710419486, "percentage": 82.97, "elapsed_time": "13:51:32", "remaining_time": "2:50:39"}
+{"current_steps": 230, "total_steps": 276, "loss": 0.3997, "lr": 6.60112750270371e-06, "epoch": 2.489851150202977, "percentage": 83.33, "elapsed_time": "13:55:08", "remaining_time": "2:47:01"}
+{"current_steps": 231, "total_steps": 276, "loss": 0.409, "lr": 6.324976706347317e-06, "epoch": 2.500676589986468, "percentage": 83.7, "elapsed_time": "13:58:45", "remaining_time": "2:43:23"}
+{"current_steps": 232, "total_steps": 276, "loss": 0.4063, "lr": 6.054229700209959e-06, "epoch": 2.5115020297699595, "percentage": 84.06, "elapsed_time": "14:02:22", "remaining_time": "2:39:45"}
+{"current_steps": 233, "total_steps": 276, "loss": 0.4013, "lr": 5.788929930735916e-06, "epoch": 2.5223274695534506, "percentage": 84.42, "elapsed_time": "14:05:59", "remaining_time": "2:36:07"}
+{"current_steps": 234, "total_steps": 276, "loss": 0.4042, "lr": 5.529119970258014e-06, "epoch": 2.533152909336942, "percentage": 84.78, "elapsed_time": "14:09:36", "remaining_time": "2:32:29"}
+{"current_steps": 235, "total_steps": 276, "loss": 0.3965, "lr": 5.274841510166062e-06, "epoch": 2.543978349120433, "percentage": 85.14, "elapsed_time": "14:13:13", "remaining_time": "2:28:51"}
+{"current_steps": 236, "total_steps": 276, "loss": 0.3964, "lr": 5.026135354216717e-06, "epoch": 2.554803788903924, "percentage": 85.51, "elapsed_time": "14:16:49", "remaining_time": "2:25:13"}
+{"current_steps": 237, "total_steps": 276, "loss": 0.4036, "lr": 4.783041411985716e-06, "epoch": 2.565629228687415, "percentage": 85.87, "elapsed_time": "14:20:26", "remaining_time": "2:21:35"}
+{"current_steps": 238, "total_steps": 276, "loss": 0.4022, "lr": 4.545598692463675e-06, "epoch": 2.5764546684709067, "percentage": 86.23, "elapsed_time": "14:24:03", "remaining_time": "2:17:57"}
+{"current_steps": 239, "total_steps": 276, "loss": 0.4, "lr": 4.3138452977963266e-06, "epoch": 2.5872801082543977, "percentage": 86.59, "elapsed_time": "14:27:40", "remaining_time": "2:14:19"}
+{"current_steps": 240, "total_steps": 276, "loss": 0.4072, "lr": 4.087818417170337e-06, "epoch": 2.598105548037889, "percentage": 86.96, "elapsed_time": "14:31:17", "remaining_time": "2:10:41"}
+{"current_steps": 241, "total_steps": 276, "loss": 0.4092, "lr": 3.867554320845601e-06, "epoch": 2.60893098782138, "percentage": 87.32, "elapsed_time": "14:34:53", "remaining_time": "2:07:03"}
+{"current_steps": 242, "total_steps": 276, "loss": 0.4086, "lr": 3.6530883543350038e-06, "epoch": 2.6197564276048713, "percentage": 87.68, "elapsed_time": "14:38:30", "remaining_time": "2:03:25"}
+{"current_steps": 243, "total_steps": 276, "loss": 0.3997, "lr": 3.4444549327325325e-06, "epoch": 2.6305818673883627, "percentage": 88.04, "elapsed_time": "14:42:07", "remaining_time": "1:59:47"}
+{"current_steps": 244, "total_steps": 276, "loss": 0.3979, "lr": 3.241687535190776e-06, "epoch": 2.641407307171854, "percentage": 88.41, "elapsed_time": "14:45:45", "remaining_time": "1:56:09"}
+{"current_steps": 245, "total_steps": 276, "loss": 0.3987, "lr": 3.0448186995485307e-06, "epoch": 2.6522327469553453, "percentage": 88.77, "elapsed_time": "14:49:21", "remaining_time": "1:52:31"}
+{"current_steps": 246, "total_steps": 276, "loss": 0.3997, "lr": 2.853880017109516e-06, "epoch": 2.6630581867388363, "percentage": 89.13, "elapsed_time": "14:52:58", "remaining_time": "1:48:53"}
+{"current_steps": 247, "total_steps": 276, "loss": 0.4053, "lr": 2.6689021275729366e-06, "epoch": 2.6738836265223274, "percentage": 89.49, "elapsed_time": "14:56:34", "remaining_time": "1:45:16"}
+{"current_steps": 248, "total_steps": 276, "loss": 0.4007, "lr": 2.489914714116788e-06, "epoch": 2.6847090663058184, "percentage": 89.86, "elapsed_time": "15:00:10", "remaining_time": "1:41:37"}
+{"current_steps": 249, "total_steps": 276, "loss": 0.3966, "lr": 2.316946498634605e-06, "epoch": 2.69553450608931, "percentage": 90.22, "elapsed_time": "15:03:46", "remaining_time": "1:38:00"}
+{"current_steps": 250, "total_steps": 276, "loss": 0.4079, "lr": 2.1500252371265253e-06, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "15:07:23", "remaining_time": "1:34:22"}
+{"current_steps": 251, "total_steps": 276, "loss": 0.404, "lr": 1.989177715245307e-06, "epoch": 2.7171853856562924, "percentage": 90.94, "elapsed_time": "15:11:00", "remaining_time": "1:30:44"}
+{"current_steps": 252, "total_steps": 276, "loss": 0.408, "lr": 1.8344297439980475e-06, "epoch": 2.7280108254397835, "percentage": 91.3, "elapsed_time": "15:14:37", "remaining_time": "1:27:06"}
+{"current_steps": 253, "total_steps": 276, "loss": 0.406, "lr": 1.685806155604346e-06, "epoch": 2.7388362652232745, "percentage": 91.67, "elapsed_time": "15:18:14", "remaining_time": "1:23:28"}
+{"current_steps": 254, "total_steps": 276, "loss": 0.4005, "lr": 1.5433307995115043e-06, "epoch": 2.749661705006766, "percentage": 92.03, "elapsed_time": "15:21:51", "remaining_time": "1:19:50"}
+{"current_steps": 255, "total_steps": 276, "loss": 0.3959, "lr": 1.4070265385674176e-06, "epoch": 2.760487144790257, "percentage": 92.39, "elapsed_time": "15:25:26", "remaining_time": "1:16:12"}
+{"current_steps": 256, "total_steps": 276, "loss": 0.3947, "lr": 1.276915245351833e-06, "epoch": 2.7713125845737485, "percentage": 92.75, "elapsed_time": "15:29:03", "remaining_time": "1:12:34"}
+{"current_steps": 257, "total_steps": 276, "loss": 0.4085, "lr": 1.1530177986664425e-06, "epoch": 2.7821380243572396, "percentage": 93.12, "elapsed_time": "15:32:40", "remaining_time": "1:08:57"}
+{"current_steps": 258, "total_steps": 276, "loss": 0.4015, "lr": 1.0353540801845229e-06, "epoch": 2.7929634641407306, "percentage": 93.48, "elapsed_time": "15:36:15", "remaining_time": "1:05:19"}
+{"current_steps": 259, "total_steps": 276, "loss": 0.3998, "lr": 9.239429712605274e-07, "epoch": 2.803788903924222, "percentage": 93.84, "elapsed_time": "15:39:51", "remaining_time": "1:01:41"}
+{"current_steps": 260, "total_steps": 276, "loss": 0.4055, "lr": 8.188023499002206e-07, "epoch": 2.814614343707713, "percentage": 94.2, "elapsed_time": "15:43:28", "remaining_time": "0:58:03"}
+{"current_steps": 261, "total_steps": 276, "loss": 0.3949, "lr": 7.199490878918314e-07, "epoch": 2.825439783491204, "percentage": 94.57, "elapsed_time": "15:47:05", "remaining_time": "0:54:25"}
+{"current_steps": 262, "total_steps": 276, "loss": 0.4005, "lr": 6.273990480986314e-07, "epoch": 2.8362652232746957, "percentage": 94.93, "elapsed_time": "15:50:42", "remaining_time": "0:50:48"}
+{"current_steps": 263, "total_steps": 276, "loss": 0.4048, "lr": 5.411670819134651e-07, "epoch": 2.8470906630581867, "percentage": 95.29, "elapsed_time": "15:54:18", "remaining_time": "0:47:10"}
+{"current_steps": 264, "total_steps": 276, "loss": 0.4003, "lr": 4.6126702687554483e-07, "epoch": 2.8579161028416777, "percentage": 95.65, "elapsed_time": "15:57:54", "remaining_time": "0:43:32"}
+{"current_steps": 265, "total_steps": 276, "loss": 0.4044, "lr": 3.8771170444996895e-07, "epoch": 2.8687415426251692, "percentage": 96.01, "elapsed_time": "16:01:30", "remaining_time": "0:39:54"}
+{"current_steps": 266, "total_steps": 276, "loss": 0.4029, "lr": 3.2051291797027925e-07, "epoch": 2.8795669824086603, "percentage": 96.38, "elapsed_time": "16:05:06", "remaining_time": "0:36:16"}
+{"current_steps": 267, "total_steps": 276, "loss": 0.3986, "lr": 2.59681450744389e-07, "epoch": 2.8903924221921518, "percentage": 96.74, "elapsed_time": "16:08:43", "remaining_time": "0:32:39"}
+{"current_steps": 268, "total_steps": 276, "loss": 0.3998, "lr": 2.0522706432419382e-07, "epoch": 2.901217861975643, "percentage": 97.1, "elapsed_time": "16:12:20", "remaining_time": "0:29:01"}
+{"current_steps": 269, "total_steps": 276, "loss": 0.402, "lr": 1.5715849693916264e-07, "epoch": 2.912043301759134, "percentage": 97.46, "elapsed_time": "16:15:58", "remaining_time": "0:25:23"}
+{"current_steps": 270, "total_steps": 276, "loss": 0.4035, "lr": 1.1548346209410366e-07, "epoch": 2.9228687415426253, "percentage": 97.83, "elapsed_time": "16:19:33", "remaining_time": "0:21:46"}
+{"current_steps": 271, "total_steps": 276, "loss": 0.4003, "lr": 8.020864733140343e-08, "epoch": 2.9336941813261164, "percentage": 98.19, "elapsed_time": "16:23:09", "remaining_time": "0:18:08"}
+{"current_steps": 272, "total_steps": 276, "loss": 0.406, "lr": 5.133971315788966e-08, "epoch": 2.944519621109608, "percentage": 98.55, "elapsed_time": "16:26:46", "remaining_time": "0:14:30"}
+{"current_steps": 273, "total_steps": 276, "loss": 0.4034, "lr": 2.8881292136468952e-08, "epoch": 2.955345060893099, "percentage": 98.91, "elapsed_time": "16:30:23", "remaining_time": "0:10:53"}
+{"current_steps": 274, "total_steps": 276, "loss": 0.402, "lr": 1.2836988142779228e-08, "epoch": 2.96617050067659, "percentage": 99.28, "elapsed_time": "16:34:01", "remaining_time": "0:07:15"}
+{"current_steps": 275, "total_steps": 276, "loss": 0.41, "lr": 3.209375786856761e-09, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "16:37:40", "remaining_time": "0:03:37"}
+{"current_steps": 276, "total_steps": 276, "loss": 0.3978, "lr": 0.0, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "16:41:17", "remaining_time": "0:00:00"}
+{"current_steps": 276, "total_steps": 276, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "16:42:49", "remaining_time": "0:00:00"}