Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf1640b0f80c313ee98046d635d70225ffcfbf03278e21d9ff3f87242a975e9
+oid sha256:05a0401007a4ec336695862d543182f1b339baea26ea18c91d27aff758a6b2ab
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e91582c1d1753264aad22e03f40dec798fec7d900974fccd64ba60e18caa06e
+oid sha256:483363659515a2992ba5973943f11db9c30d42c6773da1ae0d03c574a492f5f3
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7a2c9fd81f6d0b8ab5a6c59a288098e2dd952e6ca22ecd79a59c6760845153
+oid sha256:b534e48571feeb19ced8980bffb9ec4f84f94e6421acfe74bba6546e1eeaaf88
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad35105ce7ee6a405dd86913c0c3df2fc88940b765b92323c0dfa2775380765b
+oid sha256:32aadee8aaaa6463e16e1220858e02343b2776975e1dfa11907e9a9cbbe52291
 size 1089994880

trainer_log.jsonl

@@ -185,3 +185,93 @@
 {"current_steps": 185, "total_steps": 276, "loss": 0.6634, "lr": 4.752280031560744e-05, "epoch": 2.002706359945873, "percentage": 67.03, "elapsed_time": "5:02:14", "remaining_time": "2:28:40"}
 {"current_steps": 186, "total_steps": 276, "loss": 0.3805, "lr": 4.659928061719497e-05, "epoch": 2.013531799729364, "percentage": 67.39, "elapsed_time": "5:03:50", "remaining_time": "2:27:01"}
 {"current_steps": 187, "total_steps": 276, "loss": 0.3785, "lr": 4.5681120691785035e-05, "epoch": 2.024357239512855, "percentage": 67.75, "elapsed_time": "5:05:27", "remaining_time": "2:25:22"}
+{"current_steps": 188, "total_steps": 276, "loss": 0.3796, "lr": 4.476846787538925e-05, "epoch": 2.0351826792963466, "percentage": 68.12, "elapsed_time": "5:07:03", "remaining_time": "2:23:43"}
+{"current_steps": 189, "total_steps": 276, "loss": 0.3727, "lr": 4.386146862030023e-05, "epoch": 2.0460081190798376, "percentage": 68.48, "elapsed_time": "5:08:40", "remaining_time": "2:22:05"}
+{"current_steps": 190, "total_steps": 276, "loss": 0.3774, "lr": 4.2960268471590345e-05, "epoch": 2.0568335588633286, "percentage": 68.84, "elapsed_time": "5:10:17", "remaining_time": "2:20:26"}
+{"current_steps": 191, "total_steps": 276, "loss": 0.383, "lr": 4.20650120437564e-05, "epoch": 2.06765899864682, "percentage": 69.2, "elapsed_time": "5:11:53", "remaining_time": "2:18:48"}
+{"current_steps": 192, "total_steps": 276, "loss": 0.3862, "lr": 4.1175842997513535e-05, "epoch": 2.078484438430311, "percentage": 69.57, "elapsed_time": "5:13:30", "remaining_time": "2:17:09"}
+{"current_steps": 193, "total_steps": 276, "loss": 0.3784, "lr": 4.02929040167421e-05, "epoch": 2.089309878213802, "percentage": 69.93, "elapsed_time": "5:15:07", "remaining_time": "2:15:31"}
+{"current_steps": 194, "total_steps": 276, "loss": 0.3705, "lr": 3.9416336785591436e-05, "epoch": 2.1001353179972937, "percentage": 70.29, "elapsed_time": "5:16:44", "remaining_time": "2:13:52"}
+{"current_steps": 195, "total_steps": 276, "loss": 0.3805, "lr": 3.854628196574387e-05, "epoch": 2.1109607577807847, "percentage": 70.65, "elapsed_time": "5:18:21", "remaining_time": "2:12:14"}
+{"current_steps": 196, "total_steps": 276, "loss": 0.378, "lr": 3.768287917384303e-05, "epoch": 2.121786197564276, "percentage": 71.01, "elapsed_time": "5:19:57", "remaining_time": "2:10:35"}
+{"current_steps": 197, "total_steps": 276, "loss": 0.3729, "lr": 3.682626695908964e-05, "epoch": 2.1326116373477673, "percentage": 71.38, "elapsed_time": "5:21:34", "remaining_time": "2:08:57"}
+{"current_steps": 198, "total_steps": 276, "loss": 0.3726, "lr": 3.5976582781008695e-05, "epoch": 2.1434370771312583, "percentage": 71.74, "elapsed_time": "5:23:11", "remaining_time": "2:07:19"}
+{"current_steps": 199, "total_steps": 276, "loss": 0.3791, "lr": 3.5133962987391655e-05, "epoch": 2.15426251691475, "percentage": 72.1, "elapsed_time": "5:24:47", "remaining_time": "2:05:40"}
+{"current_steps": 200, "total_steps": 276, "loss": 0.3815, "lr": 3.42985427924166e-05, "epoch": 2.165087956698241, "percentage": 72.46, "elapsed_time": "5:26:24", "remaining_time": "2:04:02"}
+{"current_steps": 201, "total_steps": 276, "loss": 0.3753, "lr": 3.347045625495088e-05, "epoch": 2.175913396481732, "percentage": 72.83, "elapsed_time": "5:28:01", "remaining_time": "2:02:23"}
+{"current_steps": 202, "total_steps": 276, "loss": 0.3731, "lr": 3.264983625703861e-05, "epoch": 2.1867388362652234, "percentage": 73.19, "elapsed_time": "5:29:38", "remaining_time": "2:00:45"}
+{"current_steps": 203, "total_steps": 276, "loss": 0.3803, "lr": 3.1836814482577355e-05, "epoch": 2.1975642760487144, "percentage": 73.55, "elapsed_time": "5:31:15", "remaining_time": "1:59:07"}
+{"current_steps": 204, "total_steps": 276, "loss": 0.3779, "lr": 3.103152139618697e-05, "epoch": 2.208389715832206, "percentage": 73.91, "elapsed_time": "5:32:51", "remaining_time": "1:57:28"}
+{"current_steps": 205, "total_steps": 276, "loss": 0.3764, "lr": 3.02340862222741e-05, "epoch": 2.219215155615697, "percentage": 74.28, "elapsed_time": "5:34:28", "remaining_time": "1:55:50"}
+{"current_steps": 206, "total_steps": 276, "loss": 0.3772, "lr": 2.944463692429569e-05, "epoch": 2.230040595399188, "percentage": 74.64, "elapsed_time": "5:36:05", "remaining_time": "1:54:12"}
+{"current_steps": 207, "total_steps": 276, "loss": 0.3808, "lr": 2.866330018422481e-05, "epoch": 2.2408660351826795, "percentage": 75.0, "elapsed_time": "5:37:42", "remaining_time": "1:52:34"}
+{"current_steps": 208, "total_steps": 276, "loss": 0.3714, "lr": 2.789020138222224e-05, "epoch": 2.2516914749661705, "percentage": 75.36, "elapsed_time": "5:39:19", "remaining_time": "1:50:55"}
+{"current_steps": 209, "total_steps": 276, "loss": 0.3762, "lr": 2.7125464576516754e-05, "epoch": 2.2625169147496615, "percentage": 75.72, "elapsed_time": "5:40:56", "remaining_time": "1:49:17"}
+{"current_steps": 210, "total_steps": 276, "loss": 0.372, "lr": 2.6369212483497714e-05, "epoch": 2.273342354533153, "percentage": 76.09, "elapsed_time": "5:42:33", "remaining_time": "1:47:39"}
+{"current_steps": 211, "total_steps": 276, "loss": 0.3735, "lr": 2.5621566458022972e-05, "epoch": 2.284167794316644, "percentage": 76.45, "elapsed_time": "5:44:10", "remaining_time": "1:46:01"}
+{"current_steps": 212, "total_steps": 276, "loss": 0.3741, "lr": 2.4882646473945072e-05, "epoch": 2.2949932341001356, "percentage": 76.81, "elapsed_time": "5:45:46", "remaining_time": "1:44:23"}
+{"current_steps": 213, "total_steps": 276, "loss": 0.3819, "lr": 2.4152571104859284e-05, "epoch": 2.3058186738836266, "percentage": 77.17, "elapsed_time": "5:47:23", "remaining_time": "1:42:44"}
+{"current_steps": 214, "total_steps": 276, "loss": 0.3761, "lr": 2.3431457505076205e-05, "epoch": 2.3166441136671176, "percentage": 77.54, "elapsed_time": "5:49:00", "remaining_time": "1:41:06"}
+{"current_steps": 215, "total_steps": 276, "loss": 0.3768, "lr": 2.2719421390822173e-05, "epoch": 2.3274695534506087, "percentage": 77.9, "elapsed_time": "5:50:37", "remaining_time": "1:39:28"}
+{"current_steps": 216, "total_steps": 276, "loss": 0.3824, "lr": 2.201657702167042e-05, "epoch": 2.3382949932341, "percentage": 78.26, "elapsed_time": "5:52:14", "remaining_time": "1:37:50"}
+{"current_steps": 217, "total_steps": 276, "loss": 0.376, "lr": 2.1323037182205945e-05, "epoch": 2.349120433017591, "percentage": 78.62, "elapsed_time": "5:53:50", "remaining_time": "1:36:12"}
+{"current_steps": 218, "total_steps": 276, "loss": 0.3834, "lr": 2.0638913163927156e-05, "epoch": 2.3599458728010827, "percentage": 78.99, "elapsed_time": "5:55:28", "remaining_time": "1:34:34"}
+{"current_steps": 219, "total_steps": 276, "loss": 0.3803, "lr": 1.9964314747387005e-05, "epoch": 2.3707713125845737, "percentage": 79.35, "elapsed_time": "5:57:04", "remaining_time": "1:32:56"}
+{"current_steps": 220, "total_steps": 276, "loss": 0.3691, "lr": 1.9299350184576733e-05, "epoch": 2.381596752368065, "percentage": 79.71, "elapsed_time": "5:58:41", "remaining_time": "1:31:18"}
+{"current_steps": 221, "total_steps": 276, "loss": 0.3757, "lr": 1.8644126181554663e-05, "epoch": 2.3924221921515563, "percentage": 80.07, "elapsed_time": "6:00:18", "remaining_time": "1:29:40"}
+{"current_steps": 222, "total_steps": 276, "loss": 0.3806, "lr": 1.79987478813233e-05, "epoch": 2.4032476319350473, "percentage": 80.43, "elapsed_time": "6:01:55", "remaining_time": "1:28:02"}
+{"current_steps": 223, "total_steps": 276, "loss": 0.3803, "lr": 1.7363318846957175e-05, "epoch": 2.414073071718539, "percentage": 80.8, "elapsed_time": "6:03:31", "remaining_time": "1:26:24"}
+{"current_steps": 224, "total_steps": 276, "loss": 0.3784, "lr": 1.6737941044984127e-05, "epoch": 2.42489851150203, "percentage": 81.16, "elapsed_time": "6:05:08", "remaining_time": "1:24:45"}
+{"current_steps": 225, "total_steps": 276, "loss": 0.3755, "lr": 1.612271482902292e-05, "epoch": 2.435723951285521, "percentage": 81.52, "elapsed_time": "6:06:44", "remaining_time": "1:23:07"}
+{"current_steps": 226, "total_steps": 276, "loss": 0.379, "lr": 1.5517738923679616e-05, "epoch": 2.4465493910690124, "percentage": 81.88, "elapsed_time": "6:08:21", "remaining_time": "1:21:29"}
+{"current_steps": 227, "total_steps": 276, "loss": 0.3721, "lr": 1.492311040870531e-05, "epoch": 2.4573748308525034, "percentage": 82.25, "elapsed_time": "6:09:58", "remaining_time": "1:19:51"}
+{"current_steps": 228, "total_steps": 276, "loss": 0.3744, "lr": 1.4338924703417916e-05, "epoch": 2.4682002706359945, "percentage": 82.61, "elapsed_time": "6:11:35", "remaining_time": "1:18:13"}
+{"current_steps": 229, "total_steps": 276, "loss": 0.3718, "lr": 1.3765275551390293e-05, "epoch": 2.479025710419486, "percentage": 82.97, "elapsed_time": "6:13:11", "remaining_time": "1:16:35"}
+{"current_steps": 230, "total_steps": 276, "loss": 0.3724, "lr": 1.320225500540742e-05, "epoch": 2.489851150202977, "percentage": 83.33, "elapsed_time": "6:14:48", "remaining_time": "1:14:57"}
+{"current_steps": 231, "total_steps": 276, "loss": 0.3819, "lr": 1.2649953412694634e-05, "epoch": 2.500676589986468, "percentage": 83.7, "elapsed_time": "6:16:25", "remaining_time": "1:13:19"}
+{"current_steps": 232, "total_steps": 276, "loss": 0.3778, "lr": 1.2108459400419919e-05, "epoch": 2.5115020297699595, "percentage": 84.06, "elapsed_time": "6:18:01", "remaining_time": "1:11:41"}
+{"current_steps": 233, "total_steps": 276, "loss": 0.3741, "lr": 1.1577859861471833e-05, "epoch": 2.5223274695534506, "percentage": 84.42, "elapsed_time": "6:19:38", "remaining_time": "1:10:03"}
+{"current_steps": 234, "total_steps": 276, "loss": 0.3773, "lr": 1.1058239940516028e-05, "epoch": 2.533152909336942, "percentage": 84.78, "elapsed_time": "6:21:15", "remaining_time": "1:08:25"}
+{"current_steps": 235, "total_steps": 276, "loss": 0.3693, "lr": 1.0549683020332125e-05, "epoch": 2.543978349120433, "percentage": 85.14, "elapsed_time": "6:22:52", "remaining_time": "1:06:47"}
+{"current_steps": 236, "total_steps": 276, "loss": 0.3696, "lr": 1.0052270708433434e-05, "epoch": 2.554803788903924, "percentage": 85.51, "elapsed_time": "6:24:29", "remaining_time": "1:05:10"}
+{"current_steps": 237, "total_steps": 276, "loss": 0.3759, "lr": 9.566082823971432e-06, "epoch": 2.565629228687415, "percentage": 85.87, "elapsed_time": "6:26:06", "remaining_time": "1:03:32"}
+{"current_steps": 238, "total_steps": 276, "loss": 0.375, "lr": 9.09119738492735e-06, "epoch": 2.5764546684709067, "percentage": 86.23, "elapsed_time": "6:27:43", "remaining_time": "1:01:54"}
+{"current_steps": 239, "total_steps": 276, "loss": 0.3725, "lr": 8.627690595592653e-06, "epoch": 2.5872801082543977, "percentage": 86.59, "elapsed_time": "6:29:21", "remaining_time": "1:00:16"}
+{"current_steps": 240, "total_steps": 276, "loss": 0.3784, "lr": 8.175636834340674e-06, "epoch": 2.598105548037889, "percentage": 86.96, "elapsed_time": "6:30:57", "remaining_time": "0:58:38"}
+{"current_steps": 241, "total_steps": 276, "loss": 0.3814, "lr": 7.735108641691202e-06, "epoch": 2.60893098782138, "percentage": 87.32, "elapsed_time": "6:32:35", "remaining_time": "0:57:00"}
+{"current_steps": 242, "total_steps": 276, "loss": 0.381, "lr": 7.3061767086700075e-06, "epoch": 2.6197564276048713, "percentage": 87.68, "elapsed_time": "6:34:11", "remaining_time": "0:55:22"}
+{"current_steps": 243, "total_steps": 276, "loss": 0.3724, "lr": 6.888909865465065e-06, "epoch": 2.6305818673883627, "percentage": 88.04, "elapsed_time": "6:35:48", "remaining_time": "0:53:45"}
+{"current_steps": 244, "total_steps": 276, "loss": 0.3715, "lr": 6.483375070381552e-06, "epoch": 2.641407307171854, "percentage": 88.41, "elapsed_time": "6:37:25", "remaining_time": "0:52:07"}
+{"current_steps": 245, "total_steps": 276, "loss": 0.3721, "lr": 6.0896373990970614e-06, "epoch": 2.6522327469553453, "percentage": 88.77, "elapsed_time": "6:39:02", "remaining_time": "0:50:29"}
+{"current_steps": 246, "total_steps": 276, "loss": 0.3737, "lr": 5.707760034219032e-06, "epoch": 2.6630581867388363, "percentage": 89.13, "elapsed_time": "6:40:39", "remaining_time": "0:48:51"}
+{"current_steps": 247, "total_steps": 276, "loss": 0.3779, "lr": 5.337804255145873e-06, "epoch": 2.6738836265223274, "percentage": 89.49, "elapsed_time": "6:42:16", "remaining_time": "0:47:13"}
+{"current_steps": 248, "total_steps": 276, "loss": 0.3751, "lr": 4.979829428233576e-06, "epoch": 2.6847090663058184, "percentage": 89.86, "elapsed_time": "6:43:52", "remaining_time": "0:45:35"}
+{"current_steps": 249, "total_steps": 276, "loss": 0.3696, "lr": 4.63389299726921e-06, "epoch": 2.69553450608931, "percentage": 90.22, "elapsed_time": "6:45:29", "remaining_time": "0:43:58"}
+{"current_steps": 250, "total_steps": 276, "loss": 0.3809, "lr": 4.3000504742530505e-06, "epoch": 2.706359945872801, "percentage": 90.58, "elapsed_time": "6:47:06", "remaining_time": "0:42:20"}
+{"current_steps": 251, "total_steps": 276, "loss": 0.3765, "lr": 3.978355430490614e-06, "epoch": 2.7171853856562924, "percentage": 90.94, "elapsed_time": "6:48:43", "remaining_time": "0:40:42"}
+{"current_steps": 252, "total_steps": 276, "loss": 0.3799, "lr": 3.668859487996095e-06, "epoch": 2.7280108254397835, "percentage": 91.3, "elapsed_time": "6:50:19", "remaining_time": "0:39:04"}
+{"current_steps": 253, "total_steps": 276, "loss": 0.3787, "lr": 3.371612311208692e-06, "epoch": 2.7388362652232745, "percentage": 91.67, "elapsed_time": "6:51:56", "remaining_time": "0:37:26"}
+{"current_steps": 254, "total_steps": 276, "loss": 0.3726, "lr": 3.0866615990230085e-06, "epoch": 2.749661705006766, "percentage": 92.03, "elapsed_time": "6:53:33", "remaining_time": "0:35:49"}
+{"current_steps": 255, "total_steps": 276, "loss": 0.3689, "lr": 2.814053077134835e-06, "epoch": 2.760487144790257, "percentage": 92.39, "elapsed_time": "6:55:10", "remaining_time": "0:34:11"}
+{"current_steps": 256, "total_steps": 276, "loss": 0.3677, "lr": 2.553830490703666e-06, "epoch": 2.7713125845737485, "percentage": 92.75, "elapsed_time": "6:56:47", "remaining_time": "0:32:33"}
+{"current_steps": 257, "total_steps": 276, "loss": 0.3796, "lr": 2.306035597332885e-06, "epoch": 2.7821380243572396, "percentage": 93.12, "elapsed_time": "6:58:23", "remaining_time": "0:30:55"}
+{"current_steps": 258, "total_steps": 276, "loss": 0.3733, "lr": 2.0707081603690458e-06, "epoch": 2.7929634641407306, "percentage": 93.48, "elapsed_time": "7:00:00", "remaining_time": "0:29:18"}
+{"current_steps": 259, "total_steps": 276, "loss": 0.3724, "lr": 1.8478859425210548e-06, "epoch": 2.803788903924222, "percentage": 93.84, "elapsed_time": "7:01:37", "remaining_time": "0:27:40"}
+{"current_steps": 260, "total_steps": 276, "loss": 0.3784, "lr": 1.6376046998004413e-06, "epoch": 2.814614343707713, "percentage": 94.2, "elapsed_time": "7:03:14", "remaining_time": "0:26:02"}
+{"current_steps": 261, "total_steps": 276, "loss": 0.3675, "lr": 1.4398981757836628e-06, "epoch": 2.825439783491204, "percentage": 94.57, "elapsed_time": "7:04:50", "remaining_time": "0:24:24"}
+{"current_steps": 262, "total_steps": 276, "loss": 0.3722, "lr": 1.2547980961972629e-06, "epoch": 2.8362652232746957, "percentage": 94.93, "elapsed_time": "7:06:27", "remaining_time": "0:22:47"}
+{"current_steps": 263, "total_steps": 276, "loss": 0.377, "lr": 1.0823341638269303e-06, "epoch": 2.8470906630581867, "percentage": 95.29, "elapsed_time": "7:08:04", "remaining_time": "0:21:09"}
+{"current_steps": 264, "total_steps": 276, "loss": 0.3724, "lr": 9.225340537510897e-07, "epoch": 2.8579161028416777, "percentage": 95.65, "elapsed_time": "7:09:41", "remaining_time": "0:19:31"}
+{"current_steps": 265, "total_steps": 276, "loss": 0.3779, "lr": 7.754234088999379e-07, "epoch": 2.8687415426251692, "percentage": 96.01, "elapsed_time": "7:11:18", "remaining_time": "0:17:54"}
+{"current_steps": 266, "total_steps": 276, "loss": 0.3749, "lr": 6.410258359405585e-07, "epoch": 2.8795669824086603, "percentage": 96.38, "elapsed_time": "7:12:54", "remaining_time": "0:16:16"}
+{"current_steps": 267, "total_steps": 276, "loss": 0.3713, "lr": 5.19362901488778e-07, "epoch": 2.8903924221921518, "percentage": 96.74, "elapsed_time": "7:14:31", "remaining_time": "0:14:38"}
+{"current_steps": 268, "total_steps": 276, "loss": 0.3722, "lr": 4.1045412864838765e-07, "epoch": 2.901217861975643, "percentage": 97.1, "elapsed_time": "7:16:08", "remaining_time": "0:13:01"}
+{"current_steps": 269, "total_steps": 276, "loss": 0.3744, "lr": 3.143169938783253e-07, "epoch": 2.912043301759134, "percentage": 97.46, "elapsed_time": "7:17:45", "remaining_time": "0:11:23"}
+{"current_steps": 270, "total_steps": 276, "loss": 0.377, "lr": 2.3096692418820733e-07, "epoch": 2.9228687415426253, "percentage": 97.83, "elapsed_time": "7:19:22", "remaining_time": "0:09:45"}
+{"current_steps": 271, "total_steps": 276, "loss": 0.3725, "lr": 1.6041729466280686e-07, "epoch": 2.9336941813261164, "percentage": 98.19, "elapsed_time": "7:20:59", "remaining_time": "0:08:08"}
+{"current_steps": 272, "total_steps": 276, "loss": 0.3786, "lr": 1.0267942631577932e-07, "epoch": 2.944519621109608, "percentage": 98.55, "elapsed_time": "7:22:35", "remaining_time": "0:06:30"}
+{"current_steps": 273, "total_steps": 276, "loss": 0.3765, "lr": 5.7762584272937903e-08, "epoch": 2.955345060893099, "percentage": 98.91, "elapsed_time": "7:24:13", "remaining_time": "0:04:52"}
+{"current_steps": 274, "total_steps": 276, "loss": 0.3746, "lr": 2.5673976285558455e-08, "epoch": 2.96617050067659, "percentage": 99.28, "elapsed_time": "7:25:50", "remaining_time": "0:03:15"}
+{"current_steps": 275, "total_steps": 276, "loss": 0.3818, "lr": 6.418751573713522e-09, "epoch": 2.976995940460081, "percentage": 99.64, "elapsed_time": "7:27:27", "remaining_time": "0:01:37"}
+{"current_steps": 276, "total_steps": 276, "loss": 0.37, "lr": 0.0, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "7:29:04", "remaining_time": "0:00:00"}
+{"current_steps": 276, "total_steps": 276, "epoch": 2.9878213802435725, "percentage": 100.0, "elapsed_time": "7:30:30", "remaining_time": "0:00:00"}