Training in progress, epoch 3

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9aac40aed15b73df28f4948e16f647ffdba66300119b2213561f7838c602cc
+oid sha256:2750dd5cb24929767c6b5ca51d951cc4411e997dbf7ecf5eb70f65e5b50bbb58
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8548f98f0f35b1175e7b08f65f045636f16d6ab0bdd192f37bf295faa4534897
+oid sha256:af33657f8cb8268a60dc9404a24023676d4908287f04a71c8800ff0b46504781
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48dd3c72fd7a306416e85d2956ef5651dc9fc69a6bbdef7d7de06c9c5cd735ae
+oid sha256:24a866dc54df077245023bb44599f98dcebc59efc46285e6c6ff05aa3c2d8439
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5805f281d39cb1e0cfffcfad6eac3049a790cc5e10df7706925d712f9f13a12c
+oid sha256:1fe9507b777db8a4042fac0578fa4f6c41b60483078081b68b73a494a7bcc5e6
 size 1089994880

trainer_log.jsonl

@@ -229,3 +229,80 @@
 {"current_steps": 229, "total_steps": 380, "loss": 0.4952, "lr": 3.269251550189573e-05, "epoch": 2.9796913078797727, "percentage": 60.26, "elapsed_time": "6:25:39", "remaining_time": "4:14:17"}
 {"current_steps": 230, "total_steps": 380, "loss": 0.5036, "lr": 3.2331574723050474e-05, "epoch": 2.992688870836718, "percentage": 60.53, "elapsed_time": "6:27:19", "remaining_time": "4:12:36"}
 {"current_steps": 231, "total_steps": 380, "loss": 0.4787, "lr": 3.197128101331764e-05, "epoch": 3.007311129163282, "percentage": 60.79, "elapsed_time": "6:30:48", "remaining_time": "4:12:04"}
+{"current_steps": 232, "total_steps": 380, "loss": 0.4527, "lr": 3.161166477462759e-05, "epoch": 3.0203086921202273, "percentage": 61.05, "elapsed_time": "6:32:27", "remaining_time": "4:10:21"}
+{"current_steps": 233, "total_steps": 380, "loss": 0.4566, "lr": 3.125275635174497e-05, "epoch": 3.033306255077173, "percentage": 61.32, "elapsed_time": "6:34:06", "remaining_time": "4:08:38"}
+{"current_steps": 234, "total_steps": 380, "loss": 0.4492, "lr": 3.089458602970828e-05, "epoch": 3.0463038180341186, "percentage": 61.58, "elapsed_time": "6:35:46", "remaining_time": "4:06:55"}
+{"current_steps": 235, "total_steps": 380, "loss": 0.452, "lr": 3.0537184031274306e-05, "epoch": 3.059301380991064, "percentage": 61.84, "elapsed_time": "6:37:25", "remaining_time": "4:05:13"}
+{"current_steps": 236, "total_steps": 380, "loss": 0.4591, "lr": 3.0180580514368037e-05, "epoch": 3.07229894394801, "percentage": 62.11, "elapsed_time": "6:39:04", "remaining_time": "4:03:30"}
+{"current_steps": 237, "total_steps": 380, "loss": 0.4485, "lr": 2.9824805569537747e-05, "epoch": 3.0852965069049554, "percentage": 62.37, "elapsed_time": "6:40:43", "remaining_time": "4:01:47"}
+{"current_steps": 238, "total_steps": 380, "loss": 0.4556, "lr": 2.9469889217416045e-05, "epoch": 3.098294069861901, "percentage": 62.63, "elapsed_time": "6:42:22", "remaining_time": "4:00:04"}
+{"current_steps": 239, "total_steps": 380, "loss": 0.4537, "lr": 2.9115861406186593e-05, "epoch": 3.1112916328188467, "percentage": 62.89, "elapsed_time": "6:44:01", "remaining_time": "3:58:21"}
+{"current_steps": 240, "total_steps": 380, "loss": 0.4535, "lr": 2.8762752009057232e-05, "epoch": 3.124289195775792, "percentage": 63.16, "elapsed_time": "6:45:40", "remaining_time": "3:56:38"}
+{"current_steps": 241, "total_steps": 380, "loss": 0.4502, "lr": 2.841059082173902e-05, "epoch": 3.1372867587327375, "percentage": 63.42, "elapsed_time": "6:47:20", "remaining_time": "3:54:56"}
+{"current_steps": 242, "total_steps": 380, "loss": 0.4537, "lr": 2.805940755993223e-05, "epoch": 3.150284321689683, "percentage": 63.68, "elapsed_time": "6:48:59", "remaining_time": "3:53:13"}
+{"current_steps": 243, "total_steps": 380, "loss": 0.4534, "lr": 2.770923185681878e-05, "epoch": 3.163281884646629, "percentage": 63.95, "elapsed_time": "6:50:38", "remaining_time": "3:51:30"}
+{"current_steps": 244, "total_steps": 380, "loss": 0.4537, "lr": 2.7360093260561904e-05, "epoch": 3.1762794476035743, "percentage": 64.21, "elapsed_time": "6:52:17", "remaining_time": "3:49:48"}
+{"current_steps": 245, "total_steps": 380, "loss": 0.4533, "lr": 2.7012021231812666e-05, "epoch": 3.1892770105605197, "percentage": 64.47, "elapsed_time": "6:53:56", "remaining_time": "3:48:05"}
+{"current_steps": 246, "total_steps": 380, "loss": 0.451, "lr": 2.6665045141224193e-05, "epoch": 3.2022745735174656, "percentage": 64.74, "elapsed_time": "6:55:36", "remaining_time": "3:46:23"}
+{"current_steps": 247, "total_steps": 380, "loss": 0.4557, "lr": 2.6319194266973256e-05, "epoch": 3.215272136474411, "percentage": 65.0, "elapsed_time": "6:57:15", "remaining_time": "3:44:40"}
+{"current_steps": 248, "total_steps": 380, "loss": 0.4468, "lr": 2.597449779228983e-05, "epoch": 3.2282696994313564, "percentage": 65.26, "elapsed_time": "6:58:54", "remaining_time": "3:42:58"}
+{"current_steps": 249, "total_steps": 380, "loss": 0.4554, "lr": 2.563098480299451e-05, "epoch": 3.2412672623883023, "percentage": 65.53, "elapsed_time": "7:00:34", "remaining_time": "3:41:15"}
+{"current_steps": 250, "total_steps": 380, "loss": 0.4549, "lr": 2.5288684285044283e-05, "epoch": 3.2542648253452477, "percentage": 65.79, "elapsed_time": "7:02:13", "remaining_time": "3:39:33"}
+{"current_steps": 251, "total_steps": 380, "loss": 0.4543, "lr": 2.4947625122086585e-05, "epoch": 3.267262388302193, "percentage": 66.05, "elapsed_time": "7:03:52", "remaining_time": "3:37:50"}
+{"current_steps": 252, "total_steps": 380, "loss": 0.4575, "lr": 2.460783609302218e-05, "epoch": 3.280259951259139, "percentage": 66.32, "elapsed_time": "7:05:31", "remaining_time": "3:36:08"}
+{"current_steps": 253, "total_steps": 380, "loss": 0.452, "lr": 2.4269345869576676e-05, "epoch": 3.2932575142160845, "percentage": 66.58, "elapsed_time": "7:07:10", "remaining_time": "3:34:26"}
+{"current_steps": 254, "total_steps": 380, "loss": 0.4507, "lr": 2.393218301388123e-05, "epoch": 3.30625507717303, "percentage": 66.84, "elapsed_time": "7:08:49", "remaining_time": "3:32:43"}
+{"current_steps": 255, "total_steps": 380, "loss": 0.4483, "lr": 2.35963759760624e-05, "epoch": 3.319252640129976, "percentage": 67.11, "elapsed_time": "7:10:29", "remaining_time": "3:31:01"}
+{"current_steps": 256, "total_steps": 380, "loss": 0.4466, "lr": 2.3261953091841553e-05, "epoch": 3.332250203086921, "percentage": 67.37, "elapsed_time": "7:12:08", "remaining_time": "3:29:18"}
+{"current_steps": 257, "total_steps": 380, "loss": 0.457, "lr": 2.2928942580143855e-05, "epoch": 3.3452477660438666, "percentage": 67.63, "elapsed_time": "7:13:47", "remaining_time": "3:27:36"}
+{"current_steps": 258, "total_steps": 380, "loss": 0.4494, "lr": 2.2597372540717083e-05, "epoch": 3.3582453290008125, "percentage": 67.89, "elapsed_time": "7:15:26", "remaining_time": "3:25:54"}
+{"current_steps": 259, "total_steps": 380, "loss": 0.4577, "lr": 2.226727095176057e-05, "epoch": 3.371242891957758, "percentage": 68.16, "elapsed_time": "7:17:05", "remaining_time": "3:24:12"}
+{"current_steps": 260, "total_steps": 380, "loss": 0.45, "lr": 2.1938665667564435e-05, "epoch": 3.3842404549147034, "percentage": 68.42, "elapsed_time": "7:18:45", "remaining_time": "3:22:30"}
+{"current_steps": 261, "total_steps": 380, "loss": 0.4601, "lr": 2.1611584416159106e-05, "epoch": 3.3972380178716493, "percentage": 68.68, "elapsed_time": "7:20:24", "remaining_time": "3:20:47"}
+{"current_steps": 262, "total_steps": 380, "loss": 0.4544, "lr": 2.1286054796975696e-05, "epoch": 3.4102355808285947, "percentage": 68.95, "elapsed_time": "7:22:03", "remaining_time": "3:19:05"}
+{"current_steps": 263, "total_steps": 380, "loss": 0.4499, "lr": 2.096210427851706e-05, "epoch": 3.42323314378554, "percentage": 69.21, "elapsed_time": "7:23:42", "remaining_time": "3:17:23"}
+{"current_steps": 264, "total_steps": 380, "loss": 0.4492, "lr": 2.063976019604006e-05, "epoch": 3.436230706742486, "percentage": 69.47, "elapsed_time": "7:25:21", "remaining_time": "3:15:41"}
+{"current_steps": 265, "total_steps": 380, "loss": 0.4576, "lr": 2.0319049749248876e-05, "epoch": 3.4492282696994314, "percentage": 69.74, "elapsed_time": "7:27:01", "remaining_time": "3:13:59"}
+{"current_steps": 266, "total_steps": 380, "loss": 0.4478, "lr": 2.0000000000000012e-05, "epoch": 3.462225832656377, "percentage": 70.0, "elapsed_time": "7:28:40", "remaining_time": "3:12:17"}
+{"current_steps": 267, "total_steps": 380, "loss": 0.4503, "lr": 1.9682637870018638e-05, "epoch": 3.4752233956133223, "percentage": 70.26, "elapsed_time": "7:30:19", "remaining_time": "3:10:35"}
+{"current_steps": 268, "total_steps": 380, "loss": 0.451, "lr": 1.9366990138627054e-05, "epoch": 3.488220958570268, "percentage": 70.53, "elapsed_time": "7:31:58", "remaining_time": "3:08:53"}
+{"current_steps": 269, "total_steps": 380, "loss": 0.4469, "lr": 1.9053083440484887e-05, "epoch": 3.5012185215272136, "percentage": 70.79, "elapsed_time": "7:33:38", "remaining_time": "3:07:11"}
+{"current_steps": 270, "total_steps": 380, "loss": 0.4538, "lr": 1.8740944263341773e-05, "epoch": 3.5142160844841595, "percentage": 71.05, "elapsed_time": "7:35:18", "remaining_time": "3:05:29"}
+{"current_steps": 271, "total_steps": 380, "loss": 0.4578, "lr": 1.8430598945802156e-05, "epoch": 3.527213647441105, "percentage": 71.32, "elapsed_time": "7:36:58", "remaining_time": "3:03:48"}
+{"current_steps": 272, "total_steps": 380, "loss": 0.4501, "lr": 1.8122073675102935e-05, "epoch": 3.5402112103980503, "percentage": 71.58, "elapsed_time": "7:38:38", "remaining_time": "3:02:06"}
+{"current_steps": 273, "total_steps": 380, "loss": 0.4508, "lr": 1.781539448490365e-05, "epoch": 3.5532087733549957, "percentage": 71.84, "elapsed_time": "7:40:18", "remaining_time": "3:00:24"}
+{"current_steps": 274, "total_steps": 380, "loss": 0.4564, "lr": 1.7510587253089842e-05, "epoch": 3.5662063363119416, "percentage": 72.11, "elapsed_time": "7:41:57", "remaining_time": "2:58:42"}
+{"current_steps": 275, "total_steps": 380, "loss": 0.4562, "lr": 1.7207677699589355e-05, "epoch": 3.579203899268887, "percentage": 72.37, "elapsed_time": "7:43:37", "remaining_time": "2:57:01"}
+{"current_steps": 276, "total_steps": 380, "loss": 0.4539, "lr": 1.690669138420215e-05, "epoch": 3.592201462225833, "percentage": 72.63, "elapsed_time": "7:45:16", "remaining_time": "2:55:19"}
+{"current_steps": 277, "total_steps": 380, "loss": 0.4549, "lr": 1.6607653704443457e-05, "epoch": 3.6051990251827783, "percentage": 72.89, "elapsed_time": "7:46:55", "remaining_time": "2:53:37"}
+{"current_steps": 278, "total_steps": 380, "loss": 0.4495, "lr": 1.6310589893400804e-05, "epoch": 3.618196588139724, "percentage": 73.16, "elapsed_time": "7:48:34", "remaining_time": "2:51:55"}
+{"current_steps": 279, "total_steps": 380, "loss": 0.4615, "lr": 1.601552501760473e-05, "epoch": 3.631194151096669, "percentage": 73.42, "elapsed_time": "7:50:13", "remaining_time": "2:50:13"}
+{"current_steps": 280, "total_steps": 380, "loss": 0.452, "lr": 1.5722483974913737e-05, "epoch": 3.644191714053615, "percentage": 73.68, "elapsed_time": "7:51:53", "remaining_time": "2:48:31"}
+{"current_steps": 281, "total_steps": 380, "loss": 0.4509, "lr": 1.5431491492413288e-05, "epoch": 3.6571892770105605, "percentage": 73.95, "elapsed_time": "7:53:32", "remaining_time": "2:46:50"}
+{"current_steps": 282, "total_steps": 380, "loss": 0.4536, "lr": 1.5142572124329418e-05, "epoch": 3.670186839967506, "percentage": 74.21, "elapsed_time": "7:55:11", "remaining_time": "2:45:08"}
+{"current_steps": 283, "total_steps": 380, "loss": 0.4533, "lr": 1.4855750249956718e-05, "epoch": 3.683184402924452, "percentage": 74.47, "elapsed_time": "7:56:50", "remaining_time": "2:43:26"}
+{"current_steps": 284, "total_steps": 380, "loss": 0.4583, "lr": 1.457105007160129e-05, "epoch": 3.6961819658813972, "percentage": 74.74, "elapsed_time": "7:58:29", "remaining_time": "2:41:44"}
+{"current_steps": 285, "total_steps": 380, "loss": 0.4546, "lr": 1.4288495612538427e-05, "epoch": 3.7091795288383427, "percentage": 75.0, "elapsed_time": "8:00:08", "remaining_time": "2:40:02"}
+{"current_steps": 286, "total_steps": 380, "loss": 0.4562, "lr": 1.4008110714985623e-05, "epoch": 3.722177091795288, "percentage": 75.26, "elapsed_time": "8:01:47", "remaining_time": "2:38:21"}
+{"current_steps": 287, "total_steps": 380, "loss": 0.4531, "lr": 1.3729919038090627e-05, "epoch": 3.735174654752234, "percentage": 75.53, "elapsed_time": "8:03:27", "remaining_time": "2:36:39"}
+{"current_steps": 288, "total_steps": 380, "loss": 0.4554, "lr": 1.3453944055935151e-05, "epoch": 3.7481722177091794, "percentage": 75.79, "elapsed_time": "8:05:06", "remaining_time": "2:34:57"}
+{"current_steps": 289, "total_steps": 380, "loss": 0.4557, "lr": 1.3180209055554043e-05, "epoch": 3.7611697806661253, "percentage": 76.05, "elapsed_time": "8:06:45", "remaining_time": "2:33:16"}
+{"current_steps": 290, "total_steps": 380, "loss": 0.4568, "lr": 1.2908737134970367e-05, "epoch": 3.7741673436230707, "percentage": 76.32, "elapsed_time": "8:08:25", "remaining_time": "2:31:34"}
+{"current_steps": 291, "total_steps": 380, "loss": 0.4514, "lr": 1.2639551201246278e-05, "epoch": 3.787164906580016, "percentage": 76.58, "elapsed_time": "8:10:04", "remaining_time": "2:29:53"}
+{"current_steps": 292, "total_steps": 380, "loss": 0.4476, "lr": 1.2372673968550229e-05, "epoch": 3.8001624695369616, "percentage": 76.84, "elapsed_time": "8:11:43", "remaining_time": "2:28:11"}
+{"current_steps": 293, "total_steps": 380, "loss": 0.4471, "lr": 1.2108127956240186e-05, "epoch": 3.8131600324939074, "percentage": 77.11, "elapsed_time": "8:13:22", "remaining_time": "2:26:29"}
+{"current_steps": 294, "total_steps": 380, "loss": 0.4515, "lr": 1.1845935486963546e-05, "epoch": 3.826157595450853, "percentage": 77.37, "elapsed_time": "8:15:02", "remaining_time": "2:24:48"}
+{"current_steps": 295, "total_steps": 380, "loss": 0.4484, "lr": 1.158611868477344e-05, "epoch": 3.8391551584077988, "percentage": 77.63, "elapsed_time": "8:16:41", "remaining_time": "2:23:06"}
+{"current_steps": 296, "total_steps": 380, "loss": 0.446, "lr": 1.1328699473261957e-05, "epoch": 3.852152721364744, "percentage": 77.89, "elapsed_time": "8:18:20", "remaining_time": "2:21:25"}
+{"current_steps": 297, "total_steps": 380, "loss": 0.4587, "lr": 1.107369957371013e-05, "epoch": 3.8651502843216896, "percentage": 78.16, "elapsed_time": "8:19:59", "remaining_time": "2:19:43"}
+{"current_steps": 298, "total_steps": 380, "loss": 0.4478, "lr": 1.0821140503255174e-05, "epoch": 3.878147847278635, "percentage": 78.42, "elapsed_time": "8:21:39", "remaining_time": "2:18:02"}
+{"current_steps": 299, "total_steps": 380, "loss": 0.4474, "lr": 1.0571043573074737e-05, "epoch": 3.891145410235581, "percentage": 78.68, "elapsed_time": "8:23:18", "remaining_time": "2:16:20"}
+{"current_steps": 300, "total_steps": 380, "loss": 0.4558, "lr": 1.0323429886588743e-05, "epoch": 3.9041429731925263, "percentage": 78.95, "elapsed_time": "8:24:57", "remaining_time": "2:14:39"}
+{"current_steps": 301, "total_steps": 380, "loss": 0.4472, "lr": 1.0078320337678584e-05, "epoch": 3.917140536149472, "percentage": 79.21, "elapsed_time": "8:26:36", "remaining_time": "2:12:57"}
+{"current_steps": 302, "total_steps": 380, "loss": 0.4532, "lr": 9.835735608924155e-06, "epoch": 3.9301380991064176, "percentage": 79.47, "elapsed_time": "8:28:16", "remaining_time": "2:11:16"}
+{"current_steps": 303, "total_steps": 380, "loss": 0.452, "lr": 9.595696169858542e-06, "epoch": 3.943135662063363, "percentage": 79.74, "elapsed_time": "8:29:55", "remaining_time": "2:09:35"}
+{"current_steps": 304, "total_steps": 380, "loss": 0.4548, "lr": 9.358222275240884e-06, "epoch": 3.9561332250203085, "percentage": 80.0, "elapsed_time": "8:31:34", "remaining_time": "2:07:53"}
+{"current_steps": 305, "total_steps": 380, "loss": 0.4568, "lr": 9.123333963347166e-06, "epoch": 3.9691307879772544, "percentage": 80.26, "elapsed_time": "8:33:13", "remaining_time": "2:06:12"}
+{"current_steps": 306, "total_steps": 380, "loss": 0.4503, "lr": 8.89105105427945e-06, "epoch": 3.9821283509342, "percentage": 80.53, "elapsed_time": "8:34:53", "remaining_time": "2:04:30"}
+{"current_steps": 307, "total_steps": 380, "loss": 0.4514, "lr": 8.661393148293355e-06, "epoch": 3.9951259138911457, "percentage": 80.79, "elapsed_time": "8:36:32", "remaining_time": "2:02:49"}
+{"current_steps": 308, "total_steps": 380, "loss": 0.4384, "lr": 8.434379624144261e-06, "epoch": 4.0097481722177095, "percentage": 81.05, "elapsed_time": "8:39:55", "remaining_time": "2:01:32"}