Training in progress, step 279

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1533bf0bdb713130e450b940d8a89488d1d629e39bc72a1d7a2a5d5bd5c29a2b
+oid sha256:373d8228051ae330fe3aabd478142dbdb6164a5f9ec9278b828115e2f6b26514
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852dd860a1d985235fd6ed22b402b79d12af2945c1e9d98fc88f8e577770a4be
+oid sha256:aa66bcb617f93f96dd00fcf8c1e4265393e96663a286ec548e00ab78b5bddf24
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8283278b6f3a9ab7e2773057e4480480033a89dd1d5246c4b579bbc7d7ae7a0
+oid sha256:ddd7f066bd1d40a01fb8c18e683f24221942908941ef1cbe4fc4bb0b555cb5d8
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cd301e4aabc6d6293544ec24b694a863a73361d581f2afa7390037e5883312
+oid sha256:1df1d1462cdac3245775cede351dbd836f9611fa8b10c8b91b3a0b983ad804c2
 size 1089994880

trainer_log.jsonl

@@ -199,3 +199,82 @@
 {"current_steps": 199, "total_steps": 279, "loss": 0.2632, "lr": 2.356893372068855e-06, "epoch": 2.139784946236559, "percentage": 71.33, "elapsed_time": "6:44:51", "remaining_time": "2:42:45"}
 {"current_steps": 200, "total_steps": 279, "loss": 0.2136, "lr": 2.3039789734401524e-06, "epoch": 2.150537634408602, "percentage": 71.68, "elapsed_time": "6:47:58", "remaining_time": "2:41:09"}
 {"current_steps": 201, "total_steps": 279, "loss": 0.2032, "lr": 2.251486922291957e-06, "epoch": 2.161290322580645, "percentage": 72.04, "elapsed_time": "6:52:09", "remaining_time": "2:39:56"}
+{"current_steps": 202, "total_steps": 279, "loss": 0.2516, "lr": 2.1994254418114524e-06, "epoch": 2.172043010752688, "percentage": 72.4, "elapsed_time": "6:55:40", "remaining_time": "2:38:26"}
+{"current_steps": 203, "total_steps": 279, "loss": 0.1965, "lr": 2.147802687734409e-06, "epoch": 2.182795698924731, "percentage": 72.76, "elapsed_time": "6:57:51", "remaining_time": "2:36:26"}
+{"current_steps": 204, "total_steps": 279, "loss": 0.198, "lr": 2.0966267470675273e-06, "epoch": 2.193548387096774, "percentage": 73.12, "elapsed_time": "6:59:52", "remaining_time": "2:34:21"}
+{"current_steps": 205, "total_steps": 279, "loss": 0.3509, "lr": 2.0459056368215786e-06, "epoch": 2.204301075268817, "percentage": 73.48, "elapsed_time": "7:02:03", "remaining_time": "2:32:21"}
+{"current_steps": 206, "total_steps": 279, "loss": 0.2416, "lr": 1.9956473027554846e-06, "epoch": 2.21505376344086, "percentage": 73.84, "elapsed_time": "7:04:29", "remaining_time": "2:30:25"}
+{"current_steps": 207, "total_steps": 279, "loss": 0.2525, "lr": 1.9458596181315643e-06, "epoch": 2.225806451612903, "percentage": 74.19, "elapsed_time": "7:06:45", "remaining_time": "2:28:26"}
+{"current_steps": 208, "total_steps": 279, "loss": 0.2103, "lr": 1.8965503824821496e-06, "epoch": 2.236559139784946, "percentage": 74.55, "elapsed_time": "7:08:24", "remaining_time": "2:26:14"}
+{"current_steps": 209, "total_steps": 279, "loss": 0.2403, "lr": 1.84772732038774e-06, "epoch": 2.247311827956989, "percentage": 74.91, "elapsed_time": "7:10:26", "remaining_time": "2:24:09"}
+{"current_steps": 210, "total_steps": 279, "loss": 0.2059, "lr": 1.7993980802668947e-06, "epoch": 2.258064516129032, "percentage": 75.27, "elapsed_time": "7:12:21", "remaining_time": "2:22:03"}
+{"current_steps": 211, "total_steps": 279, "loss": 0.2106, "lr": 1.7515702331780753e-06, "epoch": 2.268817204301075, "percentage": 75.63, "elapsed_time": "7:14:06", "remaining_time": "2:19:54"}
+{"current_steps": 212, "total_steps": 279, "loss": 0.1833, "lr": 1.7042512716335873e-06, "epoch": 2.279569892473118, "percentage": 75.99, "elapsed_time": "7:16:04", "remaining_time": "2:17:49"}
+{"current_steps": 213, "total_steps": 279, "loss": 0.2071, "lr": 1.6574486084258369e-06, "epoch": 2.2903225806451615, "percentage": 76.34, "elapsed_time": "7:18:09", "remaining_time": "2:15:46"}
+{"current_steps": 214, "total_steps": 279, "loss": 0.2277, "lr": 1.6111695754660667e-06, "epoch": 2.3010752688172045, "percentage": 76.7, "elapsed_time": "7:20:22", "remaining_time": "2:13:45"}
+{"current_steps": 215, "total_steps": 279, "loss": 0.2318, "lr": 1.5654214226357822e-06, "epoch": 2.3118279569892475, "percentage": 77.06, "elapsed_time": "7:22:21", "remaining_time": "2:11:40"}
+{"current_steps": 216, "total_steps": 279, "loss": 0.1953, "lr": 1.5202113166510058e-06, "epoch": 2.3225806451612905, "percentage": 77.42, "elapsed_time": "7:24:35", "remaining_time": "2:09:40"}
+{"current_steps": 217, "total_steps": 279, "loss": 0.2623, "lr": 1.475546339939568e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "7:26:22", "remaining_time": "2:07:32"}
+{"current_steps": 218, "total_steps": 279, "loss": 0.2445, "lr": 1.4314334895316095e-06, "epoch": 2.3440860215053765, "percentage": 78.14, "elapsed_time": "7:28:34", "remaining_time": "2:05:31"}
+{"current_steps": 219, "total_steps": 279, "loss": 0.2306, "lr": 1.3878796759634544e-06, "epoch": 2.3548387096774195, "percentage": 78.49, "elapsed_time": "7:30:56", "remaining_time": "2:03:32"}
+{"current_steps": 220, "total_steps": 279, "loss": 0.2374, "lr": 1.3448917221950264e-06, "epoch": 2.3655913978494625, "percentage": 78.85, "elapsed_time": "7:33:27", "remaining_time": "2:01:36"}
+{"current_steps": 221, "total_steps": 279, "loss": 0.2015, "lr": 1.3024763625410025e-06, "epoch": 2.3763440860215055, "percentage": 79.21, "elapsed_time": "7:35:13", "remaining_time": "1:59:28"}
+{"current_steps": 222, "total_steps": 279, "loss": 0.2067, "lr": 1.2606402416158391e-06, "epoch": 2.3870967741935485, "percentage": 79.57, "elapsed_time": "7:37:20", "remaining_time": "1:57:25"}
+{"current_steps": 223, "total_steps": 279, "loss": 0.2183, "lr": 1.2193899132928539e-06, "epoch": 2.3978494623655915, "percentage": 79.93, "elapsed_time": "7:39:23", "remaining_time": "1:55:21"}
+{"current_steps": 224, "total_steps": 279, "loss": 0.1999, "lr": 1.1787318396775188e-06, "epoch": 2.4086021505376345, "percentage": 80.29, "elapsed_time": "7:41:07", "remaining_time": "1:53:13"}
+{"current_steps": 225, "total_steps": 279, "loss": 0.2359, "lr": 1.138672390095143e-06, "epoch": 2.4193548387096775, "percentage": 80.65, "elapsed_time": "7:42:31", "remaining_time": "1:51:00"}
+{"current_steps": 226, "total_steps": 279, "loss": 0.2212, "lr": 1.0992178400930753e-06, "epoch": 2.4301075268817205, "percentage": 81.0, "elapsed_time": "7:44:53", "remaining_time": "1:49:01"}
+{"current_steps": 227, "total_steps": 279, "loss": 0.2345, "lr": 1.0603743704575992e-06, "epoch": 2.4408602150537635, "percentage": 81.36, "elapsed_time": "7:47:00", "remaining_time": "1:46:58"}
+{"current_steps": 228, "total_steps": 279, "loss": 0.2339, "lr": 1.0221480662456845e-06, "epoch": 2.4516129032258065, "percentage": 81.72, "elapsed_time": "7:50:02", "remaining_time": "1:45:08"}
+{"current_steps": 229, "total_steps": 279, "loss": 0.2091, "lr": 9.845449158317216e-07, "epoch": 2.4623655913978495, "percentage": 82.08, "elapsed_time": "7:52:03", "remaining_time": "1:43:04"}
+{"current_steps": 230, "total_steps": 279, "loss": 0.2178, "lr": 9.475708099694125e-07, "epoch": 2.4731182795698925, "percentage": 82.44, "elapsed_time": "7:54:38", "remaining_time": "1:41:07"}
+{"current_steps": 231, "total_steps": 279, "loss": 0.4077, "lr": 9.112315408689415e-07, "epoch": 2.4838709677419355, "percentage": 82.8, "elapsed_time": "7:56:47", "remaining_time": "1:39:04"}
+{"current_steps": 232, "total_steps": 279, "loss": 0.2357, "lr": 8.755328012896002e-07, "epoch": 2.4946236559139785, "percentage": 83.15, "elapsed_time": "7:58:34", "remaining_time": "1:36:57"}
+{"current_steps": 233, "total_steps": 279, "loss": 0.2112, "lr": 8.404801836479809e-07, "epoch": 2.5053763440860215, "percentage": 83.51, "elapsed_time": "8:00:13", "remaining_time": "1:34:48"}
+{"current_steps": 234, "total_steps": 279, "loss": 0.2562, "lr": 8.060791791418887e-07, "epoch": 2.5161290322580645, "percentage": 83.87, "elapsed_time": "8:01:58", "remaining_time": "1:32:41"}
+{"current_steps": 235, "total_steps": 279, "loss": 0.2323, "lr": 7.723351768901172e-07, "epoch": 2.5268817204301075, "percentage": 84.23, "elapsed_time": "8:04:35", "remaining_time": "1:30:43"}
+{"current_steps": 236, "total_steps": 279, "loss": 0.2481, "lr": 7.392534630882092e-07, "epoch": 2.5376344086021505, "percentage": 84.59, "elapsed_time": "8:06:46", "remaining_time": "1:28:41"}
+{"current_steps": 237, "total_steps": 279, "loss": 0.2124, "lr": 7.06839220180342e-07, "epoch": 2.5483870967741935, "percentage": 84.95, "elapsed_time": "8:08:56", "remaining_time": "1:26:38"}
+{"current_steps": 238, "total_steps": 279, "loss": 0.2528, "lr": 6.750975260474718e-07, "epoch": 2.5591397849462365, "percentage": 85.3, "elapsed_time": "8:11:20", "remaining_time": "1:24:38"}
+{"current_steps": 239, "total_steps": 279, "loss": 0.218, "lr": 6.440333532118503e-07, "epoch": 2.5698924731182795, "percentage": 85.66, "elapsed_time": "8:13:12", "remaining_time": "1:22:32"}
+{"current_steps": 240, "total_steps": 279, "loss": 0.2233, "lr": 6.136515680580479e-07, "epoch": 2.5806451612903225, "percentage": 86.02, "elapsed_time": "8:15:17", "remaining_time": "1:20:29"}
+{"current_steps": 241, "total_steps": 279, "loss": 0.2116, "lr": 5.839569300706127e-07, "epoch": 2.5913978494623655, "percentage": 86.38, "elapsed_time": "8:17:24", "remaining_time": "1:18:25"}
+{"current_steps": 242, "total_steps": 279, "loss": 0.1977, "lr": 5.549540910884649e-07, "epoch": 2.6021505376344085, "percentage": 86.74, "elapsed_time": "8:19:29", "remaining_time": "1:16:22"}
+{"current_steps": 243, "total_steps": 279, "loss": 0.2062, "lr": 5.266475945761562e-07, "epoch": 2.6129032258064515, "percentage": 87.1, "elapsed_time": "8:21:12", "remaining_time": "1:14:15"}
+{"current_steps": 244, "total_steps": 279, "loss": 0.2217, "lr": 4.990418749121179e-07, "epoch": 2.6236559139784945, "percentage": 87.46, "elapsed_time": "8:23:04", "remaining_time": "1:12:09"}
+{"current_steps": 245, "total_steps": 279, "loss": 0.2265, "lr": 4.721412566939804e-07, "epoch": 2.6344086021505375, "percentage": 87.81, "elapsed_time": "8:24:58", "remaining_time": "1:10:04"}
+{"current_steps": 246, "total_steps": 279, "loss": 0.2379, "lr": 4.4594995406110785e-07, "epoch": 2.6451612903225805, "percentage": 88.17, "elapsed_time": "8:27:17", "remaining_time": "1:08:03"}
+{"current_steps": 247, "total_steps": 279, "loss": 0.2079, "lr": 4.2047207003442003e-07, "epoch": 2.6559139784946235, "percentage": 88.53, "elapsed_time": "8:29:20", "remaining_time": "1:05:59"}
+{"current_steps": 248, "total_steps": 279, "loss": 0.2321, "lr": 3.957115958736374e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "8:31:22", "remaining_time": "1:03:55"}
+{"current_steps": 249, "total_steps": 279, "loss": 0.1987, "lr": 3.7167241045202474e-07, "epoch": 2.6774193548387095, "percentage": 89.25, "elapsed_time": "8:33:12", "remaining_time": "1:01:49"}
+{"current_steps": 250, "total_steps": 279, "loss": 0.2094, "lr": 3.483582796487395e-07, "epoch": 2.688172043010753, "percentage": 89.61, "elapsed_time": "8:35:10", "remaining_time": "0:59:45"}
+{"current_steps": 251, "total_steps": 279, "loss": 0.25, "lr": 3.257728557588902e-07, "epoch": 2.698924731182796, "percentage": 89.96, "elapsed_time": "8:37:18", "remaining_time": "0:57:42"}
+{"current_steps": 252, "total_steps": 279, "loss": 0.2763, "lr": 3.039196769213787e-07, "epoch": 2.709677419354839, "percentage": 90.32, "elapsed_time": "8:39:04", "remaining_time": "0:55:36"}
+{"current_steps": 253, "total_steps": 279, "loss": 0.221, "lr": 2.828021665646341e-07, "epoch": 2.720430107526882, "percentage": 90.68, "elapsed_time": "8:41:39", "remaining_time": "0:53:36"}
+{"current_steps": 254, "total_steps": 279, "loss": 0.3025, "lr": 2.6242363287030617e-07, "epoch": 2.731182795698925, "percentage": 91.04, "elapsed_time": "8:43:48", "remaining_time": "0:51:33"}
+{"current_steps": 255, "total_steps": 279, "loss": 0.2539, "lr": 2.4278726825502696e-07, "epoch": 2.741935483870968, "percentage": 91.4, "elapsed_time": "8:45:57", "remaining_time": "0:49:30"}
+{"current_steps": 256, "total_steps": 279, "loss": 0.2281, "lr": 2.2389614887029564e-07, "epoch": 2.752688172043011, "percentage": 91.76, "elapsed_time": "8:48:02", "remaining_time": "0:47:26"}
+{"current_steps": 257, "total_steps": 279, "loss": 0.2141, "lr": 2.0575323412058036e-07, "epoch": 2.763440860215054, "percentage": 92.11, "elapsed_time": "8:50:22", "remaining_time": "0:45:24"}
+{"current_steps": 258, "total_steps": 279, "loss": 0.2195, "lr": 1.8836136619971468e-07, "epoch": 2.774193548387097, "percentage": 92.47, "elapsed_time": "8:51:58", "remaining_time": "0:43:18"}
+{"current_steps": 259, "total_steps": 279, "loss": 0.2508, "lr": 1.7172326964564777e-07, "epoch": 2.78494623655914, "percentage": 92.83, "elapsed_time": "8:54:00", "remaining_time": "0:41:14"}
+{"current_steps": 260, "total_steps": 279, "loss": 0.2264, "lr": 1.5584155091362907e-07, "epoch": 2.795698924731183, "percentage": 93.19, "elapsed_time": "8:56:00", "remaining_time": "0:39:10"}
+{"current_steps": 261, "total_steps": 279, "loss": 0.1976, "lr": 1.4071869796789427e-07, "epoch": 2.806451612903226, "percentage": 93.55, "elapsed_time": "8:58:06", "remaining_time": "0:37:06"}
+{"current_steps": 262, "total_steps": 279, "loss": 0.1927, "lr": 1.263570798919106e-07, "epoch": 2.817204301075269, "percentage": 93.91, "elapsed_time": "9:00:16", "remaining_time": "0:35:03"}
+{"current_steps": 263, "total_steps": 279, "loss": 0.1868, "lr": 1.1275894651724517e-07, "epoch": 2.827956989247312, "percentage": 94.27, "elapsed_time": "9:02:27", "remaining_time": "0:33:00"}
+{"current_steps": 264, "total_steps": 279, "loss": 0.1927, "lr": 9.992642807111486e-08, "epoch": 2.838709677419355, "percentage": 94.62, "elapsed_time": "9:04:44", "remaining_time": "0:30:57"}
+{"current_steps": 265, "total_steps": 279, "loss": 0.2234, "lr": 8.78615348426759e-08, "epoch": 2.849462365591398, "percentage": 94.98, "elapsed_time": "9:07:04", "remaining_time": "0:28:54"}
+{"current_steps": 266, "total_steps": 279, "loss": 0.1817, "lr": 7.656615686809976e-08, "epoch": 2.860215053763441, "percentage": 95.34, "elapsed_time": "9:08:59", "remaining_time": "0:26:49"}
+{"current_steps": 267, "total_steps": 279, "loss": 0.2152, "lr": 6.604206363448662e-08, "epoch": 2.870967741935484, "percentage": 95.7, "elapsed_time": "9:11:17", "remaining_time": "0:24:46"}
+{"current_steps": 268, "total_steps": 279, "loss": 0.2158, "lr": 5.6290903802665444e-08, "epoch": 2.881720430107527, "percentage": 96.06, "elapsed_time": "9:13:20", "remaining_time": "0:22:42"}
+{"current_steps": 269, "total_steps": 279, "loss": 0.2409, "lr": 4.7314204948923356e-08, "epoch": 2.89247311827957, "percentage": 96.42, "elapsed_time": "9:15:26", "remaining_time": "0:20:38"}
+{"current_steps": 270, "total_steps": 279, "loss": 0.215, "lr": 3.911337332569876e-08, "epoch": 2.903225806451613, "percentage": 96.77, "elapsed_time": "9:17:43", "remaining_time": "0:18:35"}
+{"current_steps": 271, "total_steps": 279, "loss": 0.1853, "lr": 3.168969364128527e-08, "epoch": 2.913978494623656, "percentage": 97.13, "elapsed_time": "9:19:43", "remaining_time": "0:16:31"}
+{"current_steps": 272, "total_steps": 279, "loss": 0.1822, "lr": 2.5044328858576105e-08, "epoch": 2.924731182795699, "percentage": 97.49, "elapsed_time": "9:21:50", "remaining_time": "0:14:27"}
+{"current_steps": 273, "total_steps": 279, "loss": 0.2366, "lr": 1.917832001287645e-08, "epoch": 2.935483870967742, "percentage": 97.85, "elapsed_time": "9:23:43", "remaining_time": "0:12:23"}
+{"current_steps": 274, "total_steps": 279, "loss": 0.2088, "lr": 1.4092586048820578e-08, "epoch": 2.946236559139785, "percentage": 98.21, "elapsed_time": "9:25:34", "remaining_time": "0:10:19"}
+{"current_steps": 275, "total_steps": 279, "loss": 0.2006, "lr": 9.787923676414235e-09, "epoch": 2.956989247311828, "percentage": 98.57, "elapsed_time": "9:28:00", "remaining_time": "0:08:15"}
+{"current_steps": 276, "total_steps": 279, "loss": 0.2288, "lr": 6.265007246223365e-09, "epoch": 2.967741935483871, "percentage": 98.92, "elapsed_time": "9:29:39", "remaining_time": "0:06:11"}
+{"current_steps": 277, "total_steps": 279, "loss": 0.2359, "lr": 3.524388643736387e-09, "epoch": 2.978494623655914, "percentage": 99.28, "elapsed_time": "9:31:51", "remaining_time": "0:04:07"}
+{"current_steps": 278, "total_steps": 279, "loss": 0.2032, "lr": 1.566497202904471e-09, "epoch": 2.989247311827957, "percentage": 99.64, "elapsed_time": "9:33:58", "remaining_time": "0:02:03"}
+{"current_steps": 279, "total_steps": 279, "loss": 0.2414, "lr": 3.916396388869981e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "9:35:36", "remaining_time": "0:00:00"}
+{"current_steps": 279, "total_steps": 279, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "9:37:53", "remaining_time": "0:00:00"}