Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72a5308b86ed626818fb9e9d57a83acdc469e49df9ba80958831afbba23ea08
+oid sha256:8eefc9b7b15b6b875403f8b51fb06966e89f0d6876d63acaf4e3d046fa48533d
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1b212f24d8ce46bb0c91bbba54ff0e121078c3d1dff498795a94964e105717
+oid sha256:d94d501931ca36c1ac3a6eac4d9986a9b85f03cee94ba9ee2b57aeabbd0dc58f
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4049d82f55d68063d3b2ece88ea0a8288b6e240649ae7d1ba236de28b3e3cc
+oid sha256:38ff826d6226ec88fd665374e6775b55e65bf54c433a67bfeee92f4b570bc91b
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a514a556f9953f32d3ad0d238eb08998b6c48babfdeb9270d6de11a10937f3
+oid sha256:30fbe086daf676f85da8f9bcf67a23fa714c0bfccab89f781b8362ad6a6a116b
 size 1168138808

trainer_log.jsonl

@@ -149,3 +149,78 @@
 {"current_steps": 1480, "total_steps": 2244, "loss": 0.7665, "lr": 5e-06, "epoch": 1.9782790309106097, "percentage": 65.95, "elapsed_time": "23:57:19", "remaining_time": "12:21:58"}
 {"current_steps": 1490, "total_steps": 2244, "loss": 0.7674, "lr": 5e-06, "epoch": 1.9916457811194652, "percentage": 66.4, "elapsed_time": "1 day, 0:06:57", "remaining_time": "12:12:13"}
 {"current_steps": 1496, "total_steps": 2244, "eval_loss": 0.7951143383979797, "epoch": 1.9996658312447786, "percentage": 66.67, "elapsed_time": "1 day, 0:26:11", "remaining_time": "12:13:05"}
+{"current_steps": 1500, "total_steps": 2244, "loss": 0.8233, "lr": 5e-06, "epoch": 2.0050125313283207, "percentage": 66.84, "elapsed_time": "1 day, 0:30:59", "remaining_time": "12:09:36"}
+{"current_steps": 1510, "total_steps": 2244, "loss": 0.7256, "lr": 5e-06, "epoch": 2.018379281537176, "percentage": 67.29, "elapsed_time": "1 day, 0:40:36", "remaining_time": "11:59:42"}
+{"current_steps": 1520, "total_steps": 2244, "loss": 0.7218, "lr": 5e-06, "epoch": 2.0317460317460316, "percentage": 67.74, "elapsed_time": "1 day, 0:50:13", "remaining_time": "11:49:49"}
+{"current_steps": 1530, "total_steps": 2244, "loss": 0.7285, "lr": 5e-06, "epoch": 2.045112781954887, "percentage": 68.18, "elapsed_time": "1 day, 0:59:51", "remaining_time": "11:39:55"}
+{"current_steps": 1540, "total_steps": 2244, "loss": 0.7229, "lr": 5e-06, "epoch": 2.0584795321637426, "percentage": 68.63, "elapsed_time": "1 day, 1:09:28", "remaining_time": "11:30:02"}
+{"current_steps": 1550, "total_steps": 2244, "loss": 0.7231, "lr": 5e-06, "epoch": 2.071846282372598, "percentage": 69.07, "elapsed_time": "1 day, 1:19:06", "remaining_time": "11:20:09"}
+{"current_steps": 1560, "total_steps": 2244, "loss": 0.7239, "lr": 5e-06, "epoch": 2.0852130325814535, "percentage": 69.52, "elapsed_time": "1 day, 1:28:43", "remaining_time": "11:10:17"}
+{"current_steps": 1570, "total_steps": 2244, "loss": 0.7226, "lr": 5e-06, "epoch": 2.098579782790309, "percentage": 69.96, "elapsed_time": "1 day, 1:38:21", "remaining_time": "11:00:24"}
+{"current_steps": 1580, "total_steps": 2244, "loss": 0.7277, "lr": 5e-06, "epoch": 2.1119465329991645, "percentage": 70.41, "elapsed_time": "1 day, 1:47:58", "remaining_time": "10:50:32"}
+{"current_steps": 1590, "total_steps": 2244, "loss": 0.7286, "lr": 5e-06, "epoch": 2.12531328320802, "percentage": 70.86, "elapsed_time": "1 day, 1:57:35", "remaining_time": "10:40:40"}
+{"current_steps": 1600, "total_steps": 2244, "loss": 0.726, "lr": 5e-06, "epoch": 2.1386800334168754, "percentage": 71.3, "elapsed_time": "1 day, 2:07:13", "remaining_time": "10:30:48"}
+{"current_steps": 1610, "total_steps": 2244, "loss": 0.7304, "lr": 5e-06, "epoch": 2.152046783625731, "percentage": 71.75, "elapsed_time": "1 day, 2:16:51", "remaining_time": "10:20:56"}
+{"current_steps": 1620, "total_steps": 2244, "loss": 0.7232, "lr": 5e-06, "epoch": 2.1654135338345863, "percentage": 72.19, "elapsed_time": "1 day, 2:26:29", "remaining_time": "10:11:05"}
+{"current_steps": 1630, "total_steps": 2244, "loss": 0.7336, "lr": 5e-06, "epoch": 2.178780284043442, "percentage": 72.64, "elapsed_time": "1 day, 2:36:06", "remaining_time": "10:01:13"}
+{"current_steps": 1640, "total_steps": 2244, "loss": 0.7255, "lr": 5e-06, "epoch": 2.1921470342522973, "percentage": 73.08, "elapsed_time": "1 day, 2:45:43", "remaining_time": "9:51:22"}
+{"current_steps": 1650, "total_steps": 2244, "loss": 0.7295, "lr": 5e-06, "epoch": 2.2055137844611528, "percentage": 73.53, "elapsed_time": "1 day, 2:55:21", "remaining_time": "9:41:31"}
+{"current_steps": 1660, "total_steps": 2244, "loss": 0.7274, "lr": 5e-06, "epoch": 2.2188805346700082, "percentage": 73.98, "elapsed_time": "1 day, 3:04:58", "remaining_time": "9:31:40"}
+{"current_steps": 1670, "total_steps": 2244, "loss": 0.7256, "lr": 5e-06, "epoch": 2.2322472848788637, "percentage": 74.42, "elapsed_time": "1 day, 3:14:35", "remaining_time": "9:21:49"}
+{"current_steps": 1680, "total_steps": 2244, "loss": 0.7308, "lr": 5e-06, "epoch": 2.245614035087719, "percentage": 74.87, "elapsed_time": "1 day, 3:24:12", "remaining_time": "9:11:58"}
+{"current_steps": 1690, "total_steps": 2244, "loss": 0.7314, "lr": 5e-06, "epoch": 2.2589807852965746, "percentage": 75.31, "elapsed_time": "1 day, 3:33:49", "remaining_time": "9:02:08"}
+{"current_steps": 1700, "total_steps": 2244, "loss": 0.7275, "lr": 5e-06, "epoch": 2.27234753550543, "percentage": 75.76, "elapsed_time": "1 day, 3:43:25", "remaining_time": "8:52:17"}
+{"current_steps": 1710, "total_steps": 2244, "loss": 0.727, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.2, "elapsed_time": "1 day, 3:53:03", "remaining_time": "8:42:27"}
+{"current_steps": 1720, "total_steps": 2244, "loss": 0.727, "lr": 5e-06, "epoch": 2.299081035923141, "percentage": 76.65, "elapsed_time": "1 day, 4:02:40", "remaining_time": "8:32:37"}
+{"current_steps": 1730, "total_steps": 2244, "loss": 0.7286, "lr": 5e-06, "epoch": 2.3124477861319965, "percentage": 77.09, "elapsed_time": "1 day, 4:12:17", "remaining_time": "8:22:47"}
+{"current_steps": 1740, "total_steps": 2244, "loss": 0.7271, "lr": 5e-06, "epoch": 2.325814536340852, "percentage": 77.54, "elapsed_time": "1 day, 4:21:54", "remaining_time": "8:12:58"}
+{"current_steps": 1750, "total_steps": 2244, "loss": 0.733, "lr": 5e-06, "epoch": 2.3391812865497075, "percentage": 77.99, "elapsed_time": "1 day, 4:31:31", "remaining_time": "8:03:08"}
+{"current_steps": 1760, "total_steps": 2244, "loss": 0.7302, "lr": 5e-06, "epoch": 2.352548036758563, "percentage": 78.43, "elapsed_time": "1 day, 4:41:09", "remaining_time": "7:53:19"}
+{"current_steps": 1770, "total_steps": 2244, "loss": 0.7341, "lr": 5e-06, "epoch": 2.3659147869674184, "percentage": 78.88, "elapsed_time": "1 day, 4:50:46", "remaining_time": "7:43:29"}
+{"current_steps": 1780, "total_steps": 2244, "loss": 0.7244, "lr": 5e-06, "epoch": 2.379281537176274, "percentage": 79.32, "elapsed_time": "1 day, 5:00:22", "remaining_time": "7:33:40"}
+{"current_steps": 1790, "total_steps": 2244, "loss": 0.7312, "lr": 5e-06, "epoch": 2.3926482873851294, "percentage": 79.77, "elapsed_time": "1 day, 5:09:59", "remaining_time": "7:23:51"}
+{"current_steps": 1800, "total_steps": 2244, "loss": 0.727, "lr": 5e-06, "epoch": 2.406015037593985, "percentage": 80.21, "elapsed_time": "1 day, 5:19:36", "remaining_time": "7:14:02"}
+{"current_steps": 1810, "total_steps": 2244, "loss": 0.731, "lr": 5e-06, "epoch": 2.4193817878028403, "percentage": 80.66, "elapsed_time": "1 day, 5:29:13", "remaining_time": "7:04:13"}
+{"current_steps": 1820, "total_steps": 2244, "loss": 0.7292, "lr": 5e-06, "epoch": 2.4327485380116958, "percentage": 81.11, "elapsed_time": "1 day, 5:38:50", "remaining_time": "6:54:24"}
+{"current_steps": 1830, "total_steps": 2244, "loss": 0.7295, "lr": 5e-06, "epoch": 2.4461152882205512, "percentage": 81.55, "elapsed_time": "1 day, 5:48:26", "remaining_time": "6:44:36"}
+{"current_steps": 1840, "total_steps": 2244, "loss": 0.7289, "lr": 5e-06, "epoch": 2.4594820384294067, "percentage": 82.0, "elapsed_time": "1 day, 5:58:04", "remaining_time": "6:34:47"}
+{"current_steps": 1850, "total_steps": 2244, "loss": 0.7289, "lr": 5e-06, "epoch": 2.472848788638262, "percentage": 82.44, "elapsed_time": "1 day, 6:07:41", "remaining_time": "6:24:59"}
+{"current_steps": 1860, "total_steps": 2244, "loss": 0.7281, "lr": 5e-06, "epoch": 2.4862155388471177, "percentage": 82.89, "elapsed_time": "1 day, 6:17:18", "remaining_time": "6:15:11"}
+{"current_steps": 1870, "total_steps": 2244, "loss": 0.7296, "lr": 5e-06, "epoch": 2.499582289055973, "percentage": 83.33, "elapsed_time": "1 day, 6:26:56", "remaining_time": "6:05:23"}
+{"current_steps": 1880, "total_steps": 2244, "loss": 0.7296, "lr": 5e-06, "epoch": 2.5129490392648286, "percentage": 83.78, "elapsed_time": "1 day, 6:36:31", "remaining_time": "5:55:35"}
+{"current_steps": 1890, "total_steps": 2244, "loss": 0.7303, "lr": 5e-06, "epoch": 2.526315789473684, "percentage": 84.22, "elapsed_time": "1 day, 6:46:08", "remaining_time": "5:45:47"}
+{"current_steps": 1900, "total_steps": 2244, "loss": 0.7324, "lr": 5e-06, "epoch": 2.5396825396825395, "percentage": 84.67, "elapsed_time": "1 day, 6:55:44", "remaining_time": "5:35:59"}
+{"current_steps": 1910, "total_steps": 2244, "loss": 0.7273, "lr": 5e-06, "epoch": 2.553049289891395, "percentage": 85.12, "elapsed_time": "1 day, 7:05:22", "remaining_time": "5:26:11"}
+{"current_steps": 1920, "total_steps": 2244, "loss": 0.729, "lr": 5e-06, "epoch": 2.5664160401002505, "percentage": 85.56, "elapsed_time": "1 day, 7:14:58", "remaining_time": "5:16:24"}
+{"current_steps": 1930, "total_steps": 2244, "loss": 0.7269, "lr": 5e-06, "epoch": 2.579782790309106, "percentage": 86.01, "elapsed_time": "1 day, 7:24:35", "remaining_time": "5:06:36"}
+{"current_steps": 1940, "total_steps": 2244, "loss": 0.7285, "lr": 5e-06, "epoch": 2.5931495405179614, "percentage": 86.45, "elapsed_time": "1 day, 7:34:11", "remaining_time": "4:56:49"}
+{"current_steps": 1950, "total_steps": 2244, "loss": 0.7292, "lr": 5e-06, "epoch": 2.606516290726817, "percentage": 86.9, "elapsed_time": "1 day, 7:43:48", "remaining_time": "4:47:02"}
+{"current_steps": 1960, "total_steps": 2244, "loss": 0.7264, "lr": 5e-06, "epoch": 2.6198830409356724, "percentage": 87.34, "elapsed_time": "1 day, 7:53:25", "remaining_time": "4:37:15"}
+{"current_steps": 1970, "total_steps": 2244, "loss": 0.7279, "lr": 5e-06, "epoch": 2.633249791144528, "percentage": 87.79, "elapsed_time": "1 day, 8:03:02", "remaining_time": "4:27:28"}
+{"current_steps": 1980, "total_steps": 2244, "loss": 0.7282, "lr": 5e-06, "epoch": 2.6466165413533833, "percentage": 88.24, "elapsed_time": "1 day, 8:12:38", "remaining_time": "4:17:41"}
+{"current_steps": 1990, "total_steps": 2244, "loss": 0.7331, "lr": 5e-06, "epoch": 2.659983291562239, "percentage": 88.68, "elapsed_time": "1 day, 8:22:14", "remaining_time": "4:07:54"}
+{"current_steps": 2000, "total_steps": 2244, "loss": 0.7296, "lr": 5e-06, "epoch": 2.6733500417710943, "percentage": 89.13, "elapsed_time": "1 day, 8:31:51", "remaining_time": "3:58:07"}
+{"current_steps": 2010, "total_steps": 2244, "loss": 0.7298, "lr": 5e-06, "epoch": 2.6867167919799497, "percentage": 89.57, "elapsed_time": "1 day, 8:41:28", "remaining_time": "3:48:21"}
+{"current_steps": 2020, "total_steps": 2244, "loss": 0.7268, "lr": 5e-06, "epoch": 2.700083542188805, "percentage": 90.02, "elapsed_time": "1 day, 8:51:04", "remaining_time": "3:38:34"}
+{"current_steps": 2030, "total_steps": 2244, "loss": 0.7277, "lr": 5e-06, "epoch": 2.7134502923976607, "percentage": 90.46, "elapsed_time": "1 day, 9:00:41", "remaining_time": "3:28:48"}
+{"current_steps": 2040, "total_steps": 2244, "loss": 0.7298, "lr": 5e-06, "epoch": 2.726817042606516, "percentage": 90.91, "elapsed_time": "1 day, 9:10:17", "remaining_time": "3:19:01"}
+{"current_steps": 2050, "total_steps": 2244, "loss": 0.7325, "lr": 5e-06, "epoch": 2.7401837928153716, "percentage": 91.35, "elapsed_time": "1 day, 9:19:54", "remaining_time": "3:09:15"}
+{"current_steps": 2060, "total_steps": 2244, "loss": 0.7296, "lr": 5e-06, "epoch": 2.753550543024227, "percentage": 91.8, "elapsed_time": "1 day, 9:29:29", "remaining_time": "2:59:29"}
+{"current_steps": 2070, "total_steps": 2244, "loss": 0.7281, "lr": 5e-06, "epoch": 2.7669172932330826, "percentage": 92.25, "elapsed_time": "1 day, 9:39:05", "remaining_time": "2:49:43"}
+{"current_steps": 2080, "total_steps": 2244, "loss": 0.7294, "lr": 5e-06, "epoch": 2.780284043441938, "percentage": 92.69, "elapsed_time": "1 day, 9:48:42", "remaining_time": "2:39:57"}
+{"current_steps": 2090, "total_steps": 2244, "loss": 0.7248, "lr": 5e-06, "epoch": 2.7936507936507935, "percentage": 93.14, "elapsed_time": "1 day, 9:58:18", "remaining_time": "2:30:11"}
+{"current_steps": 2100, "total_steps": 2244, "loss": 0.7311, "lr": 5e-06, "epoch": 2.807017543859649, "percentage": 93.58, "elapsed_time": "1 day, 10:07:55", "remaining_time": "2:20:25"}
+{"current_steps": 2110, "total_steps": 2244, "loss": 0.7318, "lr": 5e-06, "epoch": 2.8203842940685044, "percentage": 94.03, "elapsed_time": "1 day, 10:17:32", "remaining_time": "2:10:40"}
+{"current_steps": 2120, "total_steps": 2244, "loss": 0.7336, "lr": 5e-06, "epoch": 2.83375104427736, "percentage": 94.47, "elapsed_time": "1 day, 10:27:09", "remaining_time": "2:00:54"}
+{"current_steps": 2130, "total_steps": 2244, "loss": 0.731, "lr": 5e-06, "epoch": 2.8471177944862154, "percentage": 94.92, "elapsed_time": "1 day, 10:36:46", "remaining_time": "1:51:09"}
+{"current_steps": 2140, "total_steps": 2244, "loss": 0.7282, "lr": 5e-06, "epoch": 2.860484544695071, "percentage": 95.37, "elapsed_time": "1 day, 10:46:23", "remaining_time": "1:41:23"}
+{"current_steps": 2150, "total_steps": 2244, "loss": 0.7335, "lr": 5e-06, "epoch": 2.8738512949039263, "percentage": 95.81, "elapsed_time": "1 day, 10:56:00", "remaining_time": "1:31:38"}
+{"current_steps": 2160, "total_steps": 2244, "loss": 0.7273, "lr": 5e-06, "epoch": 2.887218045112782, "percentage": 96.26, "elapsed_time": "1 day, 11:05:36", "remaining_time": "1:21:53"}
+{"current_steps": 2170, "total_steps": 2244, "loss": 0.7332, "lr": 5e-06, "epoch": 2.9005847953216373, "percentage": 96.7, "elapsed_time": "1 day, 11:15:13", "remaining_time": "1:12:07"}
+{"current_steps": 2180, "total_steps": 2244, "loss": 0.7306, "lr": 5e-06, "epoch": 2.9139515455304927, "percentage": 97.15, "elapsed_time": "1 day, 11:24:50", "remaining_time": "1:02:22"}
+{"current_steps": 2190, "total_steps": 2244, "loss": 0.7314, "lr": 5e-06, "epoch": 2.927318295739348, "percentage": 97.59, "elapsed_time": "1 day, 11:34:27", "remaining_time": "0:52:37"}
+{"current_steps": 2200, "total_steps": 2244, "loss": 0.7298, "lr": 5e-06, "epoch": 2.9406850459482037, "percentage": 98.04, "elapsed_time": "1 day, 11:44:04", "remaining_time": "0:42:52"}
+{"current_steps": 2210, "total_steps": 2244, "loss": 0.731, "lr": 5e-06, "epoch": 2.954051796157059, "percentage": 98.48, "elapsed_time": "1 day, 11:53:40", "remaining_time": "0:33:08"}
+{"current_steps": 2220, "total_steps": 2244, "loss": 0.7322, "lr": 5e-06, "epoch": 2.9674185463659146, "percentage": 98.93, "elapsed_time": "1 day, 12:03:17", "remaining_time": "0:23:23"}
+{"current_steps": 2230, "total_steps": 2244, "loss": 0.7269, "lr": 5e-06, "epoch": 2.98078529657477, "percentage": 99.38, "elapsed_time": "1 day, 12:12:53", "remaining_time": "0:13:38"}
+{"current_steps": 2240, "total_steps": 2244, "loss": 0.7322, "lr": 5e-06, "epoch": 2.9941520467836256, "percentage": 99.82, "elapsed_time": "1 day, 12:22:30", "remaining_time": "0:03:53"}