Training in progress, step 5600
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b8cfe20dd8bcd089497b4d88d4b19036aa3dd4b65211202a75a9a28557f4593
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bb188549ca35f2d3ea370588b48938caef1e22280885a0c01a71e524e82b9cb
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db77797b328fff13a85cd9cb99a0f14c52f6baf76c07b139b7e707c2f5e50282
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d70badeae6182bebeec6a269efb9f15b2acfa76824c641b9277990b12fa4e41
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1101,3 +1101,43 @@
|
|
| 1101 |
{"current_steps": 5390, "total_steps": 6713, "loss": 0.1872, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "18:23:13", "remaining_time": "4:30:47"}
|
| 1102 |
{"current_steps": 5395, "total_steps": 6713, "loss": 0.2032, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "18:24:52", "remaining_time": "4:29:55"}
|
| 1103 |
{"current_steps": 5400, "total_steps": 6713, "loss": 0.1975, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "18:26:36", "remaining_time": "4:29:04"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1101 |
{"current_steps": 5390, "total_steps": 6713, "loss": 0.1872, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "18:23:13", "remaining_time": "4:30:47"}
|
| 1102 |
{"current_steps": 5395, "total_steps": 6713, "loss": 0.2032, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "18:24:52", "remaining_time": "4:29:55"}
|
| 1103 |
{"current_steps": 5400, "total_steps": 6713, "loss": 0.1975, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "18:26:36", "remaining_time": "4:29:04"}
|
| 1104 |
+
{"current_steps": 5405, "total_steps": 6713, "loss": 0.1926, "lr": 4.4578444411505005e-06, "epoch": 5.6374543557642145, "percentage": 80.52, "elapsed_time": "18:29:48", "remaining_time": "4:28:34"}
|
| 1105 |
+
{"current_steps": 5410, "total_steps": 6713, "loss": 0.199, "lr": 4.425167066906777e-06, "epoch": 5.642670839853938, "percentage": 80.59, "elapsed_time": "18:31:29", "remaining_time": "4:27:42"}
|
| 1106 |
+
{"current_steps": 5415, "total_steps": 6713, "loss": 0.1988, "lr": 4.392594996751891e-06, "epoch": 5.647887323943662, "percentage": 80.66, "elapsed_time": "18:33:11", "remaining_time": "4:26:50"}
|
| 1107 |
+
{"current_steps": 5420, "total_steps": 6713, "loss": 0.1954, "lr": 4.360128450911154e-06, "epoch": 5.653103808033386, "percentage": 80.74, "elapsed_time": "18:34:54", "remaining_time": "4:25:58"}
|
| 1108 |
+
{"current_steps": 5425, "total_steps": 6713, "loss": 0.2027, "lr": 4.3277676488963775e-06, "epoch": 5.6583202921231095, "percentage": 80.81, "elapsed_time": "18:36:31", "remaining_time": "4:25:05"}
|
| 1109 |
+
{"current_steps": 5430, "total_steps": 6713, "loss": 0.1887, "lr": 4.295512809504447e-06, "epoch": 5.663536776212832, "percentage": 80.89, "elapsed_time": "18:38:16", "remaining_time": "4:24:13"}
|
| 1110 |
+
{"current_steps": 5435, "total_steps": 6713, "loss": 0.1859, "lr": 4.263364150815803e-06, "epoch": 5.668753260302556, "percentage": 80.96, "elapsed_time": "18:39:56", "remaining_time": "4:23:20"}
|
| 1111 |
+
{"current_steps": 5440, "total_steps": 6713, "loss": 0.1895, "lr": 4.231321890192981e-06, "epoch": 5.67396974439228, "percentage": 81.04, "elapsed_time": "18:41:34", "remaining_time": "4:22:27"}
|
| 1112 |
+
{"current_steps": 5445, "total_steps": 6713, "loss": 0.192, "lr": 4.19938624427914e-06, "epoch": 5.679186228482003, "percentage": 81.11, "elapsed_time": "18:43:18", "remaining_time": "4:21:35"}
|
| 1113 |
+
{"current_steps": 5450, "total_steps": 6713, "loss": 0.1963, "lr": 4.167557428996611e-06, "epoch": 5.6844027125717265, "percentage": 81.19, "elapsed_time": "18:45:00", "remaining_time": "4:20:42"}
|
| 1114 |
+
{"current_steps": 5455, "total_steps": 6713, "loss": 0.2006, "lr": 4.135835659545406e-06, "epoch": 5.68961919666145, "percentage": 81.26, "elapsed_time": "18:46:48", "remaining_time": "4:19:51"}
|
| 1115 |
+
{"current_steps": 5460, "total_steps": 6713, "loss": 0.1947, "lr": 4.104221150401806e-06, "epoch": 5.694835680751174, "percentage": 81.33, "elapsed_time": "18:48:34", "remaining_time": "4:18:59"}
|
| 1116 |
+
{"current_steps": 5465, "total_steps": 6713, "loss": 0.1989, "lr": 4.072714115316863e-06, "epoch": 5.700052164840898, "percentage": 81.41, "elapsed_time": "18:50:19", "remaining_time": "4:18:07"}
|
| 1117 |
+
{"current_steps": 5470, "total_steps": 6713, "loss": 0.2002, "lr": 4.041314767314983e-06, "epoch": 5.705268648930621, "percentage": 81.48, "elapsed_time": "18:52:00", "remaining_time": "4:17:14"}
|
| 1118 |
+
{"current_steps": 5475, "total_steps": 6713, "loss": 0.1955, "lr": 4.010023318692502e-06, "epoch": 5.710485133020344, "percentage": 81.56, "elapsed_time": "18:53:40", "remaining_time": "4:16:20"}
|
| 1119 |
+
{"current_steps": 5480, "total_steps": 6713, "loss": 0.1923, "lr": 3.978839981016203e-06, "epoch": 5.715701617110068, "percentage": 81.63, "elapsed_time": "18:55:24", "remaining_time": "4:15:28"}
|
| 1120 |
+
{"current_steps": 5485, "total_steps": 6713, "loss": 0.1829, "lr": 3.947764965121934e-06, "epoch": 5.720918101199791, "percentage": 81.71, "elapsed_time": "18:57:03", "remaining_time": "4:14:34"}
|
| 1121 |
+
{"current_steps": 5490, "total_steps": 6713, "loss": 0.1833, "lr": 3.916798481113144e-06, "epoch": 5.726134585289515, "percentage": 81.78, "elapsed_time": "18:58:41", "remaining_time": "4:13:39"}
|
| 1122 |
+
{"current_steps": 5495, "total_steps": 6713, "loss": 0.1809, "lr": 3.885940738359492e-06, "epoch": 5.731351069379238, "percentage": 81.86, "elapsed_time": "19:00:22", "remaining_time": "4:12:46"}
|
| 1123 |
+
{"current_steps": 5500, "total_steps": 6713, "loss": 0.1799, "lr": 3.855191945495405e-06, "epoch": 5.736567553468962, "percentage": 81.93, "elapsed_time": "19:02:02", "remaining_time": "4:11:52"}
|
| 1124 |
+
{"current_steps": 5505, "total_steps": 6713, "loss": 0.1784, "lr": 3.824552310418703e-06, "epoch": 5.741784037558686, "percentage": 82.01, "elapsed_time": "19:03:42", "remaining_time": "4:10:58"}
|
| 1125 |
+
{"current_steps": 5510, "total_steps": 6713, "loss": 0.1922, "lr": 3.794022040289147e-06, "epoch": 5.747000521648409, "percentage": 82.08, "elapsed_time": "19:05:21", "remaining_time": "4:10:03"}
|
| 1126 |
+
{"current_steps": 5515, "total_steps": 6713, "loss": 0.2045, "lr": 3.763601341527088e-06, "epoch": 5.7522170057381325, "percentage": 82.15, "elapsed_time": "19:07:01", "remaining_time": "4:09:09"}
|
| 1127 |
+
{"current_steps": 5520, "total_steps": 6713, "loss": 0.1853, "lr": 3.733290419812019e-06, "epoch": 5.757433489827856, "percentage": 82.23, "elapsed_time": "19:08:37", "remaining_time": "4:08:14"}
|
| 1128 |
+
{"current_steps": 5525, "total_steps": 6713, "loss": 0.1998, "lr": 3.7030894800812365e-06, "epoch": 5.762649973917579, "percentage": 82.3, "elapsed_time": "19:10:19", "remaining_time": "4:07:20"}
|
| 1129 |
+
{"current_steps": 5530, "total_steps": 6713, "loss": 0.1863, "lr": 3.672998726528414e-06, "epoch": 5.767866458007303, "percentage": 82.38, "elapsed_time": "19:12:03", "remaining_time": "4:06:27"}
|
| 1130 |
+
{"current_steps": 5535, "total_steps": 6713, "loss": 0.1897, "lr": 3.6430183626022574e-06, "epoch": 5.773082942097027, "percentage": 82.45, "elapsed_time": "19:13:49", "remaining_time": "4:05:33"}
|
| 1131 |
+
{"current_steps": 5540, "total_steps": 6713, "loss": 0.1903, "lr": 3.613148591005071e-06, "epoch": 5.77829942618675, "percentage": 82.53, "elapsed_time": "19:15:32", "remaining_time": "4:04:39"}
|
| 1132 |
+
{"current_steps": 5545, "total_steps": 6713, "loss": 0.1867, "lr": 3.5833896136914705e-06, "epoch": 5.783515910276473, "percentage": 82.6, "elapsed_time": "19:17:15", "remaining_time": "4:03:45"}
|
| 1133 |
+
{"current_steps": 5550, "total_steps": 6713, "loss": 0.1901, "lr": 3.553741631866938e-06, "epoch": 5.788732394366197, "percentage": 82.68, "elapsed_time": "19:18:49", "remaining_time": "4:02:49"}
|
| 1134 |
+
{"current_steps": 5555, "total_steps": 6713, "loss": 0.1862, "lr": 3.524204845986523e-06, "epoch": 5.793948878455921, "percentage": 82.75, "elapsed_time": "19:20:32", "remaining_time": "4:01:55"}
|
| 1135 |
+
{"current_steps": 5560, "total_steps": 6713, "loss": 0.1934, "lr": 3.494779455753443e-06, "epoch": 5.7991653625456445, "percentage": 82.82, "elapsed_time": "19:22:13", "remaining_time": "4:01:00"}
|
| 1136 |
+
{"current_steps": 5565, "total_steps": 6713, "loss": 0.2057, "lr": 3.4654656601177482e-06, "epoch": 5.804381846635367, "percentage": 82.9, "elapsed_time": "19:23:52", "remaining_time": "4:00:05"}
|
| 1137 |
+
{"current_steps": 5570, "total_steps": 6713, "loss": 0.1935, "lr": 3.4362636572749984e-06, "epoch": 5.809598330725091, "percentage": 82.97, "elapsed_time": "19:25:34", "remaining_time": "3:59:10"}
|
| 1138 |
+
{"current_steps": 5575, "total_steps": 6713, "loss": 0.2102, "lr": 3.4071736446648805e-06, "epoch": 5.814814814814815, "percentage": 83.05, "elapsed_time": "19:27:12", "remaining_time": "3:58:15"}
|
| 1139 |
+
{"current_steps": 5580, "total_steps": 6713, "loss": 0.1884, "lr": 3.3781958189699183e-06, "epoch": 5.820031298904539, "percentage": 83.12, "elapsed_time": "19:28:48", "remaining_time": "3:57:19"}
|
| 1140 |
+
{"current_steps": 5585, "total_steps": 6713, "loss": 0.2111, "lr": 3.3493303761141016e-06, "epoch": 5.8252477829942615, "percentage": 83.2, "elapsed_time": "19:30:33", "remaining_time": "3:56:25"}
|
| 1141 |
+
{"current_steps": 5590, "total_steps": 6713, "loss": 0.2034, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "19:32:14", "remaining_time": "3:55:29"}
|
| 1142 |
+
{"current_steps": 5595, "total_steps": 6713, "loss": 0.1948, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "19:33:53", "remaining_time": "3:54:34"}
|
| 1143 |
+
{"current_steps": 5600, "total_steps": 6713, "loss": 0.1961, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "19:35:37", "remaining_time": "3:53:39"}
|