Training in progress, epoch 5
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 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f89dffc341f91f2e09759a6140f741c5759f7bb8999c06f76e33bddf63c5780
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adbde6e2fb003099b51a6e036a8249ffb28316d193326ba0c845ef205dd465c6
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93c2e6d7ab19312ee2287600ccd4db049957b16cd400e49845b44140b8eb239
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d76ca0e49669439cfb1c1226cf85c6ae85d14f6b62f97725d0db0180eb3befb0
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -178,3 +178,48 @@
|
|
| 178 |
{"current_steps": 1750, "total_steps": 2195, "loss": 0.5461, "lr": 5e-06, "epoch": 3.9863325740318905, "percentage": 79.73, "elapsed_time": "6:42:22", "remaining_time": "1:42:18"}
|
| 179 |
{"current_steps": 1756, "total_steps": 2195, "eval_loss": 0.6239981055259705, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "6:45:35", "remaining_time": "1:41:23"}
|
| 180 |
{"current_steps": 1760, "total_steps": 2195, "loss": 0.5355, "lr": 5e-06, "epoch": 4.009111617312073, "percentage": 80.18, "elapsed_time": "6:47:20", "remaining_time": "1:40:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
{"current_steps": 1750, "total_steps": 2195, "loss": 0.5461, "lr": 5e-06, "epoch": 3.9863325740318905, "percentage": 79.73, "elapsed_time": "6:42:22", "remaining_time": "1:42:18"}
|
| 179 |
{"current_steps": 1756, "total_steps": 2195, "eval_loss": 0.6239981055259705, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "6:45:35", "remaining_time": "1:41:23"}
|
| 180 |
{"current_steps": 1760, "total_steps": 2195, "loss": 0.5355, "lr": 5e-06, "epoch": 4.009111617312073, "percentage": 80.18, "elapsed_time": "6:47:20", "remaining_time": "1:40:40"}
|
| 181 |
+
{"current_steps": 1770, "total_steps": 2195, "loss": 0.5112, "lr": 5e-06, "epoch": 4.031890660592255, "percentage": 80.64, "elapsed_time": "6:49:35", "remaining_time": "1:38:20"}
|
| 182 |
+
{"current_steps": 1780, "total_steps": 2195, "loss": 0.5155, "lr": 5e-06, "epoch": 4.054669703872437, "percentage": 81.09, "elapsed_time": "6:51:50", "remaining_time": "1:36:01"}
|
| 183 |
+
{"current_steps": 1790, "total_steps": 2195, "loss": 0.5107, "lr": 5e-06, "epoch": 4.077448747152619, "percentage": 81.55, "elapsed_time": "6:54:05", "remaining_time": "1:33:41"}
|
| 184 |
+
{"current_steps": 1800, "total_steps": 2195, "loss": 0.5168, "lr": 5e-06, "epoch": 4.100227790432802, "percentage": 82.0, "elapsed_time": "6:56:21", "remaining_time": "1:31:21"}
|
| 185 |
+
{"current_steps": 1810, "total_steps": 2195, "loss": 0.5126, "lr": 5e-06, "epoch": 4.123006833712984, "percentage": 82.46, "elapsed_time": "6:58:36", "remaining_time": "1:29:02"}
|
| 186 |
+
{"current_steps": 1820, "total_steps": 2195, "loss": 0.5134, "lr": 5e-06, "epoch": 4.145785876993166, "percentage": 82.92, "elapsed_time": "7:00:51", "remaining_time": "1:26:42"}
|
| 187 |
+
{"current_steps": 1830, "total_steps": 2195, "loss": 0.5093, "lr": 5e-06, "epoch": 4.168564920273348, "percentage": 83.37, "elapsed_time": "7:03:06", "remaining_time": "1:24:23"}
|
| 188 |
+
{"current_steps": 1840, "total_steps": 2195, "loss": 0.5174, "lr": 5e-06, "epoch": 4.191343963553531, "percentage": 83.83, "elapsed_time": "7:05:21", "remaining_time": "1:22:03"}
|
| 189 |
+
{"current_steps": 1850, "total_steps": 2195, "loss": 0.5172, "lr": 5e-06, "epoch": 4.214123006833713, "percentage": 84.28, "elapsed_time": "7:07:36", "remaining_time": "1:19:44"}
|
| 190 |
+
{"current_steps": 1860, "total_steps": 2195, "loss": 0.5121, "lr": 5e-06, "epoch": 4.236902050113895, "percentage": 84.74, "elapsed_time": "7:09:52", "remaining_time": "1:17:25"}
|
| 191 |
+
{"current_steps": 1870, "total_steps": 2195, "loss": 0.5101, "lr": 5e-06, "epoch": 4.259681093394078, "percentage": 85.19, "elapsed_time": "7:12:07", "remaining_time": "1:15:06"}
|
| 192 |
+
{"current_steps": 1880, "total_steps": 2195, "loss": 0.5144, "lr": 5e-06, "epoch": 4.28246013667426, "percentage": 85.65, "elapsed_time": "7:14:22", "remaining_time": "1:12:46"}
|
| 193 |
+
{"current_steps": 1890, "total_steps": 2195, "loss": 0.517, "lr": 5e-06, "epoch": 4.305239179954442, "percentage": 86.1, "elapsed_time": "7:16:38", "remaining_time": "1:10:27"}
|
| 194 |
+
{"current_steps": 1900, "total_steps": 2195, "loss": 0.5163, "lr": 5e-06, "epoch": 4.328018223234624, "percentage": 86.56, "elapsed_time": "7:18:53", "remaining_time": "1:08:08"}
|
| 195 |
+
{"current_steps": 1910, "total_steps": 2195, "loss": 0.517, "lr": 5e-06, "epoch": 4.350797266514807, "percentage": 87.02, "elapsed_time": "7:21:09", "remaining_time": "1:05:49"}
|
| 196 |
+
{"current_steps": 1920, "total_steps": 2195, "loss": 0.5148, "lr": 5e-06, "epoch": 4.373576309794989, "percentage": 87.47, "elapsed_time": "7:23:24", "remaining_time": "1:03:30"}
|
| 197 |
+
{"current_steps": 1930, "total_steps": 2195, "loss": 0.5167, "lr": 5e-06, "epoch": 4.396355353075171, "percentage": 87.93, "elapsed_time": "7:25:39", "remaining_time": "1:01:11"}
|
| 198 |
+
{"current_steps": 1940, "total_steps": 2195, "loss": 0.51, "lr": 5e-06, "epoch": 4.4191343963553535, "percentage": 88.38, "elapsed_time": "7:27:54", "remaining_time": "0:58:52"}
|
| 199 |
+
{"current_steps": 1950, "total_steps": 2195, "loss": 0.5172, "lr": 5e-06, "epoch": 4.4419134396355355, "percentage": 88.84, "elapsed_time": "7:30:10", "remaining_time": "0:56:33"}
|
| 200 |
+
{"current_steps": 1960, "total_steps": 2195, "loss": 0.5134, "lr": 5e-06, "epoch": 4.4646924829157175, "percentage": 89.29, "elapsed_time": "7:32:25", "remaining_time": "0:54:14"}
|
| 201 |
+
{"current_steps": 1970, "total_steps": 2195, "loss": 0.5123, "lr": 5e-06, "epoch": 4.4874715261958995, "percentage": 89.75, "elapsed_time": "7:34:40", "remaining_time": "0:51:55"}
|
| 202 |
+
{"current_steps": 1980, "total_steps": 2195, "loss": 0.5177, "lr": 5e-06, "epoch": 4.510250569476082, "percentage": 90.21, "elapsed_time": "7:36:56", "remaining_time": "0:49:37"}
|
| 203 |
+
{"current_steps": 1990, "total_steps": 2195, "loss": 0.5095, "lr": 5e-06, "epoch": 4.533029612756264, "percentage": 90.66, "elapsed_time": "7:39:11", "remaining_time": "0:47:18"}
|
| 204 |
+
{"current_steps": 2000, "total_steps": 2195, "loss": 0.5126, "lr": 5e-06, "epoch": 4.555808656036446, "percentage": 91.12, "elapsed_time": "7:41:26", "remaining_time": "0:44:59"}
|
| 205 |
+
{"current_steps": 2010, "total_steps": 2195, "loss": 0.516, "lr": 5e-06, "epoch": 4.578587699316628, "percentage": 91.57, "elapsed_time": "7:43:41", "remaining_time": "0:42:40"}
|
| 206 |
+
{"current_steps": 2020, "total_steps": 2195, "loss": 0.516, "lr": 5e-06, "epoch": 4.601366742596811, "percentage": 92.03, "elapsed_time": "7:45:57", "remaining_time": "0:40:22"}
|
| 207 |
+
{"current_steps": 2030, "total_steps": 2195, "loss": 0.5159, "lr": 5e-06, "epoch": 4.624145785876993, "percentage": 92.48, "elapsed_time": "7:48:12", "remaining_time": "0:38:03"}
|
| 208 |
+
{"current_steps": 2040, "total_steps": 2195, "loss": 0.5103, "lr": 5e-06, "epoch": 4.646924829157175, "percentage": 92.94, "elapsed_time": "7:50:27", "remaining_time": "0:35:44"}
|
| 209 |
+
{"current_steps": 2050, "total_steps": 2195, "loss": 0.526, "lr": 5e-06, "epoch": 4.669703872437358, "percentage": 93.39, "elapsed_time": "7:52:42", "remaining_time": "0:33:26"}
|
| 210 |
+
{"current_steps": 2060, "total_steps": 2195, "loss": 0.5205, "lr": 5e-06, "epoch": 4.69248291571754, "percentage": 93.85, "elapsed_time": "7:54:58", "remaining_time": "0:31:07"}
|
| 211 |
+
{"current_steps": 2070, "total_steps": 2195, "loss": 0.5128, "lr": 5e-06, "epoch": 4.715261958997722, "percentage": 94.31, "elapsed_time": "7:57:13", "remaining_time": "0:28:49"}
|
| 212 |
+
{"current_steps": 2080, "total_steps": 2195, "loss": 0.5195, "lr": 5e-06, "epoch": 4.738041002277904, "percentage": 94.76, "elapsed_time": "7:59:28", "remaining_time": "0:26:30"}
|
| 213 |
+
{"current_steps": 2090, "total_steps": 2195, "loss": 0.5192, "lr": 5e-06, "epoch": 4.760820045558087, "percentage": 95.22, "elapsed_time": "8:01:43", "remaining_time": "0:24:12"}
|
| 214 |
+
{"current_steps": 2100, "total_steps": 2195, "loss": 0.5155, "lr": 5e-06, "epoch": 4.783599088838269, "percentage": 95.67, "elapsed_time": "8:03:59", "remaining_time": "0:21:53"}
|
| 215 |
+
{"current_steps": 2110, "total_steps": 2195, "loss": 0.5157, "lr": 5e-06, "epoch": 4.806378132118451, "percentage": 96.13, "elapsed_time": "8:06:14", "remaining_time": "0:19:35"}
|
| 216 |
+
{"current_steps": 2120, "total_steps": 2195, "loss": 0.515, "lr": 5e-06, "epoch": 4.829157175398633, "percentage": 96.58, "elapsed_time": "8:08:29", "remaining_time": "0:17:16"}
|
| 217 |
+
{"current_steps": 2130, "total_steps": 2195, "loss": 0.52, "lr": 5e-06, "epoch": 4.851936218678816, "percentage": 97.04, "elapsed_time": "8:10:44", "remaining_time": "0:14:58"}
|
| 218 |
+
{"current_steps": 2140, "total_steps": 2195, "loss": 0.5214, "lr": 5e-06, "epoch": 4.874715261958998, "percentage": 97.49, "elapsed_time": "8:13:00", "remaining_time": "0:12:40"}
|
| 219 |
+
{"current_steps": 2150, "total_steps": 2195, "loss": 0.5141, "lr": 5e-06, "epoch": 4.89749430523918, "percentage": 97.95, "elapsed_time": "8:15:15", "remaining_time": "0:10:21"}
|
| 220 |
+
{"current_steps": 2160, "total_steps": 2195, "loss": 0.5191, "lr": 5e-06, "epoch": 4.920273348519363, "percentage": 98.41, "elapsed_time": "8:17:30", "remaining_time": "0:08:03"}
|
| 221 |
+
{"current_steps": 2170, "total_steps": 2195, "loss": 0.5204, "lr": 5e-06, "epoch": 4.943052391799545, "percentage": 98.86, "elapsed_time": "8:19:45", "remaining_time": "0:05:45"}
|
| 222 |
+
{"current_steps": 2180, "total_steps": 2195, "loss": 0.5214, "lr": 5e-06, "epoch": 4.965831435079727, "percentage": 99.32, "elapsed_time": "8:22:01", "remaining_time": "0:03:27"}
|
| 223 |
+
{"current_steps": 2190, "total_steps": 2195, "loss": 0.5179, "lr": 5e-06, "epoch": 4.988610478359909, "percentage": 99.77, "elapsed_time": "8:24:16", "remaining_time": "0:01:09"}
|
| 224 |
+
{"current_steps": 2195, "total_steps": 2195, "eval_loss": 0.6346195340156555, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:28:05", "remaining_time": "0:00:00"}
|
| 225 |
+
{"current_steps": 2195, "total_steps": 2195, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:28:48", "remaining_time": "0:00:00"}
|