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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bed61f211a1137d74901da36a668a46ea399cbb28fd255eb8202d03d9df3694
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1e24ecf73810c7ac51559caae1732749eac9ab31833e709c33cb4bcea3292eb
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5162cf016739816f3dd1418e66c32106f1d17a06b18e763d6d8cc3fcb7715cd
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2b520cda03ca14c586d88f2ac07e31844d3010fc728e4ea922a307b4a6add5e
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -277,3 +277,40 @@
|
|
277 |
{"current_steps": 277, "total_steps": 315, "loss": 0.0551, "lr": 3.9326701979281623e-07, "epoch": 4.396825396825397, "percentage": 87.94, "elapsed_time": "0:26:18", "remaining_time": "0:03:36"}
|
278 |
{"current_steps": 278, "total_steps": 315, "loss": 0.0281, "lr": 3.7309911204858997e-07, "epoch": 4.412698412698413, "percentage": 88.25, "elapsed_time": "0:26:22", "remaining_time": "0:03:30"}
|
279 |
{"current_steps": 279, "total_steps": 315, "loss": 0.0404, "lr": 3.534419956965823e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "0:26:27", "remaining_time": "0:03:24"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
277 |
{"current_steps": 277, "total_steps": 315, "loss": 0.0551, "lr": 3.9326701979281623e-07, "epoch": 4.396825396825397, "percentage": 87.94, "elapsed_time": "0:26:18", "remaining_time": "0:03:36"}
|
278 |
{"current_steps": 278, "total_steps": 315, "loss": 0.0281, "lr": 3.7309911204858997e-07, "epoch": 4.412698412698413, "percentage": 88.25, "elapsed_time": "0:26:22", "remaining_time": "0:03:30"}
|
279 |
{"current_steps": 279, "total_steps": 315, "loss": 0.0404, "lr": 3.534419956965823e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "0:26:27", "remaining_time": "0:03:24"}
|
280 |
+
{"current_steps": 280, "total_steps": 315, "loss": 0.0379, "lr": 3.3429784080398765e-07, "epoch": 4.444444444444445, "percentage": 88.89, "elapsed_time": "0:26:32", "remaining_time": "0:03:19"}
|
281 |
+
{"current_steps": 281, "total_steps": 315, "loss": 0.0542, "lr": 3.1566876080910193e-07, "epoch": 4.4603174603174605, "percentage": 89.21, "elapsed_time": "0:26:37", "remaining_time": "0:03:13"}
|
282 |
+
{"current_steps": 282, "total_steps": 315, "loss": 0.0273, "lr": 2.9755681228800904e-07, "epoch": 4.476190476190476, "percentage": 89.52, "elapsed_time": "0:26:41", "remaining_time": "0:03:07"}
|
283 |
+
{"current_steps": 283, "total_steps": 315, "loss": 0.0308, "lr": 2.799639947275412e-07, "epoch": 4.492063492063492, "percentage": 89.84, "elapsed_time": "0:26:46", "remaining_time": "0:03:01"}
|
284 |
+
{"current_steps": 284, "total_steps": 315, "loss": 0.0328, "lr": 2.6289225030454556e-07, "epoch": 4.507936507936508, "percentage": 90.16, "elapsed_time": "0:26:51", "remaining_time": "0:02:55"}
|
285 |
+
{"current_steps": 285, "total_steps": 315, "loss": 0.0505, "lr": 2.4634346367147233e-07, "epoch": 4.523809523809524, "percentage": 90.48, "elapsed_time": "0:26:56", "remaining_time": "0:02:50"}
|
286 |
+
{"current_steps": 286, "total_steps": 315, "loss": 0.0309, "lr": 2.303194617483212e-07, "epoch": 4.5396825396825395, "percentage": 90.79, "elapsed_time": "0:27:01", "remaining_time": "0:02:44"}
|
287 |
+
{"current_steps": 287, "total_steps": 315, "loss": 0.0425, "lr": 2.1482201352095277e-07, "epoch": 4.555555555555555, "percentage": 91.11, "elapsed_time": "0:27:06", "remaining_time": "0:02:38"}
|
288 |
+
{"current_steps": 288, "total_steps": 315, "loss": 0.041, "lr": 1.998528298458019e-07, "epoch": 4.571428571428571, "percentage": 91.43, "elapsed_time": "0:27:11", "remaining_time": "0:02:32"}
|
289 |
+
{"current_steps": 289, "total_steps": 315, "loss": 0.0363, "lr": 1.8541356326100436e-07, "epoch": 4.587301587301587, "percentage": 91.75, "elapsed_time": "0:27:15", "remaining_time": "0:02:27"}
|
290 |
+
{"current_steps": 290, "total_steps": 315, "loss": 0.0589, "lr": 1.7150580780396385e-07, "epoch": 4.603174603174603, "percentage": 92.06, "elapsed_time": "0:27:20", "remaining_time": "0:02:21"}
|
291 |
+
{"current_steps": 291, "total_steps": 315, "loss": 0.0441, "lr": 1.5813109883537792e-07, "epoch": 4.619047619047619, "percentage": 92.38, "elapsed_time": "0:27:25", "remaining_time": "0:02:15"}
|
292 |
+
{"current_steps": 292, "total_steps": 315, "loss": 0.0407, "lr": 1.4529091286973994e-07, "epoch": 4.634920634920634, "percentage": 92.7, "elapsed_time": "0:27:30", "remaining_time": "0:02:10"}
|
293 |
+
{"current_steps": 293, "total_steps": 315, "loss": 0.0314, "lr": 1.3298666741233424e-07, "epoch": 4.650793650793651, "percentage": 93.02, "elapsed_time": "0:27:35", "remaining_time": "0:02:04"}
|
294 |
+
{"current_steps": 294, "total_steps": 315, "loss": 0.0287, "lr": 1.2121972080275378e-07, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "0:27:40", "remaining_time": "0:01:58"}
|
295 |
+
{"current_steps": 295, "total_steps": 315, "loss": 0.0492, "lr": 1.0999137206494315e-07, "epoch": 4.682539682539683, "percentage": 93.65, "elapsed_time": "0:27:45", "remaining_time": "0:01:52"}
|
296 |
+
{"current_steps": 296, "total_steps": 315, "loss": 0.0461, "lr": 9.93028607637908e-08, "epoch": 4.698412698412699, "percentage": 93.97, "elapsed_time": "0:27:50", "remaining_time": "0:01:47"}
|
297 |
+
{"current_steps": 297, "total_steps": 315, "loss": 0.0402, "lr": 8.915536686828764e-08, "epoch": 4.714285714285714, "percentage": 94.29, "elapsed_time": "0:27:55", "remaining_time": "0:01:41"}
|
298 |
+
{"current_steps": 298, "total_steps": 315, "loss": 0.0346, "lr": 7.955001062125989e-08, "epoch": 4.73015873015873, "percentage": 94.6, "elapsed_time": "0:28:00", "remaining_time": "0:01:35"}
|
299 |
+
{"current_steps": 299, "total_steps": 315, "loss": 0.0385, "lr": 7.048785241570321e-08, "epoch": 4.746031746031746, "percentage": 94.92, "elapsed_time": "0:28:05", "remaining_time": "0:01:30"}
|
300 |
+
{"current_steps": 300, "total_steps": 315, "loss": 0.0473, "lr": 6.19698926777168e-08, "epoch": 4.761904761904762, "percentage": 95.24, "elapsed_time": "0:28:09", "remaining_time": "0:01:24"}
|
301 |
+
{"current_steps": 301, "total_steps": 315, "loss": 0.0448, "lr": 5.399707175606117e-08, "epoch": 4.777777777777778, "percentage": 95.56, "elapsed_time": "0:28:14", "remaining_time": "0:01:18"}
|
302 |
+
{"current_steps": 302, "total_steps": 315, "loss": 0.0382, "lr": 4.657026981834623e-08, "epoch": 4.7936507936507935, "percentage": 95.87, "elapsed_time": "0:28:19", "remaining_time": "0:01:13"}
|
303 |
+
{"current_steps": 303, "total_steps": 315, "loss": 0.0346, "lr": 3.9690306753866204e-08, "epoch": 4.809523809523809, "percentage": 96.19, "elapsed_time": "0:28:24", "remaining_time": "0:01:07"}
|
304 |
+
{"current_steps": 304, "total_steps": 315, "loss": 0.0419, "lr": 3.3357942083085404e-08, "epoch": 4.825396825396825, "percentage": 96.51, "elapsed_time": "0:28:29", "remaining_time": "0:01:01"}
|
305 |
+
{"current_steps": 305, "total_steps": 315, "loss": 0.0385, "lr": 2.7573874873791372e-08, "epoch": 4.841269841269841, "percentage": 96.83, "elapsed_time": "0:28:33", "remaining_time": "0:00:56"}
|
306 |
+
{"current_steps": 306, "total_steps": 315, "loss": 0.0415, "lr": 2.233874366391997e-08, "epoch": 4.857142857142857, "percentage": 97.14, "elapsed_time": "0:28:38", "remaining_time": "0:00:50"}
|
307 |
+
{"current_steps": 307, "total_steps": 315, "loss": 0.0445, "lr": 1.7653126391063425e-08, "epoch": 4.8730158730158735, "percentage": 97.46, "elapsed_time": "0:28:43", "remaining_time": "0:00:44"}
|
308 |
+
{"current_steps": 308, "total_steps": 315, "loss": 0.0414, "lr": 1.3517540328669143e-08, "epoch": 4.888888888888889, "percentage": 97.78, "elapsed_time": "0:28:48", "remaining_time": "0:00:39"}
|
309 |
+
{"current_steps": 309, "total_steps": 315, "loss": 0.0274, "lr": 9.93244202893262e-09, "epoch": 4.904761904761905, "percentage": 98.1, "elapsed_time": "0:28:53", "remaining_time": "0:00:33"}
|
310 |
+
{"current_steps": 310, "total_steps": 315, "loss": 0.0375, "lr": 6.898227272398306e-09, "epoch": 4.920634920634921, "percentage": 98.41, "elapsed_time": "0:28:58", "remaining_time": "0:00:28"}
|
311 |
+
{"current_steps": 311, "total_steps": 315, "loss": 0.0282, "lr": 4.415231024265665e-09, "epoch": 4.936507936507937, "percentage": 98.73, "elapsed_time": "0:29:03", "remaining_time": "0:00:22"}
|
312 |
+
{"current_steps": 312, "total_steps": 315, "loss": 0.0271, "lr": 2.4837273974115393e-09, "epoch": 4.9523809523809526, "percentage": 99.05, "elapsed_time": "0:29:07", "remaining_time": "0:00:16"}
|
313 |
+
{"current_steps": 313, "total_steps": 315, "loss": 0.0419, "lr": 1.1039296221276863e-09, "epoch": 4.968253968253968, "percentage": 99.37, "elapsed_time": "0:29:13", "remaining_time": "0:00:11"}
|
314 |
+
{"current_steps": 314, "total_steps": 315, "loss": 0.0467, "lr": 2.7599002258127395e-10, "epoch": 4.984126984126984, "percentage": 99.68, "elapsed_time": "0:29:17", "remaining_time": "0:00:05"}
|
315 |
+
{"current_steps": 315, "total_steps": 315, "loss": 0.0281, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:29:22", "remaining_time": "0:00:00"}
|
316 |
+
{"current_steps": 315, "total_steps": 315, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:31:17", "remaining_time": "0:00:00"}
|