Training in progress, step 2200
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 sha256:6a404183474528b6bcd927c3999a1502fb5122d0318664fea83cbe695f236f3d
|
| 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:af6099e253e716e86128aa33d9f1b9483352e37ad2d31697dc4548d67cafa75f
|
| 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 sha256:81e80bcad604e4cfe5795cb677e667e7e5e816890ef31cf5b9ef9632cec2d141
|
| 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 sha256:29292b100cc2ee2457bc0dc61596ce1ac9e30c27c16af163764002e7d3958179
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -398,3 +398,43 @@
|
|
| 398 |
{"current_steps": 1990, "total_steps": 3850, "loss": 0.2209, "lr": 2.232486003600126e-05, "epoch": 3.618744313011829, "percentage": 51.69, "elapsed_time": "13:18:19", "remaining_time": "12:26:10"}
|
| 399 |
{"current_steps": 1995, "total_steps": 3850, "loss": 0.2267, "lr": 2.223478464642952e-05, "epoch": 3.6278434940855324, "percentage": 51.82, "elapsed_time": "13:20:27", "remaining_time": "12:24:16"}
|
| 400 |
{"current_steps": 2000, "total_steps": 3850, "loss": 0.2339, "lr": 2.2144663329843653e-05, "epoch": 3.6369426751592355, "percentage": 51.95, "elapsed_time": "13:22:21", "remaining_time": "12:22:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 398 |
{"current_steps": 1990, "total_steps": 3850, "loss": 0.2209, "lr": 2.232486003600126e-05, "epoch": 3.618744313011829, "percentage": 51.69, "elapsed_time": "13:18:19", "remaining_time": "12:26:10"}
|
| 399 |
{"current_steps": 1995, "total_steps": 3850, "loss": 0.2267, "lr": 2.223478464642952e-05, "epoch": 3.6278434940855324, "percentage": 51.82, "elapsed_time": "13:20:27", "remaining_time": "12:24:16"}
|
| 400 |
{"current_steps": 2000, "total_steps": 3850, "loss": 0.2339, "lr": 2.2144663329843653e-05, "epoch": 3.6369426751592355, "percentage": 51.95, "elapsed_time": "13:22:21", "remaining_time": "12:22:10"}
|
| 401 |
+
{"current_steps": 2005, "total_steps": 3850, "loss": 0.2284, "lr": 2.205449793832502e-05, "epoch": 3.646041856232939, "percentage": 52.08, "elapsed_time": "13:25:39", "remaining_time": "12:21:22"}
|
| 402 |
+
{"current_steps": 2010, "total_steps": 3850, "loss": 0.216, "lr": 2.1964290324860746e-05, "epoch": 3.6551410373066426, "percentage": 52.21, "elapsed_time": "13:27:47", "remaining_time": "12:19:28"}
|
| 403 |
+
{"current_steps": 2015, "total_steps": 3850, "loss": 0.2497, "lr": 2.1874042343305685e-05, "epoch": 3.6642402183803457, "percentage": 52.34, "elapsed_time": "13:29:34", "remaining_time": "12:17:15"}
|
| 404 |
+
{"current_steps": 2020, "total_steps": 3850, "loss": 0.222, "lr": 2.1783755848344276e-05, "epoch": 3.673339399454049, "percentage": 52.47, "elapsed_time": "13:31:41", "remaining_time": "12:15:21"}
|
| 405 |
+
{"current_steps": 2025, "total_steps": 3850, "loss": 0.2503, "lr": 2.1693432695452467e-05, "epoch": 3.6824385805277524, "percentage": 52.6, "elapsed_time": "13:33:40", "remaining_time": "12:13:18"}
|
| 406 |
+
{"current_steps": 2030, "total_steps": 3850, "loss": 0.2319, "lr": 2.1603074740859534e-05, "epoch": 3.691537761601456, "percentage": 52.73, "elapsed_time": "13:35:32", "remaining_time": "12:11:10"}
|
| 407 |
+
{"current_steps": 2035, "total_steps": 3850, "loss": 0.242, "lr": 2.1512683841509982e-05, "epoch": 3.700636942675159, "percentage": 52.86, "elapsed_time": "13:37:45", "remaining_time": "12:09:20"}
|
| 408 |
+
{"current_steps": 2040, "total_steps": 3850, "loss": 0.2382, "lr": 2.1422261855025357e-05, "epoch": 3.7097361237488626, "percentage": 52.99, "elapsed_time": "13:39:40", "remaining_time": "12:07:15"}
|
| 409 |
+
{"current_steps": 2045, "total_steps": 3850, "loss": 0.2257, "lr": 2.133181063966608e-05, "epoch": 3.7188353048225657, "percentage": 53.12, "elapsed_time": "13:41:28", "remaining_time": "12:05:04"}
|
| 410 |
+
{"current_steps": 2050, "total_steps": 3850, "loss": 0.2368, "lr": 2.1241332054293243e-05, "epoch": 3.7279344858962693, "percentage": 53.25, "elapsed_time": "13:43:47", "remaining_time": "12:03:19"}
|
| 411 |
+
{"current_steps": 2055, "total_steps": 3850, "loss": 0.2339, "lr": 2.115082795833044e-05, "epoch": 3.737033666969973, "percentage": 53.38, "elapsed_time": "13:46:01", "remaining_time": "12:01:31"}
|
| 412 |
+
{"current_steps": 2060, "total_steps": 3850, "loss": 0.2266, "lr": 2.1060300211725496e-05, "epoch": 3.746132848043676, "percentage": 53.51, "elapsed_time": "13:48:03", "remaining_time": "11:59:31"}
|
| 413 |
+
{"current_steps": 2065, "total_steps": 3850, "loss": 0.2142, "lr": 2.096975067491233e-05, "epoch": 3.7552320291173795, "percentage": 53.64, "elapsed_time": "13:50:15", "remaining_time": "11:57:41"}
|
| 414 |
+
{"current_steps": 2070, "total_steps": 3850, "loss": 0.2361, "lr": 2.087918120877263e-05, "epoch": 3.7643312101910826, "percentage": 53.77, "elapsed_time": "13:52:04", "remaining_time": "11:55:30"}
|
| 415 |
+
{"current_steps": 2075, "total_steps": 3850, "loss": 0.2499, "lr": 2.0788593674597663e-05, "epoch": 3.773430391264786, "percentage": 53.9, "elapsed_time": "13:53:53", "remaining_time": "11:53:20"}
|
| 416 |
+
{"current_steps": 2080, "total_steps": 3850, "loss": 0.2336, "lr": 2.0697989934050025e-05, "epoch": 3.7825295723384897, "percentage": 54.03, "elapsed_time": "13:55:50", "remaining_time": "11:51:15"}
|
| 417 |
+
{"current_steps": 2085, "total_steps": 3850, "loss": 0.2272, "lr": 2.0607371849125345e-05, "epoch": 3.791628753412193, "percentage": 54.16, "elapsed_time": "13:57:57", "remaining_time": "11:49:21"}
|
| 418 |
+
{"current_steps": 2090, "total_steps": 3850, "loss": 0.2324, "lr": 2.0516741282114062e-05, "epoch": 3.8007279344858964, "percentage": 54.29, "elapsed_time": "13:59:57", "remaining_time": "11:47:19"}
|
| 419 |
+
{"current_steps": 2095, "total_steps": 3850, "loss": 0.2286, "lr": 2.0426100095563132e-05, "epoch": 3.8098271155595995, "percentage": 54.42, "elapsed_time": "14:01:52", "remaining_time": "11:45:14"}
|
| 420 |
+
{"current_steps": 2100, "total_steps": 3850, "loss": 0.2348, "lr": 2.0335450152237742e-05, "epoch": 3.818926296633303, "percentage": 54.55, "elapsed_time": "14:03:54", "remaining_time": "11:43:15"}
|
| 421 |
+
{"current_steps": 2105, "total_steps": 3850, "loss": 0.2458, "lr": 2.0244793315083043e-05, "epoch": 3.8280254777070066, "percentage": 54.68, "elapsed_time": "14:05:43", "remaining_time": "11:41:05"}
|
| 422 |
+
{"current_steps": 2110, "total_steps": 3850, "loss": 0.2371, "lr": 2.0154131447185876e-05, "epoch": 3.8371246587807097, "percentage": 54.81, "elapsed_time": "14:07:25", "remaining_time": "11:38:49"}
|
| 423 |
+
{"current_steps": 2115, "total_steps": 3850, "loss": 0.2385, "lr": 2.0063466411736447e-05, "epoch": 3.846223839854413, "percentage": 54.94, "elapsed_time": "14:09:29", "remaining_time": "11:36:51"}
|
| 424 |
+
{"current_steps": 2120, "total_steps": 3850, "loss": 0.2202, "lr": 1.997280007199008e-05, "epoch": 3.8553230209281164, "percentage": 55.06, "elapsed_time": "14:11:41", "remaining_time": "11:35:01"}
|
| 425 |
+
{"current_steps": 2125, "total_steps": 3850, "loss": 0.2247, "lr": 1.9882134291228877e-05, "epoch": 3.86442220200182, "percentage": 55.19, "elapsed_time": "14:13:30", "remaining_time": "11:32:50"}
|
| 426 |
+
{"current_steps": 2130, "total_steps": 3850, "loss": 0.2363, "lr": 1.9791470932723486e-05, "epoch": 3.873521383075523, "percentage": 55.32, "elapsed_time": "14:15:36", "remaining_time": "11:30:55"}
|
| 427 |
+
{"current_steps": 2135, "total_steps": 3850, "loss": 0.2153, "lr": 1.9700811859694734e-05, "epoch": 3.8826205641492266, "percentage": 55.45, "elapsed_time": "14:17:38", "remaining_time": "11:28:55"}
|
| 428 |
+
{"current_steps": 2140, "total_steps": 3850, "loss": 0.24, "lr": 1.961015893527541e-05, "epoch": 3.8917197452229297, "percentage": 55.58, "elapsed_time": "14:19:30", "remaining_time": "11:26:48"}
|
| 429 |
+
{"current_steps": 2145, "total_steps": 3850, "loss": 0.224, "lr": 1.9519514022471933e-05, "epoch": 3.9008189262966333, "percentage": 55.71, "elapsed_time": "14:21:33", "remaining_time": "11:24:49"}
|
| 430 |
+
{"current_steps": 2150, "total_steps": 3850, "loss": 0.2441, "lr": 1.942887898412608e-05, "epoch": 3.909918107370337, "percentage": 55.84, "elapsed_time": "14:23:27", "remaining_time": "11:22:44"}
|
| 431 |
+
{"current_steps": 2155, "total_steps": 3850, "loss": 0.2296, "lr": 1.9338255682876682e-05, "epoch": 3.91901728844404, "percentage": 55.97, "elapsed_time": "14:25:28", "remaining_time": "11:20:43"}
|
| 432 |
+
{"current_steps": 2160, "total_steps": 3850, "loss": 0.2252, "lr": 1.924764598112138e-05, "epoch": 3.9281164695177435, "percentage": 56.1, "elapsed_time": "14:27:38", "remaining_time": "11:18:51"}
|
| 433 |
+
{"current_steps": 2165, "total_steps": 3850, "loss": 0.2304, "lr": 1.9157051740978326e-05, "epoch": 3.9372156505914466, "percentage": 56.23, "elapsed_time": "14:29:44", "remaining_time": "11:16:55"}
|
| 434 |
+
{"current_steps": 2170, "total_steps": 3850, "loss": 0.2451, "lr": 1.9066474824247913e-05, "epoch": 3.94631483166515, "percentage": 56.36, "elapsed_time": "14:31:42", "remaining_time": "11:14:51"}
|
| 435 |
+
{"current_steps": 2175, "total_steps": 3850, "loss": 0.2363, "lr": 1.8975917092374542e-05, "epoch": 3.9554140127388537, "percentage": 56.49, "elapsed_time": "14:33:33", "remaining_time": "11:12:44"}
|
| 436 |
+
{"current_steps": 2180, "total_steps": 3850, "loss": 0.2255, "lr": 1.888538040640831e-05, "epoch": 3.964513193812557, "percentage": 56.62, "elapsed_time": "14:35:41", "remaining_time": "11:10:49"}
|
| 437 |
+
{"current_steps": 2185, "total_steps": 3850, "loss": 0.2267, "lr": 1.8794866626966834e-05, "epoch": 3.9736123748862604, "percentage": 56.75, "elapsed_time": "14:37:31", "remaining_time": "11:08:41"}
|
| 438 |
+
{"current_steps": 2190, "total_steps": 3850, "loss": 0.2209, "lr": 1.8704377614196963e-05, "epoch": 3.9827115559599635, "percentage": 56.88, "elapsed_time": "14:39:39", "remaining_time": "11:06:46"}
|
| 439 |
+
{"current_steps": 2195, "total_steps": 3850, "loss": 0.2489, "lr": 1.8613915227736584e-05, "epoch": 3.991810737033667, "percentage": 57.01, "elapsed_time": "14:41:37", "remaining_time": "11:04:43"}
|
| 440 |
+
{"current_steps": 2200, "total_steps": 3850, "loss": 0.2441, "lr": 1.852348132667635e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "14:43:07", "remaining_time": "11:02:20"}
|