Training in progress, step 1400
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 sha256:64a4ec56f142c9f76671fd542624ea226cec104f1b8e9cd557dc97a8184725f4
|
| 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 sha256:621d12af10d5dcb2ded2fd2d808a2248829268da3f39cacac9e6dcf4fcc3dc36
|
| 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:d2c6c4ecd175c4bd9d3a369b9551b84c1f2c3ca1ed2ad06da3b0d3d753a78dfc
|
| 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:dcc00edfdca62ad34f574f268b3e06457d85acfa34d64277db5b049ff1914cf7
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -240,3 +240,41 @@
|
|
| 240 |
{"current_steps": 1200, "total_steps": 3850, "loss": 0.2593, "lr": 3.4795977520951684e-05, "epoch": 2.1819836214740675, "percentage": 31.17, "elapsed_time": "8:01:41", "remaining_time": "17:43:44"}
|
| 241 |
{"current_steps": 1205, "total_steps": 3850, "loss": 0.2545, "lr": 3.47348227575281e-05, "epoch": 2.1910828025477707, "percentage": 31.3, "elapsed_time": "8:04:39", "remaining_time": "17:43:51"}
|
| 242 |
{"current_steps": 1210, "total_steps": 3850, "loss": 0.2596, "lr": 3.467336517905966e-05, "epoch": 2.200181983621474, "percentage": 31.43, "elapsed_time": "8:06:52", "remaining_time": "17:42:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
{"current_steps": 1200, "total_steps": 3850, "loss": 0.2593, "lr": 3.4795977520951684e-05, "epoch": 2.1819836214740675, "percentage": 31.17, "elapsed_time": "8:01:41", "remaining_time": "17:43:44"}
|
| 241 |
{"current_steps": 1205, "total_steps": 3850, "loss": 0.2545, "lr": 3.47348227575281e-05, "epoch": 2.1910828025477707, "percentage": 31.3, "elapsed_time": "8:04:39", "remaining_time": "17:43:51"}
|
| 242 |
{"current_steps": 1210, "total_steps": 3850, "loss": 0.2596, "lr": 3.467336517905966e-05, "epoch": 2.200181983621474, "percentage": 31.43, "elapsed_time": "8:06:52", "remaining_time": "17:42:15"}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 3850, "loss": 0.26, "lr": 3.46116060485598e-05, "epoch": 2.2092811646951773, "percentage": 31.56, "elapsed_time": "8:08:53", "remaining_time": "17:40:16"}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 3850, "loss": 0.2741, "lr": 3.4549546635239167e-05, "epoch": 2.218380345768881, "percentage": 31.69, "elapsed_time": "8:10:42", "remaining_time": "17:37:49"}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 3850, "loss": 0.2698, "lr": 3.448718821447953e-05, "epoch": 2.227479526842584, "percentage": 31.82, "elapsed_time": "8:12:22", "remaining_time": "17:35:06"}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 3850, "loss": 0.2781, "lr": 3.442453206780751e-05, "epoch": 2.2365787079162875, "percentage": 31.95, "elapsed_time": "8:14:24", "remaining_time": "17:33:08"}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 3850, "loss": 0.2686, "lr": 3.4361579482868325e-05, "epoch": 2.245677888989991, "percentage": 32.08, "elapsed_time": "8:16:20", "remaining_time": "17:30:57"}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 3850, "loss": 0.2633, "lr": 3.429833175339927e-05, "epoch": 2.254777070063694, "percentage": 32.21, "elapsed_time": "8:18:05", "remaining_time": "17:28:23"}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 3850, "loss": 0.2612, "lr": 3.423479017920317e-05, "epoch": 2.2638762511373978, "percentage": 32.34, "elapsed_time": "8:19:59", "remaining_time": "17:26:10"}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 3850, "loss": 0.2645, "lr": 3.4170956066121616e-05, "epoch": 2.272975432211101, "percentage": 32.47, "elapsed_time": "8:21:53", "remaining_time": "17:23:55"}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 3850, "loss": 0.2803, "lr": 3.410683072600818e-05, "epoch": 2.2820746132848044, "percentage": 32.6, "elapsed_time": "8:23:52", "remaining_time": "17:21:52"}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 3850, "loss": 0.2529, "lr": 3.4042415476701434e-05, "epoch": 2.2911737943585075, "percentage": 32.73, "elapsed_time": "8:26:14", "remaining_time": "17:20:35"}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 3850, "loss": 0.2434, "lr": 3.397771164199787e-05, "epoch": 2.300272975432211, "percentage": 32.86, "elapsed_time": "8:28:25", "remaining_time": "17:18:58"}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 3850, "loss": 0.2519, "lr": 3.3912720551624684e-05, "epoch": 2.3093721565059147, "percentage": 32.99, "elapsed_time": "8:30:33", "remaining_time": "17:17:11"}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 3850, "loss": 0.2601, "lr": 3.384744354121246e-05, "epoch": 2.3184713375796178, "percentage": 33.12, "elapsed_time": "8:32:25", "remaining_time": "17:14:53"}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 3850, "loss": 0.258, "lr": 3.3781881952267715e-05, "epoch": 2.3275705186533213, "percentage": 33.25, "elapsed_time": "8:34:33", "remaining_time": "17:13:07"}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 3850, "loss": 0.2674, "lr": 3.3716037132145354e-05, "epoch": 2.3366696997270244, "percentage": 33.38, "elapsed_time": "8:36:31", "remaining_time": "17:11:02"}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 3850, "loss": 0.2734, "lr": 3.3649910434020934e-05, "epoch": 2.345768880800728, "percentage": 33.51, "elapsed_time": "8:38:52", "remaining_time": "17:09:43"}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 3850, "loss": 0.2704, "lr": 3.35835032168629e-05, "epoch": 2.3548680618744315, "percentage": 33.64, "elapsed_time": "8:40:49", "remaining_time": "17:07:35"}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 3850, "loss": 0.2702, "lr": 3.351681684540462e-05, "epoch": 2.3639672429481347, "percentage": 33.77, "elapsed_time": "8:42:39", "remaining_time": "17:05:12"}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 3850, "loss": 0.2557, "lr": 3.3449852690116375e-05, "epoch": 2.373066424021838, "percentage": 33.9, "elapsed_time": "8:44:41", "remaining_time": "17:03:15"}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 3850, "loss": 0.2489, "lr": 3.3382612127177166e-05, "epoch": 2.3821656050955413, "percentage": 34.03, "elapsed_time": "8:46:46", "remaining_time": "17:01:21"}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 3850, "loss": 0.2371, "lr": 3.331509653844644e-05, "epoch": 2.391264786169245, "percentage": 34.16, "elapsed_time": "8:48:35", "remaining_time": "16:59:00"}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 3850, "loss": 0.2827, "lr": 3.324730731143571e-05, "epoch": 2.400363967242948, "percentage": 34.29, "elapsed_time": "8:50:31", "remaining_time": "16:56:51"}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 3850, "loss": 0.2506, "lr": 3.317924583927999e-05, "epoch": 2.4094631483166515, "percentage": 34.42, "elapsed_time": "8:52:35", "remaining_time": "16:54:56"}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 3850, "loss": 0.2644, "lr": 3.311091352070924e-05, "epoch": 2.4185623293903546, "percentage": 34.55, "elapsed_time": "8:54:39", "remaining_time": "16:53:03"}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 3850, "loss": 0.2733, "lr": 3.3042311760019554e-05, "epoch": 2.427661510464058, "percentage": 34.68, "elapsed_time": "8:56:42", "remaining_time": "16:51:06"}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 3850, "loss": 0.253, "lr": 3.297344196704431e-05, "epoch": 2.4367606915377618, "percentage": 34.81, "elapsed_time": "8:58:40", "remaining_time": "16:48:59"}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 3850, "loss": 0.2732, "lr": 3.2904305557125265e-05, "epoch": 2.445859872611465, "percentage": 34.94, "elapsed_time": "9:00:29", "remaining_time": "16:46:38"}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 3850, "loss": 0.2771, "lr": 3.2834903951083363e-05, "epoch": 2.4549590536851684, "percentage": 35.06, "elapsed_time": "9:02:16", "remaining_time": "16:44:12"}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 3850, "loss": 0.2546, "lr": 3.27652385751896e-05, "epoch": 2.4640582347588715, "percentage": 35.19, "elapsed_time": "9:04:03", "remaining_time": "16:41:48"}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 3850, "loss": 0.2753, "lr": 3.269531086113573e-05, "epoch": 2.473157415832575, "percentage": 35.32, "elapsed_time": "9:05:57", "remaining_time": "16:39:34"}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 3850, "loss": 0.2563, "lr": 3.262512224600478e-05, "epoch": 2.4822565969062786, "percentage": 35.45, "elapsed_time": "9:07:59", "remaining_time": "16:37:37"}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 3850, "loss": 0.2566, "lr": 3.2554674172241565e-05, "epoch": 2.4913557779799818, "percentage": 35.58, "elapsed_time": "9:09:46", "remaining_time": "16:35:11"}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 3850, "loss": 0.2681, "lr": 3.2483968087623026e-05, "epoch": 2.5004549590536853, "percentage": 35.71, "elapsed_time": "9:11:47", "remaining_time": "16:33:13"}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 3850, "loss": 0.2685, "lr": 3.241300544522848e-05, "epoch": 2.5095541401273884, "percentage": 35.84, "elapsed_time": "9:13:43", "remaining_time": "16:31:05"}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 3850, "loss": 0.2557, "lr": 3.234178770340975e-05, "epoch": 2.518653321201092, "percentage": 35.97, "elapsed_time": "9:15:48", "remaining_time": "16:29:12"}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 3850, "loss": 0.252, "lr": 3.227031632576122e-05, "epoch": 2.5277525022747955, "percentage": 36.1, "elapsed_time": "9:17:46", "remaining_time": "16:27:08"}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 3850, "loss": 0.2679, "lr": 3.219859278108972e-05, "epoch": 2.5368516833484986, "percentage": 36.23, "elapsed_time": "9:19:53", "remaining_time": "16:25:19"}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 3850, "loss": 0.2602, "lr": 3.212661854338438e-05, "epoch": 2.5459508644222018, "percentage": 36.36, "elapsed_time": "9:21:57", "remaining_time": "16:23:25"}
|