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:ad4ea33eeeba571528837842f89bf91a16a1597f414f34be8156d15606b7814a
|
| 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 sha256:6928da316d1adf208d8587d8a37d90ce79de3e06b20d338908d6ede080f33ffd
|
| 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:e9e429810c471b2da039a72090ab2ffd8f8f4b269c3c1be2054304d53986048f
|
| 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 sha256:82128247196921d19e0abba920b721c16a661f33c9863814c3eb022e358b8896
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -239,3 +239,43 @@
|
|
| 239 |
{"current_steps": 1195, "total_steps": 9128, "loss": 0.331, "lr": 3.988463361545309e-05, "epoch": 0.9167625623321826, "percentage": 13.09, "elapsed_time": "7:23:01", "remaining_time": "2 days, 1:01:00"}
|
| 240 |
{"current_steps": 1200, "total_steps": 9128, "loss": 0.326, "lr": 3.988049565362048e-05, "epoch": 0.9205983889528193, "percentage": 13.15, "elapsed_time": "7:24:41", "remaining_time": "2 days, 0:57:58"}
|
| 241 |
{"current_steps": 1205, "total_steps": 9128, "loss": 0.332, "lr": 3.987628500563318e-05, "epoch": 0.9244342155734561, "percentage": 13.2, "elapsed_time": "7:27:34", "remaining_time": "2 days, 1:02:47"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 239 |
{"current_steps": 1195, "total_steps": 9128, "loss": 0.331, "lr": 3.988463361545309e-05, "epoch": 0.9167625623321826, "percentage": 13.09, "elapsed_time": "7:23:01", "remaining_time": "2 days, 1:01:00"}
|
| 240 |
{"current_steps": 1200, "total_steps": 9128, "loss": 0.326, "lr": 3.988049565362048e-05, "epoch": 0.9205983889528193, "percentage": 13.15, "elapsed_time": "7:24:41", "remaining_time": "2 days, 0:57:58"}
|
| 241 |
{"current_steps": 1205, "total_steps": 9128, "loss": 0.332, "lr": 3.987628500563318e-05, "epoch": 0.9244342155734561, "percentage": 13.2, "elapsed_time": "7:27:34", "remaining_time": "2 days, 1:02:47"}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 9128, "loss": 0.3262, "lr": 3.987200168688595e-05, "epoch": 0.9282700421940928, "percentage": 13.26, "elapsed_time": "7:29:19", "remaining_time": "2 days, 1:00:20"}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 9128, "loss": 0.3163, "lr": 3.9867645713039275e-05, "epoch": 0.9321058688147296, "percentage": 13.31, "elapsed_time": "7:31:09", "remaining_time": "2 days, 0:58:14"}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 9128, "loss": 0.3091, "lr": 3.9863217100019264e-05, "epoch": 0.9359416954353663, "percentage": 13.37, "elapsed_time": "7:32:55", "remaining_time": "2 days, 0:55:48"}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 9128, "loss": 0.3142, "lr": 3.9858715864017604e-05, "epoch": 0.9397775220560031, "percentage": 13.42, "elapsed_time": "7:34:39", "remaining_time": "2 days, 0:53:12"}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 9128, "loss": 0.3234, "lr": 3.985414202149151e-05, "epoch": 0.9436133486766398, "percentage": 13.48, "elapsed_time": "7:36:19", "remaining_time": "2 days, 0:50:09"}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 9128, "loss": 0.3113, "lr": 3.984949558916366e-05, "epoch": 0.9474491752972766, "percentage": 13.53, "elapsed_time": "7:38:00", "remaining_time": "2 days, 0:47:12"}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 9128, "loss": 0.3141, "lr": 3.984477658402212e-05, "epoch": 0.9512850019179133, "percentage": 13.58, "elapsed_time": "7:39:42", "remaining_time": "2 days, 0:44:22"}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 9128, "loss": 0.3191, "lr": 3.9839985023320305e-05, "epoch": 0.9551208285385501, "percentage": 13.64, "elapsed_time": "7:41:20", "remaining_time": "2 days, 0:41:03"}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 9128, "loss": 0.3127, "lr": 3.9835120924576885e-05, "epoch": 0.9589566551591868, "percentage": 13.69, "elapsed_time": "7:43:02", "remaining_time": "2 days, 0:38:18"}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 9128, "loss": 0.3393, "lr": 3.9830184305575775e-05, "epoch": 0.9627924817798236, "percentage": 13.75, "elapsed_time": "7:44:42", "remaining_time": "2 days, 0:35:12"}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 9128, "loss": 0.3286, "lr": 3.9825175184366e-05, "epoch": 0.9666283084004603, "percentage": 13.8, "elapsed_time": "7:46:14", "remaining_time": "2 days, 0:31:27"}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 9128, "loss": 0.3279, "lr": 3.9820093579261685e-05, "epoch": 0.9704641350210971, "percentage": 13.86, "elapsed_time": "7:54:46", "remaining_time": "2 days, 1:11:09"}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 9128, "loss": 0.3106, "lr": 3.981493950884196e-05, "epoch": 0.9742999616417338, "percentage": 13.91, "elapsed_time": "7:56:23", "remaining_time": "2 days, 1:07:36"}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 9128, "loss": 0.3224, "lr": 3.9809712991950905e-05, "epoch": 0.9781357882623706, "percentage": 13.97, "elapsed_time": "7:58:00", "remaining_time": "2 days, 1:04:09"}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 9128, "loss": 0.3191, "lr": 3.980441404769746e-05, "epoch": 0.9819716148830073, "percentage": 14.02, "elapsed_time": "7:59:40", "remaining_time": "2 days, 1:01:01"}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 9128, "loss": 0.3287, "lr": 3.979904269545538e-05, "epoch": 0.9858074415036441, "percentage": 14.08, "elapsed_time": "8:01:20", "remaining_time": "2 days, 0:57:54"}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 9128, "loss": 0.3228, "lr": 3.979359895486318e-05, "epoch": 0.9896432681242808, "percentage": 14.13, "elapsed_time": "8:03:01", "remaining_time": "2 days, 0:54:49"}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 9128, "loss": 0.3208, "lr": 3.978808284582399e-05, "epoch": 0.9934790947449176, "percentage": 14.19, "elapsed_time": "8:04:40", "remaining_time": "2 days, 0:51:37"}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 9128, "loss": 0.3289, "lr": 3.9782494388505564e-05, "epoch": 0.9973149213655543, "percentage": 14.24, "elapsed_time": "8:06:21", "remaining_time": "2 days, 0:48:35"}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 9128, "loss": 0.2988, "lr": 3.977683360334015e-05, "epoch": 1.0007671653241272, "percentage": 14.3, "elapsed_time": "8:08:22", "remaining_time": "2 days, 0:47:39"}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 9128, "loss": 0.273, "lr": 3.9771100511024473e-05, "epoch": 1.004602991944764, "percentage": 14.35, "elapsed_time": "8:11:17", "remaining_time": "2 days, 0:51:57"}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 9128, "loss": 0.2708, "lr": 3.976529513251959e-05, "epoch": 1.0084388185654007, "percentage": 14.41, "elapsed_time": "8:14:04", "remaining_time": "2 days, 0:55:30"}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 9128, "loss": 0.2607, "lr": 3.9759417489050854e-05, "epoch": 1.0122746451860376, "percentage": 14.46, "elapsed_time": "8:17:02", "remaining_time": "2 days, 1:00:03"}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 9128, "loss": 0.2398, "lr": 3.975346760210784e-05, "epoch": 1.0161104718066742, "percentage": 14.52, "elapsed_time": "8:20:06", "remaining_time": "2 days, 1:05:08"}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 9128, "loss": 0.247, "lr": 3.974744549344426e-05, "epoch": 1.019946298427311, "percentage": 14.57, "elapsed_time": "8:23:09", "remaining_time": "2 days, 1:10:04"}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 9128, "loss": 0.2641, "lr": 3.9741351185077856e-05, "epoch": 1.0237821250479477, "percentage": 14.63, "elapsed_time": "8:26:08", "remaining_time": "2 days, 1:14:33"}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 9128, "loss": 0.2598, "lr": 3.9735184699290365e-05, "epoch": 1.0276179516685846, "percentage": 14.68, "elapsed_time": "8:29:06", "remaining_time": "2 days, 1:18:54"}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 9128, "loss": 0.2477, "lr": 3.972894605862742e-05, "epoch": 1.0314537782892212, "percentage": 14.73, "elapsed_time": "8:31:59", "remaining_time": "2 days, 1:22:41"}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 9128, "loss": 0.2461, "lr": 3.972263528589843e-05, "epoch": 1.035289604909858, "percentage": 14.79, "elapsed_time": "8:34:29", "remaining_time": "2 days, 1:24:11"}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 9128, "loss": 0.2407, "lr": 3.971625240417656e-05, "epoch": 1.0391254315304947, "percentage": 14.84, "elapsed_time": "8:37:21", "remaining_time": "2 days, 1:27:48"}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 9128, "loss": 0.2426, "lr": 3.9709797436798623e-05, "epoch": 1.0429612581511316, "percentage": 14.9, "elapsed_time": "8:40:11", "remaining_time": "2 days, 1:31:13"}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 9128, "loss": 0.2387, "lr": 3.970327040736495e-05, "epoch": 1.0467970847717682, "percentage": 14.95, "elapsed_time": "8:42:58", "remaining_time": "2 days, 1:34:14"}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 9128, "loss": 0.2365, "lr": 3.9696671339739395e-05, "epoch": 1.0506329113924051, "percentage": 15.01, "elapsed_time": "8:45:45", "remaining_time": "2 days, 1:37:12"}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 9128, "loss": 0.2295, "lr": 3.9690000258049144e-05, "epoch": 1.0544687380130418, "percentage": 15.06, "elapsed_time": "8:48:34", "remaining_time": "2 days, 1:40:24"}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 9128, "loss": 0.2339, "lr": 3.96832571866847e-05, "epoch": 1.0583045646336786, "percentage": 15.12, "elapsed_time": "8:51:17", "remaining_time": "2 days, 1:42:54"}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 9128, "loss": 0.2372, "lr": 3.967644215029979e-05, "epoch": 1.0621403912543153, "percentage": 15.17, "elapsed_time": "8:54:02", "remaining_time": "2 days, 1:45:36"}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 9128, "loss": 0.2286, "lr": 3.966955517381121e-05, "epoch": 1.0659762178749521, "percentage": 15.23, "elapsed_time": "8:56:59", "remaining_time": "2 days, 1:49:23"}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 9128, "loss": 0.2485, "lr": 3.9662596282398824e-05, "epoch": 1.0698120444955888, "percentage": 15.28, "elapsed_time": "8:59:50", "remaining_time": "2 days, 1:52:30"}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 9128, "loss": 0.2602, "lr": 3.965556550150541e-05, "epoch": 1.0736478711162256, "percentage": 15.34, "elapsed_time": "9:02:39", "remaining_time": "2 days, 1:55:25"}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 9128, "loss": 0.2187, "lr": 3.964846285683658e-05, "epoch": 1.0774836977368623, "percentage": 15.39, "elapsed_time": "9:06:29", "remaining_time": "2 days, 2:03:55"}
|