Training in progress, epoch 4
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 sha256:0561f3b20a35da300fc9645b5363c16357193c68b4361786af12540213cb2eea
|
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:b0650c5bb55668455c6aabef076f430e931331c503532c2d4f34e44e07e9b426
|
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:e5c3f25db6529c23c76b7a9fcb5a918e82f6bc52b82d5d5fc2b5edfaa3224977
|
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:a1f4de31278549571acaecf5790c8e63ba00f4206747d66987209dcd448cb2bc
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -257,3 +257,62 @@
|
|
257 |
{"current_steps": 235, "total_steps": 295, "loss": 0.4935, "lr": 9.699550313535196e-06, "epoch": 3.9788583509513744, "percentage": 79.66, "elapsed_time": "3:21:17", "remaining_time": "0:51:23"}
|
258 |
{"current_steps": 236, "total_steps": 295, "loss": 0.4957, "lr": 9.392116803884113e-06, "epoch": 3.995771670190275, "percentage": 80.0, "elapsed_time": "3:22:59", "remaining_time": "0:50:44"}
|
259 |
{"current_steps": 237, "total_steps": 295, "loss": 0.4642, "lr": 9.088984955474749e-06, "epoch": 4.012684989429175, "percentage": 80.34, "elapsed_time": "3:26:36", "remaining_time": "0:50:33"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
257 |
{"current_steps": 235, "total_steps": 295, "loss": 0.4935, "lr": 9.699550313535196e-06, "epoch": 3.9788583509513744, "percentage": 79.66, "elapsed_time": "3:21:17", "remaining_time": "0:51:23"}
|
258 |
{"current_steps": 236, "total_steps": 295, "loss": 0.4957, "lr": 9.392116803884113e-06, "epoch": 3.995771670190275, "percentage": 80.0, "elapsed_time": "3:22:59", "remaining_time": "0:50:44"}
|
259 |
{"current_steps": 237, "total_steps": 295, "loss": 0.4642, "lr": 9.088984955474749e-06, "epoch": 4.012684989429175, "percentage": 80.34, "elapsed_time": "3:26:36", "remaining_time": "0:50:33"}
|
260 |
+
{"current_steps": 238, "total_steps": 295, "loss": 0.4702, "lr": 8.790197370747662e-06, "epoch": 4.029598308668076, "percentage": 80.68, "elapsed_time": "3:28:19", "remaining_time": "0:49:53"}
|
261 |
+
{"current_steps": 239, "total_steps": 295, "loss": 0.4616, "lr": 8.495796041596379e-06, "epoch": 4.046511627906977, "percentage": 81.02, "elapsed_time": "3:30:03", "remaining_time": "0:49:13"}
|
262 |
+
{"current_steps": 240, "total_steps": 295, "loss": 0.4672, "lr": 8.205822343465865e-06, "epoch": 4.063424947145878, "percentage": 81.36, "elapsed_time": "3:31:46", "remaining_time": "0:48:31"}
|
263 |
+
{"current_steps": 241, "total_steps": 295, "loss": 0.4673, "lr": 7.92031702953762e-06, "epoch": 4.080338266384778, "percentage": 81.69, "elapsed_time": "3:33:29", "remaining_time": "0:47:50"}
|
264 |
+
{"current_steps": 242, "total_steps": 295, "loss": 0.4643, "lr": 7.639320225002106e-06, "epoch": 4.097251585623678, "percentage": 82.03, "elapsed_time": "3:35:12", "remaining_time": "0:47:07"}
|
265 |
+
{"current_steps": 243, "total_steps": 295, "loss": 0.4621, "lr": 7.3628714214195505e-06, "epoch": 4.114164904862579, "percentage": 82.37, "elapsed_time": "3:36:55", "remaining_time": "0:46:25"}
|
266 |
+
{"current_steps": 244, "total_steps": 295, "loss": 0.469, "lr": 7.091009471169808e-06, "epoch": 4.13107822410148, "percentage": 82.71, "elapsed_time": "3:38:37", "remaining_time": "0:45:41"}
|
267 |
+
{"current_steps": 245, "total_steps": 295, "loss": 0.4653, "lr": 6.82377258199193e-06, "epoch": 4.147991543340381, "percentage": 83.05, "elapsed_time": "3:40:21", "remaining_time": "0:44:58"}
|
268 |
+
{"current_steps": 246, "total_steps": 295, "loss": 0.4643, "lr": 6.561198311614458e-06, "epoch": 4.164904862579281, "percentage": 83.39, "elapsed_time": "3:42:04", "remaining_time": "0:44:14"}
|
269 |
+
{"current_steps": 247, "total_steps": 295, "loss": 0.4639, "lr": 6.303323562477044e-06, "epoch": 4.181818181818182, "percentage": 83.73, "elapsed_time": "3:43:49", "remaining_time": "0:43:29"}
|
270 |
+
{"current_steps": 248, "total_steps": 295, "loss": 0.4632, "lr": 6.050184576544089e-06, "epoch": 4.1987315010570825, "percentage": 84.07, "elapsed_time": "3:45:32", "remaining_time": "0:42:44"}
|
271 |
+
{"current_steps": 249, "total_steps": 295, "loss": 0.4628, "lr": 5.801816930211304e-06, "epoch": 4.215644820295983, "percentage": 84.41, "elapsed_time": "3:47:16", "remaining_time": "0:41:59"}
|
272 |
+
{"current_steps": 250, "total_steps": 295, "loss": 0.4604, "lr": 5.558255529305779e-06, "epoch": 4.232558139534884, "percentage": 84.75, "elapsed_time": "3:48:59", "remaining_time": "0:41:13"}
|
273 |
+
{"current_steps": 251, "total_steps": 295, "loss": 0.4628, "lr": 5.319534604180239e-06, "epoch": 4.249471458773784, "percentage": 85.08, "elapsed_time": "3:50:43", "remaining_time": "0:40:26"}
|
274 |
+
{"current_steps": 252, "total_steps": 295, "loss": 0.466, "lr": 5.085687704902311e-06, "epoch": 4.266384778012685, "percentage": 85.42, "elapsed_time": "3:52:27", "remaining_time": "0:39:39"}
|
275 |
+
{"current_steps": 253, "total_steps": 295, "loss": 0.46, "lr": 4.856747696539352e-06, "epoch": 4.283298097251586, "percentage": 85.76, "elapsed_time": "3:54:11", "remaining_time": "0:38:52"}
|
276 |
+
{"current_steps": 254, "total_steps": 295, "loss": 0.4683, "lr": 4.632746754539592e-06, "epoch": 4.3002114164904865, "percentage": 86.1, "elapsed_time": "3:55:54", "remaining_time": "0:38:04"}
|
277 |
+
{"current_steps": 255, "total_steps": 295, "loss": 0.4637, "lr": 4.4137163602101114e-06, "epoch": 4.3171247357293865, "percentage": 86.44, "elapsed_time": "3:57:38", "remaining_time": "0:37:16"}
|
278 |
+
{"current_steps": 256, "total_steps": 295, "loss": 0.4681, "lr": 4.199687296292463e-06, "epoch": 4.334038054968287, "percentage": 86.78, "elapsed_time": "3:59:21", "remaining_time": "0:36:27"}
|
279 |
+
{"current_steps": 257, "total_steps": 295, "loss": 0.463, "lr": 3.990689642636451e-06, "epoch": 4.350951374207188, "percentage": 87.12, "elapsed_time": "4:01:05", "remaining_time": "0:35:38"}
|
280 |
+
{"current_steps": 258, "total_steps": 295, "loss": 0.4647, "lr": 3.786752771972633e-06, "epoch": 4.367864693446089, "percentage": 87.46, "elapsed_time": "4:02:49", "remaining_time": "0:34:49"}
|
281 |
+
{"current_steps": 259, "total_steps": 295, "loss": 0.4621, "lr": 3.5879053457842727e-06, "epoch": 4.38477801268499, "percentage": 87.8, "elapsed_time": "4:04:32", "remaining_time": "0:33:59"}
|
282 |
+
{"current_steps": 260, "total_steps": 295, "loss": 0.4654, "lr": 3.3941753102792617e-06, "epoch": 4.40169133192389, "percentage": 88.14, "elapsed_time": "4:06:16", "remaining_time": "0:33:09"}
|
283 |
+
{"current_steps": 261, "total_steps": 295, "loss": 0.463, "lr": 3.205589892462464e-06, "epoch": 4.4186046511627906, "percentage": 88.47, "elapsed_time": "4:07:59", "remaining_time": "0:32:18"}
|
284 |
+
{"current_steps": 262, "total_steps": 295, "loss": 0.466, "lr": 3.0221755963092535e-06, "epoch": 4.435517970401691, "percentage": 88.81, "elapsed_time": "4:09:43", "remaining_time": "0:31:27"}
|
285 |
+
{"current_steps": 263, "total_steps": 295, "loss": 0.465, "lr": 2.8439581990406282e-06, "epoch": 4.452431289640592, "percentage": 89.15, "elapsed_time": "4:11:27", "remaining_time": "0:30:35"}
|
286 |
+
{"current_steps": 264, "total_steps": 295, "loss": 0.4607, "lr": 2.670962747500405e-06, "epoch": 4.469344608879492, "percentage": 89.49, "elapsed_time": "4:13:10", "remaining_time": "0:29:43"}
|
287 |
+
{"current_steps": 265, "total_steps": 295, "loss": 0.4596, "lr": 2.5032135546351644e-06, "epoch": 4.486257928118393, "percentage": 89.83, "elapsed_time": "4:14:54", "remaining_time": "0:28:51"}
|
288 |
+
{"current_steps": 266, "total_steps": 295, "loss": 0.4658, "lr": 2.3407341960772543e-06, "epoch": 4.503171247357294, "percentage": 90.17, "elapsed_time": "4:16:38", "remaining_time": "0:27:58"}
|
289 |
+
{"current_steps": 267, "total_steps": 295, "loss": 0.4639, "lr": 2.1835475068314692e-06, "epoch": 4.520084566596195, "percentage": 90.51, "elapsed_time": "4:18:20", "remaining_time": "0:27:05"}
|
290 |
+
{"current_steps": 268, "total_steps": 295, "loss": 0.4653, "lr": 2.0316755780657705e-06, "epoch": 4.5369978858350954, "percentage": 90.85, "elapsed_time": "4:20:04", "remaining_time": "0:26:12"}
|
291 |
+
{"current_steps": 269, "total_steps": 295, "loss": 0.4597, "lr": 1.8851397540065886e-06, "epoch": 4.553911205073996, "percentage": 91.19, "elapsed_time": "4:21:47", "remaining_time": "0:25:18"}
|
292 |
+
{"current_steps": 270, "total_steps": 295, "loss": 0.4666, "lr": 1.7439606289391032e-06, "epoch": 4.570824524312896, "percentage": 91.53, "elapsed_time": "4:23:30", "remaining_time": "0:24:23"}
|
293 |
+
{"current_steps": 271, "total_steps": 295, "loss": 0.466, "lr": 1.608158044312864e-06, "epoch": 4.587737843551797, "percentage": 91.86, "elapsed_time": "4:25:13", "remaining_time": "0:23:29"}
|
294 |
+
{"current_steps": 272, "total_steps": 295, "loss": 0.4687, "lr": 1.4777510859532763e-06, "epoch": 4.604651162790698, "percentage": 92.2, "elapsed_time": "4:26:55", "remaining_time": "0:22:34"}
|
295 |
+
{"current_steps": 273, "total_steps": 295, "loss": 0.4581, "lr": 1.3527580813792728e-06, "epoch": 4.621564482029599, "percentage": 92.54, "elapsed_time": "4:28:38", "remaining_time": "0:21:38"}
|
296 |
+
{"current_steps": 274, "total_steps": 295, "loss": 0.4628, "lr": 1.2331965972275107e-06, "epoch": 4.638477801268499, "percentage": 92.88, "elapsed_time": "4:30:21", "remaining_time": "0:20:43"}
|
297 |
+
{"current_steps": 275, "total_steps": 295, "loss": 0.4647, "lr": 1.1190834367835701e-06, "epoch": 4.6553911205073994, "percentage": 93.22, "elapsed_time": "4:32:03", "remaining_time": "0:19:47"}
|
298 |
+
{"current_steps": 276, "total_steps": 295, "loss": 0.4659, "lr": 1.010434637620401e-06, "epoch": 4.6723044397463, "percentage": 93.56, "elapsed_time": "4:33:45", "remaining_time": "0:18:50"}
|
299 |
+
{"current_steps": 277, "total_steps": 295, "loss": 0.4635, "lr": 9.072654693443783e-07, "epoch": 4.689217758985201, "percentage": 93.9, "elapsed_time": "4:35:28", "remaining_time": "0:17:54"}
|
300 |
+
{"current_steps": 278, "total_steps": 295, "loss": 0.4625, "lr": 8.095904314492942e-07, "epoch": 4.706131078224102, "percentage": 94.24, "elapsed_time": "4:37:10", "remaining_time": "0:16:56"}
|
301 |
+
{"current_steps": 279, "total_steps": 295, "loss": 0.462, "lr": 7.174232512785973e-07, "epoch": 4.723044397463002, "percentage": 94.58, "elapsed_time": "4:38:53", "remaining_time": "0:15:59"}
|
302 |
+
{"current_steps": 280, "total_steps": 295, "loss": 0.4662, "lr": 6.307768820961269e-07, "epoch": 4.739957716701903, "percentage": 94.92, "elapsed_time": "4:40:38", "remaining_time": "0:15:02"}
|
303 |
+
{"current_steps": 281, "total_steps": 295, "loss": 0.4617, "lr": 5.496635012656626e-07, "epoch": 4.7568710359408035, "percentage": 95.25, "elapsed_time": "4:42:20", "remaining_time": "0:14:04"}
|
304 |
+
{"current_steps": 282, "total_steps": 295, "loss": 0.4607, "lr": 4.740945085394888e-07, "epoch": 4.773784355179704, "percentage": 95.59, "elapsed_time": "4:44:03", "remaining_time": "0:13:05"}
|
305 |
+
{"current_steps": 283, "total_steps": 295, "loss": 0.4616, "lr": 4.040805244562762e-07, "epoch": 4.790697674418604, "percentage": 95.93, "elapsed_time": "4:45:47", "remaining_time": "0:12:07"}
|
306 |
+
{"current_steps": 284, "total_steps": 295, "loss": 0.4633, "lr": 3.3963138884845817e-07, "epoch": 4.807610993657505, "percentage": 96.27, "elapsed_time": "4:47:29", "remaining_time": "0:11:08"}
|
307 |
+
{"current_steps": 285, "total_steps": 295, "loss": 0.4628, "lr": 2.8075615945932333e-07, "epoch": 4.824524312896406, "percentage": 96.61, "elapsed_time": "4:49:12", "remaining_time": "0:10:08"}
|
308 |
+
{"current_steps": 286, "total_steps": 295, "loss": 0.4639, "lr": 2.2746311067004312e-07, "epoch": 4.841437632135307, "percentage": 96.95, "elapsed_time": "4:50:55", "remaining_time": "0:09:09"}
|
309 |
+
{"current_steps": 287, "total_steps": 295, "loss": 0.4625, "lr": 1.7975973233677058e-07, "epoch": 4.858350951374208, "percentage": 97.29, "elapsed_time": "4:52:37", "remaining_time": "0:08:09"}
|
310 |
+
{"current_steps": 288, "total_steps": 295, "loss": 0.4576, "lr": 1.3765272873802914e-07, "epoch": 4.8752642706131075, "percentage": 97.63, "elapsed_time": "4:54:20", "remaining_time": "0:07:09"}
|
311 |
+
{"current_steps": 289, "total_steps": 295, "loss": 0.4616, "lr": 1.0114801763245751e-07, "epoch": 4.892177589852008, "percentage": 97.97, "elapsed_time": "4:56:03", "remaining_time": "0:06:08"}
|
312 |
+
{"current_steps": 290, "total_steps": 295, "loss": 0.4647, "lr": 7.025072942714595e-08, "epoch": 4.909090909090909, "percentage": 98.31, "elapsed_time": "4:57:46", "remaining_time": "0:05:08"}
|
313 |
+
{"current_steps": 291, "total_steps": 295, "loss": 0.4656, "lr": 4.496520645659086e-08, "epoch": 4.92600422832981, "percentage": 98.64, "elapsed_time": "4:59:28", "remaining_time": "0:04:06"}
|
314 |
+
{"current_steps": 292, "total_steps": 295, "loss": 0.4642, "lr": 2.5295002372427436e-08, "epoch": 4.94291754756871, "percentage": 98.98, "elapsed_time": "5:01:11", "remaining_time": "0:03:05"}
|
315 |
+
{"current_steps": 293, "total_steps": 295, "loss": 0.4629, "lr": 1.1242881643993563e-08, "epoch": 4.959830866807611, "percentage": 99.32, "elapsed_time": "5:02:54", "remaining_time": "0:02:04"}
|
316 |
+
{"current_steps": 294, "total_steps": 295, "loss": 0.4655, "lr": 2.8108191698050793e-09, "epoch": 4.976744186046512, "percentage": 99.66, "elapsed_time": "5:04:37", "remaining_time": "0:01:02"}
|
317 |
+
{"current_steps": 295, "total_steps": 295, "loss": 0.4663, "lr": 0.0, "epoch": 4.993657505285412, "percentage": 100.0, "elapsed_time": "5:06:22", "remaining_time": "0:00:00"}
|
318 |
+
{"current_steps": 295, "total_steps": 295, "epoch": 4.993657505285412, "percentage": 100.0, "elapsed_time": "5:09:27", "remaining_time": "0:00:00"}
|