Training in progress, epoch 4
Browse files- model-00001-of-00014.safetensors +1 -1
- model-00002-of-00014.safetensors +1 -1
- model-00003-of-00014.safetensors +1 -1
- model-00004-of-00014.safetensors +1 -1
- model-00005-of-00014.safetensors +1 -1
- model-00006-of-00014.safetensors +1 -1
- model-00007-of-00014.safetensors +1 -1
- model-00008-of-00014.safetensors +1 -1
- model-00009-of-00014.safetensors +1 -1
- model-00010-of-00014.safetensors +1 -1
- model-00011-of-00014.safetensors +1 -1
- model-00012-of-00014.safetensors +1 -1
- model-00013-of-00014.safetensors +1 -1
- model-00014-of-00014.safetensors +1 -1
- trainer_log.jsonl +55 -0
model-00001-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4891730992
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9eaeea74ba3c9e3fe32a1a46ed3532d0989a24941b85c20370cef2562d6c88a
|
3 |
size 4891730992
|
model-00002-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b512ec911eb2e9933dee046e39017506808c15c9f72aac27295a316bd1a890
|
3 |
size 4876059352
|
model-00003-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3fba1003c6b3dc2ed5d8dc142e66948b4fff08089c31f6b71046a9369f05148
|
3 |
size 4876059384
|
model-00004-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:905d8db55a0d0fc9de66842e0b53f3941c761f668b8f87759048bb1739a2b91f
|
3 |
size 4876059416
|
model-00005-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:748858eb186162ab1ede1e20ee21e1b561953327c80a925f9a8d89d0963e60bf
|
3 |
size 4876059416
|
model-00006-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb9c6024687379fe88db7af38d547b65cf28cd621b10a6e48c5cb9afb196d0a
|
3 |
size 4876059416
|
model-00007-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12d3e6f2ba2272ba6ec573197f28aeebb4a9719ec10b2b431f46851a4d5339d3
|
3 |
size 4876059416
|
model-00008-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb5d2528b63b8517ab84313cf4554f4881670c2d34097c22e01b2e9024bc1b2b
|
3 |
size 4876059416
|
model-00009-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b1b6adecc9dde2434537781cac44fce728e3100e49ed4d2bf6acacfd498507a
|
3 |
size 4876059416
|
model-00010-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f9d8fd0e0d07573161f8d122fb4f4f97d730e2fc743004739b26ac24b81c31c
|
3 |
size 4876059416
|
model-00011-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d7ebcb23e684080daa555759b68ed7afd2c1317595174107711cfcaaf90dffe
|
3 |
size 4876059416
|
model-00012-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f73c256da60e14f87b42c8ceef36481b5e6e5da56ee8c81a7067fbcbc3ae4b3
|
3 |
size 4876059416
|
model-00013-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4876059416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6360807bdd6c793507c622b821748cc402dc606d8965aadf91ab4ac2a49bdfb8
|
3 |
size 4876059416
|
model-00014-of-00014.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2123397800
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea9300b52f811836931c6e0f60715bc4d41b3c09764e92966099268a9bb646f
|
3 |
size 2123397800
|
trainer_log.jsonl
CHANGED
@@ -239,3 +239,58 @@
|
|
239 |
{"current_steps": 239, "total_steps": 295, "loss": 0.3164, "lr": 8.495796041596379e-06, "epoch": 4.016806722689076, "percentage": 81.02, "elapsed_time": "12:20:23", "remaining_time": "2:53:28"}
|
240 |
{"current_steps": 240, "total_steps": 295, "loss": 0.3188, "lr": 8.205822343465865e-06, "epoch": 4.033613445378151, "percentage": 81.36, "elapsed_time": "12:23:23", "remaining_time": "2:50:21"}
|
241 |
{"current_steps": 241, "total_steps": 295, "loss": 0.3163, "lr": 7.92031702953762e-06, "epoch": 4.050420168067227, "percentage": 81.69, "elapsed_time": "12:26:24", "remaining_time": "2:47:14"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
239 |
{"current_steps": 239, "total_steps": 295, "loss": 0.3164, "lr": 8.495796041596379e-06, "epoch": 4.016806722689076, "percentage": 81.02, "elapsed_time": "12:20:23", "remaining_time": "2:53:28"}
|
240 |
{"current_steps": 240, "total_steps": 295, "loss": 0.3188, "lr": 8.205822343465865e-06, "epoch": 4.033613445378151, "percentage": 81.36, "elapsed_time": "12:23:23", "remaining_time": "2:50:21"}
|
241 |
{"current_steps": 241, "total_steps": 295, "loss": 0.3163, "lr": 7.92031702953762e-06, "epoch": 4.050420168067227, "percentage": 81.69, "elapsed_time": "12:26:24", "remaining_time": "2:47:14"}
|
242 |
+
{"current_steps": 242, "total_steps": 295, "loss": 0.3105, "lr": 7.639320225002106e-06, "epoch": 4.067226890756302, "percentage": 82.03, "elapsed_time": "12:29:25", "remaining_time": "2:44:07"}
|
243 |
+
{"current_steps": 243, "total_steps": 295, "loss": 0.3055, "lr": 7.3628714214195505e-06, "epoch": 4.084033613445378, "percentage": 82.37, "elapsed_time": "12:32:25", "remaining_time": "2:41:00"}
|
244 |
+
{"current_steps": 244, "total_steps": 295, "loss": 0.3236, "lr": 7.091009471169808e-06, "epoch": 4.100840336134453, "percentage": 82.71, "elapsed_time": "12:35:26", "remaining_time": "2:37:53"}
|
245 |
+
{"current_steps": 245, "total_steps": 295, "loss": 0.3193, "lr": 6.82377258199193e-06, "epoch": 4.117647058823529, "percentage": 83.05, "elapsed_time": "12:38:44", "remaining_time": "2:34:50"}
|
246 |
+
{"current_steps": 246, "total_steps": 295, "loss": 0.3203, "lr": 6.561198311614458e-06, "epoch": 4.1344537815126055, "percentage": 83.39, "elapsed_time": "12:41:45", "remaining_time": "2:31:43"}
|
247 |
+
{"current_steps": 247, "total_steps": 295, "loss": 0.3158, "lr": 6.303323562477044e-06, "epoch": 4.151260504201681, "percentage": 83.73, "elapsed_time": "12:44:45", "remaining_time": "2:28:37"}
|
248 |
+
{"current_steps": 248, "total_steps": 295, "loss": 0.3164, "lr": 6.050184576544089e-06, "epoch": 4.168067226890757, "percentage": 84.07, "elapsed_time": "12:47:46", "remaining_time": "2:25:30"}
|
249 |
+
{"current_steps": 249, "total_steps": 295, "loss": 0.3098, "lr": 5.801816930211304e-06, "epoch": 4.184873949579832, "percentage": 84.41, "elapsed_time": "12:50:47", "remaining_time": "2:22:23"}
|
250 |
+
{"current_steps": 250, "total_steps": 295, "loss": 0.3172, "lr": 5.558255529305779e-06, "epoch": 4.201680672268908, "percentage": 84.75, "elapsed_time": "12:53:47", "remaining_time": "2:19:16"}
|
251 |
+
{"current_steps": 251, "total_steps": 295, "loss": 0.3101, "lr": 5.319534604180239e-06, "epoch": 4.218487394957983, "percentage": 85.08, "elapsed_time": "12:56:48", "remaining_time": "2:16:10"}
|
252 |
+
{"current_steps": 252, "total_steps": 295, "loss": 0.3088, "lr": 5.085687704902311e-06, "epoch": 4.235294117647059, "percentage": 85.42, "elapsed_time": "12:59:54", "remaining_time": "2:13:04"}
|
253 |
+
{"current_steps": 253, "total_steps": 295, "loss": 0.317, "lr": 4.856747696539352e-06, "epoch": 4.2521008403361344, "percentage": 85.76, "elapsed_time": "13:03:07", "remaining_time": "2:10:00"}
|
254 |
+
{"current_steps": 254, "total_steps": 295, "loss": 0.3114, "lr": 4.632746754539592e-06, "epoch": 4.26890756302521, "percentage": 86.1, "elapsed_time": "13:06:07", "remaining_time": "2:06:53"}
|
255 |
+
{"current_steps": 255, "total_steps": 295, "loss": 0.315, "lr": 4.4137163602101114e-06, "epoch": 4.285714285714286, "percentage": 86.44, "elapsed_time": "13:09:08", "remaining_time": "2:03:47"}
|
256 |
+
{"current_steps": 256, "total_steps": 295, "loss": 0.3167, "lr": 4.199687296292463e-06, "epoch": 4.302521008403361, "percentage": 86.78, "elapsed_time": "13:12:08", "remaining_time": "2:00:40"}
|
257 |
+
{"current_steps": 257, "total_steps": 295, "loss": 0.3209, "lr": 3.990689642636451e-06, "epoch": 4.319327731092437, "percentage": 87.12, "elapsed_time": "13:15:09", "remaining_time": "1:57:34"}
|
258 |
+
{"current_steps": 258, "total_steps": 295, "loss": 0.3166, "lr": 3.786752771972633e-06, "epoch": 4.336134453781512, "percentage": 87.46, "elapsed_time": "13:18:09", "remaining_time": "1:54:27"}
|
259 |
+
{"current_steps": 259, "total_steps": 295, "loss": 0.3127, "lr": 3.5879053457842727e-06, "epoch": 4.352941176470588, "percentage": 87.8, "elapsed_time": "13:21:10", "remaining_time": "1:51:21"}
|
260 |
+
{"current_steps": 260, "total_steps": 295, "loss": 0.3207, "lr": 3.3941753102792617e-06, "epoch": 4.369747899159664, "percentage": 88.14, "elapsed_time": "13:24:27", "remaining_time": "1:48:17"}
|
261 |
+
{"current_steps": 261, "total_steps": 295, "loss": 0.3097, "lr": 3.205589892462464e-06, "epoch": 4.38655462184874, "percentage": 88.47, "elapsed_time": "13:27:28", "remaining_time": "1:45:11"}
|
262 |
+
{"current_steps": 262, "total_steps": 295, "loss": 0.3086, "lr": 3.0221755963092535e-06, "epoch": 4.4033613445378155, "percentage": 88.81, "elapsed_time": "13:30:28", "remaining_time": "1:42:04"}
|
263 |
+
{"current_steps": 263, "total_steps": 295, "loss": 0.3235, "lr": 2.8439581990406282e-06, "epoch": 4.420168067226891, "percentage": 89.15, "elapsed_time": "13:33:29", "remaining_time": "1:38:58"}
|
264 |
+
{"current_steps": 264, "total_steps": 295, "loss": 0.3113, "lr": 2.670962747500405e-06, "epoch": 4.436974789915967, "percentage": 89.49, "elapsed_time": "13:36:29", "remaining_time": "1:35:52"}
|
265 |
+
{"current_steps": 265, "total_steps": 295, "loss": 0.3207, "lr": 2.5032135546351644e-06, "epoch": 4.453781512605042, "percentage": 89.83, "elapsed_time": "13:39:30", "remaining_time": "1:32:46"}
|
266 |
+
{"current_steps": 266, "total_steps": 295, "loss": 0.3185, "lr": 2.3407341960772543e-06, "epoch": 4.470588235294118, "percentage": 90.17, "elapsed_time": "13:42:30", "remaining_time": "1:29:40"}
|
267 |
+
{"current_steps": 267, "total_steps": 295, "loss": 0.3148, "lr": 2.1835475068314692e-06, "epoch": 4.487394957983193, "percentage": 90.51, "elapsed_time": "13:45:37", "remaining_time": "1:26:34"}
|
268 |
+
{"current_steps": 268, "total_steps": 295, "loss": 0.3202, "lr": 2.0316755780657705e-06, "epoch": 4.504201680672269, "percentage": 90.85, "elapsed_time": "13:48:49", "remaining_time": "1:23:30"}
|
269 |
+
{"current_steps": 269, "total_steps": 295, "loss": 0.3099, "lr": 1.8851397540065886e-06, "epoch": 4.5210084033613445, "percentage": 91.19, "elapsed_time": "13:51:49", "remaining_time": "1:20:24"}
|
270 |
+
{"current_steps": 270, "total_steps": 295, "loss": 0.3147, "lr": 1.7439606289391032e-06, "epoch": 4.53781512605042, "percentage": 91.53, "elapsed_time": "13:54:50", "remaining_time": "1:17:17"}
|
271 |
+
{"current_steps": 271, "total_steps": 295, "loss": 0.308, "lr": 1.608158044312864e-06, "epoch": 4.554621848739496, "percentage": 91.86, "elapsed_time": "13:57:50", "remaining_time": "1:14:12"}
|
272 |
+
{"current_steps": 272, "total_steps": 295, "loss": 0.3141, "lr": 1.4777510859532763e-06, "epoch": 4.571428571428571, "percentage": 92.2, "elapsed_time": "14:00:51", "remaining_time": "1:11:06"}
|
273 |
+
{"current_steps": 273, "total_steps": 295, "loss": 0.3141, "lr": 1.3527580813792728e-06, "epoch": 4.588235294117647, "percentage": 92.54, "elapsed_time": "14:03:52", "remaining_time": "1:08:00"}
|
274 |
+
{"current_steps": 274, "total_steps": 295, "loss": 0.319, "lr": 1.2331965972275107e-06, "epoch": 4.605042016806722, "percentage": 92.88, "elapsed_time": "14:06:52", "remaining_time": "1:04:54"}
|
275 |
+
{"current_steps": 275, "total_steps": 295, "loss": 0.3131, "lr": 1.1190834367835701e-06, "epoch": 4.621848739495798, "percentage": 93.22, "elapsed_time": "14:10:11", "remaining_time": "1:01:49"}
|
276 |
+
{"current_steps": 276, "total_steps": 295, "loss": 0.3211, "lr": 1.010434637620401e-06, "epoch": 4.6386554621848735, "percentage": 93.56, "elapsed_time": "14:13:11", "remaining_time": "0:58:44"}
|
277 |
+
{"current_steps": 277, "total_steps": 295, "loss": 0.3087, "lr": 9.072654693443783e-07, "epoch": 4.65546218487395, "percentage": 93.9, "elapsed_time": "14:16:12", "remaining_time": "0:55:38"}
|
278 |
+
{"current_steps": 278, "total_steps": 295, "loss": 0.3155, "lr": 8.095904314492942e-07, "epoch": 4.6722689075630255, "percentage": 94.24, "elapsed_time": "14:19:13", "remaining_time": "0:52:32"}
|
279 |
+
{"current_steps": 279, "total_steps": 295, "loss": 0.3158, "lr": 7.174232512785973e-07, "epoch": 4.689075630252101, "percentage": 94.58, "elapsed_time": "14:22:14", "remaining_time": "0:49:26"}
|
280 |
+
{"current_steps": 280, "total_steps": 295, "loss": 0.3155, "lr": 6.307768820961269e-07, "epoch": 4.705882352941177, "percentage": 94.92, "elapsed_time": "14:25:14", "remaining_time": "0:46:21"}
|
281 |
+
{"current_steps": 281, "total_steps": 295, "loss": 0.3205, "lr": 5.496635012656626e-07, "epoch": 4.722689075630252, "percentage": 95.25, "elapsed_time": "14:28:15", "remaining_time": "0:43:15"}
|
282 |
+
{"current_steps": 282, "total_steps": 295, "loss": 0.3102, "lr": 4.740945085394888e-07, "epoch": 4.739495798319328, "percentage": 95.59, "elapsed_time": "14:31:22", "remaining_time": "0:40:10"}
|
283 |
+
{"current_steps": 283, "total_steps": 295, "loss": 0.3197, "lr": 4.040805244562762e-07, "epoch": 4.756302521008403, "percentage": 95.93, "elapsed_time": "14:34:33", "remaining_time": "0:37:05"}
|
284 |
+
{"current_steps": 284, "total_steps": 295, "loss": 0.3099, "lr": 3.3963138884845817e-07, "epoch": 4.773109243697479, "percentage": 96.27, "elapsed_time": "14:37:33", "remaining_time": "0:33:59"}
|
285 |
+
{"current_steps": 285, "total_steps": 295, "loss": 0.3174, "lr": 2.8075615945932333e-07, "epoch": 4.7899159663865545, "percentage": 96.61, "elapsed_time": "14:40:34", "remaining_time": "0:30:53"}
|
286 |
+
{"current_steps": 286, "total_steps": 295, "loss": 0.3195, "lr": 2.2746311067004312e-07, "epoch": 4.80672268907563, "percentage": 96.95, "elapsed_time": "14:43:34", "remaining_time": "0:27:48"}
|
287 |
+
{"current_steps": 287, "total_steps": 295, "loss": 0.3181, "lr": 1.7975973233677058e-07, "epoch": 4.823529411764706, "percentage": 97.29, "elapsed_time": "14:46:35", "remaining_time": "0:24:42"}
|
288 |
+
{"current_steps": 288, "total_steps": 295, "loss": 0.31, "lr": 1.3765272873802914e-07, "epoch": 4.840336134453781, "percentage": 97.63, "elapsed_time": "14:49:35", "remaining_time": "0:21:37"}
|
289 |
+
{"current_steps": 289, "total_steps": 295, "loss": 0.3206, "lr": 1.0114801763245751e-07, "epoch": 4.857142857142857, "percentage": 97.97, "elapsed_time": "14:52:36", "remaining_time": "0:18:31"}
|
290 |
+
{"current_steps": 290, "total_steps": 295, "loss": 0.31, "lr": 7.025072942714595e-08, "epoch": 4.873949579831933, "percentage": 98.31, "elapsed_time": "14:55:53", "remaining_time": "0:15:26"}
|
291 |
+
{"current_steps": 291, "total_steps": 295, "loss": 0.3187, "lr": 4.496520645659086e-08, "epoch": 4.890756302521009, "percentage": 98.64, "elapsed_time": "14:58:54", "remaining_time": "0:12:21"}
|
292 |
+
{"current_steps": 292, "total_steps": 295, "loss": 0.3135, "lr": 2.5295002372427436e-08, "epoch": 4.907563025210084, "percentage": 98.98, "elapsed_time": "15:01:54", "remaining_time": "0:09:15"}
|
293 |
+
{"current_steps": 293, "total_steps": 295, "loss": 0.3209, "lr": 1.1242881643993563e-08, "epoch": 4.92436974789916, "percentage": 99.32, "elapsed_time": "15:04:55", "remaining_time": "0:06:10"}
|
294 |
+
{"current_steps": 294, "total_steps": 295, "loss": 0.3105, "lr": 2.8108191698050793e-09, "epoch": 4.9411764705882355, "percentage": 99.66, "elapsed_time": "15:07:55", "remaining_time": "0:03:05"}
|
295 |
+
{"current_steps": 295, "total_steps": 295, "loss": 0.316, "lr": 0.0, "epoch": 4.957983193277311, "percentage": 100.0, "elapsed_time": "15:10:56", "remaining_time": "0:00:00"}
|
296 |
+
{"current_steps": 295, "total_steps": 295, "epoch": 4.957983193277311, "percentage": 100.0, "elapsed_time": "15:17:02", "remaining_time": "0:00:00"}
|