Training in progress, step 2500
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 4968243304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46ca4eafd6d1981d6fa4124792dfb76a9f30263cf09336275f62d54b416d7417
|
3 |
size 4968243304
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4991495816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081596166dbe52040585956da05a2903d5731c3d244c69126f4562f3b0ca486d
|
3 |
size 4991495816
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00223bb08a3aafecd8d60ee0707ce264ca5b2f2aed8b67a8a8d786214bedcd94
|
3 |
size 4932751040
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1691924384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77b6927eb756914035fc3488bba8eb56edfe0af20b24d2550c7bca353788b3da
|
3 |
size 1691924384
|
trainer_log.jsonl
CHANGED
@@ -199,3 +199,53 @@
|
|
199 |
{"current_steps": 1990, "total_steps": 7042, "loss": 0.4092, "lr": 1.8038576797434945e-05, "epoch": 0.5651803464924737, "percentage": 28.26, "elapsed_time": "6:02:49", "remaining_time": "15:21:07"}
|
200 |
{"current_steps": 2000, "total_steps": 7042, "loss": 0.3916, "lr": 1.8008989617058088e-05, "epoch": 0.5680204487361545, "percentage": 28.4, "elapsed_time": "6:04:37", "remaining_time": "15:19:13"}
|
201 |
{"current_steps": 2010, "total_steps": 7042, "loss": 0.3908, "lr": 1.797920559857761e-05, "epoch": 0.5708605509798352, "percentage": 28.54, "elapsed_time": "6:07:31", "remaining_time": "15:20:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
199 |
{"current_steps": 1990, "total_steps": 7042, "loss": 0.4092, "lr": 1.8038576797434945e-05, "epoch": 0.5651803464924737, "percentage": 28.26, "elapsed_time": "6:02:49", "remaining_time": "15:21:07"}
|
200 |
{"current_steps": 2000, "total_steps": 7042, "loss": 0.3916, "lr": 1.8008989617058088e-05, "epoch": 0.5680204487361545, "percentage": 28.4, "elapsed_time": "6:04:37", "remaining_time": "15:19:13"}
|
201 |
{"current_steps": 2010, "total_steps": 7042, "loss": 0.3908, "lr": 1.797920559857761e-05, "epoch": 0.5708605509798352, "percentage": 28.54, "elapsed_time": "6:07:31", "remaining_time": "15:20:05"}
|
202 |
+
{"current_steps": 2020, "total_steps": 7042, "loss": 0.4008, "lr": 1.794922547399967e-05, "epoch": 0.573700653223516, "percentage": 28.69, "elapsed_time": "6:09:18", "remaining_time": "15:18:09"}
|
203 |
+
{"current_steps": 2030, "total_steps": 7042, "loss": 0.3922, "lr": 1.7919049980150155e-05, "epoch": 0.5765407554671969, "percentage": 28.83, "elapsed_time": "6:11:05", "remaining_time": "15:16:13"}
|
204 |
+
{"current_steps": 2040, "total_steps": 7042, "loss": 0.3874, "lr": 1.7888679858656566e-05, "epoch": 0.5793808577108776, "percentage": 28.97, "elapsed_time": "6:12:53", "remaining_time": "15:14:18"}
|
205 |
+
{"current_steps": 2050, "total_steps": 7042, "loss": 0.3915, "lr": 1.7858115855929797e-05, "epoch": 0.5822209599545584, "percentage": 29.11, "elapsed_time": "6:14:43", "remaining_time": "15:12:29"}
|
206 |
+
{"current_steps": 2060, "total_steps": 7042, "loss": 0.3911, "lr": 1.7827358723145803e-05, "epoch": 0.5850610621982392, "percentage": 29.25, "elapsed_time": "6:16:32", "remaining_time": "15:10:38"}
|
207 |
+
{"current_steps": 2070, "total_steps": 7042, "loss": 0.3854, "lr": 1.77964092162271e-05, "epoch": 0.5879011644419199, "percentage": 29.4, "elapsed_time": "6:18:18", "remaining_time": "15:08:41"}
|
208 |
+
{"current_steps": 2080, "total_steps": 7042, "loss": 0.3956, "lr": 1.7765268095824234e-05, "epoch": 0.5907412666856007, "percentage": 29.54, "elapsed_time": "6:20:08", "remaining_time": "15:06:50"}
|
209 |
+
{"current_steps": 2090, "total_steps": 7042, "loss": 0.3844, "lr": 1.7733936127297053e-05, "epoch": 0.5935813689292815, "percentage": 29.68, "elapsed_time": "6:21:57", "remaining_time": "15:05:00"}
|
210 |
+
{"current_steps": 2100, "total_steps": 7042, "loss": 0.3837, "lr": 1.7702414080695907e-05, "epoch": 0.5964214711729622, "percentage": 29.82, "elapsed_time": "6:23:47", "remaining_time": "15:03:10"}
|
211 |
+
{"current_steps": 2110, "total_steps": 7042, "loss": 0.3788, "lr": 1.7670702730742722e-05, "epoch": 0.599261573416643, "percentage": 29.96, "elapsed_time": "6:25:34", "remaining_time": "15:01:14"}
|
212 |
+
{"current_steps": 2120, "total_steps": 7042, "loss": 0.3848, "lr": 1.763880285681196e-05, "epoch": 0.6021016756603238, "percentage": 30.11, "elapsed_time": "6:27:20", "remaining_time": "14:59:18"}
|
213 |
+
{"current_steps": 2130, "total_steps": 7042, "loss": 0.3958, "lr": 1.7606715242911468e-05, "epoch": 0.6049417779040045, "percentage": 30.25, "elapsed_time": "6:29:07", "remaining_time": "14:57:21"}
|
214 |
+
{"current_steps": 2140, "total_steps": 7042, "loss": 0.3877, "lr": 1.7574440677663212e-05, "epoch": 0.6077818801476853, "percentage": 30.39, "elapsed_time": "6:30:56", "remaining_time": "14:55:31"}
|
215 |
+
{"current_steps": 2150, "total_steps": 7042, "loss": 0.3858, "lr": 1.7541979954283864e-05, "epoch": 0.6106219823913661, "percentage": 30.53, "elapsed_time": "6:32:42", "remaining_time": "14:53:32"}
|
216 |
+
{"current_steps": 2160, "total_steps": 7042, "loss": 0.3791, "lr": 1.7509333870565364e-05, "epoch": 0.6134620846350468, "percentage": 30.67, "elapsed_time": "6:34:32", "remaining_time": "14:51:43"}
|
217 |
+
{"current_steps": 2170, "total_steps": 7042, "loss": 0.3903, "lr": 1.7476503228855254e-05, "epoch": 0.6163021868787276, "percentage": 30.82, "elapsed_time": "6:36:21", "remaining_time": "14:49:52"}
|
218 |
+
{"current_steps": 2180, "total_steps": 7042, "loss": 0.3925, "lr": 1.744348883603699e-05, "epoch": 0.6191422891224084, "percentage": 30.96, "elapsed_time": "6:38:10", "remaining_time": "14:48:02"}
|
219 |
+
{"current_steps": 2190, "total_steps": 7042, "loss": 0.3901, "lr": 1.741029150351012e-05, "epoch": 0.6219823913660891, "percentage": 31.1, "elapsed_time": "6:40:00", "remaining_time": "14:46:13"}
|
220 |
+
{"current_steps": 2200, "total_steps": 7042, "loss": 0.3963, "lr": 1.7376912047170312e-05, "epoch": 0.6248224936097699, "percentage": 31.24, "elapsed_time": "6:41:48", "remaining_time": "14:44:20"}
|
221 |
+
{"current_steps": 2210, "total_steps": 7042, "loss": 0.3801, "lr": 1.7343351287389328e-05, "epoch": 0.6276625958534507, "percentage": 31.38, "elapsed_time": "6:43:36", "remaining_time": "14:42:27"}
|
222 |
+
{"current_steps": 2220, "total_steps": 7042, "loss": 0.3961, "lr": 1.730961004899484e-05, "epoch": 0.6305026980971314, "percentage": 31.53, "elapsed_time": "6:45:25", "remaining_time": "14:40:37"}
|
223 |
+
{"current_steps": 2230, "total_steps": 7042, "loss": 0.3914, "lr": 1.727568916125018e-05, "epoch": 0.6333428003408123, "percentage": 31.67, "elapsed_time": "6:47:13", "remaining_time": "14:38:43"}
|
224 |
+
{"current_steps": 2240, "total_steps": 7042, "loss": 0.3853, "lr": 1.724158945783394e-05, "epoch": 0.6361829025844931, "percentage": 31.81, "elapsed_time": "6:49:02", "remaining_time": "14:36:53"}
|
225 |
+
{"current_steps": 2250, "total_steps": 7042, "loss": 0.3939, "lr": 1.72073117768195e-05, "epoch": 0.6390230048281739, "percentage": 31.95, "elapsed_time": "6:50:51", "remaining_time": "14:35:01"}
|
226 |
+
{"current_steps": 2260, "total_steps": 7042, "loss": 0.373, "lr": 1.717285696065441e-05, "epoch": 0.6418631070718546, "percentage": 32.09, "elapsed_time": "6:52:38", "remaining_time": "14:33:06"}
|
227 |
+
{"current_steps": 2270, "total_steps": 7042, "loss": 0.3961, "lr": 1.7138225856139707e-05, "epoch": 0.6447032093155354, "percentage": 32.24, "elapsed_time": "6:54:27", "remaining_time": "14:31:15"}
|
228 |
+
{"current_steps": 2280, "total_steps": 7042, "loss": 0.3874, "lr": 1.7103419314409084e-05, "epoch": 0.6475433115592162, "percentage": 32.38, "elapsed_time": "6:56:16", "remaining_time": "14:29:25"}
|
229 |
+
{"current_steps": 2290, "total_steps": 7042, "loss": 0.3802, "lr": 1.7068438190907987e-05, "epoch": 0.6503834138028969, "percentage": 32.52, "elapsed_time": "6:58:02", "remaining_time": "14:27:29"}
|
230 |
+
{"current_steps": 2300, "total_steps": 7042, "loss": 0.3895, "lr": 1.7033283345372577e-05, "epoch": 0.6532235160465777, "percentage": 32.66, "elapsed_time": "6:59:52", "remaining_time": "14:25:39"}
|
231 |
+
{"current_steps": 2310, "total_steps": 7042, "loss": 0.4052, "lr": 1.6997955641808607e-05, "epoch": 0.6560636182902585, "percentage": 32.8, "elapsed_time": "7:01:44", "remaining_time": "14:23:55"}
|
232 |
+
{"current_steps": 2320, "total_steps": 7042, "loss": 0.3883, "lr": 1.6962455948470197e-05, "epoch": 0.6589037205339392, "percentage": 32.95, "elapsed_time": "7:03:34", "remaining_time": "14:22:07"}
|
233 |
+
{"current_steps": 2330, "total_steps": 7042, "loss": 0.3877, "lr": 1.6926785137838475e-05, "epoch": 0.66174382277762, "percentage": 33.09, "elapsed_time": "7:05:25", "remaining_time": "14:20:20"}
|
234 |
+
{"current_steps": 2340, "total_steps": 7042, "loss": 0.3796, "lr": 1.6890944086600145e-05, "epoch": 0.6645839250213008, "percentage": 33.23, "elapsed_time": "7:07:14", "remaining_time": "14:18:30"}
|
235 |
+
{"current_steps": 2350, "total_steps": 7042, "loss": 0.3828, "lr": 1.685493367562594e-05, "epoch": 0.6674240272649815, "percentage": 33.37, "elapsed_time": "7:09:05", "remaining_time": "14:16:42"}
|
236 |
+
{"current_steps": 2360, "total_steps": 7042, "loss": 0.3836, "lr": 1.6818754789948974e-05, "epoch": 0.6702641295086623, "percentage": 33.51, "elapsed_time": "7:10:55", "remaining_time": "14:14:55"}
|
237 |
+
{"current_steps": 2370, "total_steps": 7042, "loss": 0.388, "lr": 1.678240831874299e-05, "epoch": 0.6731042317523431, "percentage": 33.66, "elapsed_time": "7:12:45", "remaining_time": "14:13:05"}
|
238 |
+
{"current_steps": 2380, "total_steps": 7042, "loss": 0.3803, "lr": 1.674589515530049e-05, "epoch": 0.6759443339960238, "percentage": 33.8, "elapsed_time": "7:14:35", "remaining_time": "14:11:17"}
|
239 |
+
{"current_steps": 2390, "total_steps": 7042, "loss": 0.3812, "lr": 1.670921619701082e-05, "epoch": 0.6787844362397046, "percentage": 33.94, "elapsed_time": "7:16:25", "remaining_time": "14:09:28"}
|
240 |
+
{"current_steps": 2400, "total_steps": 7042, "loss": 0.3792, "lr": 1.6672372345338067e-05, "epoch": 0.6816245384833854, "percentage": 34.08, "elapsed_time": "7:18:11", "remaining_time": "14:07:31"}
|
241 |
+
{"current_steps": 2410, "total_steps": 7042, "loss": 0.3882, "lr": 1.6635364505798946e-05, "epoch": 0.6844646407270661, "percentage": 34.22, "elapsed_time": "7:19:59", "remaining_time": "14:05:39"}
|
242 |
+
{"current_steps": 2420, "total_steps": 7042, "loss": 0.3812, "lr": 1.6598193587940508e-05, "epoch": 0.687304742970747, "percentage": 34.37, "elapsed_time": "7:21:48", "remaining_time": "14:03:48"}
|
243 |
+
{"current_steps": 2430, "total_steps": 7042, "loss": 0.3851, "lr": 1.6560860505317813e-05, "epoch": 0.6901448452144278, "percentage": 34.51, "elapsed_time": "7:23:38", "remaining_time": "14:02:00"}
|
244 |
+
{"current_steps": 2440, "total_steps": 7042, "loss": 0.3926, "lr": 1.652336617547147e-05, "epoch": 0.6929849474581085, "percentage": 34.65, "elapsed_time": "7:25:26", "remaining_time": "14:00:07"}
|
245 |
+
{"current_steps": 2450, "total_steps": 7042, "loss": 0.3811, "lr": 1.648571151990508e-05, "epoch": 0.6958250497017893, "percentage": 34.79, "elapsed_time": "7:27:16", "remaining_time": "13:58:19"}
|
246 |
+
{"current_steps": 2460, "total_steps": 7042, "loss": 0.3944, "lr": 1.6447897464062593e-05, "epoch": 0.6986651519454701, "percentage": 34.93, "elapsed_time": "7:29:03", "remaining_time": "13:56:24"}
|
247 |
+
{"current_steps": 2470, "total_steps": 7042, "loss": 0.3687, "lr": 1.6409924937305567e-05, "epoch": 0.7015052541891508, "percentage": 35.08, "elapsed_time": "7:30:50", "remaining_time": "13:54:31"}
|
248 |
+
{"current_steps": 2480, "total_steps": 7042, "loss": 0.393, "lr": 1.637179487289032e-05, "epoch": 0.7043453564328316, "percentage": 35.22, "elapsed_time": "7:32:36", "remaining_time": "13:52:35"}
|
249 |
+
{"current_steps": 2490, "total_steps": 7042, "loss": 0.3874, "lr": 1.6333508207944987e-05, "epoch": 0.7071854586765124, "percentage": 35.36, "elapsed_time": "7:34:25", "remaining_time": "13:50:44"}
|
250 |
+
{"current_steps": 2500, "total_steps": 7042, "loss": 0.3759, "lr": 1.6295065883446514e-05, "epoch": 0.7100255609201931, "percentage": 35.5, "elapsed_time": "7:36:14", "remaining_time": "13:48:53"}
|
251 |
+
{"current_steps": 2510, "total_steps": 7042, "loss": 0.3839, "lr": 1.6256468844197503e-05, "epoch": 0.7128656631638739, "percentage": 35.64, "elapsed_time": "7:39:09", "remaining_time": "13:49:02"}
|