sedrickkeh commited on
Commit
b74a431
·
verified ·
1 Parent(s): 0c36e87

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b937356a11de7765df782058109eb92a08bd80f1facbfdcc5fed0129d2f13d7e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5649322b9e77d2f4d4eaa3dd9da87ed158c215f66b2cb96eb5164f23f7bcb02
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:320bd4c3cc2080091c18f3ab0b70d39c5d83b3cd67960ed84e4abf3ae1a4ab7d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4596af4a97c272a84010bc1487d6d8373bb06a6f823cb09389371e5f389653
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:e39d139b061470c718265467e436a4cf9282a3a1ae657bd20563dc789a968892
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c562c41b2b63ca20e380a565625de9ec9b3caabc58be1e4fb8b1a99b8e6ebb
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:a367c3f610e995972c4c30fcb7677595f906f2f3529b0a78dc89e6b92e05a0bc
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234f1882e82b83ad4d5f2c7429db860ddb962dd514bc2c608a6faa6df72aa82c
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -199,3 +199,70 @@
199
  {"current_steps": 199, "total_steps": 335, "loss": 0.3458, "lr": 3.396951433983266e-05, "epoch": 2.9646182495344506, "percentage": 59.4, "elapsed_time": "8:25:05", "remaining_time": "5:45:11"}
200
  {"current_steps": 200, "total_steps": 335, "loss": 0.3463, "lr": 3.355713475223382e-05, "epoch": 2.97951582867784, "percentage": 59.7, "elapsed_time": "8:27:35", "remaining_time": "5:42:37"}
201
  {"current_steps": 201, "total_steps": 335, "loss": 0.3491, "lr": 3.314545701068475e-05, "epoch": 2.994413407821229, "percentage": 60.0, "elapsed_time": "8:30:05", "remaining_time": "5:40:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199
  {"current_steps": 199, "total_steps": 335, "loss": 0.3458, "lr": 3.396951433983266e-05, "epoch": 2.9646182495344506, "percentage": 59.4, "elapsed_time": "8:25:05", "remaining_time": "5:45:11"}
200
  {"current_steps": 200, "total_steps": 335, "loss": 0.3463, "lr": 3.355713475223382e-05, "epoch": 2.97951582867784, "percentage": 59.7, "elapsed_time": "8:27:35", "remaining_time": "5:42:37"}
201
  {"current_steps": 201, "total_steps": 335, "loss": 0.3491, "lr": 3.314545701068475e-05, "epoch": 2.994413407821229, "percentage": 60.0, "elapsed_time": "8:30:05", "remaining_time": "5:40:03"}
202
+ {"current_steps": 202, "total_steps": 335, "loss": 0.6352, "lr": 3.2734525960822545e-05, "epoch": 3.009310986964618, "percentage": 60.3, "elapsed_time": "8:34:13", "remaining_time": "5:38:34"}
203
+ {"current_steps": 203, "total_steps": 335, "loss": 0.3224, "lr": 3.232438636694431e-05, "epoch": 3.0242085661080074, "percentage": 60.6, "elapsed_time": "8:36:43", "remaining_time": "5:35:59"}
204
+ {"current_steps": 204, "total_steps": 335, "loss": 0.3206, "lr": 3.191508290713079e-05, "epoch": 3.0391061452513966, "percentage": 60.9, "elapsed_time": "8:39:14", "remaining_time": "5:33:26"}
205
+ {"current_steps": 205, "total_steps": 335, "loss": 0.3264, "lr": 3.150666016837947e-05, "epoch": 3.0540037243947857, "percentage": 61.19, "elapsed_time": "8:41:45", "remaining_time": "5:30:52"}
206
+ {"current_steps": 206, "total_steps": 335, "loss": 0.327, "lr": 3.109916264174743e-05, "epoch": 3.068901303538175, "percentage": 61.49, "elapsed_time": "8:44:15", "remaining_time": "5:28:18"}
207
+ {"current_steps": 207, "total_steps": 335, "loss": 0.3223, "lr": 3.069263471750493e-05, "epoch": 3.083798882681564, "percentage": 61.79, "elapsed_time": "8:46:46", "remaining_time": "5:25:43"}
208
+ {"current_steps": 208, "total_steps": 335, "loss": 0.3238, "lr": 3.0287120680299677e-05, "epoch": 3.0986964618249533, "percentage": 62.09, "elapsed_time": "8:49:17", "remaining_time": "5:23:10"}
209
+ {"current_steps": 209, "total_steps": 335, "loss": 0.3249, "lr": 2.988266470433277e-05, "epoch": 3.1135940409683425, "percentage": 62.39, "elapsed_time": "8:51:47", "remaining_time": "5:20:36"}
210
+ {"current_steps": 210, "total_steps": 335, "loss": 0.3243, "lr": 2.9479310848546644e-05, "epoch": 3.1284916201117317, "percentage": 62.69, "elapsed_time": "8:54:18", "remaining_time": "5:18:02"}
211
+ {"current_steps": 211, "total_steps": 335, "loss": 0.3203, "lr": 2.9077103051825567e-05, "epoch": 3.143389199255121, "percentage": 62.99, "elapsed_time": "8:56:48", "remaining_time": "5:15:28"}
212
+ {"current_steps": 212, "total_steps": 335, "loss": 0.3237, "lr": 2.8676085128209133e-05, "epoch": 3.1582867783985105, "percentage": 63.28, "elapsed_time": "8:59:24", "remaining_time": "5:12:57"}
213
+ {"current_steps": 213, "total_steps": 335, "loss": 0.3196, "lr": 2.8276300762119553e-05, "epoch": 3.1731843575418996, "percentage": 63.58, "elapsed_time": "9:01:56", "remaining_time": "5:10:24"}
214
+ {"current_steps": 214, "total_steps": 335, "loss": 0.3196, "lr": 2.787779350360286e-05, "epoch": 3.188081936685289, "percentage": 63.88, "elapsed_time": "9:04:28", "remaining_time": "5:07:51"}
215
+ {"current_steps": 215, "total_steps": 335, "loss": 0.3192, "lr": 2.748060676358484e-05, "epoch": 3.202979515828678, "percentage": 64.18, "elapsed_time": "9:06:59", "remaining_time": "5:05:18"}
216
+ {"current_steps": 216, "total_steps": 335, "loss": 0.3192, "lr": 2.7084783809142164e-05, "epoch": 3.217877094972067, "percentage": 64.48, "elapsed_time": "9:09:30", "remaining_time": "5:02:44"}
217
+ {"current_steps": 217, "total_steps": 335, "loss": 0.328, "lr": 2.6690367758789046e-05, "epoch": 3.2327746741154564, "percentage": 64.78, "elapsed_time": "9:12:01", "remaining_time": "5:00:10"}
218
+ {"current_steps": 218, "total_steps": 335, "loss": 0.322, "lr": 2.6297401577780295e-05, "epoch": 3.2476722532588456, "percentage": 65.07, "elapsed_time": "9:14:33", "remaining_time": "4:57:37"}
219
+ {"current_steps": 219, "total_steps": 335, "loss": 0.319, "lr": 2.5905928073430854e-05, "epoch": 3.2625698324022347, "percentage": 65.37, "elapsed_time": "9:17:05", "remaining_time": "4:55:04"}
220
+ {"current_steps": 220, "total_steps": 335, "loss": 0.3237, "lr": 2.5515989890452674e-05, "epoch": 3.277467411545624, "percentage": 65.67, "elapsed_time": "9:19:36", "remaining_time": "4:52:31"}
221
+ {"current_steps": 221, "total_steps": 335, "loss": 0.3205, "lr": 2.5127629506309264e-05, "epoch": 3.292364990689013, "percentage": 65.97, "elapsed_time": "9:22:07", "remaining_time": "4:49:57"}
222
+ {"current_steps": 222, "total_steps": 335, "loss": 0.3188, "lr": 2.474088922658842e-05, "epoch": 3.3072625698324023, "percentage": 66.27, "elapsed_time": "9:24:40", "remaining_time": "4:47:25"}
223
+ {"current_steps": 223, "total_steps": 335, "loss": 0.3195, "lr": 2.4355811180393767e-05, "epoch": 3.3221601489757915, "percentage": 66.57, "elapsed_time": "9:27:11", "remaining_time": "4:44:52"}
224
+ {"current_steps": 224, "total_steps": 335, "loss": 0.3201, "lr": 2.397243731575543e-05, "epoch": 3.3370577281191807, "percentage": 66.87, "elapsed_time": "9:29:42", "remaining_time": "4:42:18"}
225
+ {"current_steps": 225, "total_steps": 335, "loss": 0.32, "lr": 2.359080939506052e-05, "epoch": 3.35195530726257, "percentage": 67.16, "elapsed_time": "9:32:12", "remaining_time": "4:39:44"}
226
+ {"current_steps": 226, "total_steps": 335, "loss": 0.3208, "lr": 2.3210968990503755e-05, "epoch": 3.366852886405959, "percentage": 67.46, "elapsed_time": "9:34:43", "remaining_time": "4:37:11"}
227
+ {"current_steps": 227, "total_steps": 335, "loss": 0.317, "lr": 2.2832957479558866e-05, "epoch": 3.381750465549348, "percentage": 67.76, "elapsed_time": "9:37:13", "remaining_time": "4:34:37"}
228
+ {"current_steps": 228, "total_steps": 335, "loss": 0.3179, "lr": 2.245681604047114e-05, "epoch": 3.3966480446927374, "percentage": 68.06, "elapsed_time": "9:39:43", "remaining_time": "4:32:03"}
229
+ {"current_steps": 229, "total_steps": 335, "loss": 0.3228, "lr": 2.2082585647771807e-05, "epoch": 3.4115456238361266, "percentage": 68.36, "elapsed_time": "9:42:13", "remaining_time": "4:29:30"}
230
+ {"current_steps": 230, "total_steps": 335, "loss": 0.3222, "lr": 2.171030706781446e-05, "epoch": 3.4264432029795158, "percentage": 68.66, "elapsed_time": "9:44:44", "remaining_time": "4:26:56"}
231
+ {"current_steps": 231, "total_steps": 335, "loss": 0.3181, "lr": 2.1340020854334246e-05, "epoch": 3.441340782122905, "percentage": 68.96, "elapsed_time": "9:47:15", "remaining_time": "4:24:23"}
232
+ {"current_steps": 232, "total_steps": 335, "loss": 0.3225, "lr": 2.0971767344030144e-05, "epoch": 3.456238361266294, "percentage": 69.25, "elapsed_time": "9:49:45", "remaining_time": "4:21:49"}
233
+ {"current_steps": 233, "total_steps": 335, "loss": 0.321, "lr": 2.0605586652170998e-05, "epoch": 3.4711359404096833, "percentage": 69.55, "elapsed_time": "9:52:16", "remaining_time": "4:19:16"}
234
+ {"current_steps": 234, "total_steps": 335, "loss": 0.3252, "lr": 2.0241518668225595e-05, "epoch": 3.4860335195530725, "percentage": 69.85, "elapsed_time": "9:54:46", "remaining_time": "4:16:43"}
235
+ {"current_steps": 235, "total_steps": 335, "loss": 0.3173, "lr": 1.98796030515173e-05, "epoch": 3.5009310986964617, "percentage": 70.15, "elapsed_time": "9:57:17", "remaining_time": "4:14:10"}
236
+ {"current_steps": 236, "total_steps": 335, "loss": 0.3188, "lr": 1.9519879226903903e-05, "epoch": 3.515828677839851, "percentage": 70.45, "elapsed_time": "9:59:48", "remaining_time": "4:11:36"}
237
+ {"current_steps": 237, "total_steps": 335, "loss": 0.3174, "lr": 1.9162386380482795e-05, "epoch": 3.5307262569832405, "percentage": 70.75, "elapsed_time": "10:02:18", "remaining_time": "4:09:03"}
238
+ {"current_steps": 238, "total_steps": 335, "loss": 0.3219, "lr": 1.88071634553224e-05, "epoch": 3.5456238361266292, "percentage": 71.04, "elapsed_time": "10:04:49", "remaining_time": "4:06:30"}
239
+ {"current_steps": 239, "total_steps": 335, "loss": 0.3252, "lr": 1.845424914721988e-05, "epoch": 3.560521415270019, "percentage": 71.34, "elapsed_time": "10:07:20", "remaining_time": "4:03:57"}
240
+ {"current_steps": 240, "total_steps": 335, "loss": 0.3163, "lr": 1.81036819004859e-05, "epoch": 3.5754189944134076, "percentage": 71.64, "elapsed_time": "10:09:50", "remaining_time": "4:01:23"}
241
+ {"current_steps": 241, "total_steps": 335, "loss": 0.3259, "lr": 1.7755499903756704e-05, "epoch": 3.5903165735567972, "percentage": 71.94, "elapsed_time": "10:12:20", "remaining_time": "3:58:50"}
242
+ {"current_steps": 242, "total_steps": 335, "loss": 0.3191, "lr": 1.7409741085834066e-05, "epoch": 3.605214152700186, "percentage": 72.24, "elapsed_time": "10:14:51", "remaining_time": "3:56:17"}
243
+ {"current_steps": 243, "total_steps": 335, "loss": 0.3211, "lr": 1.7066443111553627e-05, "epoch": 3.6201117318435756, "percentage": 72.54, "elapsed_time": "10:17:22", "remaining_time": "3:53:44"}
244
+ {"current_steps": 244, "total_steps": 335, "loss": 0.3225, "lr": 1.6725643377681893e-05, "epoch": 3.635009310986965, "percentage": 72.84, "elapsed_time": "10:19:52", "remaining_time": "3:51:11"}
245
+ {"current_steps": 245, "total_steps": 335, "loss": 0.3214, "lr": 1.638737900884239e-05, "epoch": 3.649906890130354, "percentage": 73.13, "elapsed_time": "10:22:23", "remaining_time": "3:48:38"}
246
+ {"current_steps": 246, "total_steps": 335, "loss": 0.3252, "lr": 1.6051686853471667e-05, "epoch": 3.664804469273743, "percentage": 73.43, "elapsed_time": "10:24:54", "remaining_time": "3:46:05"}
247
+ {"current_steps": 247, "total_steps": 335, "loss": 0.3235, "lr": 1.5718603479805113e-05, "epoch": 3.6797020484171323, "percentage": 73.73, "elapsed_time": "10:27:27", "remaining_time": "3:43:32"}
248
+ {"current_steps": 248, "total_steps": 335, "loss": 0.3228, "lr": 1.538816517189356e-05, "epoch": 3.6945996275605215, "percentage": 74.03, "elapsed_time": "10:29:57", "remaining_time": "3:40:59"}
249
+ {"current_steps": 249, "total_steps": 335, "loss": 0.3234, "lr": 1.5060407925650662e-05, "epoch": 3.7094972067039107, "percentage": 74.33, "elapsed_time": "10:32:28", "remaining_time": "3:38:26"}
250
+ {"current_steps": 250, "total_steps": 335, "loss": 0.3192, "lr": 1.4735367444931722e-05, "epoch": 3.7243947858473, "percentage": 74.63, "elapsed_time": "10:35:01", "remaining_time": "3:35:54"}
251
+ {"current_steps": 251, "total_steps": 335, "loss": 0.3162, "lr": 1.4413079137644358e-05, "epoch": 3.739292364990689, "percentage": 74.93, "elapsed_time": "10:37:33", "remaining_time": "3:33:21"}
252
+ {"current_steps": 252, "total_steps": 335, "loss": 0.3189, "lr": 1.4093578111891333e-05, "epoch": 3.7541899441340782, "percentage": 75.22, "elapsed_time": "10:40:03", "remaining_time": "3:30:48"}
253
+ {"current_steps": 253, "total_steps": 335, "loss": 0.3258, "lr": 1.377689917214617e-05, "epoch": 3.7690875232774674, "percentage": 75.52, "elapsed_time": "10:42:36", "remaining_time": "3:28:16"}
254
+ {"current_steps": 254, "total_steps": 335, "loss": 0.3195, "lr": 1.3463076815461703e-05, "epoch": 3.7839851024208566, "percentage": 75.82, "elapsed_time": "10:45:07", "remaining_time": "3:25:43"}
255
+ {"current_steps": 255, "total_steps": 335, "loss": 0.314, "lr": 1.3152145227712221e-05, "epoch": 3.798882681564246, "percentage": 76.12, "elapsed_time": "10:47:37", "remaining_time": "3:23:10"}
256
+ {"current_steps": 256, "total_steps": 335, "loss": 0.3255, "lr": 1.284413827986946e-05, "epoch": 3.813780260707635, "percentage": 76.42, "elapsed_time": "10:50:08", "remaining_time": "3:20:37"}
257
+ {"current_steps": 257, "total_steps": 335, "loss": 0.3261, "lr": 1.2539089524312855e-05, "epoch": 3.828677839851024, "percentage": 76.72, "elapsed_time": "10:52:41", "remaining_time": "3:18:05"}
258
+ {"current_steps": 258, "total_steps": 335, "loss": 0.3202, "lr": 1.2237032191174642e-05, "epoch": 3.8435754189944134, "percentage": 77.01, "elapsed_time": "10:55:15", "remaining_time": "3:15:33"}
259
+ {"current_steps": 259, "total_steps": 335, "loss": 0.3212, "lr": 1.1937999184719926e-05, "epoch": 3.8584729981378025, "percentage": 77.31, "elapsed_time": "10:57:48", "remaining_time": "3:13:01"}
260
+ {"current_steps": 260, "total_steps": 335, "loss": 0.319, "lr": 1.1642023079762281e-05, "epoch": 3.8733705772811917, "percentage": 77.61, "elapsed_time": "11:00:20", "remaining_time": "3:10:29"}
261
+ {"current_steps": 261, "total_steps": 335, "loss": 0.3154, "lr": 1.1349136118115242e-05, "epoch": 3.888268156424581, "percentage": 77.91, "elapsed_time": "11:02:50", "remaining_time": "3:07:56"}
262
+ {"current_steps": 262, "total_steps": 335, "loss": 0.3226, "lr": 1.1059370205080157e-05, "epoch": 3.90316573556797, "percentage": 78.21, "elapsed_time": "11:05:21", "remaining_time": "3:05:23"}
263
+ {"current_steps": 263, "total_steps": 335, "loss": 0.3229, "lr": 1.07727569059705e-05, "epoch": 3.9180633147113593, "percentage": 78.51, "elapsed_time": "11:07:51", "remaining_time": "3:02:50"}
264
+ {"current_steps": 264, "total_steps": 335, "loss": 0.3227, "lr": 1.0489327442673459e-05, "epoch": 3.9329608938547485, "percentage": 78.81, "elapsed_time": "11:10:22", "remaining_time": "3:00:17"}
265
+ {"current_steps": 265, "total_steps": 335, "loss": 0.3177, "lr": 1.0209112690248726e-05, "epoch": 3.9478584729981376, "percentage": 79.1, "elapsed_time": "11:12:52", "remaining_time": "2:57:44"}
266
+ {"current_steps": 266, "total_steps": 335, "loss": 0.3227, "lr": 9.932143173565225e-06, "epoch": 3.9627560521415273, "percentage": 79.4, "elapsed_time": "11:15:23", "remaining_time": "2:55:11"}
267
+ {"current_steps": 267, "total_steps": 335, "loss": 0.3216, "lr": 9.658449063975875e-06, "epoch": 3.977653631284916, "percentage": 79.7, "elapsed_time": "11:17:54", "remaining_time": "2:52:38"}
268
+ {"current_steps": 268, "total_steps": 335, "loss": 0.3226, "lr": 9.388060176030907e-06, "epoch": 3.9925512104283056, "percentage": 80.0, "elapsed_time": "11:20:23", "remaining_time": "2:50:05"}