ryanmarten commited on
Commit
4b65df9
·
verified ·
1 Parent(s): 71f97ca

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd6f495bb0dfa7968382eca1c2e515a27ad5ecb1b1b1b25bfadb91ba7df0386d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187a9a4e116944f94b9920d1d36a7be33ff5b0db0fe6deaf20c7deabd62fede6
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:d6042aa198e435a9f490fa9a76ad1ca0e4fd7e6cdf85d7eea5b24b1f7b3a5561
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b0c1399e5317144a78373ff3456992e6048ff2e6d2ec89184b62e88c4ba61a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:266b84f0dce5c61a68e97f4b20f15d57a283377c0dc175994dda2373103749b2
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4bc2306c0ebf473e82431956d96f1501791f7c7fd038a0656b099d83319b29
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:be0cb6cc8dfe4334b387ea886a1965edd3de29012b64d9da648502dbcc5b365c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e59c101316bc6505817ae4b10cdc41a8ceca3a1428d9020d6e17204d646992
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -156,3 +156,81 @@
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.9792, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "4:03:44", "remaining_time": "6:05:36"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.9135, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "4:05:59", "remaining_time": "6:05:04"}
158
  {"current_steps": 158, "total_steps": 390, "loss": 0.9157, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "4:07:41", "remaining_time": "6:03:41"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.9792, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "4:03:44", "remaining_time": "6:05:36"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.9135, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "4:05:59", "remaining_time": "6:05:04"}
158
  {"current_steps": 158, "total_steps": 390, "loss": 0.9157, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "4:07:41", "remaining_time": "6:03:41"}
159
+ {"current_steps": 159, "total_steps": 390, "loss": 0.9183, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "4:09:14", "remaining_time": "6:02:06"}
160
+ {"current_steps": 160, "total_steps": 390, "loss": 0.9225, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "4:10:42", "remaining_time": "6:00:23"}
161
+ {"current_steps": 161, "total_steps": 390, "loss": 0.9046, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "4:12:12", "remaining_time": "5:58:43"}
162
+ {"current_steps": 162, "total_steps": 390, "loss": 0.9099, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "4:13:46", "remaining_time": "5:57:10"}
163
+ {"current_steps": 163, "total_steps": 390, "loss": 0.9061, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "4:15:17", "remaining_time": "5:55:31"}
164
+ {"current_steps": 164, "total_steps": 390, "loss": 0.8724, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "4:16:55", "remaining_time": "5:54:03"}
165
+ {"current_steps": 165, "total_steps": 390, "loss": 0.8924, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "4:18:20", "remaining_time": "5:52:17"}
166
+ {"current_steps": 166, "total_steps": 390, "loss": 0.949, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "4:19:49", "remaining_time": "5:50:35"}
167
+ {"current_steps": 167, "total_steps": 390, "loss": 0.898, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "4:21:11", "remaining_time": "5:48:46"}
168
+ {"current_steps": 168, "total_steps": 390, "loss": 0.913, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "4:22:43", "remaining_time": "5:47:10"}
169
+ {"current_steps": 169, "total_steps": 390, "loss": 0.8939, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "4:24:19", "remaining_time": "5:45:38"}
170
+ {"current_steps": 170, "total_steps": 390, "loss": 0.9381, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "4:25:46", "remaining_time": "5:43:56"}
171
+ {"current_steps": 171, "total_steps": 390, "loss": 0.8788, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "4:27:23", "remaining_time": "5:42:26"}
172
+ {"current_steps": 172, "total_steps": 390, "loss": 0.9172, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "4:28:44", "remaining_time": "5:40:37"}
173
+ {"current_steps": 173, "total_steps": 390, "loss": 0.9211, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "4:30:16", "remaining_time": "5:39:01"}
174
+ {"current_steps": 174, "total_steps": 390, "loss": 0.8969, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "4:31:44", "remaining_time": "5:37:20"}
175
+ {"current_steps": 175, "total_steps": 390, "loss": 0.9284, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "4:33:11", "remaining_time": "5:35:37"}
176
+ {"current_steps": 176, "total_steps": 390, "loss": 0.8979, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "4:34:44", "remaining_time": "5:34:04"}
177
+ {"current_steps": 177, "total_steps": 390, "loss": 0.942, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "4:36:16", "remaining_time": "5:32:27"}
178
+ {"current_steps": 178, "total_steps": 390, "loss": 0.8899, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "4:37:44", "remaining_time": "5:30:47"}
179
+ {"current_steps": 179, "total_steps": 390, "loss": 0.926, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "4:39:25", "remaining_time": "5:29:22"}
180
+ {"current_steps": 180, "total_steps": 390, "loss": 0.886, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "4:41:04", "remaining_time": "5:27:54"}
181
+ {"current_steps": 181, "total_steps": 390, "loss": 0.9249, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "4:42:33", "remaining_time": "5:26:15"}
182
+ {"current_steps": 182, "total_steps": 390, "loss": 0.9061, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "4:44:01", "remaining_time": "5:24:36"}
183
+ {"current_steps": 183, "total_steps": 390, "loss": 0.9265, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "4:45:36", "remaining_time": "5:23:03"}
184
+ {"current_steps": 184, "total_steps": 390, "loss": 0.884, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "4:47:14", "remaining_time": "5:21:35"}
185
+ {"current_steps": 185, "total_steps": 390, "loss": 0.9194, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "4:48:44", "remaining_time": "5:19:57"}
186
+ {"current_steps": 186, "total_steps": 390, "loss": 0.9251, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "4:50:19", "remaining_time": "5:18:25"}
187
+ {"current_steps": 187, "total_steps": 390, "loss": 0.9099, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "4:52:08", "remaining_time": "5:17:07"}
188
+ {"current_steps": 188, "total_steps": 390, "loss": 0.9009, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "4:53:41", "remaining_time": "5:15:34"}
189
+ {"current_steps": 189, "total_steps": 390, "loss": 0.9129, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "4:55:17", "remaining_time": "5:14:02"}
190
+ {"current_steps": 190, "total_steps": 390, "loss": 0.9187, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "4:56:49", "remaining_time": "5:12:26"}
191
+ {"current_steps": 191, "total_steps": 390, "loss": 0.8951, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "4:58:23", "remaining_time": "5:10:53"}
192
+ {"current_steps": 192, "total_steps": 390, "loss": 0.9298, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "4:59:56", "remaining_time": "5:09:18"}
193
+ {"current_steps": 193, "total_steps": 390, "loss": 0.898, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "5:01:21", "remaining_time": "5:07:36"}
194
+ {"current_steps": 194, "total_steps": 390, "loss": 0.8989, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "5:02:54", "remaining_time": "5:06:01"}
195
+ {"current_steps": 195, "total_steps": 390, "loss": 0.926, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "5:04:32", "remaining_time": "5:04:32"}
196
+ {"current_steps": 196, "total_steps": 390, "loss": 0.9153, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "5:06:00", "remaining_time": "5:02:53"}
197
+ {"current_steps": 197, "total_steps": 390, "loss": 0.8897, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "5:07:37", "remaining_time": "5:01:22"}
198
+ {"current_steps": 198, "total_steps": 390, "loss": 0.9154, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "5:09:23", "remaining_time": "5:00:00"}
199
+ {"current_steps": 199, "total_steps": 390, "loss": 0.9325, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "5:10:57", "remaining_time": "4:58:27"}
200
+ {"current_steps": 200, "total_steps": 390, "loss": 0.9142, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "5:12:33", "remaining_time": "4:56:55"}
201
+ {"current_steps": 201, "total_steps": 390, "loss": 0.8686, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "5:14:01", "remaining_time": "4:55:17"}
202
+ {"current_steps": 202, "total_steps": 390, "loss": 0.9129, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "5:15:26", "remaining_time": "4:53:34"}
203
+ {"current_steps": 203, "total_steps": 390, "loss": 0.8861, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "5:17:00", "remaining_time": "4:52:01"}
204
+ {"current_steps": 204, "total_steps": 390, "loss": 0.9203, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "5:18:36", "remaining_time": "4:50:29"}
205
+ {"current_steps": 205, "total_steps": 390, "loss": 0.9343, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "5:20:07", "remaining_time": "4:48:53"}
206
+ {"current_steps": 206, "total_steps": 390, "loss": 0.9106, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "5:21:42", "remaining_time": "4:47:21"}
207
+ {"current_steps": 207, "total_steps": 390, "loss": 0.9009, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "5:23:11", "remaining_time": "4:45:43"}
208
+ {"current_steps": 208, "total_steps": 390, "loss": 0.8912, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "5:24:38", "remaining_time": "4:44:04"}
209
+ {"current_steps": 209, "total_steps": 390, "loss": 0.9117, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "5:26:10", "remaining_time": "4:42:28"}
210
+ {"current_steps": 210, "total_steps": 390, "loss": 0.9373, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "5:27:50", "remaining_time": "4:41:00"}
211
+ {"current_steps": 211, "total_steps": 390, "loss": 0.9212, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "5:29:19", "remaining_time": "4:39:22"}
212
+ {"current_steps": 212, "total_steps": 390, "loss": 0.9141, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "5:30:54", "remaining_time": "4:37:50"}
213
+ {"current_steps": 213, "total_steps": 390, "loss": 0.8972, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "5:32:36", "remaining_time": "4:36:23"}
214
+ {"current_steps": 214, "total_steps": 390, "loss": 0.9417, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "5:34:11", "remaining_time": "4:34:50"}
215
+ {"current_steps": 215, "total_steps": 390, "loss": 0.9116, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "5:35:52", "remaining_time": "4:33:23"}
216
+ {"current_steps": 216, "total_steps": 390, "loss": 0.9312, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "5:37:34", "remaining_time": "4:31:56"}
217
+ {"current_steps": 217, "total_steps": 390, "loss": 0.909, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "5:39:05", "remaining_time": "4:30:20"}
218
+ {"current_steps": 218, "total_steps": 390, "loss": 0.9112, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "5:40:40", "remaining_time": "4:28:47"}
219
+ {"current_steps": 219, "total_steps": 390, "loss": 0.8721, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "5:42:19", "remaining_time": "4:27:17"}
220
+ {"current_steps": 220, "total_steps": 390, "loss": 0.9252, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "5:43:47", "remaining_time": "4:25:39"}
221
+ {"current_steps": 221, "total_steps": 390, "loss": 0.9063, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "5:45:26", "remaining_time": "4:24:09"}
222
+ {"current_steps": 222, "total_steps": 390, "loss": 0.9167, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "5:47:09", "remaining_time": "4:22:42"}
223
+ {"current_steps": 223, "total_steps": 390, "loss": 0.9101, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "5:48:41", "remaining_time": "4:21:07"}
224
+ {"current_steps": 224, "total_steps": 390, "loss": 0.9046, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "5:50:12", "remaining_time": "4:19:31"}
225
+ {"current_steps": 225, "total_steps": 390, "loss": 0.916, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "5:51:44", "remaining_time": "4:17:56"}
226
+ {"current_steps": 226, "total_steps": 390, "loss": 0.9176, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "5:53:15", "remaining_time": "4:16:21"}
227
+ {"current_steps": 227, "total_steps": 390, "loss": 0.9161, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "5:54:53", "remaining_time": "4:14:49"}
228
+ {"current_steps": 228, "total_steps": 390, "loss": 0.9267, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "5:56:24", "remaining_time": "4:13:14"}
229
+ {"current_steps": 229, "total_steps": 390, "loss": 0.8952, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "5:58:02", "remaining_time": "4:11:43"}
230
+ {"current_steps": 230, "total_steps": 390, "loss": 0.8949, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "5:59:42", "remaining_time": "4:10:13"}
231
+ {"current_steps": 231, "total_steps": 390, "loss": 0.9065, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "6:01:15", "remaining_time": "4:08:39"}
232
+ {"current_steps": 232, "total_steps": 390, "loss": 0.908, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "6:02:45", "remaining_time": "4:07:02"}
233
+ {"current_steps": 233, "total_steps": 390, "loss": 0.9149, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "6:04:28", "remaining_time": "4:05:35"}
234
+ {"current_steps": 234, "total_steps": 390, "loss": 0.9124, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "6:05:55", "remaining_time": "4:03:57"}
235
+ {"current_steps": 235, "total_steps": 390, "loss": 0.8634, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "6:08:18", "remaining_time": "4:02:55"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.8606, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "6:09:51", "remaining_time": "4:01:21"}