ryanmarten commited on
Commit
611095b
·
verified ·
1 Parent(s): fb07277

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 sha256:767973945c04a783250e50617dd75818e60fef98fa3726e0d3fef24d7497c2ca
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734496dc0968271249fb7332972f8ee521b70acfb5393bce913f82736f167f6a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f37c07ec505a8bcb322b7035dd07be46b6697a0a23d29e36bbc03a2cc4f8430
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99083b4c4c8067379fed894b942430e4aa0f3a45c1b1745c548f6001ed0bc86f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3348846a52e9be9009d2be7aae0c34eb428f16c02e5a53f1dacf297a238710b1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6fc49efa7dec7524d2919ebdd48a3fcb48319f9ab5f7363f5c05217d3769ed
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef9eaa458f49b7cce18b2e4423aacda78708e19be5ed6aeca08aff28fb9f571
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e9f637d2ace71166483f2ea50743b6be32c3d3dc36ba02972f54778e21234f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -155,3 +155,81 @@
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5702, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:01:38", "remaining_time": "10:39:15"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5817, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:04:19", "remaining_time": "10:36:28"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.5251, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:07:44", "remaining_time": "10:34:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5702, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:01:38", "remaining_time": "10:39:15"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5817, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:04:19", "remaining_time": "10:36:28"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.5251, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:07:44", "remaining_time": "10:34:47"}
158
+ {"current_steps": 158, "total_steps": 390, "loss": 0.5019, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "7:10:28", "remaining_time": "10:32:05"}
159
+ {"current_steps": 159, "total_steps": 390, "loss": 0.5033, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "7:13:08", "remaining_time": "10:29:16"}
160
+ {"current_steps": 160, "total_steps": 390, "loss": 0.5012, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "7:15:43", "remaining_time": "10:26:21"}
161
+ {"current_steps": 161, "total_steps": 390, "loss": 0.4948, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "7:18:29", "remaining_time": "10:23:41"}
162
+ {"current_steps": 162, "total_steps": 390, "loss": 0.5028, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "7:21:10", "remaining_time": "10:20:55"}
163
+ {"current_steps": 163, "total_steps": 390, "loss": 0.49, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "7:23:51", "remaining_time": "10:18:07"}
164
+ {"current_steps": 164, "total_steps": 390, "loss": 0.492, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "7:26:31", "remaining_time": "10:15:20"}
165
+ {"current_steps": 165, "total_steps": 390, "loss": 0.4914, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "7:29:17", "remaining_time": "10:12:40"}
166
+ {"current_steps": 166, "total_steps": 390, "loss": 0.487, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:31:54", "remaining_time": "10:09:48"}
167
+ {"current_steps": 167, "total_steps": 390, "loss": 0.4919, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:34:35", "remaining_time": "10:07:01"}
168
+ {"current_steps": 168, "total_steps": 390, "loss": 0.494, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:37:24", "remaining_time": "10:04:26"}
169
+ {"current_steps": 169, "total_steps": 390, "loss": 0.4882, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:40:06", "remaining_time": "10:01:40"}
170
+ {"current_steps": 170, "total_steps": 390, "loss": 0.4934, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:42:43", "remaining_time": "9:58:49"}
171
+ {"current_steps": 171, "total_steps": 390, "loss": 0.4837, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:45:32", "remaining_time": "9:56:12"}
172
+ {"current_steps": 172, "total_steps": 390, "loss": 0.4971, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:48:07", "remaining_time": "9:53:19"}
173
+ {"current_steps": 173, "total_steps": 390, "loss": 0.4928, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:50:58", "remaining_time": "9:50:45"}
174
+ {"current_steps": 174, "total_steps": 390, "loss": 0.4915, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:53:41", "remaining_time": "9:48:01"}
175
+ {"current_steps": 175, "total_steps": 390, "loss": 0.4968, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:56:32", "remaining_time": "9:45:28"}
176
+ {"current_steps": 176, "total_steps": 390, "loss": 0.4844, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:59:09", "remaining_time": "9:42:36"}
177
+ {"current_steps": 177, "total_steps": 390, "loss": 0.4874, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "8:01:49", "remaining_time": "9:39:49"}
178
+ {"current_steps": 178, "total_steps": 390, "loss": 0.4854, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "8:04:25", "remaining_time": "9:36:56"}
179
+ {"current_steps": 179, "total_steps": 390, "loss": 0.5074, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "8:07:02", "remaining_time": "9:34:06"}
180
+ {"current_steps": 180, "total_steps": 390, "loss": 0.4902, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "8:09:47", "remaining_time": "9:31:25"}
181
+ {"current_steps": 181, "total_steps": 390, "loss": 0.4922, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "8:12:29", "remaining_time": "9:28:41"}
182
+ {"current_steps": 182, "total_steps": 390, "loss": 0.4959, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "8:15:13", "remaining_time": "9:25:58"}
183
+ {"current_steps": 183, "total_steps": 390, "loss": 0.4951, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "8:17:50", "remaining_time": "9:23:08"}
184
+ {"current_steps": 184, "total_steps": 390, "loss": 0.4852, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "8:20:27", "remaining_time": "9:20:17"}
185
+ {"current_steps": 185, "total_steps": 390, "loss": 0.4872, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "8:23:15", "remaining_time": "9:17:40"}
186
+ {"current_steps": 186, "total_steps": 390, "loss": 0.4833, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "8:26:08", "remaining_time": "9:15:07"}
187
+ {"current_steps": 187, "total_steps": 390, "loss": 0.4918, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "8:28:43", "remaining_time": "9:12:15"}
188
+ {"current_steps": 188, "total_steps": 390, "loss": 0.4977, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "8:31:30", "remaining_time": "9:09:36"}
189
+ {"current_steps": 189, "total_steps": 390, "loss": 0.495, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "8:34:09", "remaining_time": "9:06:48"}
190
+ {"current_steps": 190, "total_steps": 390, "loss": 0.5134, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "8:37:01", "remaining_time": "9:04:14"}
191
+ {"current_steps": 191, "total_steps": 390, "loss": 0.5006, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:39:41", "remaining_time": "9:01:27"}
192
+ {"current_steps": 192, "total_steps": 390, "loss": 0.5005, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:42:27", "remaining_time": "8:58:47"}
193
+ {"current_steps": 193, "total_steps": 390, "loss": 0.4944, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:45:05", "remaining_time": "8:55:58"}
194
+ {"current_steps": 194, "total_steps": 390, "loss": 0.5019, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:47:32", "remaining_time": "8:52:58"}
195
+ {"current_steps": 195, "total_steps": 390, "loss": 0.4982, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:50:19", "remaining_time": "8:50:19"}
196
+ {"current_steps": 196, "total_steps": 390, "loss": 0.4967, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:52:59", "remaining_time": "8:47:33"}
197
+ {"current_steps": 197, "total_steps": 390, "loss": 0.4898, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:55:53", "remaining_time": "8:45:00"}
198
+ {"current_steps": 198, "total_steps": 390, "loss": 0.4896, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:58:45", "remaining_time": "8:42:26"}
199
+ {"current_steps": 199, "total_steps": 390, "loss": 0.4955, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "9:01:19", "remaining_time": "8:39:34"}
200
+ {"current_steps": 200, "total_steps": 390, "loss": 0.4932, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "9:03:59", "remaining_time": "8:36:47"}
201
+ {"current_steps": 201, "total_steps": 390, "loss": 0.4864, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "9:06:45", "remaining_time": "8:34:07"}
202
+ {"current_steps": 202, "total_steps": 390, "loss": 0.4889, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "9:09:27", "remaining_time": "8:31:22"}
203
+ {"current_steps": 203, "total_steps": 390, "loss": 0.4912, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "9:12:26", "remaining_time": "8:28:54"}
204
+ {"current_steps": 204, "total_steps": 390, "loss": 0.4953, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "9:15:16", "remaining_time": "8:26:16"}
205
+ {"current_steps": 205, "total_steps": 390, "loss": 0.4977, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "9:17:58", "remaining_time": "8:23:32"}
206
+ {"current_steps": 206, "total_steps": 390, "loss": 0.4923, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "9:20:38", "remaining_time": "8:20:46"}
207
+ {"current_steps": 207, "total_steps": 390, "loss": 0.488, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "9:23:24", "remaining_time": "8:18:04"}
208
+ {"current_steps": 208, "total_steps": 390, "loss": 0.4871, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "9:25:59", "remaining_time": "8:15:14"}
209
+ {"current_steps": 209, "total_steps": 390, "loss": 0.4863, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "9:28:51", "remaining_time": "8:12:38"}
210
+ {"current_steps": 210, "total_steps": 390, "loss": 0.5008, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "9:31:39", "remaining_time": "8:09:59"}
211
+ {"current_steps": 211, "total_steps": 390, "loss": 0.4916, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "9:34:18", "remaining_time": "8:07:12"}
212
+ {"current_steps": 212, "total_steps": 390, "loss": 0.4819, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "9:37:11", "remaining_time": "8:04:37"}
213
+ {"current_steps": 213, "total_steps": 390, "loss": 0.4896, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "9:39:48", "remaining_time": "8:01:48"}
214
+ {"current_steps": 214, "total_steps": 390, "loss": 0.4805, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "9:42:27", "remaining_time": "7:59:02"}
215
+ {"current_steps": 215, "total_steps": 390, "loss": 0.4912, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:45:22", "remaining_time": "7:56:27"}
216
+ {"current_steps": 216, "total_steps": 390, "loss": 0.5007, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:47:50", "remaining_time": "7:53:32"}
217
+ {"current_steps": 217, "total_steps": 390, "loss": 0.4877, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:50:29", "remaining_time": "7:50:45"}
218
+ {"current_steps": 218, "total_steps": 390, "loss": 0.501, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:53:04", "remaining_time": "7:47:55"}
219
+ {"current_steps": 219, "total_steps": 390, "loss": 0.4996, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:55:44", "remaining_time": "7:45:10"}
220
+ {"current_steps": 220, "total_steps": 390, "loss": 0.4908, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:58:24", "remaining_time": "7:42:24"}
221
+ {"current_steps": 221, "total_steps": 390, "loss": 0.4906, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "10:01:03", "remaining_time": "7:39:37"}
222
+ {"current_steps": 222, "total_steps": 390, "loss": 0.5032, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "10:03:46", "remaining_time": "7:36:55"}
223
+ {"current_steps": 223, "total_steps": 390, "loss": 0.4995, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "10:06:27", "remaining_time": "7:34:09"}
224
+ {"current_steps": 224, "total_steps": 390, "loss": 0.5035, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "10:08:52", "remaining_time": "7:31:13"}
225
+ {"current_steps": 225, "total_steps": 390, "loss": 0.4985, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "10:11:34", "remaining_time": "7:28:29"}
226
+ {"current_steps": 226, "total_steps": 390, "loss": 0.4986, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "10:14:02", "remaining_time": "7:25:35"}
227
+ {"current_steps": 227, "total_steps": 390, "loss": 0.4738, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "10:16:47", "remaining_time": "7:22:53"}
228
+ {"current_steps": 228, "total_steps": 390, "loss": 0.4898, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "10:19:32", "remaining_time": "7:20:11"}
229
+ {"current_steps": 229, "total_steps": 390, "loss": 0.5099, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "10:22:23", "remaining_time": "7:17:34"}
230
+ {"current_steps": 230, "total_steps": 390, "loss": 0.4821, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "10:25:16", "remaining_time": "7:14:58"}
231
+ {"current_steps": 231, "total_steps": 390, "loss": 0.4902, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "10:28:00", "remaining_time": "7:12:16"}
232
+ {"current_steps": 232, "total_steps": 390, "loss": 0.4957, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "10:30:46", "remaining_time": "7:09:34"}
233
+ {"current_steps": 233, "total_steps": 390, "loss": 0.503, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:33:22", "remaining_time": "7:06:47"}
234
+ {"current_steps": 234, "total_steps": 390, "loss": 0.4947, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:36:12", "remaining_time": "7:04:08"}
235
+ {"current_steps": 235, "total_steps": 390, "loss": 0.4604, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:39:41", "remaining_time": "7:01:55"}