ryanmarten commited on
Commit
1ea09a4
·
verified ·
1 Parent(s): 8d5a4f6

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 sha256:6521756723865d68279ad46e3e41141e652835361af2d1b50a6d185850e0423c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0357b18050a9ffd64a9364f0351c5bb872b9b247b06e45547a7b18f768a32800
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8268138485e746461cd0990d8930fdd855eb2425a2cc0486aba2aafe68efbe90
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431b4d5058b808113169a059d3cf446eb11b6fb9ef3dea83d6c9312c40b310f6
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96b99acdcec2eada76fe72de8f8cb44b6ab6d178620c5f787593a4860a7bdc6e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a831fcf87de1024780dddb23685839cfeb1ab49e7783c139cf8a07ed9046eb82
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66d28ff01245b8b25f338e5f8862cac67b4ff57ac9ac9097810fb66a8e67a44b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d7c6a62cfb801f9ad8a57c228085137a1aadf96b6dc30838984ac7a780ea25
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -155,3 +155,81 @@
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5589, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:38:58", "remaining_time": "10:04:53"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5563, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:41:34", "remaining_time": "10:02:22"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.5318, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:45:02", "remaining_time": "10:01:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5589, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:38:58", "remaining_time": "10:04:53"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5563, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:41:34", "remaining_time": "10:02:22"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.5318, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:45:02", "remaining_time": "10:01:07"}
158
+ {"current_steps": 158, "total_steps": 390, "loss": 0.5086, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "6:47:39", "remaining_time": "9:58:34"}
159
+ {"current_steps": 159, "total_steps": 390, "loss": 0.4972, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "6:50:16", "remaining_time": "9:56:03"}
160
+ {"current_steps": 160, "total_steps": 390, "loss": 0.4981, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "6:52:42", "remaining_time": "9:53:16"}
161
+ {"current_steps": 161, "total_steps": 390, "loss": 0.494, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "6:55:21", "remaining_time": "9:50:47"}
162
+ {"current_steps": 162, "total_steps": 390, "loss": 0.4994, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "6:58:01", "remaining_time": "9:48:19"}
163
+ {"current_steps": 163, "total_steps": 390, "loss": 0.499, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "7:00:42", "remaining_time": "9:45:53"}
164
+ {"current_steps": 164, "total_steps": 390, "loss": 0.4795, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "7:03:15", "remaining_time": "9:43:16"}
165
+ {"current_steps": 165, "total_steps": 390, "loss": 0.489, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "7:05:58", "remaining_time": "9:40:52"}
166
+ {"current_steps": 166, "total_steps": 390, "loss": 0.4964, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:08:34", "remaining_time": "9:38:19"}
167
+ {"current_steps": 167, "total_steps": 390, "loss": 0.4951, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:11:14", "remaining_time": "9:35:51"}
168
+ {"current_steps": 168, "total_steps": 390, "loss": 0.4951, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:13:41", "remaining_time": "9:33:05"}
169
+ {"current_steps": 169, "total_steps": 390, "loss": 0.514, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:16:15", "remaining_time": "9:30:30"}
170
+ {"current_steps": 170, "total_steps": 390, "loss": 0.4827, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:18:49", "remaining_time": "9:27:53"}
171
+ {"current_steps": 171, "total_steps": 390, "loss": 0.4861, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:21:14", "remaining_time": "9:25:05"}
172
+ {"current_steps": 172, "total_steps": 390, "loss": 0.4981, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:23:42", "remaining_time": "9:22:21"}
173
+ {"current_steps": 173, "total_steps": 390, "loss": 0.4807, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:26:20", "remaining_time": "9:19:51"}
174
+ {"current_steps": 174, "total_steps": 390, "loss": 0.5023, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:28:54", "remaining_time": "9:17:15"}
175
+ {"current_steps": 175, "total_steps": 390, "loss": 0.5218, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:31:37", "remaining_time": "9:14:51"}
176
+ {"current_steps": 176, "total_steps": 390, "loss": 0.5053, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:34:16", "remaining_time": "9:12:20"}
177
+ {"current_steps": 177, "total_steps": 390, "loss": 0.4931, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "7:36:46", "remaining_time": "9:09:40"}
178
+ {"current_steps": 178, "total_steps": 390, "loss": 0.5025, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "7:39:26", "remaining_time": "9:07:11"}
179
+ {"current_steps": 179, "total_steps": 390, "loss": 0.5012, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "7:42:02", "remaining_time": "9:04:38"}
180
+ {"current_steps": 180, "total_steps": 390, "loss": 0.5017, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "7:44:40", "remaining_time": "9:02:07"}
181
+ {"current_steps": 181, "total_steps": 390, "loss": 0.497, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "7:47:12", "remaining_time": "8:59:28"}
182
+ {"current_steps": 182, "total_steps": 390, "loss": 0.4859, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "7:49:46", "remaining_time": "8:56:52"}
183
+ {"current_steps": 183, "total_steps": 390, "loss": 0.5015, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "7:52:32", "remaining_time": "8:54:30"}
184
+ {"current_steps": 184, "total_steps": 390, "loss": 0.4913, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "7:55:13", "remaining_time": "8:52:02"}
185
+ {"current_steps": 185, "total_steps": 390, "loss": 0.5135, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "7:57:41", "remaining_time": "8:49:20"}
186
+ {"current_steps": 186, "total_steps": 390, "loss": 0.4932, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "8:00:14", "remaining_time": "8:46:42"}
187
+ {"current_steps": 187, "total_steps": 390, "loss": 0.5064, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "8:02:53", "remaining_time": "8:44:12"}
188
+ {"current_steps": 188, "total_steps": 390, "loss": 0.4905, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "8:05:24", "remaining_time": "8:41:33"}
189
+ {"current_steps": 189, "total_steps": 390, "loss": 0.4884, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "8:07:58", "remaining_time": "8:38:57"}
190
+ {"current_steps": 190, "total_steps": 390, "loss": 0.4997, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "8:10:45", "remaining_time": "8:36:34"}
191
+ {"current_steps": 191, "total_steps": 390, "loss": 0.495, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:13:31", "remaining_time": "8:34:11"}
192
+ {"current_steps": 192, "total_steps": 390, "loss": 0.5057, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:16:08", "remaining_time": "8:31:39"}
193
+ {"current_steps": 193, "total_steps": 390, "loss": 0.4887, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:18:36", "remaining_time": "8:28:56"}
194
+ {"current_steps": 194, "total_steps": 390, "loss": 0.4947, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:21:13", "remaining_time": "8:26:23"}
195
+ {"current_steps": 195, "total_steps": 390, "loss": 0.5063, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:23:32", "remaining_time": "8:23:32"}
196
+ {"current_steps": 196, "total_steps": 390, "loss": 0.5027, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:26:01", "remaining_time": "8:20:51"}
197
+ {"current_steps": 197, "total_steps": 390, "loss": 0.4808, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:28:29", "remaining_time": "8:18:09"}
198
+ {"current_steps": 198, "total_steps": 390, "loss": 0.5001, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:31:09", "remaining_time": "8:15:40"}
199
+ {"current_steps": 199, "total_steps": 390, "loss": 0.4977, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "8:33:34", "remaining_time": "8:12:55"}
200
+ {"current_steps": 200, "total_steps": 390, "loss": 0.4897, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "8:36:26", "remaining_time": "8:10:36"}
201
+ {"current_steps": 201, "total_steps": 390, "loss": 0.4936, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "8:38:57", "remaining_time": "8:07:58"}
202
+ {"current_steps": 202, "total_steps": 390, "loss": 0.5034, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "8:41:35", "remaining_time": "8:05:26"}
203
+ {"current_steps": 203, "total_steps": 390, "loss": 0.4931, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "8:44:13", "remaining_time": "8:02:54"}
204
+ {"current_steps": 204, "total_steps": 390, "loss": 0.4902, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "8:46:48", "remaining_time": "8:00:19"}
205
+ {"current_steps": 205, "total_steps": 390, "loss": 0.5048, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "8:49:27", "remaining_time": "7:57:47"}
206
+ {"current_steps": 206, "total_steps": 390, "loss": 0.5, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "8:51:59", "remaining_time": "7:55:10"}
207
+ {"current_steps": 207, "total_steps": 390, "loss": 0.5005, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "8:54:31", "remaining_time": "7:52:32"}
208
+ {"current_steps": 208, "total_steps": 390, "loss": 0.5086, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "8:57:21", "remaining_time": "7:50:11"}
209
+ {"current_steps": 209, "total_steps": 390, "loss": 0.501, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "9:00:05", "remaining_time": "7:47:44"}
210
+ {"current_steps": 210, "total_steps": 390, "loss": 0.493, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "9:02:33", "remaining_time": "7:45:03"}
211
+ {"current_steps": 211, "total_steps": 390, "loss": 0.4881, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "9:05:08", "remaining_time": "7:42:27"}
212
+ {"current_steps": 212, "total_steps": 390, "loss": 0.4865, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "9:07:39", "remaining_time": "7:39:49"}
213
+ {"current_steps": 213, "total_steps": 390, "loss": 0.4999, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "9:10:02", "remaining_time": "7:37:04"}
214
+ {"current_steps": 214, "total_steps": 390, "loss": 0.4936, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "9:12:36", "remaining_time": "7:34:28"}
215
+ {"current_steps": 215, "total_steps": 390, "loss": 0.4963, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:15:20", "remaining_time": "7:32:01"}
216
+ {"current_steps": 216, "total_steps": 390, "loss": 0.485, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:17:41", "remaining_time": "7:29:15"}
217
+ {"current_steps": 217, "total_steps": 390, "loss": 0.5057, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:20:16", "remaining_time": "7:26:40"}
218
+ {"current_steps": 218, "total_steps": 390, "loss": 0.48, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:22:32", "remaining_time": "7:23:50"}
219
+ {"current_steps": 219, "total_steps": 390, "loss": 0.4902, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:25:05", "remaining_time": "7:21:14"}
220
+ {"current_steps": 220, "total_steps": 390, "loss": 0.4996, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:27:36", "remaining_time": "7:18:36"}
221
+ {"current_steps": 221, "total_steps": 390, "loss": 0.4991, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "9:30:18", "remaining_time": "7:16:07"}
222
+ {"current_steps": 222, "total_steps": 390, "loss": 0.4855, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "9:32:50", "remaining_time": "7:13:29"}
223
+ {"current_steps": 223, "total_steps": 390, "loss": 0.5102, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "9:35:31", "remaining_time": "7:11:00"}
224
+ {"current_steps": 224, "total_steps": 390, "loss": 0.4897, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "9:38:02", "remaining_time": "7:08:21"}
225
+ {"current_steps": 225, "total_steps": 390, "loss": 0.4899, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "9:40:24", "remaining_time": "7:05:38"}
226
+ {"current_steps": 226, "total_steps": 390, "loss": 0.6007, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "9:42:50", "remaining_time": "7:02:56"}
227
+ {"current_steps": 227, "total_steps": 390, "loss": 0.9543, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "9:45:26", "remaining_time": "7:00:22"}
228
+ {"current_steps": 228, "total_steps": 390, "loss": 0.7363, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "9:48:07", "remaining_time": "6:57:52"}
229
+ {"current_steps": 229, "total_steps": 390, "loss": 0.4983, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "9:50:27", "remaining_time": "6:55:07"}
230
+ {"current_steps": 230, "total_steps": 390, "loss": 0.4948, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "9:52:55", "remaining_time": "6:52:27"}
231
+ {"current_steps": 231, "total_steps": 390, "loss": 0.4963, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "9:55:33", "remaining_time": "6:49:55"}
232
+ {"current_steps": 232, "total_steps": 390, "loss": 0.4991, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "9:57:58", "remaining_time": "6:47:14"}
233
+ {"current_steps": 233, "total_steps": 390, "loss": 0.4764, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:00:46", "remaining_time": "6:44:48"}
234
+ {"current_steps": 234, "total_steps": 390, "loss": 0.5048, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:03:21", "remaining_time": "6:42:14"}
235
+ {"current_steps": 235, "total_steps": 390, "loss": 0.4821, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:06:53", "remaining_time": "6:40:17"}