ryanmarten commited on
Commit
ad377e1
·
verified ·
1 Parent(s): 55dc97c

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:fa44b2f9f7fb00ad4c40e379eb6a5ee6d1b7a73ff245566cddf93f33d5a41558
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad02f4ad22dcd016e9ee2d14e33c5b0c22b0fb2593c51aa1909411d2fa5850d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f20bf3dc2100d64074f7eb122b242ea0646cea7d9d223605a2636caa6d5a5d7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5869393dfa3cc42c3a368e755867c76759d63e029a3421c0f57ac92226c086b6
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35dc6f58b630e1092e2a5eb673c0024befd1ac427ccaed5d3b20f20e7dfc26bc
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9115da86cea008bedbed386d87760eabb6a211d58b4ec20458d1f01795fc7af4
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:617b8e258eb8c32290b5c7b106c5e3bfd2a08d11edf3d055285b8ee0903872a7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494d8eede7c41cdf1142c5472d928ef3d5734ffc55f18a5d8079194e70b1cef5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -155,3 +155,81 @@
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5556, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:30:17", "remaining_time": "9:51:44"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5375, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:32:37", "remaining_time": "9:48:56"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.4848, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:35:48", "remaining_time": "9:47:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  {"current_steps": 155, "total_steps": 390, "loss": 0.5556, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:30:17", "remaining_time": "9:51:44"}
156
  {"current_steps": 156, "total_steps": 390, "loss": 0.5375, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:32:37", "remaining_time": "9:48:56"}
157
  {"current_steps": 157, "total_steps": 390, "loss": 0.4848, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:35:48", "remaining_time": "9:47:25"}
158
+ {"current_steps": 158, "total_steps": 390, "loss": 0.4739, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "6:38:04", "remaining_time": "9:44:31"}
159
+ {"current_steps": 159, "total_steps": 390, "loss": 0.46, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "6:40:19", "remaining_time": "9:41:36"}
160
+ {"current_steps": 160, "total_steps": 390, "loss": 0.4612, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "6:42:59", "remaining_time": "9:39:17"}
161
+ {"current_steps": 161, "total_steps": 390, "loss": 0.4394, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "6:45:06", "remaining_time": "9:36:13"}
162
+ {"current_steps": 162, "total_steps": 390, "loss": 0.4426, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "6:47:37", "remaining_time": "9:33:42"}
163
+ {"current_steps": 163, "total_steps": 390, "loss": 0.4408, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "6:49:54", "remaining_time": "9:30:50"}
164
+ {"current_steps": 164, "total_steps": 390, "loss": 0.4456, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "6:52:19", "remaining_time": "9:28:11"}
165
+ {"current_steps": 165, "total_steps": 390, "loss": 0.467, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "6:54:34", "remaining_time": "9:25:19"}
166
+ {"current_steps": 166, "total_steps": 390, "loss": 0.4319, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "6:56:58", "remaining_time": "9:22:39"}
167
+ {"current_steps": 167, "total_steps": 390, "loss": 0.468, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "6:59:13", "remaining_time": "9:19:48"}
168
+ {"current_steps": 168, "total_steps": 390, "loss": 0.448, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:01:48", "remaining_time": "9:17:23"}
169
+ {"current_steps": 169, "total_steps": 390, "loss": 0.4185, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:04:10", "remaining_time": "9:14:40"}
170
+ {"current_steps": 170, "total_steps": 390, "loss": 0.444, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:06:28", "remaining_time": "9:11:54"}
171
+ {"current_steps": 171, "total_steps": 390, "loss": 0.4459, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:08:35", "remaining_time": "9:08:53"}
172
+ {"current_steps": 172, "total_steps": 390, "loss": 0.4566, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:10:44", "remaining_time": "9:05:56"}
173
+ {"current_steps": 173, "total_steps": 390, "loss": 0.4574, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:13:04", "remaining_time": "9:03:13"}
174
+ {"current_steps": 174, "total_steps": 390, "loss": 0.4727, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:15:41", "remaining_time": "9:00:52"}
175
+ {"current_steps": 175, "total_steps": 390, "loss": 0.4313, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:17:54", "remaining_time": "8:58:00"}
176
+ {"current_steps": 176, "total_steps": 390, "loss": 0.4692, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:20:33", "remaining_time": "8:55:41"}
177
+ {"current_steps": 177, "total_steps": 390, "loss": 0.4704, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "7:22:56", "remaining_time": "8:53:02"}
178
+ {"current_steps": 178, "total_steps": 390, "loss": 0.4503, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "7:25:22", "remaining_time": "8:50:26"}
179
+ {"current_steps": 179, "total_steps": 390, "loss": 0.466, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "7:27:54", "remaining_time": "8:47:58"}
180
+ {"current_steps": 180, "total_steps": 390, "loss": 0.4587, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "7:30:04", "remaining_time": "8:45:04"}
181
+ {"current_steps": 181, "total_steps": 390, "loss": 0.4564, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "7:32:30", "remaining_time": "8:42:30"}
182
+ {"current_steps": 182, "total_steps": 390, "loss": 0.4461, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "7:34:58", "remaining_time": "8:39:57"}
183
+ {"current_steps": 183, "total_steps": 390, "loss": 0.4479, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "7:37:19", "remaining_time": "8:37:18"}
184
+ {"current_steps": 184, "total_steps": 390, "loss": 0.4704, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "7:40:03", "remaining_time": "8:35:04"}
185
+ {"current_steps": 185, "total_steps": 390, "loss": 0.4644, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "7:42:35", "remaining_time": "8:32:36"}
186
+ {"current_steps": 186, "total_steps": 390, "loss": 0.4353, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "7:45:01", "remaining_time": "8:30:01"}
187
+ {"current_steps": 187, "total_steps": 390, "loss": 0.4636, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "7:47:28", "remaining_time": "8:27:28"}
188
+ {"current_steps": 188, "total_steps": 390, "loss": 0.4144, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "7:49:30", "remaining_time": "8:24:28"}
189
+ {"current_steps": 189, "total_steps": 390, "loss": 0.4444, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "7:51:45", "remaining_time": "8:21:42"}
190
+ {"current_steps": 190, "total_steps": 390, "loss": 0.4597, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "7:54:28", "remaining_time": "8:19:26"}
191
+ {"current_steps": 191, "total_steps": 390, "loss": 0.437, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "7:56:53", "remaining_time": "8:16:52"}
192
+ {"current_steps": 192, "total_steps": 390, "loss": 0.4524, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "7:59:19", "remaining_time": "8:14:18"}
193
+ {"current_steps": 193, "total_steps": 390, "loss": 0.449, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:01:46", "remaining_time": "8:11:45"}
194
+ {"current_steps": 194, "total_steps": 390, "loss": 0.4246, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:04:05", "remaining_time": "8:09:04"}
195
+ {"current_steps": 195, "total_steps": 390, "loss": 0.4573, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:06:45", "remaining_time": "8:06:45"}
196
+ {"current_steps": 196, "total_steps": 390, "loss": 0.4576, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:09:18", "remaining_time": "8:04:18"}
197
+ {"current_steps": 197, "total_steps": 390, "loss": 0.4478, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:11:52", "remaining_time": "8:01:53"}
198
+ {"current_steps": 198, "total_steps": 390, "loss": 0.4521, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:14:32", "remaining_time": "7:59:33"}
199
+ {"current_steps": 199, "total_steps": 390, "loss": 0.4551, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "8:16:36", "remaining_time": "7:56:38"}
200
+ {"current_steps": 200, "total_steps": 390, "loss": 0.4445, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "8:18:46", "remaining_time": "7:53:50"}
201
+ {"current_steps": 201, "total_steps": 390, "loss": 0.461, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "8:21:19", "remaining_time": "7:51:23"}
202
+ {"current_steps": 202, "total_steps": 390, "loss": 0.4538, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "8:23:44", "remaining_time": "7:48:49"}
203
+ {"current_steps": 203, "total_steps": 390, "loss": 0.4532, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "8:26:09", "remaining_time": "7:46:16"}
204
+ {"current_steps": 204, "total_steps": 390, "loss": 0.4378, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "8:28:30", "remaining_time": "7:43:38"}
205
+ {"current_steps": 205, "total_steps": 390, "loss": 0.4313, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "8:30:41", "remaining_time": "7:40:52"}
206
+ {"current_steps": 206, "total_steps": 390, "loss": 0.459, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "8:33:16", "remaining_time": "7:38:27"}
207
+ {"current_steps": 207, "total_steps": 390, "loss": 0.4723, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "8:35:58", "remaining_time": "7:36:08"}
208
+ {"current_steps": 208, "total_steps": 390, "loss": 0.43, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "8:38:17", "remaining_time": "7:33:30"}
209
+ {"current_steps": 209, "total_steps": 390, "loss": 0.4435, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "8:40:50", "remaining_time": "7:31:04"}
210
+ {"current_steps": 210, "total_steps": 390, "loss": 0.4709, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "8:43:25", "remaining_time": "7:28:38"}
211
+ {"current_steps": 211, "total_steps": 390, "loss": 0.4246, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "8:45:35", "remaining_time": "7:25:53"}
212
+ {"current_steps": 212, "total_steps": 390, "loss": 0.4426, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "8:47:52", "remaining_time": "7:23:12"}
213
+ {"current_steps": 213, "total_steps": 390, "loss": 0.4488, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "8:50:13", "remaining_time": "7:20:36"}
214
+ {"current_steps": 214, "total_steps": 390, "loss": 0.4333, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "8:52:20", "remaining_time": "7:17:48"}
215
+ {"current_steps": 215, "total_steps": 390, "loss": 0.4565, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "8:54:50", "remaining_time": "7:15:19"}
216
+ {"current_steps": 216, "total_steps": 390, "loss": 0.4442, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "8:57:12", "remaining_time": "7:12:44"}
217
+ {"current_steps": 217, "total_steps": 390, "loss": 0.4662, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "8:59:39", "remaining_time": "7:10:14"}
218
+ {"current_steps": 218, "total_steps": 390, "loss": 0.4334, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:01:56", "remaining_time": "7:07:35"}
219
+ {"current_steps": 219, "total_steps": 390, "loss": 0.4591, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:04:36", "remaining_time": "7:05:14"}
220
+ {"current_steps": 220, "total_steps": 390, "loss": 0.4434, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:06:58", "remaining_time": "7:02:40"}
221
+ {"current_steps": 221, "total_steps": 390, "loss": 0.4524, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "9:09:25", "remaining_time": "7:00:09"}
222
+ {"current_steps": 222, "total_steps": 390, "loss": 0.4485, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "9:11:49", "remaining_time": "6:57:35"}
223
+ {"current_steps": 223, "total_steps": 390, "loss": 0.4744, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "9:14:20", "remaining_time": "6:55:07"}
224
+ {"current_steps": 224, "total_steps": 390, "loss": 0.4592, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "9:16:48", "remaining_time": "6:52:38"}
225
+ {"current_steps": 225, "total_steps": 390, "loss": 0.4538, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "9:19:22", "remaining_time": "6:50:12"}
226
+ {"current_steps": 226, "total_steps": 390, "loss": 0.442, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "9:21:40", "remaining_time": "6:47:35"}
227
+ {"current_steps": 227, "total_steps": 390, "loss": 0.4601, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "9:24:13", "remaining_time": "6:45:08"}
228
+ {"current_steps": 228, "total_steps": 390, "loss": 0.4221, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "9:26:20", "remaining_time": "6:42:24"}
229
+ {"current_steps": 229, "total_steps": 390, "loss": 0.4453, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "9:28:32", "remaining_time": "6:39:43"}
230
+ {"current_steps": 230, "total_steps": 390, "loss": 0.4467, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "9:31:00", "remaining_time": "6:37:13"}
231
+ {"current_steps": 231, "total_steps": 390, "loss": 0.4707, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "9:33:35", "remaining_time": "6:34:48"}
232
+ {"current_steps": 232, "total_steps": 390, "loss": 0.4331, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "9:35:50", "remaining_time": "6:32:10"}
233
+ {"current_steps": 233, "total_steps": 390, "loss": 0.4566, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "9:38:05", "remaining_time": "6:29:31"}
234
+ {"current_steps": 234, "total_steps": 390, "loss": 0.4301, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:40:16", "remaining_time": "6:26:51"}
235
+ {"current_steps": 235, "total_steps": 390, "loss": 0.3689, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:43:17", "remaining_time": "6:24:43"}