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:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36ab3a512326afbfb91e564fa3aebd75d4a0bec68ee6a7d8119dbf502d8d3f6e
|
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:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e64dde9f02d5a6a4d92c75d1417fd887836c6cfe13d04490fde8649abdbd6be2
|
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:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64002d3f6dc24011e2667902de587efe522e50ac40697ef22c1c46cba58f944d
|
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:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c3773cfd0f6b0962ea89b61415cd0d4b7b1a53b9d026e86030263d0fa2c2a08
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -155,3 +155,81 @@
|
|
155 |
{"current_steps": 155, "total_steps": 390, "loss": 0.574, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:03:50", "remaining_time": "10:42:35"}
|
156 |
{"current_steps": 156, "total_steps": 390, "loss": 0.5767, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:06:29", "remaining_time": "10:39:44"}
|
157 |
{"current_steps": 157, "total_steps": 390, "loss": 0.5201, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:10:10", "remaining_time": "10:38:25"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
{"current_steps": 155, "total_steps": 390, "loss": 0.574, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:03:50", "remaining_time": "10:42:35"}
|
156 |
{"current_steps": 156, "total_steps": 390, "loss": 0.5767, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:06:29", "remaining_time": "10:39:44"}
|
157 |
{"current_steps": 157, "total_steps": 390, "loss": 0.5201, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:10:10", "remaining_time": "10:38:25"}
|
158 |
+
{"current_steps": 158, "total_steps": 390, "loss": 0.5094, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "7:12:44", "remaining_time": "10:35:25"}
|
159 |
+
{"current_steps": 159, "total_steps": 390, "loss": 0.5072, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "7:15:20", "remaining_time": "10:32:28"}
|
160 |
+
{"current_steps": 160, "total_steps": 390, "loss": 0.4907, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "7:18:07", "remaining_time": "10:29:48"}
|
161 |
+
{"current_steps": 161, "total_steps": 390, "loss": 0.5084, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "7:20:53", "remaining_time": "10:27:06"}
|
162 |
+
{"current_steps": 162, "total_steps": 390, "loss": 0.5003, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "7:23:19", "remaining_time": "10:23:55"}
|
163 |
+
{"current_steps": 163, "total_steps": 390, "loss": 0.4919, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "7:25:55", "remaining_time": "10:21:00"}
|
164 |
+
{"current_steps": 164, "total_steps": 390, "loss": 0.5046, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "7:28:37", "remaining_time": "10:18:12"}
|
165 |
+
{"current_steps": 165, "total_steps": 390, "loss": 0.488, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "7:31:18", "remaining_time": "10:15:25"}
|
166 |
+
{"current_steps": 166, "total_steps": 390, "loss": 0.5128, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:33:53", "remaining_time": "10:12:28"}
|
167 |
+
{"current_steps": 167, "total_steps": 390, "loss": 0.5062, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:36:50", "remaining_time": "10:10:01"}
|
168 |
+
{"current_steps": 168, "total_steps": 390, "loss": 0.4993, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:39:38", "remaining_time": "10:07:23"}
|
169 |
+
{"current_steps": 169, "total_steps": 390, "loss": 0.5001, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:42:14", "remaining_time": "10:04:28"}
|
170 |
+
{"current_steps": 170, "total_steps": 390, "loss": 0.5029, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:45:05", "remaining_time": "10:01:52"}
|
171 |
+
{"current_steps": 171, "total_steps": 390, "loss": 0.5083, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:47:34", "remaining_time": "9:58:49"}
|
172 |
+
{"current_steps": 172, "total_steps": 390, "loss": 0.5147, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:50:29", "remaining_time": "9:56:19"}
|
173 |
+
{"current_steps": 173, "total_steps": 390, "loss": 0.5029, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:53:13", "remaining_time": "9:53:35"}
|
174 |
+
{"current_steps": 174, "total_steps": 390, "loss": 0.4785, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:55:54", "remaining_time": "9:50:46"}
|
175 |
+
{"current_steps": 175, "total_steps": 390, "loss": 0.4872, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:58:35", "remaining_time": "9:47:58"}
|
176 |
+
{"current_steps": 176, "total_steps": 390, "loss": 0.5073, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "8:01:16", "remaining_time": "9:45:10"}
|
177 |
+
{"current_steps": 177, "total_steps": 390, "loss": 0.4866, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "8:04:07", "remaining_time": "9:42:35"}
|
178 |
+
{"current_steps": 178, "total_steps": 390, "loss": 0.5094, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "8:06:38", "remaining_time": "9:39:36"}
|
179 |
+
{"current_steps": 179, "total_steps": 390, "loss": 0.5135, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "8:09:30", "remaining_time": "9:37:01"}
|
180 |
+
{"current_steps": 180, "total_steps": 390, "loss": 0.4957, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "8:12:18", "remaining_time": "9:34:22"}
|
181 |
+
{"current_steps": 181, "total_steps": 390, "loss": 0.498, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "8:15:03", "remaining_time": "9:31:38"}
|
182 |
+
{"current_steps": 182, "total_steps": 390, "loss": 0.4985, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "8:17:49", "remaining_time": "9:28:56"}
|
183 |
+
{"current_steps": 183, "total_steps": 390, "loss": 0.4935, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "8:20:38", "remaining_time": "9:26:17"}
|
184 |
+
{"current_steps": 184, "total_steps": 390, "loss": 0.508, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "8:23:13", "remaining_time": "9:23:23"}
|
185 |
+
{"current_steps": 185, "total_steps": 390, "loss": 0.5051, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "8:25:57", "remaining_time": "9:20:39"}
|
186 |
+
{"current_steps": 186, "total_steps": 390, "loss": 0.4925, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "8:28:42", "remaining_time": "9:17:56"}
|
187 |
+
{"current_steps": 187, "total_steps": 390, "loss": 0.5084, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "8:31:34", "remaining_time": "9:15:21"}
|
188 |
+
{"current_steps": 188, "total_steps": 390, "loss": 0.4916, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "8:34:09", "remaining_time": "9:12:27"}
|
189 |
+
{"current_steps": 189, "total_steps": 390, "loss": 0.5014, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "8:37:06", "remaining_time": "9:09:56"}
|
190 |
+
{"current_steps": 190, "total_steps": 390, "loss": 0.5072, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "8:39:55", "remaining_time": "9:07:17"}
|
191 |
+
{"current_steps": 191, "total_steps": 390, "loss": 0.5051, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:42:26", "remaining_time": "9:04:19"}
|
192 |
+
{"current_steps": 192, "total_steps": 390, "loss": 0.4934, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:45:07", "remaining_time": "9:01:32"}
|
193 |
+
{"current_steps": 193, "total_steps": 390, "loss": 0.5028, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:47:59", "remaining_time": "8:58:56"}
|
194 |
+
{"current_steps": 194, "total_steps": 390, "loss": 0.4959, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:50:51", "remaining_time": "8:56:19"}
|
195 |
+
{"current_steps": 195, "total_steps": 390, "loss": 0.5057, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:53:36", "remaining_time": "8:53:36"}
|
196 |
+
{"current_steps": 196, "total_steps": 390, "loss": 0.4995, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:56:32", "remaining_time": "8:51:03"}
|
197 |
+
{"current_steps": 197, "total_steps": 390, "loss": 0.4817, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:59:07", "remaining_time": "8:48:10"}
|
198 |
+
{"current_steps": 198, "total_steps": 390, "loss": 0.5164, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "9:01:42", "remaining_time": "8:45:17"}
|
199 |
+
{"current_steps": 199, "total_steps": 390, "loss": 0.5033, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "9:04:31", "remaining_time": "8:42:38"}
|
200 |
+
{"current_steps": 200, "total_steps": 390, "loss": 0.4991, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "9:07:11", "remaining_time": "8:39:49"}
|
201 |
+
{"current_steps": 201, "total_steps": 390, "loss": 0.4997, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "9:10:10", "remaining_time": "8:37:19"}
|
202 |
+
{"current_steps": 202, "total_steps": 390, "loss": 0.4932, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "9:12:51", "remaining_time": "8:34:32"}
|
203 |
+
{"current_steps": 203, "total_steps": 390, "loss": 0.5039, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "9:15:31", "remaining_time": "8:31:44"}
|
204 |
+
{"current_steps": 204, "total_steps": 390, "loss": 0.5031, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "9:18:24", "remaining_time": "8:29:07"}
|
205 |
+
{"current_steps": 205, "total_steps": 390, "loss": 0.4954, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "9:21:09", "remaining_time": "8:26:24"}
|
206 |
+
{"current_steps": 206, "total_steps": 390, "loss": 0.5009, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "9:23:48", "remaining_time": "8:23:36"}
|
207 |
+
{"current_steps": 207, "total_steps": 390, "loss": 0.4918, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "9:26:28", "remaining_time": "8:20:47"}
|
208 |
+
{"current_steps": 208, "total_steps": 390, "loss": 0.497, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "9:29:10", "remaining_time": "8:18:01"}
|
209 |
+
{"current_steps": 209, "total_steps": 390, "loss": 0.501, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "9:31:57", "remaining_time": "8:15:19"}
|
210 |
+
{"current_steps": 210, "total_steps": 390, "loss": 0.5024, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "9:34:36", "remaining_time": "8:12:31"}
|
211 |
+
{"current_steps": 211, "total_steps": 390, "loss": 0.4967, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "9:37:13", "remaining_time": "8:09:40"}
|
212 |
+
{"current_steps": 212, "total_steps": 390, "loss": 0.4918, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "9:39:49", "remaining_time": "8:06:50"}
|
213 |
+
{"current_steps": 213, "total_steps": 390, "loss": 0.4996, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "9:42:46", "remaining_time": "8:04:16"}
|
214 |
+
{"current_steps": 214, "total_steps": 390, "loss": 0.4934, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "9:45:30", "remaining_time": "8:01:32"}
|
215 |
+
{"current_steps": 215, "total_steps": 390, "loss": 0.5035, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:47:53", "remaining_time": "7:58:30"}
|
216 |
+
{"current_steps": 216, "total_steps": 390, "loss": 0.5094, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:50:44", "remaining_time": "7:55:52"}
|
217 |
+
{"current_steps": 217, "total_steps": 390, "loss": 0.5119, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:53:26", "remaining_time": "7:53:06"}
|
218 |
+
{"current_steps": 218, "total_steps": 390, "loss": 0.5047, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:56:10", "remaining_time": "7:50:22"}
|
219 |
+
{"current_steps": 219, "total_steps": 390, "loss": 0.5023, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:58:59", "remaining_time": "7:47:42"}
|
220 |
+
{"current_steps": 220, "total_steps": 390, "loss": 0.5052, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "10:01:58", "remaining_time": "7:45:09"}
|
221 |
+
{"current_steps": 221, "total_steps": 390, "loss": 0.495, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "10:04:50", "remaining_time": "7:42:31"}
|
222 |
+
{"current_steps": 222, "total_steps": 390, "loss": 0.4917, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "10:07:42", "remaining_time": "7:39:53"}
|
223 |
+
{"current_steps": 223, "total_steps": 390, "loss": 0.5185, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "10:10:24", "remaining_time": "7:37:07"}
|
224 |
+
{"current_steps": 224, "total_steps": 390, "loss": 0.4923, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "10:13:09", "remaining_time": "7:34:23"}
|
225 |
+
{"current_steps": 225, "total_steps": 390, "loss": 0.5065, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "10:15:59", "remaining_time": "7:31:43"}
|
226 |
+
{"current_steps": 226, "total_steps": 390, "loss": 0.4982, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "10:18:44", "remaining_time": "7:28:59"}
|
227 |
+
{"current_steps": 227, "total_steps": 390, "loss": 0.5079, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "10:21:30", "remaining_time": "7:26:17"}
|
228 |
+
{"current_steps": 228, "total_steps": 390, "loss": 0.4881, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "10:24:09", "remaining_time": "7:23:28"}
|
229 |
+
{"current_steps": 229, "total_steps": 390, "loss": 0.4961, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "10:26:57", "remaining_time": "7:20:46"}
|
230 |
+
{"current_steps": 230, "total_steps": 390, "loss": 0.5132, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "10:29:36", "remaining_time": "7:17:59"}
|
231 |
+
{"current_steps": 231, "total_steps": 390, "loss": 0.4947, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "10:32:07", "remaining_time": "7:15:05"}
|
232 |
+
{"current_steps": 232, "total_steps": 390, "loss": 0.4975, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "10:34:44", "remaining_time": "7:12:16"}
|
233 |
+
{"current_steps": 233, "total_steps": 390, "loss": 0.5153, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:37:24", "remaining_time": "7:09:29"}
|
234 |
+
{"current_steps": 234, "total_steps": 390, "loss": 0.4941, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:40:08", "remaining_time": "7:06:45"}
|
235 |
+
{"current_steps": 235, "total_steps": 390, "loss": 0.4681, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:43:39", "remaining_time": "7:04:32"}
|