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:f09c81b380a14102c93cea2a5c8aefc6ddfcc674f49af58420e502377d484058
|
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 sha256:751ac2782cd11ac7d6d55703a1139ec37d7f505e7456c36cbe0cf29c4a244739
|
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:dd82f728c0ecfa18292717026f8af1324746a84d725618930ce08ac467447ddb
|
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 sha256:2917c588f5d941748c0273c512df96a2e45ea77d4125d79bb2ea6bc69b4afe89
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -158,3 +158,78 @@
|
|
158 |
{"current_steps": 158, "total_steps": 390, "loss": 0.3453, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "5:39:27", "remaining_time": "8:18:27"}
|
159 |
{"current_steps": 159, "total_steps": 390, "loss": 0.3449, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "5:41:36", "remaining_time": "8:16:18"}
|
160 |
{"current_steps": 160, "total_steps": 390, "loss": 0.3175, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "5:43:41", "remaining_time": "8:14:03"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
{"current_steps": 158, "total_steps": 390, "loss": 0.3453, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "5:39:27", "remaining_time": "8:18:27"}
|
159 |
{"current_steps": 159, "total_steps": 390, "loss": 0.3449, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "5:41:36", "remaining_time": "8:16:18"}
|
160 |
{"current_steps": 160, "total_steps": 390, "loss": 0.3175, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "5:43:41", "remaining_time": "8:14:03"}
|
161 |
+
{"current_steps": 161, "total_steps": 390, "loss": 0.3357, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "5:46:02", "remaining_time": "8:12:11"}
|
162 |
+
{"current_steps": 162, "total_steps": 390, "loss": 0.3214, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "5:48:09", "remaining_time": "8:10:00"}
|
163 |
+
{"current_steps": 163, "total_steps": 390, "loss": 0.307, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "5:50:08", "remaining_time": "8:07:37"}
|
164 |
+
{"current_steps": 164, "total_steps": 390, "loss": 0.3119, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "5:52:15", "remaining_time": "8:05:25"}
|
165 |
+
{"current_steps": 165, "total_steps": 390, "loss": 0.3501, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "5:54:35", "remaining_time": "8:03:32"}
|
166 |
+
{"current_steps": 166, "total_steps": 390, "loss": 0.3178, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "5:56:38", "remaining_time": "8:01:14"}
|
167 |
+
{"current_steps": 167, "total_steps": 390, "loss": 0.3296, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "5:58:32", "remaining_time": "7:58:46"}
|
168 |
+
{"current_steps": 168, "total_steps": 390, "loss": 0.3573, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "6:00:44", "remaining_time": "7:56:41"}
|
169 |
+
{"current_steps": 169, "total_steps": 390, "loss": 0.3363, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "6:02:45", "remaining_time": "7:54:22"}
|
170 |
+
{"current_steps": 170, "total_steps": 390, "loss": 0.3381, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "6:04:52", "remaining_time": "7:52:11"}
|
171 |
+
{"current_steps": 171, "total_steps": 390, "loss": 0.3308, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "6:06:51", "remaining_time": "7:49:49"}
|
172 |
+
{"current_steps": 172, "total_steps": 390, "loss": 0.3288, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "6:08:48", "remaining_time": "7:47:26"}
|
173 |
+
{"current_steps": 173, "total_steps": 390, "loss": 0.3257, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "6:10:36", "remaining_time": "7:44:52"}
|
174 |
+
{"current_steps": 174, "total_steps": 390, "loss": 0.3158, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "6:12:39", "remaining_time": "7:42:36"}
|
175 |
+
{"current_steps": 175, "total_steps": 390, "loss": 0.322, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "6:14:34", "remaining_time": "7:40:12"}
|
176 |
+
{"current_steps": 176, "total_steps": 390, "loss": 0.3077, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "6:16:32", "remaining_time": "7:37:49"}
|
177 |
+
{"current_steps": 177, "total_steps": 390, "loss": 0.3067, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "6:18:21", "remaining_time": "7:35:18"}
|
178 |
+
{"current_steps": 178, "total_steps": 390, "loss": 0.3147, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "6:20:18", "remaining_time": "7:32:57"}
|
179 |
+
{"current_steps": 179, "total_steps": 390, "loss": 0.3375, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "6:22:14", "remaining_time": "7:30:34"}
|
180 |
+
{"current_steps": 180, "total_steps": 390, "loss": 0.3341, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "6:24:16", "remaining_time": "7:28:19"}
|
181 |
+
{"current_steps": 181, "total_steps": 390, "loss": 0.3231, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "6:26:13", "remaining_time": "7:25:57"}
|
182 |
+
{"current_steps": 182, "total_steps": 390, "loss": 0.3226, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "6:28:11", "remaining_time": "7:23:38"}
|
183 |
+
{"current_steps": 183, "total_steps": 390, "loss": 0.3341, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "6:30:13", "remaining_time": "7:21:23"}
|
184 |
+
{"current_steps": 184, "total_steps": 390, "loss": 0.3237, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "6:32:10", "remaining_time": "7:19:03"}
|
185 |
+
{"current_steps": 185, "total_steps": 390, "loss": 0.3141, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "6:34:01", "remaining_time": "7:16:37"}
|
186 |
+
{"current_steps": 186, "total_steps": 390, "loss": 0.3233, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "6:35:55", "remaining_time": "7:14:14"}
|
187 |
+
{"current_steps": 187, "total_steps": 390, "loss": 0.3222, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "6:37:45", "remaining_time": "7:11:47"}
|
188 |
+
{"current_steps": 188, "total_steps": 390, "loss": 0.3056, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "6:39:48", "remaining_time": "7:09:34"}
|
189 |
+
{"current_steps": 189, "total_steps": 390, "loss": 0.3296, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "6:41:33", "remaining_time": "7:07:03"}
|
190 |
+
{"current_steps": 190, "total_steps": 390, "loss": 0.3166, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "6:43:38", "remaining_time": "7:04:53"}
|
191 |
+
{"current_steps": 191, "total_steps": 390, "loss": 0.327, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "6:45:45", "remaining_time": "7:02:45"}
|
192 |
+
{"current_steps": 192, "total_steps": 390, "loss": 0.3272, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "6:47:53", "remaining_time": "7:00:37"}
|
193 |
+
{"current_steps": 193, "total_steps": 390, "loss": 0.3323, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "6:49:57", "remaining_time": "6:58:27"}
|
194 |
+
{"current_steps": 194, "total_steps": 390, "loss": 0.3443, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "6:51:59", "remaining_time": "6:56:14"}
|
195 |
+
{"current_steps": 195, "total_steps": 390, "loss": 0.3267, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "6:53:50", "remaining_time": "6:53:50"}
|
196 |
+
{"current_steps": 196, "total_steps": 390, "loss": 0.2975, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "6:55:33", "remaining_time": "6:51:19"}
|
197 |
+
{"current_steps": 197, "total_steps": 390, "loss": 0.3243, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "6:57:42", "remaining_time": "6:49:13"}
|
198 |
+
{"current_steps": 198, "total_steps": 390, "loss": 0.3252, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "6:59:34", "remaining_time": "6:46:51"}
|
199 |
+
{"current_steps": 199, "total_steps": 390, "loss": 0.3287, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "7:01:38", "remaining_time": "6:44:41"}
|
200 |
+
{"current_steps": 200, "total_steps": 390, "loss": 0.3364, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "7:03:52", "remaining_time": "6:42:40"}
|
201 |
+
{"current_steps": 201, "total_steps": 390, "loss": 0.3313, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "7:05:55", "remaining_time": "6:40:29"}
|
202 |
+
{"current_steps": 202, "total_steps": 390, "loss": 0.2996, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "7:07:42", "remaining_time": "6:38:04"}
|
203 |
+
{"current_steps": 203, "total_steps": 390, "loss": 0.3319, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "7:09:51", "remaining_time": "6:35:58"}
|
204 |
+
{"current_steps": 204, "total_steps": 390, "loss": 0.3333, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "7:11:58", "remaining_time": "6:33:51"}
|
205 |
+
{"current_steps": 205, "total_steps": 390, "loss": 0.3245, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "7:13:58", "remaining_time": "6:31:38"}
|
206 |
+
{"current_steps": 206, "total_steps": 390, "loss": 0.3244, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "7:16:07", "remaining_time": "6:29:32"}
|
207 |
+
{"current_steps": 207, "total_steps": 390, "loss": 0.3406, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "7:18:10", "remaining_time": "6:27:22"}
|
208 |
+
{"current_steps": 208, "total_steps": 390, "loss": 0.3006, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "7:20:03", "remaining_time": "6:25:03"}
|
209 |
+
{"current_steps": 209, "total_steps": 390, "loss": 0.3143, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "7:22:03", "remaining_time": "6:22:49"}
|
210 |
+
{"current_steps": 210, "total_steps": 390, "loss": 0.3241, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "7:23:54", "remaining_time": "6:20:29"}
|
211 |
+
{"current_steps": 211, "total_steps": 390, "loss": 0.3375, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "7:25:58", "remaining_time": "6:18:20"}
|
212 |
+
{"current_steps": 212, "total_steps": 390, "loss": 0.3258, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "7:28:02", "remaining_time": "6:16:11"}
|
213 |
+
{"current_steps": 213, "total_steps": 390, "loss": 0.3351, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "7:30:04", "remaining_time": "6:14:00"}
|
214 |
+
{"current_steps": 214, "total_steps": 390, "loss": 0.3312, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "7:32:14", "remaining_time": "6:11:56"}
|
215 |
+
{"current_steps": 215, "total_steps": 390, "loss": 0.3259, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "7:34:09", "remaining_time": "6:09:40"}
|
216 |
+
{"current_steps": 216, "total_steps": 390, "loss": 0.3348, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "7:36:10", "remaining_time": "6:07:28"}
|
217 |
+
{"current_steps": 217, "total_steps": 390, "loss": 0.3453, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "7:38:14", "remaining_time": "6:05:19"}
|
218 |
+
{"current_steps": 218, "total_steps": 390, "loss": 0.3086, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "7:40:08", "remaining_time": "6:03:02"}
|
219 |
+
{"current_steps": 219, "total_steps": 390, "loss": 0.322, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "7:42:08", "remaining_time": "6:00:50"}
|
220 |
+
{"current_steps": 220, "total_steps": 390, "loss": 0.3266, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "7:44:05", "remaining_time": "5:58:37"}
|
221 |
+
{"current_steps": 221, "total_steps": 390, "loss": 0.3324, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "7:45:56", "remaining_time": "5:56:18"}
|
222 |
+
{"current_steps": 222, "total_steps": 390, "loss": 0.3241, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "7:47:55", "remaining_time": "5:54:06"}
|
223 |
+
{"current_steps": 223, "total_steps": 390, "loss": 0.3179, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "7:49:51", "remaining_time": "5:51:52"}
|
224 |
+
{"current_steps": 224, "total_steps": 390, "loss": 0.3494, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "7:52:12", "remaining_time": "5:49:56"}
|
225 |
+
{"current_steps": 225, "total_steps": 390, "loss": 0.3329, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "7:54:06", "remaining_time": "5:47:40"}
|
226 |
+
{"current_steps": 226, "total_steps": 390, "loss": 0.3172, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "7:56:02", "remaining_time": "5:45:26"}
|
227 |
+
{"current_steps": 227, "total_steps": 390, "loss": 0.3159, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "7:58:05", "remaining_time": "5:43:17"}
|
228 |
+
{"current_steps": 228, "total_steps": 390, "loss": 0.3184, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "8:00:17", "remaining_time": "5:41:15"}
|
229 |
+
{"current_steps": 229, "total_steps": 390, "loss": 0.3188, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "8:02:29", "remaining_time": "5:39:12"}
|
230 |
+
{"current_steps": 230, "total_steps": 390, "loss": 0.3153, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "8:04:43", "remaining_time": "5:37:11"}
|
231 |
+
{"current_steps": 231, "total_steps": 390, "loss": 0.3297, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "8:06:48", "remaining_time": "5:35:04"}
|
232 |
+
{"current_steps": 232, "total_steps": 390, "loss": 0.3078, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "8:08:42", "remaining_time": "5:32:49"}
|
233 |
+
{"current_steps": 233, "total_steps": 390, "loss": 0.3314, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "8:10:42", "remaining_time": "5:30:38"}
|
234 |
+
{"current_steps": 234, "total_steps": 390, "loss": 0.3307, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:12:42", "remaining_time": "5:28:28"}
|
235 |
+
{"current_steps": 235, "total_steps": 390, "loss": 0.2769, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:15:26", "remaining_time": "5:26:46"}
|