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 sha256:7e48c6d5e81e88da452b76d8aa77d43741f7d06bc2c43d9a23fcc102e9326232
|
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 sha256:1b46947a44b742ded00a9d9eeb48fae60b818d1a16a41ab56ab94478c4136747
|
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:c6b190c3bca2ade4912486e9aa6d37ce53597cda9ad06f45ef5715648e45d93a
|
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 sha256:46db54cf29e4a84be42136b96f99dc0f85d85cdc5416792c4c945c3cf922c3cd
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -155,3 +155,82 @@
|
|
155 |
{"current_steps": 155, "total_steps": 390, "loss": 0.3934, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:33:09", "remaining_time": "9:56:05"}
|
156 |
{"current_steps": 156, "total_steps": 390, "loss": 0.3809, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:35:37", "remaining_time": "9:53:26"}
|
157 |
{"current_steps": 157, "total_steps": 390, "loss": 0.3455, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:38:55", "remaining_time": "9:52:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
{"current_steps": 155, "total_steps": 390, "loss": 0.3934, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:33:09", "remaining_time": "9:56:05"}
|
156 |
{"current_steps": 156, "total_steps": 390, "loss": 0.3809, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:35:37", "remaining_time": "9:53:26"}
|
157 |
{"current_steps": 157, "total_steps": 390, "loss": 0.3455, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:38:55", "remaining_time": "9:52:02"}
|
158 |
+
{"current_steps": 158, "total_steps": 390, "loss": 0.3263, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "6:41:16", "remaining_time": "9:49:12"}
|
159 |
+
{"current_steps": 159, "total_steps": 390, "loss": 0.3349, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "6:43:41", "remaining_time": "9:46:30"}
|
160 |
+
{"current_steps": 160, "total_steps": 390, "loss": 0.3442, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "6:46:01", "remaining_time": "9:43:39"}
|
161 |
+
{"current_steps": 161, "total_steps": 390, "loss": 0.3205, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "6:48:43", "remaining_time": "9:41:21"}
|
162 |
+
{"current_steps": 162, "total_steps": 390, "loss": 0.3275, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "6:51:28", "remaining_time": "9:39:06"}
|
163 |
+
{"current_steps": 163, "total_steps": 390, "loss": 0.317, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "6:53:46", "remaining_time": "9:36:13"}
|
164 |
+
{"current_steps": 164, "total_steps": 390, "loss": 0.3207, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "6:56:13", "remaining_time": "9:33:34"}
|
165 |
+
{"current_steps": 165, "total_steps": 390, "loss": 0.317, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "6:58:41", "remaining_time": "9:30:57"}
|
166 |
+
{"current_steps": 166, "total_steps": 390, "loss": 0.3189, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:01:06", "remaining_time": "9:28:14"}
|
167 |
+
{"current_steps": 167, "total_steps": 390, "loss": 0.3322, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:03:37", "remaining_time": "9:25:40"}
|
168 |
+
{"current_steps": 168, "total_steps": 390, "loss": 0.3251, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:05:55", "remaining_time": "9:22:49"}
|
169 |
+
{"current_steps": 169, "total_steps": 390, "loss": 0.3064, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:08:38", "remaining_time": "9:20:32"}
|
170 |
+
{"current_steps": 170, "total_steps": 390, "loss": 0.3202, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:11:02", "remaining_time": "9:17:49"}
|
171 |
+
{"current_steps": 171, "total_steps": 390, "loss": 0.3172, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:13:31", "remaining_time": "9:15:13"}
|
172 |
+
{"current_steps": 172, "total_steps": 390, "loss": 0.3278, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:16:00", "remaining_time": "9:12:37"}
|
173 |
+
{"current_steps": 173, "total_steps": 390, "loss": 0.3231, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:18:19", "remaining_time": "9:09:48"}
|
174 |
+
{"current_steps": 174, "total_steps": 390, "loss": 0.3258, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:20:42", "remaining_time": "9:07:05"}
|
175 |
+
{"current_steps": 175, "total_steps": 390, "loss": 0.3234, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:23:10", "remaining_time": "9:04:28"}
|
176 |
+
{"current_steps": 176, "total_steps": 390, "loss": 0.3251, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:25:19", "remaining_time": "9:01:29"}
|
177 |
+
{"current_steps": 177, "total_steps": 390, "loss": 0.3277, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "7:27:47", "remaining_time": "8:58:52"}
|
178 |
+
{"current_steps": 178, "total_steps": 390, "loss": 0.3312, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "7:30:13", "remaining_time": "8:56:13"}
|
179 |
+
{"current_steps": 179, "total_steps": 390, "loss": 0.3217, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "7:32:43", "remaining_time": "8:53:39"}
|
180 |
+
{"current_steps": 180, "total_steps": 390, "loss": 0.3059, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "7:35:19", "remaining_time": "8:51:12"}
|
181 |
+
{"current_steps": 181, "total_steps": 390, "loss": 0.3216, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "7:37:43", "remaining_time": "8:48:31"}
|
182 |
+
{"current_steps": 182, "total_steps": 390, "loss": 0.3339, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "7:40:12", "remaining_time": "8:45:56"}
|
183 |
+
{"current_steps": 183, "total_steps": 390, "loss": 0.3299, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "7:42:40", "remaining_time": "8:43:20"}
|
184 |
+
{"current_steps": 184, "total_steps": 390, "loss": 0.3306, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "7:45:04", "remaining_time": "8:40:41"}
|
185 |
+
{"current_steps": 185, "total_steps": 390, "loss": 0.3259, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "7:47:28", "remaining_time": "8:38:00"}
|
186 |
+
{"current_steps": 186, "total_steps": 390, "loss": 0.323, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "7:49:53", "remaining_time": "8:35:21"}
|
187 |
+
{"current_steps": 187, "total_steps": 390, "loss": 0.3242, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "7:52:15", "remaining_time": "8:32:39"}
|
188 |
+
{"current_steps": 188, "total_steps": 390, "loss": 0.3279, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "7:54:38", "remaining_time": "8:29:59"}
|
189 |
+
{"current_steps": 189, "total_steps": 390, "loss": 0.3304, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "7:57:08", "remaining_time": "8:27:25"}
|
190 |
+
{"current_steps": 190, "total_steps": 390, "loss": 0.336, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "7:59:39", "remaining_time": "8:24:53"}
|
191 |
+
{"current_steps": 191, "total_steps": 390, "loss": 0.3315, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:02:03", "remaining_time": "8:22:15"}
|
192 |
+
{"current_steps": 192, "total_steps": 390, "loss": 0.3222, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:04:36", "remaining_time": "8:19:44"}
|
193 |
+
{"current_steps": 193, "total_steps": 390, "loss": 0.3216, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:07:17", "remaining_time": "8:17:23"}
|
194 |
+
{"current_steps": 194, "total_steps": 390, "loss": 0.333, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:09:50", "remaining_time": "8:14:53"}
|
195 |
+
{"current_steps": 195, "total_steps": 390, "loss": 0.3266, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:12:18", "remaining_time": "8:12:18"}
|
196 |
+
{"current_steps": 196, "total_steps": 390, "loss": 0.3291, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:14:48", "remaining_time": "8:09:45"}
|
197 |
+
{"current_steps": 197, "total_steps": 390, "loss": 0.3268, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:17:29", "remaining_time": "8:07:23"}
|
198 |
+
{"current_steps": 198, "total_steps": 390, "loss": 0.3234, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:20:04", "remaining_time": "8:04:55"}
|
199 |
+
{"current_steps": 199, "total_steps": 390, "loss": 0.3324, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "8:22:35", "remaining_time": "8:02:23"}
|
200 |
+
{"current_steps": 200, "total_steps": 390, "loss": 0.332, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "8:24:53", "remaining_time": "7:59:38"}
|
201 |
+
{"current_steps": 201, "total_steps": 390, "loss": 0.3337, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "8:27:27", "remaining_time": "7:57:10"}
|
202 |
+
{"current_steps": 202, "total_steps": 390, "loss": 0.3256, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "8:29:58", "remaining_time": "7:54:37"}
|
203 |
+
{"current_steps": 203, "total_steps": 390, "loss": 0.3264, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "8:32:21", "remaining_time": "7:51:58"}
|
204 |
+
{"current_steps": 204, "total_steps": 390, "loss": 0.328, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "8:35:03", "remaining_time": "7:49:37"}
|
205 |
+
{"current_steps": 205, "total_steps": 390, "loss": 0.3322, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "8:37:25", "remaining_time": "7:46:56"}
|
206 |
+
{"current_steps": 206, "total_steps": 390, "loss": 0.3249, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "8:39:45", "remaining_time": "7:44:15"}
|
207 |
+
{"current_steps": 207, "total_steps": 390, "loss": 0.3279, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "8:42:06", "remaining_time": "7:41:34"}
|
208 |
+
{"current_steps": 208, "total_steps": 390, "loss": 0.3316, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "8:44:46", "remaining_time": "7:39:10"}
|
209 |
+
{"current_steps": 209, "total_steps": 390, "loss": 0.3065, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "8:46:59", "remaining_time": "7:36:23"}
|
210 |
+
{"current_steps": 210, "total_steps": 390, "loss": 0.3356, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "8:49:34", "remaining_time": "7:33:55"}
|
211 |
+
{"current_steps": 211, "total_steps": 390, "loss": 0.3301, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "8:51:59", "remaining_time": "7:31:18"}
|
212 |
+
{"current_steps": 212, "total_steps": 390, "loss": 0.317, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "8:54:36", "remaining_time": "7:28:51"}
|
213 |
+
{"current_steps": 213, "total_steps": 390, "loss": 0.3222, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "8:57:08", "remaining_time": "7:26:21"}
|
214 |
+
{"current_steps": 214, "total_steps": 390, "loss": 0.3139, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "8:59:32", "remaining_time": "7:23:44"}
|
215 |
+
{"current_steps": 215, "total_steps": 390, "loss": 0.3238, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:01:46", "remaining_time": "7:20:58"}
|
216 |
+
{"current_steps": 216, "total_steps": 390, "loss": 0.3252, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:04:19", "remaining_time": "7:18:29"}
|
217 |
+
{"current_steps": 217, "total_steps": 390, "loss": 0.3338, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:06:55", "remaining_time": "7:16:02"}
|
218 |
+
{"current_steps": 218, "total_steps": 390, "loss": 0.31, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:09:27", "remaining_time": "7:13:31"}
|
219 |
+
{"current_steps": 219, "total_steps": 390, "loss": 0.3276, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:12:09", "remaining_time": "7:11:08"}
|
220 |
+
{"current_steps": 220, "total_steps": 390, "loss": 0.315, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:14:18", "remaining_time": "7:08:19"}
|
221 |
+
{"current_steps": 221, "total_steps": 390, "loss": 0.3278, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "9:16:35", "remaining_time": "7:05:37"}
|
222 |
+
{"current_steps": 222, "total_steps": 390, "loss": 0.3212, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "9:19:03", "remaining_time": "7:03:04"}
|
223 |
+
{"current_steps": 223, "total_steps": 390, "loss": 0.3292, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "9:21:38", "remaining_time": "7:00:35"}
|
224 |
+
{"current_steps": 224, "total_steps": 390, "loss": 0.3186, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "9:24:03", "remaining_time": "6:58:00"}
|
225 |
+
{"current_steps": 225, "total_steps": 390, "loss": 0.321, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "9:26:17", "remaining_time": "6:55:16"}
|
226 |
+
{"current_steps": 226, "total_steps": 390, "loss": 0.3075, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "9:28:41", "remaining_time": "6:52:40"}
|
227 |
+
{"current_steps": 227, "total_steps": 390, "loss": 0.325, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "9:31:13", "remaining_time": "6:50:10"}
|
228 |
+
{"current_steps": 228, "total_steps": 390, "loss": 0.3225, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "9:33:49", "remaining_time": "6:47:43"}
|
229 |
+
{"current_steps": 229, "total_steps": 390, "loss": 0.3222, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "9:36:23", "remaining_time": "6:45:14"}
|
230 |
+
{"current_steps": 230, "total_steps": 390, "loss": 0.3285, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "9:38:49", "remaining_time": "6:42:39"}
|
231 |
+
{"current_steps": 231, "total_steps": 390, "loss": 0.3247, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "9:41:11", "remaining_time": "6:40:02"}
|
232 |
+
{"current_steps": 232, "total_steps": 390, "loss": 0.3223, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "9:43:37", "remaining_time": "6:37:28"}
|
233 |
+
{"current_steps": 233, "total_steps": 390, "loss": 0.3201, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "9:45:58", "remaining_time": "6:34:50"}
|
234 |
+
{"current_steps": 234, "total_steps": 390, "loss": 0.3235, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:48:17", "remaining_time": "6:32:11"}
|
235 |
+
{"current_steps": 235, "total_steps": 390, "loss": 0.2979, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:51:41", "remaining_time": "6:30:15"}
|
236 |
+
{"current_steps": 236, "total_steps": 390, "loss": 0.2682, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "9:54:20", "remaining_time": "6:27:49"}
|