Upload training.log with huggingface_hub
Browse files- training.log +89 -0
training.log
CHANGED
|
@@ -190,3 +190,92 @@
|
|
| 190 |
[2026-01-28 10:26:52] Prompt: 'Hello! Tell me a story about a robot.'
|
| 191 |
[2026-01-28 10:26:52] Response: ''
|
| 192 |
[2026-01-28 10:26:58] Uploading diffreaper6_step_6000.pt to HF...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
[2026-01-28 10:26:52] Prompt: 'Hello! Tell me a story about a robot.'
|
| 191 |
[2026-01-28 10:26:52] Response: ''
|
| 192 |
[2026-01-28 10:26:58] Uploading diffreaper6_step_6000.pt to HF...
|
| 193 |
+
[2026-01-28 10:27:48] Step 6050 | Loss: 0.096225 | LR: 5.00e-05 | Speed: 3.95 it/s
|
| 194 |
+
[2026-01-28 10:27:59] Step 6100 | Loss: 0.025130 | LR: 5.00e-05 | Speed: 3.95 it/s
|
| 195 |
+
[2026-01-28 10:28:11] Step 6150 | Loss: 0.167280 | LR: 5.00e-05 | Speed: 3.95 it/s
|
| 196 |
+
[2026-01-28 10:28:22] Step 6200 | Loss: 0.104535 | LR: 5.00e-05 | Speed: 3.96 it/s
|
| 197 |
+
[2026-01-28 10:28:34] Step 6250 | Loss: 0.080572 | LR: 5.00e-05 | Speed: 3.96 it/s
|
| 198 |
+
[2026-01-28 10:28:45] Step 6300 | Loss: 0.051455 | LR: 5.00e-05 | Speed: 3.96 it/s
|
| 199 |
+
[2026-01-28 10:28:57] Step 6350 | Loss: 0.022109 | LR: 5.00e-05 | Speed: 3.97 it/s
|
| 200 |
+
[2026-01-28 10:29:08] Step 6400 | Loss: 0.110670 | LR: 5.00e-05 | Speed: 3.97 it/s
|
| 201 |
+
[2026-01-28 10:29:20] Step 6450 | Loss: 0.101431 | LR: 5.00e-05 | Speed: 3.97 it/s
|
| 202 |
+
[2026-01-28 10:29:31] Step 6500 | Loss: 0.081690 | LR: 5.00e-05 | Speed: 3.97 it/s
|
| 203 |
+
[2026-01-28 10:29:31] --- DiffReaper-6 Diagnostic [Step 6500] ---
|
| 204 |
+
[2026-01-28 10:29:32] Prompt: 'Hello! Tell me a story about a robot.'
|
| 205 |
+
[2026-01-28 10:29:32] Response: ''
|
| 206 |
+
[2026-01-28 10:29:43] Step 6550 | Loss: 0.031969 | LR: 5.00e-05 | Speed: 3.98 it/s
|
| 207 |
+
[2026-01-28 10:29:55] Step 6600 | Loss: 0.089200 | LR: 5.00e-05 | Speed: 3.98 it/s
|
| 208 |
+
[2026-01-28 10:30:06] Step 6650 | Loss: 0.163045 | LR: 5.00e-05 | Speed: 3.98 it/s
|
| 209 |
+
[2026-01-28 10:30:18] Step 6700 | Loss: 0.096775 | LR: 5.00e-05 | Speed: 3.98 it/s
|
| 210 |
+
[2026-01-28 10:30:29] Step 6750 | Loss: 0.038136 | LR: 5.00e-05 | Speed: 3.99 it/s
|
| 211 |
+
[2026-01-28 10:30:41] Step 6800 | Loss: 0.140960 | LR: 5.00e-05 | Speed: 3.99 it/s
|
| 212 |
+
[2026-01-28 10:38:02] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 213 |
+
[2026-01-28 10:38:13] Loading Dataset (Conversational Focus)...
|
| 214 |
+
[2026-01-28 10:38:15] DiffReaper-6 Training Started.
|
| 215 |
+
[2026-01-28 10:38:16] Step 0 | Loss: 0.264430 | LR: 0.00e+00 | Speed: 1.48 it/s
|
| 216 |
+
[2026-01-28 10:38:27] Step 50 | Loss: 0.208394 | LR: 1.20e-06 | Speed: 4.24 it/s
|
| 217 |
+
[2026-01-28 10:38:39] Step 100 | Loss: 0.164046 | LR: 2.50e-06 | Speed: 4.30 it/s
|
| 218 |
+
[2026-01-28 10:38:50] Step 150 | Loss: 0.177519 | LR: 3.70e-06 | Speed: 4.34 it/s
|
| 219 |
+
[2026-01-28 10:38:58] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 220 |
+
[2026-01-28 10:39:02] Step 200 | Loss: 0.259050 | LR: 5.00e-06 | Speed: 4.35 it/s
|
| 221 |
+
[2026-01-28 10:39:09] Loading Dataset (Conversational Focus)...
|
| 222 |
+
[2026-01-28 10:39:11] DiffReaper-6 Training Started.
|
| 223 |
+
[2026-01-28 10:39:12] Step 0 | Loss: 0.104277 | LR: 0.00e+00 | Speed: 1.17 it/s
|
| 224 |
+
[2026-01-28 10:39:14] Step 250 | Loss: 0.209021 | LR: 6.20e-06 | Speed: 4.28 it/s
|
| 225 |
+
[2026-01-28 10:39:36] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 226 |
+
[2026-01-28 10:39:46] Loading Dataset (Conversational Focus)...
|
| 227 |
+
[2026-01-28 10:39:48] DiffReaper-6 Training Started.
|
| 228 |
+
[2026-01-28 10:39:49] Step 0 | Loss: 0.219953 | LR: 0.00e+00 | Speed: 1.53 it/s
|
| 229 |
+
[2026-01-28 10:40:00] Step 50 | Loss: 0.233822 | LR: 1.20e-06 | Speed: 4.17 it/s
|
| 230 |
+
[2026-01-28 10:40:12] Step 100 | Loss: 0.141279 | LR: 2.50e-06 | Speed: 4.23 it/s
|
| 231 |
+
[2026-01-28 10:40:23] Step 150 | Loss: 0.108951 | LR: 3.70e-06 | Speed: 4.27 it/s
|
| 232 |
+
[2026-01-28 10:40:35] Step 200 | Loss: 0.084777 | LR: 5.00e-06 | Speed: 4.29 it/s
|
| 233 |
+
[2026-01-28 10:40:46] Step 250 | Loss: 0.214907 | LR: 6.20e-06 | Speed: 4.31 it/s
|
| 234 |
+
[2026-01-28 10:40:58] Step 300 | Loss: 0.244203 | LR: 7.50e-06 | Speed: 4.31 it/s
|
| 235 |
+
[2026-01-28 10:41:09] Step 350 | Loss: 0.105432 | LR: 8.70e-06 | Speed: 4.32 it/s
|
| 236 |
+
[2026-01-28 10:41:21] Step 400 | Loss: 0.200470 | LR: 1.00e-05 | Speed: 4.32 it/s
|
| 237 |
+
[2026-01-28 10:41:32] Step 450 | Loss: 0.117323 | LR: 1.12e-05 | Speed: 4.32 it/s
|
| 238 |
+
[2026-01-28 10:41:44] Step 500 | Loss: 0.178847 | LR: 1.25e-05 | Speed: 4.32 it/s
|
| 239 |
+
[2026-01-28 10:41:44] --- DiffReaper-6 Diagnostic [Step 500] ---
|
| 240 |
+
[2026-01-28 10:41:44] Prompt: 'Hello! Tell me a story about a robot.'
|
| 241 |
+
[2026-01-28 10:41:44] Response: ''
|
| 242 |
+
[2026-01-28 10:41:56] Step 550 | Loss: 0.151509 | LR: 1.37e-05 | Speed: 4.31 it/s
|
| 243 |
+
[2026-01-28 10:42:07] Step 600 | Loss: 0.200565 | LR: 1.50e-05 | Speed: 4.31 it/s
|
| 244 |
+
[2026-01-28 10:42:19] Step 650 | Loss: 0.167721 | LR: 1.62e-05 | Speed: 4.32 it/s
|
| 245 |
+
[2026-01-28 10:42:30] Step 700 | Loss: 0.177636 | LR: 1.75e-05 | Speed: 4.32 it/s
|
| 246 |
+
[2026-01-28 10:42:42] Step 750 | Loss: 0.111848 | LR: 1.87e-05 | Speed: 4.32 it/s
|
| 247 |
+
[2026-01-28 10:42:53] Step 800 | Loss: 0.154761 | LR: 2.00e-05 | Speed: 4.32 it/s
|
| 248 |
+
[2026-01-28 10:43:05] Step 850 | Loss: 0.108399 | LR: 2.12e-05 | Speed: 4.33 it/s
|
| 249 |
+
[2026-01-28 10:43:16] Step 900 | Loss: 0.139020 | LR: 2.25e-05 | Speed: 4.33 it/s
|
| 250 |
+
[2026-01-28 10:43:28] Step 950 | Loss: 0.147052 | LR: 2.37e-05 | Speed: 4.33 it/s
|
| 251 |
+
[2026-01-28 10:43:40] Step 1000 | Loss: 0.076133 | LR: 2.50e-05 | Speed: 4.32 it/s
|
| 252 |
+
[2026-01-28 10:43:40] --- DiffReaper-6 Diagnostic [Step 1000] ---
|
| 253 |
+
[2026-01-28 10:43:40] Prompt: 'Hello! Tell me a story about a robot.'
|
| 254 |
+
[2026-01-28 10:43:40] Response: '...... the........'
|
| 255 |
+
[2026-01-28 10:43:51] Step 1050 | Loss: 0.128835 | LR: 2.62e-05 | Speed: 4.32 it/s
|
| 256 |
+
[2026-01-28 10:44:03] Step 1100 | Loss: 0.097552 | LR: 2.75e-05 | Speed: 4.32 it/s
|
| 257 |
+
[2026-01-28 10:44:14] Step 1150 | Loss: 0.179753 | LR: 2.87e-05 | Speed: 4.32 it/s
|
| 258 |
+
[2026-01-28 10:44:26] Step 1200 | Loss: 0.127252 | LR: 3.00e-05 | Speed: 4.32 it/s
|
| 259 |
+
[2026-01-28 10:44:37] Step 1250 | Loss: 0.070038 | LR: 3.12e-05 | Speed: 4.33 it/s
|
| 260 |
+
[2026-01-28 10:44:49] Step 1300 | Loss: 0.094586 | LR: 3.25e-05 | Speed: 4.33 it/s
|
| 261 |
+
[2026-01-28 10:45:00] Step 1350 | Loss: 0.220502 | LR: 3.37e-05 | Speed: 4.33 it/s
|
| 262 |
+
[2026-01-28 10:45:12] Step 1400 | Loss: 0.098690 | LR: 3.50e-05 | Speed: 4.33 it/s
|
| 263 |
+
[2026-01-28 10:45:23] Step 1450 | Loss: 0.126949 | LR: 3.62e-05 | Speed: 4.33 it/s
|
| 264 |
+
[2026-01-28 10:45:35] Step 1500 | Loss: 0.043959 | LR: 3.75e-05 | Speed: 4.33 it/s
|
| 265 |
+
[2026-01-28 10:45:35] --- DiffReaper-6 Diagnostic [Step 1500] ---
|
| 266 |
+
[2026-01-28 10:45:35] Prompt: 'Hello! Tell me a story about a robot.'
|
| 267 |
+
[2026-01-28 10:45:35] Response: ',.. the a.,. the. and. and,...... the of the the and.. a. the. and and,.. the..,. and, and,.., and and the the.'
|
| 268 |
+
[2026-01-28 10:45:47] Step 1550 | Loss: 0.150234 | LR: 3.87e-05 | Speed: 4.33 it/s
|
| 269 |
+
[2026-01-28 10:45:58] Step 1600 | Loss: 0.080693 | LR: 4.00e-05 | Speed: 4.33 it/s
|
| 270 |
+
[2026-01-28 10:46:10] Step 1650 | Loss: 0.136036 | LR: 4.12e-05 | Speed: 4.33 it/s
|
| 271 |
+
[2026-01-28 10:46:21] Step 1700 | Loss: 0.070312 | LR: 4.25e-05 | Speed: 4.33 it/s
|
| 272 |
+
[2026-01-28 10:46:33] Step 1750 | Loss: 0.149436 | LR: 4.37e-05 | Speed: 4.33 it/s
|
| 273 |
+
[2026-01-28 10:46:44] Step 1800 | Loss: 0.126840 | LR: 4.50e-05 | Speed: 4.33 it/s
|
| 274 |
+
[2026-01-28 10:46:56] Step 1850 | Loss: 0.100248 | LR: 4.62e-05 | Speed: 4.33 it/s
|
| 275 |
+
[2026-01-28 10:47:07] Step 1900 | Loss: 0.151892 | LR: 4.75e-05 | Speed: 4.33 it/s
|
| 276 |
+
[2026-01-28 10:47:19] Step 1950 | Loss: 0.043785 | LR: 4.87e-05 | Speed: 4.33 it/s
|
| 277 |
+
[2026-01-28 10:47:30] Step 2000 | Loss: 0.106149 | LR: 5.00e-05 | Speed: 4.33 it/s
|
| 278 |
+
[2026-01-28 10:47:30] --- DiffReaper-6 Diagnostic [Step 2000] ---
|
| 279 |
+
[2026-01-28 10:47:31] Prompt: 'Hello! Tell me a story about a robot.'
|
| 280 |
+
[2026-01-28 10:47:31] Response: ',,, the, the the,. the and,,.,,, the., and,,,,,,,,,,,,,,'
|
| 281 |
+
[2026-01-28 10:47:35] Uploading diffreaper6_step_2000.pt to HF...
|