Upload training.log with huggingface_hub
Browse files- training.log +86 -0
training.log
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[2026-01-28 09:56:44] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 2 |
+
[2026-01-28 09:57:14] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 3 |
+
[2026-01-28 09:57:34] Loading Dataset (Conversational Focus)...
|
| 4 |
+
[2026-01-28 09:57:44] DiffReaper-6 Training Started.
|
| 5 |
+
[2026-01-28 09:58:16] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 6 |
+
[2026-01-28 09:58:32] Loading Dataset (Conversational Focus)...
|
| 7 |
+
[2026-01-28 09:58:34] DiffReaper-6 Training Started.
|
| 8 |
+
[2026-01-28 09:58:35] Step 0 | Loss: 0.252853 | LR: 0.00e+00 | Speed: 1.52 it/s
|
| 9 |
+
[2026-01-28 09:58:53] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 10 |
+
[2026-01-28 09:59:11] Loading Dataset (Conversational Focus)...
|
| 11 |
+
[2026-01-28 09:59:13] DiffReaper-6 Training Started.
|
| 12 |
+
[2026-01-28 09:59:14] Step 0 | Loss: 0.217347 | LR: 0.00e+00 | Speed: 1.53 it/s
|
| 13 |
+
[2026-01-28 09:59:44] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 14 |
+
[2026-01-28 09:59:54] Loading Dataset (Conversational Focus)...
|
| 15 |
+
[2026-01-28 09:59:56] DiffReaper-6 Training Started.
|
| 16 |
+
[2026-01-28 09:59:56] Step 0 | Loss: 0.178516 | LR: 0.00e+00 | Speed: 1.48 it/s
|
| 17 |
+
[2026-01-28 10:00:08] Step 50 | Loss: 0.172741 | LR: 1.20e-06 | Speed: 4.32 it/s
|
| 18 |
+
[2026-01-28 10:00:19] Step 100 | Loss: 0.085050 | LR: 2.50e-06 | Speed: 4.37 it/s
|
| 19 |
+
[2026-01-28 10:00:30] Step 150 | Loss: 0.093833 | LR: 3.70e-06 | Speed: 4.41 it/s
|
| 20 |
+
[2026-01-28 10:00:30] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 21 |
+
[2026-01-28 10:00:41] Loading Dataset (Conversational Focus)...
|
| 22 |
+
[2026-01-28 10:00:41] Step 200 | Loss: 0.041686 | LR: 5.00e-06 | Speed: 4.41 it/s
|
| 23 |
+
[2026-01-28 10:00:43] DiffReaper-6 Training Started.
|
| 24 |
+
[2026-01-28 10:00:44] Step 0 | Loss: 0.141989 | LR: 0.00e+00 | Speed: 1.20 it/s
|
| 25 |
+
[2026-01-28 10:00:54] Step 250 | Loss: 0.201472 | LR: 6.20e-06 | Speed: 4.34 it/s
|
| 26 |
+
[2026-01-28 10:01:16] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 27 |
+
[2026-01-28 10:01:34] Loading Dataset (Conversational Focus)...
|
| 28 |
+
[2026-01-28 10:01:36] DiffReaper-6 Training Started.
|
| 29 |
+
[2026-01-28 10:01:37] Step 0 | Loss: 0.147129 | LR: 0.00e+00 | Speed: 1.42 it/s
|
| 30 |
+
[2026-01-28 10:02:04] Initializing DiffReaper-6 (DifferenceLabs)...
|
| 31 |
+
[2026-01-28 10:02:13] Loading Dataset (Conversational Focus)...
|
| 32 |
+
[2026-01-28 10:02:15] DiffReaper-6 Training Started.
|
| 33 |
+
[2026-01-28 10:02:16] Step 0 | Loss: 0.248774 | LR: 0.00e+00 | Speed: 1.35 it/s
|
| 34 |
+
[2026-01-28 10:02:27] Step 50 | Loss: 0.059270 | LR: 1.20e-06 | Speed: 4.21 it/s
|
| 35 |
+
[2026-01-28 10:02:39] Step 100 | Loss: 0.146728 | LR: 2.50e-06 | Speed: 4.29 it/s
|
| 36 |
+
[2026-01-28 10:02:50] Step 150 | Loss: 0.202562 | LR: 3.70e-06 | Speed: 4.34 it/s
|
| 37 |
+
[2026-01-28 10:03:01] Step 200 | Loss: 0.214605 | LR: 5.00e-06 | Speed: 4.35 it/s
|
| 38 |
+
[2026-01-28 10:03:13] Step 250 | Loss: 0.169669 | LR: 6.20e-06 | Speed: 4.36 it/s
|
| 39 |
+
[2026-01-28 10:03:24] Step 300 | Loss: 0.114161 | LR: 7.50e-06 | Speed: 4.35 it/s
|
| 40 |
+
[2026-01-28 10:03:36] Step 350 | Loss: 0.146113 | LR: 8.70e-06 | Speed: 4.36 it/s
|
| 41 |
+
[2026-01-28 10:03:47] Step 400 | Loss: 0.118177 | LR: 1.00e-05 | Speed: 4.35 it/s
|
| 42 |
+
[2026-01-28 10:03:59] Step 450 | Loss: 0.174843 | LR: 1.12e-05 | Speed: 4.36 it/s
|
| 43 |
+
[2026-01-28 10:04:10] Step 500 | Loss: 0.103264 | LR: 1.25e-05 | Speed: 4.35 it/s
|
| 44 |
+
[2026-01-28 10:04:10] --- DiffReaper-6 Diagnostic [Step 500] ---
|
| 45 |
+
[2026-01-28 10:04:11] Prompt: 'Hello! Tell me a story about a robot.'
|
| 46 |
+
[2026-01-28 10:04:11] Response: ''
|
| 47 |
+
[2026-01-28 10:04:22] Step 550 | Loss: 0.162759 | LR: 1.37e-05 | Speed: 4.34 it/s
|
| 48 |
+
[2026-01-28 10:04:34] Step 600 | Loss: 0.244592 | LR: 1.50e-05 | Speed: 4.34 it/s
|
| 49 |
+
[2026-01-28 10:04:45] Step 650 | Loss: 0.152834 | LR: 1.62e-05 | Speed: 4.34 it/s
|
| 50 |
+
[2026-01-28 10:04:57] Step 700 | Loss: 0.124072 | LR: 1.75e-05 | Speed: 4.34 it/s
|
| 51 |
+
[2026-01-28 10:05:08] Step 750 | Loss: 0.153756 | LR: 1.87e-05 | Speed: 4.34 it/s
|
| 52 |
+
[2026-01-28 10:05:20] Step 800 | Loss: 0.062768 | LR: 2.00e-05 | Speed: 4.34 it/s
|
| 53 |
+
[2026-01-28 10:05:31] Step 850 | Loss: 0.123713 | LR: 2.12e-05 | Speed: 4.34 it/s
|
| 54 |
+
[2026-01-28 10:05:43] Step 900 | Loss: 0.134409 | LR: 2.25e-05 | Speed: 4.34 it/s
|
| 55 |
+
[2026-01-28 10:05:55] Step 950 | Loss: 0.117195 | LR: 2.37e-05 | Speed: 4.34 it/s
|
| 56 |
+
[2026-01-28 10:06:06] Step 1000 | Loss: 0.151960 | LR: 2.50e-05 | Speed: 4.34 it/s
|
| 57 |
+
[2026-01-28 10:06:06] --- DiffReaper-6 Diagnostic [Step 1000] ---
|
| 58 |
+
[2026-01-28 10:06:06] Prompt: 'Hello! Tell me a story about a robot.'
|
| 59 |
+
[2026-01-28 10:06:06] Response: '.,,,.,. the,'
|
| 60 |
+
[2026-01-28 10:06:18] Step 1050 | Loss: 0.095175 | LR: 2.62e-05 | Speed: 4.33 it/s
|
| 61 |
+
[2026-01-28 10:06:29] Step 1100 | Loss: 0.191805 | LR: 2.75e-05 | Speed: 4.33 it/s
|
| 62 |
+
[2026-01-28 10:06:41] Step 1150 | Loss: 0.075036 | LR: 2.87e-05 | Speed: 4.33 it/s
|
| 63 |
+
[2026-01-28 10:06:52] Step 1200 | Loss: 0.136675 | LR: 3.00e-05 | Speed: 4.33 it/s
|
| 64 |
+
[2026-01-28 10:07:04] Step 1250 | Loss: 0.109159 | LR: 3.12e-05 | Speed: 4.33 it/s
|
| 65 |
+
[2026-01-28 10:07:15] Step 1300 | Loss: 0.133371 | LR: 3.25e-05 | Speed: 4.33 it/s
|
| 66 |
+
[2026-01-28 10:07:27] Step 1350 | Loss: 0.110480 | LR: 3.37e-05 | Speed: 4.33 it/s
|
| 67 |
+
[2026-01-28 10:07:39] Step 1400 | Loss: 0.170866 | LR: 3.50e-05 | Speed: 4.33 it/s
|
| 68 |
+
[2026-01-28 10:07:50] Step 1450 | Loss: 0.103821 | LR: 3.62e-05 | Speed: 4.33 it/s
|
| 69 |
+
[2026-01-28 10:08:02] Step 1500 | Loss: 0.108363 | LR: 3.75e-05 | Speed: 4.33 it/s
|
| 70 |
+
[2026-01-28 10:08:02] --- DiffReaper-6 Diagnostic [Step 1500] ---
|
| 71 |
+
[2026-01-28 10:08:02] Prompt: 'Hello! Tell me a story about a robot.'
|
| 72 |
+
[2026-01-28 10:08:02] Response: ', the the,..,, to the.. to,..., the the'
|
| 73 |
+
[2026-01-28 10:08:13] Step 1550 | Loss: 0.093708 | LR: 3.87e-05 | Speed: 4.33 it/s
|
| 74 |
+
[2026-01-28 10:08:25] Step 1600 | Loss: 0.068044 | LR: 4.00e-05 | Speed: 4.33 it/s
|
| 75 |
+
[2026-01-28 10:08:37] Step 1650 | Loss: 0.173991 | LR: 4.12e-05 | Speed: 4.33 it/s
|
| 76 |
+
[2026-01-28 10:08:48] Step 1700 | Loss: 0.143518 | LR: 4.25e-05 | Speed: 4.33 it/s
|
| 77 |
+
[2026-01-28 10:09:00] Step 1750 | Loss: 0.186624 | LR: 4.37e-05 | Speed: 4.33 it/s
|
| 78 |
+
[2026-01-28 10:09:11] Step 1800 | Loss: 0.161601 | LR: 4.50e-05 | Speed: 4.33 it/s
|
| 79 |
+
[2026-01-28 10:09:23] Step 1850 | Loss: 0.121069 | LR: 4.62e-05 | Speed: 4.33 it/s
|
| 80 |
+
[2026-01-28 10:09:34] Step 1900 | Loss: 0.057303 | LR: 4.75e-05 | Speed: 4.33 it/s
|
| 81 |
+
[2026-01-28 10:09:46] Step 1950 | Loss: 0.098007 | LR: 4.87e-05 | Speed: 4.33 it/s
|
| 82 |
+
[2026-01-28 10:09:57] Step 2000 | Loss: 0.089101 | LR: 5.00e-05 | Speed: 4.33 it/s
|
| 83 |
+
[2026-01-28 10:09:57] --- DiffReaper-6 Diagnostic [Step 2000] ---
|
| 84 |
+
[2026-01-28 10:09:58] Prompt: 'Hello! Tell me a story about a robot.'
|
| 85 |
+
[2026-01-28 10:09:58] Response: '.. the the the the, the.... the, the the the.. the.. the......, the the... the.. the the. and.,... and the the. the and the. the the. the... the the the and.. the the the.. the,. the and, and. and. the. the'
|
| 86 |
+
[2026-01-28 10:10:03] Uploading diffreaper6_step_2000.pt to HF...
|