Training in progress, epoch 1

KETI_b1_s4_e2_training_log.log

@@ -25,3 +25,20 @@
 03/31/2025 07:32:34 - INFO  - [Epoch 0.99] [Step 90] loss: 2.8435
 03/31/2025 07:34:08 - INFO  - [Epoch 1.09] [Step 100] loss: 2.7393
 03/31/2025 07:34:31 - INFO  - [Epoch 1.20] [Step 110] loss: 2.7271
+03/31/2025 07:34:54 - INFO  - [Epoch 1.31] [Step 120] loss: 2.7266
+03/31/2025 07:35:17 - INFO  - [Epoch 1.42] [Step 130] loss: 2.7222
+03/31/2025 07:35:40 - INFO  - [Epoch 1.53] [Step 140] loss: 2.7247
+03/31/2025 07:36:03 - INFO  - [Epoch 1.64] [Step 150] loss: 2.7279
+03/31/2025 07:36:26 - INFO  - [Epoch 1.75] [Step 160] loss: 2.7273
+03/31/2025 07:36:49 - INFO  - [Epoch 1.85] [Step 170] loss: 2.7270
+03/31/2025 07:37:12 - INFO  - [Epoch 1.96] [Step 180] loss: 2.7116
+03/31/2025 07:38:27 - INFO  - ✅ Training complete. Logging system usage...
+03/31/2025 07:38:27 - INFO  - >> System Usage - CPU: 5.8%, RAM: 2.7%, SSD: 75.50GB / 1888.43GB
+03/31/2025 07:38:27 - INFO  - >> GPU 0: 76.86 GB used
+03/31/2025 07:38:27 - INFO  - >> GPU 1: 73.42 GB used
+03/31/2025 07:38:27 - INFO  - >> GPU 2: 76.32 GB used
+03/31/2025 07:38:27 - INFO  - >> GPU 3: 75.68 GB used
+03/31/2025 07:38:27 - INFO  - >> GPU 4: 76.52 GB used
+03/31/2025 07:38:27 - INFO  - >> GPU 5: 74.11 GB used
+03/31/2025 07:38:27 - INFO  - >> Total GPU Memory Used: 452.92 GB
+03/31/2025 07:38:28 - INFO  - >> Total GPU Power Consumption: 531.23 W

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e09562240a8b0ad1a634d61a28c7c6ffe1b231368c14bbcb650cbb6e618942
+oid sha256:003fb87b41c0a085e09b7d0323c92becb74ce67273854b7b5fa0950b45c005f8
 size 454183400

runs/Mar31_07-28-56_llm-server-779876f58-9zzqd/events.out.tfevents.1743406143.llm-server-779876f58-9zzqd.4193438.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fc0c4d9c7379255e1653abb6cc22a139e4cdc6ca4b2a5e6160d755556464dd
-size 8779
+oid sha256:d1ee38a489eac312c68d98e7bd6f8164edad874de46d3b07600b23af11fc8e95
+size 12204