5/50k-ish so far 20h in.

my checkpoints comeout every 4h and 2m .

checkpoint-5120/adapter_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name_or_path": "models/llama-30b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 128,
+  "lora_dropout": 0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-5120/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2e7653c25e0bfaf84dd07aae7d5a1ce6475f110b2b64da3163aefd5a28e38b
+size 409031373