Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "upstage/SOLAR-10.7B-v1.0",
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -15,18 +15,18 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
-    "gate_proj",
-    "o_proj",
-    "down_proj",
+    "w1",
     "q_proj",
-    "up_proj",
+    "lm_head",
+    "w3",
     "k_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "w2"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2f784cbc7691b0fb9e5ae17a7ec7a6b9fecf18ab9a61bd06b143271c2c85a0
-size 651362912
+oid sha256:25c0807b203372b0a5c0aa1c7be1120f88cc267072074c3502f39ea9e06a21db
+size 1487361648

runs/Dec17_16-59-04_24d5ee9be080/events.out.tfevents.1702832357.24d5ee9be080.2742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2538b8d5f0596194a4217f277dad93052cfc5af33963ebe23147d3a764ee249c
+size 10654

tokenizer_config.json

@@ -39,5 +39,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8657b92de7d7f0ae3b1180b20678dde29e00e4ebc7319f99700962b9f595b6
+oid sha256:0b761f5a7283e86f9070a77780157867eaea2e844967e3f1eecb5ae0a7566ba9
 size 4728