Training in progress, step 50

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-Instruct-v0.1-sharded",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80fa730fca5dc3c0f7146124c89c1304d0019d8042d59450f15c7e8bbf7669d
+oid sha256:9d8fe614289c2412531512505e9404e1f7106803e1f25f49ca7e30bea94f296c
 size 42002584

runs/Jun06_06-36-30_3b37d1e25df6/events.out.tfevents.1717656072.3b37d1e25df6.388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c6d592d452db584305e1fa8cb4525e5412aa4355094a8bb550a40f847c1a18
+size 16987

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700e2ffca061353ef9e5698b2619b2dcba0c46609c85e640fbe8ae9cd993bfaa
+oid sha256:b0990a8975d3cbb48347c0356c8a82077a643c97b32fdc1a40adcf389b954848
 size 6904

training_config.json

@@ -40,7 +40,7 @@
   "tokenizer_padding_side": null,
   "collator_key": "lm",
   "max_length": 2048,
-  "model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
+  "model_name_or_path": "filipealmeida/Mistral-7B-Instruct-v0.1-sharded",
   "push_to_hub_bos_add_bos_token": false,
   "use_flash_attention_2": false,
   "trust_remote_code": false,