Training in progress, step 3

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: llama31_8b_instruct_finetuned
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "gate_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
     "v_proj",
-    "down_proj"
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37bd6878b1bb91c4d33f45a1d3e4becffffb1c3a2635a72ab2f632e76a4b8f3e
+oid sha256:ab4d83217635058215ef2ced86427982ac41ebdb07ed2ae73cd1106dbb3eea86
 size 167832240

runs/Jul18_16-42-54_5c9559bf46d5/events.out.tfevents.1752856976.5c9559bf46d5.19520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38bcd9adb97d35426c6922417641e04e6d18d1038f7fa5670432d20e46b21ba
+size 6697

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|eot_id|>"
+  }
 }

tokenizer_config.json

@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683c6afd08d1a59496e47b0101f9b8c6c65002fa4928d9661f23707742051993
+oid sha256:7bf3d4de656f7c69f2d09326238e97d60cd46668080948f8f48829b9c70aa83e
 size 5752