End of training

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: SOC_Query_Generation_Base_Llama_3B
 tags:
 - generated_from_trainer
-- unsloth
 - trl
+- unsloth
 - sft
 licence: license
 ---
@@ -35,11 +35,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
-- Transformers: 4.55.4
+- TRL: 0.23.0
+- Transformers: 4.56.2
 - Pytorch: 2.7.0
 - Datasets: 3.6.0
-- Tokenizers: 0.21.4
+- Tokenizers: 0.22.1
 
 ## Citations
 

adapter_config.json

@@ -1,6 +1,10 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
   "base_model_name_or_path": "acezxn/ACI_Cyber_Base_Llama_3B",
   "bias": "none",
   "corda_config": null,
@@ -25,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
-    "up_proj",
     "k_proj",
-    "down_proj",
     "v_proj",
-    "gate_proj",
-    "q_proj"
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81509db19f90e91387968101680116fe2655a94547fbdde998b0fec198e6e938
+oid sha256:d95a1c5d6803cff0378d7bf10da1ccf3b5e403f855d9432cf547fcec69c06970
 size 194563400

runs/Oct11_17-52-43_19c6da89d26e/events.out.tfevents.1760205179.19c6da89d26e.62545.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0cf9d5d8768b2e8b04fa0a224f646e61d7fa4495ca800117febbe8c067c9dd
+size 6219

runs/Oct11_17-57-18_19c6da89d26e/events.out.tfevents.1760205441.19c6da89d26e.63683.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533699c83ff2794a26f9d07b48a71ef210cbf704929558dd979fd7234e62eb40
+size 16919

tokenizer_config.json

@@ -2060,7 +2060,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34edf1c5ae1dc1bfbfc0104bbc48fac3dd36edc53b6c73f2aad7cca65d50cc44
-size 6289
+oid sha256:69fc783d902c0b19eabcfe518500da7711ea508bf2cbbddaf31e92652c67373d
+size 6353