End of training

README.md

@@ -36,10 +36,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.14.0
-- Transformers: 4.48.2
+- TRL: 0.15.0
+- Transformers: 4.48.3
 - Pytorch: 2.5.1+cu124
-- Datasets: 3.2.0
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 
 ## Citations

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16753c62a19882bb837450badac5d5616e4c70712c6846695d858845ce6fb81c
+size 7380952

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa417b38194267b39d7fbd8ea35dade1c1ef29cad6c9d5ab7ceaae6e897f01ce
-size 5560
+oid sha256:c4ec3e5c5ec9e65429c5a221310c12603fb1171e46379c794490d863469a2d22
+size 5624