End of training

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/agreu77/huggingface/runs/d0or5tlg)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/agreu77/huggingface/runs/64jcqo2e)
 
 This model was trained with SFT.
 

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c2fcc90b63ee8c8888109c26331c21f4c1a749b096e00a46ce982a74ba5a19
-size 4994182536
+oid sha256:abf278f991ceaf39bc671ca4c872694cf06b9cd59e67539ecad72247571bf27e
+size 4957859248

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b14f6ea6e74e1d4fcf69875093d96d88b500bbcee1ea10770a217f5ad10fc9b
-size 240938000
+oid sha256:4f042708de529cc90e56bad5c6039ac86eb2e081943367a52626d15cad4474b2
+size 283651216

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5235073536
+    "total_size": 5241463296
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -261,7 +261,7 @@
     "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",

runs/Dec05_17-30-22_4184e4e168f8/events.out.tfevents.1733419842.4184e4e168f8.189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd8a8dccb476a2dae15176bf5597eb9c4fb55e1b0673a31bcd69bf182e0fe3a
+size 5614

runs/Dec05_17-32-00_4184e4e168f8/events.out.tfevents.1733419939.4184e4e168f8.189.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf1a186a3fb8092c1184802bc433d10e1e344d2e3a696dab7680696a7ee527f
+size 7236

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8867d9ccf97412fda9e0d20d707c96c160f4d3b3cd034ee2bba92eb01cf84930
+oid sha256:c0abe8d78075218fb2f0e35fe2ca31576d3241bac60637fd1c3274c4ee9dd486
 size 5560