End of training

README.md

@@ -29,7 +29,7 @@ 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/connectwitharya23-arya/huggingface/runs/co9svush) 
 
 
 This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.14.0
-- Transformers: 4.47.1
+- Transformers: 4.48.2
 - Pytorch: 2.5.1+cu124
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.2",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.48.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ac0ca77b56e848e2a45f7263e18c8652ae3572a9d13da190e5a58057df68fb
+oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
 size 538090408

runs/Feb07_21-11-57_520b5f5c16bd/events.out.tfevents.1738962787.520b5f5c16bd.647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09420b634806a4aa981745b74dee7c0cdbf6bd34f2bc00778faea0720809b8e2
+size 32387

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:f2af485a31a9220d6f96b57b488a38caf4b3ba1937111d8db8d07e500eef5bc2
+oid sha256:38b5c300f31efa49a322b53d1b1f72c979d2b787c38d9708d8c63437493568f6
 size 5624