Training in progress, step 1

config.json

@@ -25,7 +25,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b898b4a4d9a25625596064fd8be15e69680bc52d9a0d0f0d0641a5daace885b2
+oid sha256:81f59c1751e936e5c3d61de9397e4e776c177c1ec2e0c93152a14e94c04cef23
 size 2023586384

tokenizer_config.json

@@ -216,7 +216,6 @@
   "chat_template": "{% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '\n\n'}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "padding_side": "left",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80dacc473c31529fef7a00eb3193a1afbf2d53563adf0a2b990de56ab1c6281
-size 7160
+oid sha256:339c7a9548a2e06f53d3b217602679eecbb0b4abc9bb3f7d91c8a44d5a931e47
+size 7096