Training in progress, step 6

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855d3ef8e703db5cbd18b22f1654123853cbc6a09f21ce4a327eadbe313de010
+oid sha256:9c0a943fca0e94e7e8006736d302cdaca949111c938556cbcc4729707a0ffeaf
 size 159967880

config.json

@@ -14,7 +14,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_length": 4096,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
@@ -27,7 +27,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.48.1",
+  "transformers_version": "4.46.3",
   "use_cache": false,
   "vocab_size": 46336
 }

tokenizer_config.json

@@ -71,7 +71,6 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f0529a4ec5700e384743cbdf1b663399ea3e9152f91ce196042e0be4e12915
-size 6520
+oid sha256:a8f72a47124e638e8e41619a2dae021e86edc0680b71921e6223382dd20d1c72
+size 6392