Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "codellama/CodeLlama-7b-Python-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -10,7 +10,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 16384,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -18,7 +18,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.35.2",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97ebe0869e4da086c8a8392e013692d82f47121ba2a6082d25098fc507095d2
+oid sha256:f971e89130ab14677b161c3621b75ab3dc723437e62e0d2ef80d386b818877ad
 size 4664