Training in progress, step 68

adapter_config.json

@@ -3,8 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
   "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -12,14 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef44b7b13f7853872a550c99e59cb7db1ba108f5b7ad40f7b2024d4a5f75040c
-size 159967880
+oid sha256:a3e1e5cbe344caee19db7f1f4e0b9ed8a7ae5c18bc8cddc5ce91288aa46dce17
+size 639691872

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.48.1",
+  "transformers_version": "4.46.3",
   "use_cache": false,
   "vocab_size": 32016
 }

tokenizer_config.json

@@ -31,7 +31,6 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7258e1bb5efa6c312e6320b084b12740f12b87baf41187e8811856ff68d262
-size 6456
+oid sha256:a22ea4ea49e9bc4f4920cd748e18daf7a28e66ad1aff4cdd98921fb2f55391d0
+size 6328