Training in progress, epoch 0

adapter_config.json

@@ -1,6 +1,7 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/CodeLlama-7B-fp16",
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -12,15 +13,16 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 32,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "gate_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
+    "down_proj",
     "o_proj",
-    "k_proj",
-    "q_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927fc06b079b0a6bcb5144c46feed8cde74c722dadb2fe4088de81a71b56680b
+oid sha256:396bf764dd7fd3b635ee45c5823a963089cb6103f4eb859d6be2e99630c24a39
 size 319876032

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -1,21 +1,16 @@
 {
-  "_name_or_path": "TheBloke/CodeLlama-7B-fp16",
+  "_name_or_path": "TheBloke/Llama-2-7B-fp16",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "TheBloke/CodeLlama-7B-fp16--configuration_llama.LlamaConfig",
-    "AutoModel": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaModel",
-    "AutoModelForCausalLM": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForCausalLM",
-    "AutoModelForSequenceClassification": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForSequenceClassification"
-  },
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 16384,
+  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -36,10 +31,10 @@
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.35.0.dev0",
   "use_cache": false,
-  "vocab_size": 32016
+  "vocab_size": 32000
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
-size 500058
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,38 +1,45 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
   },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": null,
+  "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": "/root/.cache/model/huggingface/hub/models--TheBloke--Llama-2-7B-fp16/snapshots/ba2306439903c2ebf7d09970a973ef44d1402239/tokenizer.json",
   "trust_remote_code": false,
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "unk_token": "<unk>",
   "use_default_system_prompt": true,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb9172d83e1ba2d4f5d1ae3aa40d91e1184e52d3fa21a82f2c62cf9bfe214bf
+oid sha256:710008004c3917182b08218d0ee0cd47987620af8087b3e4bddefe7ba183f72c
 size 4475