Training in progress, epoch 0

adapter_config.json

@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "k_proj",
-    "up_proj",
-    "gate_proj",
-    "q_proj",
     "o_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:029eaa93c3c580f30ab5a6f20bf21d064e4c016f1a846ccfa346b65efcedebda
+oid sha256:c29852f5cb6a3143c6c97f560414775e63bfa7e535f05dcfdf9bf07c5ec6033d
 size 500897101

added_tokens.json

@@ -1,3 +1,6 @@
 {
-  "<pad>": 32000
+  "</s>": 2,
+  "<pad>": 32000,
+  "<s>": 1,
+  "<unk>": 0
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/N/u/oleykin/BigRed200/SLATE/AdvertLlama-13b-chat",
+  "_name_or_path": "NousResearch/Llama-2-13b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,12 +16,24 @@
   "num_key_value_heads": 40,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.34.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32001
 }

tokenizer_config.json

@@ -1,26 +1,28 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -43,6 +45,9 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": null,
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": true,
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963ee409d83ee5b7ce2c79e123e263fa8d53fea7ffdaec236f76a5dc35ac44fb
+oid sha256:8fa31bea8c729aa47dee7c9c205a5c8d836a64cee9b393986dd02619c1669b66
 size 4475