Training in progress, epoch 0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5640f420333763f9b915a88dc3bbabcdb27f625ac0e6cfa1f9d7d88a0524fb6
+size 319876032

config.json

@@ -17,12 +17,24 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32016
 }

special_tokens_map.json

@@ -1,10 +1,4 @@
 {
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -19,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -25,59 +25,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32007": {
-      "content": "▁<PRE>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "▁<SUF>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "▁<MID>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "▁<EOT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "prefix_token": "▁<PRE>",
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "CodeLlamaTokenizer",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef7e944707a960f35d3883ae6a57b0933d26a8b89fd1e62dedc69edfc6c87e5
+size 4859