Training in progress, epoch 1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "up_proj",
+    "o_proj",
     "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
     "down_proj",
-    "o_proj",
-    "k_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab56799a8e4f4184f545a18a9d929ca9d284b1cf31eee370fe8e8c9295452e61
+oid sha256:32912e9c3b14c4fc18ccacf07685b08f6cf9ab08db6c76a0f8fd647da4ce3435
 size 319876032

config.json

@@ -19,12 +19,27 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "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": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0",
-  "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

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,59 +26,18 @@
       "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",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ababd2183db88b03b47b303e09f5c4cd2470040848d593341c6948d45dd9ab8d
+oid sha256:d3845973994f2cd9dae1ddfb30ae6677578a6f72de7723d87db38bcde4d10bc2
 size 6136