Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/phi-1_5",
+  "base_model_name_or_path": "phi1_5_updated",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0c1b952069807908a2407f4fa1d9a56e8e13c92c13fb9feaf1cade1085bd5a
+oid sha256:9f2b618f8810a13cdd7f95421aaf0892390d0750b78acec85324013c7956603e
 size 18893616

special_tokens_map.json

@@ -1,21 +1,48 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,8 +1,39 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,13 +41,14 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "is_split_into_words": true,
-  "model_max_length": 512,
-  "pad_token": "<|endoftext|>",
-  "return_token_type_ids": false,
-  "tokenizer_class": "CodeGenTokenizer",
-  "unk_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6db5524e8c4bf8d0f27027ee6bf07bff4e2df2b2f485535e55fb49cd4b152cf
-size 5112
+oid sha256:5bc157820ea8e71249c6e81853e9ad3af4c38a702b5d1cebb110b6df5e4e1fd8
+size 5176