Training in progress, step 500

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076abe20133970df17b89c2d6f335d8bfef13c8cd5ce977be2a286078f6159ab
+oid sha256:4ef4a673cd91de5af8f89bf3a1e79af9e4dc91e17b5edad72e9a6ff2b7dbeb09
 size 1188025

added_tokens.json

@@ -1,13 +1,12 @@
 {
   "<ASSISTANT_TASK:>": 32771,
   "<END_TASK>": 32772,
-  "<PAD>": 32773,
   "<SYSTEM_TASK:>": 32769,
   "<USER_TASK:>": 32770,
   "<|PAD|>": 32768,
-  "additional_special_tokens": 32778,
-  "bos_token": 32774,
-  "eos_token": 32775,
-  "pad_token": 32777,
-  "unk_token": 32776
+  "additional_special_tokens": 32777,
+  "bos_token": 32773,
+  "eos_token": 32774,
+  "pad_token": 32776,
+  "unk_token": 32775
 }

tokenizer.json

@@ -59,15 +59,6 @@
     },
     {
       "id": 32773,
-      "content": "<PAD>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32774,
       "content": "bos_token",
       "single_word": false,
       "lstrip": false,
@@ -76,7 +67,7 @@
       "special": false
     },
     {
-      "id": 32775,
+      "id": 32774,
       "content": "eos_token",
       "single_word": false,
       "lstrip": false,
@@ -85,7 +76,7 @@
       "special": false
     },
     {
-      "id": 32776,
+      "id": 32775,
       "content": "unk_token",
       "single_word": false,
       "lstrip": false,
@@ -94,7 +85,7 @@
       "special": false
     },
     {
-      "id": 32777,
+      "id": 32776,
       "content": "pad_token",
       "single_word": false,
       "lstrip": false,
@@ -103,7 +94,7 @@
       "special": false
     },
     {
-      "id": 32778,
+      "id": 32777,
       "content": "additional_special_tokens",
       "single_word": false,
       "lstrip": false,

tokenizer_config.json

@@ -9,8 +9,8 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 3000,
-  "pad_token": "<PAD>",
+  "model_max_length": 5000,
+  "pad_token": "<|PAD|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }