Training in progress, step 126

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "GPTNeoXForCausalLM",
     "parent_library": "transformers.models.gpt_neox.modeling_gpt_neox"
   },
-  "base_model_name_or_path": "databricks/dolly-v2-3b",
+  "base_model_name_or_path": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4c316dc9cdd75c32ff0a3ec1d00e9492b07fd42d4acaddf6b977665fddf607
-size 10494984
+oid sha256:c1ec86f9fbcb545a428256ceb8b677a48e2a0c2f4d3b25931c209df3f99b88de
+size 23603456

special_tokens_map.json

@@ -1,8 +1,10 @@
 {
   "additional_special_tokens": [
-    "### End",
-    "### Instruction:",
-    "### Response:"
+    "<|system|>",
+    "<|assistant|>",
+    "<|prefix_begin|>",
+    "<|prefix_end|>",
+    "<|prompter|>"
   ],
   "bos_token": {
     "content": "<|endoftext|>",
@@ -19,6 +21,13 @@
     "single_word": false
   },
   "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<|padding|>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -230,7 +244,7 @@
     },
     {
       "id": 50277,
-      "content": "### End",
+      "content": "<|prefix_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -239,7 +253,7 @@
     },
     {
       "id": 50278,
-      "content": "### Instruction:",
+      "content": "<|prefix_begin|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -248,7 +262,25 @@
     },
     {
       "id": 50279,
-      "content": "### Response:",
+      "content": "<|prompter|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50280,
+      "content": "<|system|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50281,
+      "content": "<|assistant|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -204,7 +204,7 @@
       "special": false
     },
     "50277": {
-      "content": "### End",
+      "content": "<|prefix_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -212,7 +212,7 @@
       "special": true
     },
     "50278": {
-      "content": "### Instruction:",
+      "content": "<|prefix_begin|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -220,7 +220,23 @@
       "special": true
     },
     "50279": {
-      "content": "### Response:",
+      "content": "<|prompter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -229,16 +245,19 @@
     }
   },
   "additional_special_tokens": [
-    "### End",
-    "### Instruction:",
-    "### Response:"
+    "<|system|>",
+    "<|assistant|>",
+    "<|prefix_begin|>",
+    "<|prefix_end|>",
+    "<|prompter|>"
   ],
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|padding|>",
+  "sep_token": "<|endoftext|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab309e2baded7ed3fde47e810fc7a42c14faec1dcf2f80ca8fc30fd855adfab9
+oid sha256:231481c050bd17627c2d07ca8e01a64183cead3d867fb3b758abc0dd0fcccd61
 size 5496