Training in progress, step 3

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/opt-350m",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa52da129390528037efac18b63e73d6ddebb933c96c5a3c35fbe42a92ed34c
-size 25179464
+oid sha256:e874cc18354c498482cfdae9db39ee6943081c19dfcf6849f42a1223364b20aa
+size 4517152

special_tokens_map.json

@@ -1,29 +1,29 @@
 {
   "bos_token": {
-    "content": "</s>",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "</s>",
+    "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,11 +1,20 @@
 {
   "add_bos_token": true,
-  "add_prefix_space": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,19 +22,22 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "</s>",
+  "bos_token": "<s>",
   "chat_template": "{% for message in messages %}<|im_start|>{{ message.role }}\n{% if message.role == 'system' %}{{ message.content }}{% if tools and tools | length > 0 %}\n\nYou have access to the following functions:\n{% for tool in tools %}\nfunctions.{{ tool.function.name }}:\n{{ tool.function.parameters | tojson }}\n{% endfor %}\n\nYou can respond to users messages with either a single message or one or more function calls.\n\nTo respond with a message begin the message with 'message:', use the following format:\n\nmessage:\n<message>\n\nTo respond with one or more function calls begin the message with 'functions.<function_name>:', use the following format:\n\nfunctions.<function_name>:\n{ \"arg1\": \"value1\", \"arg2\": \"value2\" }\nfunctions.<function_name>:\n{ \"arg1\": \"value1\", \"arg2\": \"value2\" }{% endif %}<|im_end|>\n{% endif %}{% if message.role == 'user' %}{{ message.content }}<|im_end|>\n{% endif %}{% if message.role == 'assistant' %}{% if message.content and message.content | length > 0 %}{% if tools %}message:\n{% endif %}{{ message.content }}<|im_end|>\n{% endif %}{% if message.tool_calls and message.tool_calls | length > 0 %}{% for tool_call in message.tool_calls %}functions.{{ tool_call.function.name }}:\n{{ tool_call.function.arguments }}{% endfor %}<|im_end|>\n{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "</s>"
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034b64aca1bab281748444050397d633aad6ce30aa72d390559deb71def8cdf2
+oid sha256:98da2b50eb5ac443d4ba16f23f78b5f0ef4181c2778e9f672a1de258af3eb97c
 size 5496