Training in progress, epoch 1

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: facebook/opt-350m
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: transformers
 model_name: tiny-chatbot-model-dpo
 tags:
 - generated_from_trainer
-- dpo
 - trl
+- dpo
 licence: license
 ---
 
 # Model Card for tiny-chatbot-model-dpo
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m).
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -35,8 +35,8 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.1
-- Pytorch: 2.6.0+cu124
+- Transformers: 4.55.2
+- Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
 - Tokenizers: 0.21.4
 

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",
   "corda_config": null,
   "eva_config": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9187514ef9e43e27875c3731c26807f988463dd8c9f8b5910e91d346ece7ee90
-size 3159096
+oid sha256:0710dbbdb085ae0209bd3f83e2345eaee093665dbe11a297b21432f969dde850
+size 4517152

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

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>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "</s>"
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "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 sha256:04f648754ec3caf63a70a74ee59c5e441363b9fe880a4c77d48189d144dc1d9c
-size 6392
+oid sha256:d16d997a3daec92cfcc123c87163a83edfec0be4b8a2e957d8625ddf3ccb2ce2
+size 6737