Model save

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7411
-- Accuracy: 0.5943
+- Loss: 0.6514
+- Accuracy: 0.625
 
 ## Model description
 
@@ -45,15 +45,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2.0
+- num_epochs: 1.0
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.524         | 0.6410 | 100  | 0.6454          | 0.6373   |
-| 0.3259        | 1.2821 | 200  | 0.6920          | 0.6066   |
-| 0.237         | 1.9231 | 300  | 0.7411          | 0.5943   |
+| 0.6033        | 0.6410 | 100  | 0.6514          | 0.625    |
 
 
 ### Framework versions

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -29,15 +29,13 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{message['content']}}{% endfor %}{{eos_token}}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false