Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.8682
+- Loss: 6.9015
 
 ## Model description
 
@@ -46,8 +46,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 7.2874        | 0.5214 | 500  | 7.1310          |
-| 6.8115        | 1.0428 | 1000 | 6.8682          |
+| 7.2863        | 0.5214 | 500  | 7.1323          |
+| 6.8168        | 1.0428 | 1000 | 6.9015          |
 
 
 ### Framework versions

config.json

@@ -4,9 +4,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 3,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "eos_token_id": 2,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -16,6 +16,7 @@
   "n_inner": null,
   "n_layer": 4,
   "n_positions": 64,
+  "pad_token_id": 1,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -27,6 +28,7 @@
   "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
+  "unk_token_id": 0,
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 3,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9680709df71ae71c1ab82ae988403f239eb1b8e990e1606aa496d1a32b1a4d0
+oid sha256:0ae279fe143d3a72aad4391e032d8872966f5729862b3d5a4daa690e25541963
 size 273357888

special_tokens_map.json

@@ -1,3 +1,6 @@
 {
-  "pad_token": "[PAD]"
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -23,10 +23,21 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "3": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "[BOS]",
   "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123930e80256c46af25f67796c70eec2e28270c84a966d973bbd9708a0eee480
+oid sha256:a92b46728c53ce5b964c094407071a099d8f41d18b50e1060a0ea7bdf536a98f
 size 5048