Training completed

README.md

@@ -4,6 +4,8 @@ license: mit
 base_model: EleutherAI/gpt-neo-125M
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: temp_gpt_neo
   results: []
@@ -16,7 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3250
+- Loss: 3.3814
+- Bleu: 0.0
 
 ## Model description
 
@@ -47,13 +50,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.9091 | 5    | 5.9921          |
-| No log        | 2.0    | 11   | 3.0731          |
-| No log        | 2.9091 | 16   | 1.7838          |
-| No log        | 4.0    | 22   | 1.3521          |
-| No log        | 4.5455 | 25   | 1.3250          |
+| Training Loss | Epoch  | Step | Validation Loss | Bleu |
+|:-------------:|:------:|:----:|:---------------:|:----:|
+| No log        | 0.9091 | 5    | 7.9635          | 0.0  |
+| No log        | 2.0    | 11   | 5.3680          | 0.0  |
+| No log        | 2.9091 | 16   | 4.0323          | 0.0  |
+| No log        | 4.0    | 22   | 3.4255          | 0.0  |
+| No log        | 4.5455 | 25   | 3.3814          | 0.0  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022efb5e7b8828635658edac523279a6e193937e4ef5a67d2b2e0f49825a096f
+oid sha256:1a3eb7c7e81bfc9c8ca65d4a1b619654112375af48297f5468b002842edc3ca3
 size 500811336

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,