Model save

README.md

@@ -1,28 +1,13 @@
 ---
-base_model: google/mt5-small
-datasets:
-- arrow
 license: apache-2.0
-metrics:
-- bleu
+base_model: google/mt5-base
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: mt5-base-ainu
-  results:
-  - task:
-      type: text2text-generation
-      name: Sequence-to-sequence Language Modeling
-    dataset:
-      name: arrow
-      type: arrow
-      config: default
-      split: None
-      args: default
-    metrics:
-    - type: bleu
-      value: 35.096583697771194
-      name: Bleu
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mt5-base-ainu
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the arrow dataset.
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3701
-- Bleu: 35.0966
+- Loss: 3.5796
+- Bleu: 0.1912
 
 ## Model description
 
@@ -65,28 +50,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step   | Validation Loss | Bleu    |
-|:-------------:|:-------:|:------:|:---------------:|:-------:|
-| 2.73          | 0.9999  | 9341   | 2.2938          | 11.6604 |
-| 2.0536        | 2.0     | 18683  | 1.7883          | 19.8648 |
-| 1.7955        | 2.9999  | 28024  | 1.6060          | 24.9245 |
-| 1.6331        | 4.0     | 37366  | 1.5038          | 27.6152 |
-| 1.5107        | 4.9999  | 46707  | 1.4442          | 28.4249 |
-| 1.4255        | 6.0     | 56049  | 1.4058          | 30.0986 |
-| 1.3373        | 6.9999  | 65390  | 1.3769          | 30.9550 |
-| 1.2758        | 8.0     | 74732  | 1.3546          | 31.6075 |
-| 1.2259        | 8.9999  | 84073  | 1.3380          | 32.0155 |
-| 1.1555        | 10.0    | 93415  | 1.3318          | 32.5095 |
-| 1.1166        | 10.9999 | 102756 | 1.3263          | 32.9619 |
-| 1.0564        | 12.0    | 112098 | 1.3220          | 33.5983 |
-| 1.0222        | 12.9999 | 121439 | 1.3162          | 33.7293 |
-| 0.9764        | 14.0    | 130781 | 1.3304          | 34.0143 |
-| 0.9472        | 14.9999 | 140122 | 1.3353          | 34.3792 |
-| 0.9034        | 16.0    | 149464 | 1.3429          | 34.4296 |
-| 0.8732        | 16.9999 | 158805 | 1.3470          | 34.5817 |
-| 0.8465        | 18.0    | 168147 | 1.3554          | 34.9795 |
-| 0.8171        | 18.9999 | 177488 | 1.3618          | 34.9659 |
-| 0.7912        | 19.9989 | 186820 | 1.3701          | 35.0966 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 25   | 7.8298          | 0.0139 |
+| No log        | 2.0   | 50   | 4.7659          | 0.3532 |
+| No log        | 3.0   | 75   | 3.9025          | 0.2150 |
+| No log        | 4.0   | 100  | 3.7058          | 0.2334 |
+| No log        | 5.0   | 125  | 3.5796          | 0.1912 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2aaca3d6c7e880e5babba51d8e1093a502645168a43bcb2fae5e048a3bd380
+oid sha256:66b038fcfeed81a2ca3d241c532cf898a062642d8afcb769a70552f8b523c8e3
 size 2329638768