finetuned_RuReCl8

README.md

@@ -1,7 +1,9 @@
 ---
-base_model: mika5883/pretrain_rugec
+base_model: mika5883/RuReCl8
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: RuReCl8
   results: []
@@ -12,7 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # RuReCl8
 
-This model is a fine-tuned version of [mika5883/pretrain_rugec](https://huggingface.co/mika5883/pretrain_rugec) on the None dataset.
+This model is a fine-tuned version of [mika5883/RuReCl8](https://huggingface.co/mika5883/RuReCl8) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1825
+- Bleu: 61.2481
+- Gen Len: 16.234
 
 ## Model description
 
@@ -31,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 3.83229e-05
 - train_batch_size: 128
 - eval_batch_size: 16
 - seed: 42
@@ -42,6 +48,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 20   | 0.1898          | 61.0474 | 16.2296 |
+| No log        | 2.0   | 40   | 0.1825          | 61.2481 | 16.234  |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mika5883/pretrain_rugec",
+  "_name_or_path": "mika5883/RuReCl8",
   "_num_labels": 2,
   "architectures": [
     "T5ForConditionalGeneration"

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9682a243ab775519f1b20e50940037f366473fa67a44a0d9c964c125d8702d2
+oid sha256:e91a14b61917f87f71c84957b118627e8de5f5259588c0db45913086026e0ade
 size 891644712

runs/May21_12-10-30_ebc91b8fe69c/events.out.tfevents.1716293432.ebc91b8fe69c.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908896730288c43e87679acec6226e96f4667eb2c5bf036cf0d453a9284504f4
+size 6704

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 50,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 50
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1c5f3d79ff7230d03c7f2457e7bcd7d8cfd51866dde4301d5b246fe962a2f3
+oid sha256:55bdfec7b769f1a6b45e2b28e5859996fbb0ddec0bdf92e0ac1c2890d30f1762
 size 5048