End of training

README.md

@@ -14,12 +14,21 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [eenzeenee/t5-base-korean-summarization](https://huggingface.co/eenzeenee/t5-base-korean-summarization) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5818
-- eval_runtime: 22.9524
-- eval_samples_per_second: 15.772
-- eval_steps_per_second: 3.965
-- epoch: 5.0
-- step: 8675
+- Loss: 0.6214
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
 
 ### Training hyperparameters
 
@@ -32,9 +41,21 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 20
 
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.2945        | 1.0   | 1735  | 0.7757          |
+| 0.8016        | 2.0   | 3470  | 0.6987          |
+| 0.7058        | 3.0   | 5205  | 0.6617          |
+| 0.6402        | 4.0   | 6940  | 0.6387          |
+| 0.5864        | 5.0   | 8675  | 0.6283          |
+| 0.5476        | 6.0   | 10410 | 0.6214          |
+
+
 ### Framework versions
 
-- Transformers 4.33.2
+- Transformers 4.33.3
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3

config.json

@@ -27,7 +27,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.33.3",
   "use_cache": true,
   "vocab_size": 50358
 }

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 1,
   "max_length": 128,
   "pad_token_id": 0,
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.33.3"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab395ab847a699aa674fbba898089431c2e7d26e19a6dae8adcd39c45180f339
+oid sha256:0f5db4ff4b026b00bbe0ffd0f98a0d7304eb322c541a36349de07d0b8c244bde
 size 1102414005

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fcbc2e40d4d1f589d6e2888465258a8809d1fd6d8c223bfe7dff9e8210b717
+oid sha256:589d6ef16d7d6c9282260394deef21f4724842f5182f0422cea9abe3f5c8a361
 size 4155