Training in progress, step 500

README.md

@@ -4,18 +4,18 @@ base_model: facebook/bart-base
 tags:
 - generated_from_trainer
 model-index:
-- name: bart-with-vocab-noise-data
+- name: bart-with-noise-data
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bart-with-vocab-noise-data
+# bart-with-noise-data
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1180
+- Loss: 0.2749
 
 ## Model description
 
@@ -42,19 +42,20 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
 - num_epochs: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1538        | 0.87  | 500  | 0.1459          |
-| 0.098         | 1.73  | 1000 | 0.1252          |
-| 0.0738        | 2.6   | 1500 | 0.1180          |
+| 0.5397        | 0.87  | 500  | 0.3145          |
+| 0.2586        | 1.73  | 1000 | 0.2909          |
+| 0.2764        | 2.6   | 1500 | 0.2749          |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.2
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

config.json

@@ -69,7 +69,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -9,5 +9,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b87ba753206870f0ec3d3889fd5e2068d24f8a06a76cf0461b3fbcea89f2f6c
+oid sha256:edc86ce36ee9db09d79c259767d49e0db4169132fc0752ec7014499b72c3c02d
 size 557912620

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0562c9711921d22b9b619159db51464ea88829d6967a2925a803ba569d8cf2bd
+oid sha256:7542a1b0d22daa47449aa4c78be7dcbc4df1dc6ec0c4a11512baace3f970fa5e
 size 4664