fekpghojezpoh/sarcasm_BARThez

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [moussaKam/barthez-orangesum-abstract](https://huggingface.co/moussaKam/barthez-orangesum-abstract) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 12.3591
+- Loss: 1.2689
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 12.3591         |
+| No log        | 1.0   | 5    | 1.2689          |
 
 
 ### Framework versions

config.json

@@ -19,6 +19,7 @@
   "decoder_start_token_id": 2,
   "do_blenderbot_90_layernorm": false,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -26,6 +27,7 @@
   "eos_token_id": 2,
   "extra_pos_embeddings": 2,
   "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -42,7 +44,6 @@
   "model_type": "mbart",
   "normalize_before": true,
   "normalize_embedding": true,
-  "num_beams": 2,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887c0ec1471a11e4e09da0ff289cd295b3446e027bc6b1eee2f1ca7a36e2fb80
+oid sha256:1e1209921a56568d60eeae837eb6bd98a7ac88eec576e1e5f3315592b311754e
 size 557116312

runs/Feb27_12-43-53_aa9548bf9a52/events.out.tfevents.1709037834.aa9548bf9a52.4055.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1c6c2773cc40a8ccb99f80f312a2feb2bcbe4dac695bdc4156a3cb8fd335b1
+size 6301

runs/Feb27_12-43-53_aa9548bf9a52/events.out.tfevents.1709037864.aa9548bf9a52.4055.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d612c014112a6709bbc024e390066b152c83294b111262c607c2ffea897c6e
+size 354

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08cac45b34f92a57d8587b674dceca13a552f95a665ecf24f89b8e5ff6e3cfa8
+oid sha256:6d461d26b86b2dd1e52391f36ee6ac53d7c7f2fb11557dc3f25ffaccdf045f53
 size 5112