sarcasm_BARThez

README.md

@@ -1,5 +1,57 @@
 ---
-language:
-- fr
-- en
----
+license: apache-2.0
+base_model: moussaKam/barthez-orangesum-abstract
+tags:
+- generated_from_trainer
+model-index:
+- name: sarcasm_BARThez
+  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. -->
+
+# sarcasm_BARThez
+
+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: 7.9423
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 11   | 7.9423          |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -1,4 +1,4 @@
-MBartConfig {
+{
   "_name_or_path": "moussaKam/barthez-orangesum-abstract",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
@@ -39,10 +39,12 @@ MBartConfig {
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "max_new_tokens": 30,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
   "normalize_before": true,
   "normalize_embedding": true,
+  "num_beams": 2,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
@@ -58,6 +60,7 @@ MBartConfig {
     }
   },
   "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 50002

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "do_sample": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
   "eos_token_id": 2,
+  "forced_eos_token_id": 2,
   "max_new_tokens": 30,
   "num_beams": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.38.1"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0ca8fdc67e62598596e133cfc8174bd06c8684ec4cdc950246531ca3786a6e
+size 557116312

runs/Feb27_08-56-36_28bdebfef1da/events.out.tfevents.1709024198.28bdebfef1da.4281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b78761dd81d0825659f8a49a82df9caaaf7bf469ba334010f848d3f25dbce9
+size 6327

runs/Feb27_09-04-28_28bdebfef1da/events.out.tfevents.1709024672.28bdebfef1da.4281.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ddd8899ff9c6e8dbeb990ca8d43554cc5560643e8a65edf7b327ea05dfe3ea
+size 6309

runs/Feb27_09-35-18_28bdebfef1da/events.out.tfevents.1709026523.28bdebfef1da.4281.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afc8668769f2ccad5b59a422e76abb63a98aeb482b7f80139951d20f54d0918
+size 6351

runs/Feb27_09-35-18_28bdebfef1da/events.out.tfevents.1709026817.28bdebfef1da.4281.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b06c4356218a8833b7c702e6add725174cf35b402652478a53c2536022f686
+size 354

runs/Feb27_10-16-23_28bdebfef1da/events.out.tfevents.1709028987.28bdebfef1da.4281.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d448b20604d0c5d81dc836c19b21020664ba6784ff38ca842d74d709be4a2c
+size 5725

runs/Feb27_10-17-14_28bdebfef1da/events.out.tfevents.1709029037.28bdebfef1da.4281.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b2079a4ef75c46ce43f5bfc3a648415a7be043403af3256343a282f3d86b1f
+size 5774

runs/Feb27_10-22-16_28bdebfef1da/events.out.tfevents.1709029338.28bdebfef1da.25649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8f38c86aa3ed673e36d43fb53a446309e501ed37837365038fe296672ccb8f
+size 6332

runs/Feb27_10-22-16_28bdebfef1da/events.out.tfevents.1709029583.28bdebfef1da.25649.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2377ad52fda56efff588f14635b0a797081a1116d6c649e4bba6c75aef8bba50
+size 354

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582403da7cb525c4cac90b495e553cb766b818be71755e6bd885072a1067314a
+size 1115393

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BarthezTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e94e3f7cc3b56281210a0c9b05ab3db07dc8d4a9f4eebfd8cadd8320e0828a
+size 5112