End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- rouge
+model-index:
+- name: a8024a29a840323de5125cbce765f819
+  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. -->
+
+# a8024a29a840323de5125cbce765f819
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the nyu-mll/glue [qnli] dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6960
+- Data Size: 0.125
+- Epoch Runtime: 74.0500
+- Accuracy: 0.4943
+- F1 Macro: 0.3308
+- Rouge1: 0.4947
+- Rouge2: 0.0
+- Rougel: 0.4943
+- Rougelsum: 0.4944
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:-------------:|:--------:|:--------:|:------:|:------:|:------:|:---------:|
+| No log        | 0     | 0     | 0.7043          | 0         | 7.9201        | 0.4943   | 0.3308   | 0.4947 | 0.0    | 0.4943 | 0.4944    |
+| No log        | 1     | 3273  | 0.6937          | 0.0078    | 12.2617       | 0.5057   | 0.3359   | 0.5053 | 0.0    | 0.5057 | 0.5056    |
+| 0.0115        | 2     | 6546  | 0.6998          | 0.0156    | 16.8721       | 0.5057   | 0.3359   | 0.5053 | 0.0    | 0.5057 | 0.5056    |
+| 0.7045        | 3     | 9819  | 0.6988          | 0.0312    | 25.7930       | 0.4943   | 0.3308   | 0.4947 | 0.0    | 0.4943 | 0.4944    |
+| 0.7009        | 4     | 13092 | 0.6937          | 0.0625    | 41.6408       | 0.4943   | 0.3308   | 0.4947 | 0.0    | 0.4943 | 0.4944    |
+| 0.7002        | 5     | 16365 | 0.6960          | 0.125     | 74.0500       | 0.4943   | 0.3308   | 0.4947 | 0.0    | 0.4943 | 0.4944    |
+
+
+### Framework versions
+
+- Transformers 4.57.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.3.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3961d510771d28377b3ee37a2dfffd3b9dc389b979b520fe4bbb17df087b61
+size 2239618672

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f75f25c95a8383834e0f6a27b329e591e881ee78b5dc3481f982857ae7310f
+size 5969