nhankins/es_euph_classifier_1.0

.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 +1,72 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+model-index:
+- name: xlm-roberta-large-lora-text-classification
+  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. -->
+
+# xlm-roberta-large-lora-text-classification
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6343
+- Precision: 0.6371
+- Recall: 0.9958
+- F1 and accuracy: {'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688}
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 and accuracy                                            |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:----------------------------------------------------------:|
+| No log        | 1.0   | 372  | 0.6553          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6758        | 2.0   | 744  | 0.6534          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6765        | 3.0   | 1116 | 0.6518          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6765        | 4.0   | 1488 | 0.6519          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6722        | 5.0   | 1860 | 0.6470          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6654        | 6.0   | 2232 | 0.6425          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6626        | 7.0   | 2604 | 0.6419          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6626        | 8.0   | 2976 | 0.6404          | 0.6371    | 0.9958 | {'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688} |
+| 0.6547        | 9.0   | 3348 | 0.6356          | 0.6381    | 1.0    | {'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}  |
+| 0.6544        | 10.0  | 3720 | 0.6343          | 0.6371    | 0.9958 | {'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688} |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "FacebookAI/xlm-roberta-large",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b7f3a6d5852a1bcb53791c559a0d40a715d9f18c938f6bd142a6f337ba6b5c
+size 5000440

runs/Feb10_15-36-52_50f7ce92a495/events.out.tfevents.1707579417.50f7ce92a495.462.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7befd7fdc9c76f021e1288b8339f8cca6571e20e91c23b1f948ad35072e12790
+size 9705

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:619b5766deb20fb5a327ec968bf9849576a8f8c6993e519a86fdd032b36680d0
+size 17082853

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": true,
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:33d06353be766e6a9a47f23f7369f85a582dcaa0087ea59c7e1fdfddff6486bd
+size 4664