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 +1,76 @@
+---
+library_name: transformers
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output_fp16
+  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. -->
+
+# output_fp16
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4230
+- Accuracy: 0.8382
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:--------:|
+| 0.5485        | 1.0   | 12272  | 0.4865          | 0.8100   |
+| 0.4989        | 2.0   | 24544  | 0.4720          | 0.8193   |
+| 0.4743        | 3.0   | 36816  | 0.5417          | 0.7859   |
+| 0.4762        | 4.0   | 49088  | 0.4359          | 0.8313   |
+| 0.4525        | 5.0   | 61360  | 0.4297          | 0.8365   |
+| 0.4457        | 6.0   | 73632  | 0.4273          | 0.8398   |
+| 0.4205        | 7.0   | 85904  | 0.4343          | 0.8321   |
+| 0.4315        | 8.0   | 98176  | 0.4287          | 0.8357   |
+| 0.4271        | 9.0   | 110448 | 0.4299          | 0.8394   |
+| 0.4031        | 10.0  | 122720 | 0.4250          | 0.8353   |
+| 0.4           | 11.0  | 134992 | 0.4401          | 0.8345   |
+| 0.3899        | 12.0  | 147264 | 0.4178          | 0.8418   |
+| 0.3921        | 13.0  | 159536 | 0.4313          | 0.8386   |
+| 0.3849        | 14.0  | 171808 | 0.4212          | 0.8378   |
+| 0.3777        | 15.0  | 184080 | 0.4230          | 0.8382   |
+
+
+### Framework versions
+
+- Transformers 4.53.2
+- Pytorch 2.6.0+cu124
+- Datasets 2.18.0
+- Tokenizers 0.21.2

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "xlm-roberta-base",
+  "beta1": 0.85,
+  "beta2": 0.85,
+  "bias": "none",
+  "deltaT": 10,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "init_r": 12,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.3,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier"
+  ],
+  "orth_reg_weight": 0.5,
+  "peft_type": "ADALORA",
+  "r": 32,
+  "rank_pattern": null,
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "target_r": 8,
+  "task_type": "SEQ_CLS",
+  "tfinal": 1000,
+  "tinit": 200,
+  "total_step": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed0137c081173cc950be4b9e7f3413adaffaedb638c4c69bc74474631e7922f
+size 4152508

all_results.json

@@ -0,0 +1,10 @@
+{
+    "avg_token_length": 41.888755020080325,
+    "epoch": 15.0,
+    "eval_accuracy": 0.8381525874137878,
+    "eval_loss": 0.4230376183986664,
+    "eval_runtime": 13.4164,
+    "eval_samples": 2490,
+    "eval_samples_per_second": 185.594,
+    "eval_steps_per_second": 23.255
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "avg_token_length": 41.888755020080325,
+    "epoch": 15.0,
+    "eval_accuracy": 0.8381525874137878,
+    "eval_loss": 0.4230376183986664,
+    "eval_runtime": 13.4164,
+    "eval_samples": 2490,
+    "eval_samples_per_second": 185.594,
+    "eval_steps_per_second": 23.255
+}

runs/Jul24_08-11-06_11885c69abfc/events.out.tfevents.1753344835.11885c69abfc.5848.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0542c7e65f690246ed0fdd1ed2dfac5dc8d86aea980dc44e4ca419a1a2d90a29
+size 89416

runs/Jul24_08-11-06_11885c69abfc/events.out.tfevents.1753367148.11885c69abfc.5848.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb59b0e6335a2bbeb11fac9c288771baab2a939f5cf0ab23b79a8c54f57704
+size 417

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 sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
+size 17082999

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 sha256:5c9ff689cdf2eaf701fc19bf1512eebd775b7a786a2c188a8daab3d8decd6c2f
+size 5368