adding models

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: walia_large_xlmr_250k
+  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. -->
+
+# walia_large_xlmr_250k
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0552
+
+## 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: 10
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.0551953315734863,
+    "eval_runtime": 1549.8799,
+    "eval_samples": 146099,
+    "eval_samples_per_second": 94.265,
+    "eval_steps_per_second": 11.783,
+    "perplexity": 21.225331099339662,
+    "train_loss": 3.7000725246486845,
+    "train_runtime": 189673.1431,
+    "train_samples": 584792,
+    "train_samples_per_second": 30.832,
+    "train_steps_per_second": 3.083
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.0551953315734863,
+    "eval_runtime": 1549.8799,
+    "eval_samples": 146099,
+    "eval_samples_per_second": 94.265,
+    "eval_steps_per_second": 11.783,
+    "perplexity": 21.225331099339662
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783d25d3290c4196351ad0cb4101c0d63c0ae7af8908955d92978fe1b0ff1053
+size 2240706037

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b775eefca433d144d14818647186b2d7d0467f444afe0e11b4e3141bd83f2ef3
+size 5613453

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 3.7000725246486845,
+    "train_runtime": 189673.1431,
+    "train_samples": 584792,
+    "train_samples_per_second": 30.832,
+    "train_steps_per_second": 3.083
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c210f0be6464af3853add069048555bf656b68816b7f4fc561b5c89591fb67
+size 4027