add model files

.gitattributes

@@ -32,3 +32,4 @@ 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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.592957808732054,
+    "train_runtime": 5580.5786,
+    "train_samples": 392702,
+    "train_samples_per_second": 140.739,
+    "train_steps_per_second": 0.55
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "xnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7640c343b74a8e5c92e8634637a3ae76a5f409bb08532743bb960372519e2deb
+size 1112257205

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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "cardiffnlp/twitter-xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.592957808732054,
+    "train_runtime": 5580.5786,
+    "train_samples": 392702,
+    "train_samples_per_second": 140.739,
+    "train_steps_per_second": 0.55
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 3068,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.185136897001304e-05,
+      "loss": 0.7763,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.370273794002607e-05,
+      "loss": 0.6385,
+      "step": 1000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.5554106910039117e-05,
+      "loss": 0.6041,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.740547588005215e-05,
+      "loss": 0.5271,
+      "step": 2000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.25684485006519e-06,
+      "loss": 0.515,
+      "step": 2500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.108213820078227e-06,
+      "loss": 0.5088,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "step": 3068,
+      "total_flos": 5.166258268431053e+16,
+      "train_loss": 0.592957808732054,
+      "train_runtime": 5580.5786,
+      "train_samples_per_second": 140.739,
+      "train_steps_per_second": 0.55
+    }
+  ],
+  "max_steps": 3068,
+  "num_train_epochs": 2,
+  "total_flos": 5.166258268431053e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25264ef7c81e634ff4aca43d3bdbcbf11d269d51c1f08411d2eb0d3fc8bb5a1
+size 3387