Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8120772838592529,
+    "eval_loss": 0.44183820486068726,
+    "eval_runtime": 9.3745,
+    "eval_samples": 2070,
+    "eval_samples_per_second": 220.813,
+    "eval_steps_per_second": 27.628,
+    "train_loss": 0.33380090084002606,
+    "train_runtime": 3958.9622,
+    "train_samples": 58265,
+    "train_samples_per_second": 73.586,
+    "train_steps_per_second": 2.3
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8120772838592529,
+    "eval_loss": 0.44183820486068726,
+    "eval_runtime": 9.3745,
+    "eval_samples": 2070,
+    "eval_samples_per_second": 220.813,
+    "eval_steps_per_second": 27.628
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db02481e2e8c4c02f5e12bb1befc272658897fa668b52b8ca5e7cda0bd3717d
+size 1112266157

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.33380090084002606,
+    "train_runtime": 3958.9622,
+    "train_samples": 58265,
+    "train_samples_per_second": 73.586,
+    "train_steps_per_second": 2.3
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8120772838592529,
+  "best_model_checkpoint": "./xlm-roberta-base/fine_tuned_models_en_fa/checkpoint-5463",
+  "epoch": 5.0,
+  "global_step": 9105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.777886258237735e-05,
+      "loss": 0.5548,
+      "step": 1821
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5613526701927185,
+      "eval_loss": 0.6830180287361145,
+      "eval_runtime": 9.3317,
+      "eval_samples_per_second": 221.824,
+      "eval_steps_per_second": 27.755,
+      "step": 1821
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3334146936783012e-05,
+      "loss": 0.3887,
+      "step": 3642
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7971014380455017,
+      "eval_loss": 0.44974568486213684,
+      "eval_runtime": 9.3381,
+      "eval_samples_per_second": 221.672,
+      "eval_steps_per_second": 27.736,
+      "step": 3642
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.889431291188675e-06,
+      "loss": 0.2979,
+      "step": 5463
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8120772838592529,
+      "eval_loss": 0.44183820486068726,
+      "eval_runtime": 9.3303,
+      "eval_samples_per_second": 221.859,
+      "eval_steps_per_second": 27.759,
+      "step": 5463
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.4447156455943375e-06,
+      "loss": 0.2356,
+      "step": 7284
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8072463870048523,
+      "eval_loss": 0.44395601749420166,
+      "eval_runtime": 9.3313,
+      "eval_samples_per_second": 221.834,
+      "eval_steps_per_second": 27.756,
+      "step": 7284
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.192,
+      "step": 9105
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8072463870048523,
+      "eval_loss": 0.48133036494255066,
+      "eval_runtime": 9.3257,
+      "eval_samples_per_second": 221.966,
+      "eval_steps_per_second": 27.773,
+      "step": 9105
+    },
+    {
+      "epoch": 5.0,
+      "step": 9105,
+      "total_flos": 1.9162707050688e+16,
+      "train_loss": 0.33380090084002606,
+      "train_runtime": 3958.9622,
+      "train_samples_per_second": 73.586,
+      "train_steps_per_second": 2.3
+    }
+  ],
+  "max_steps": 9105,
+  "num_train_epochs": 5,
+  "total_flos": 1.9162707050688e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a45b59f059b63010729c7961e3c2e48fca1cc211f087f74d2b5c54569ca11b6
+size 2735