Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8120772838592529,
+    "eval_loss": 0.4710211753845215,
+    "eval_runtime": 9.3483,
+    "eval_samples": 2070,
+    "eval_samples_per_second": 221.43,
+    "eval_steps_per_second": 27.705,
+    "train_loss": 0.4380302508397086,
+    "train_runtime": 1381.1035,
+    "train_samples": 18496,
+    "train_samples_per_second": 66.961,
+    "train_steps_per_second": 2.093
+}

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": 0.4710211753845215,
+    "eval_runtime": 9.3483,
+    "eval_samples": 2070,
+    "eval_samples_per_second": 221.43,
+    "eval_steps_per_second": 27.705
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfc18f3c2dbdf401d43067db4cd5d13f0c1e224239638544a1bebce8fb4c952
+size 1112266157

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": 0.4380302508397086,
+    "train_runtime": 1381.1035,
+    "train_samples": 18496,
+    "train_samples_per_second": 66.961,
+    "train_steps_per_second": 2.093
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8120772838592529,
+  "best_model_checkpoint": "./xlm-roberta-base/fine_tuned_models_fa/checkpoint-2312",
+  "epoch": 5.0,
+  "global_step": 2890,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8585209003215436e-05,
+      "loss": 0.6364,
+      "step": 578
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7149758338928223,
+      "eval_loss": 0.5824872255325317,
+      "eval_runtime": 9.3258,
+      "eval_samples_per_second": 221.964,
+      "eval_steps_per_second": 27.772,
+      "step": 578
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.529100529100529e-05,
+      "loss": 0.5021,
+      "step": 1156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7772946953773499,
+      "eval_loss": 0.481751948595047,
+      "eval_runtime": 9.33,
+      "eval_samples_per_second": 221.864,
+      "eval_steps_per_second": 27.76,
+      "step": 1156
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.0194003527336862e-05,
+      "loss": 0.411,
+      "step": 1734
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8106279969215393,
+      "eval_loss": 0.45674559473991394,
+      "eval_runtime": 9.3205,
+      "eval_samples_per_second": 222.092,
+      "eval_steps_per_second": 27.788,
+      "step": 1734
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.097001763668431e-06,
+      "loss": 0.3452,
+      "step": 2312
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8120772838592529,
+      "eval_loss": 0.4710211753845215,
+      "eval_runtime": 9.3338,
+      "eval_samples_per_second": 221.775,
+      "eval_steps_per_second": 27.749,
+      "step": 2312
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.2955,
+      "step": 2890
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8101449012756348,
+      "eval_loss": 0.4912046492099762,
+      "eval_runtime": 9.331,
+      "eval_samples_per_second": 221.842,
+      "eval_steps_per_second": 27.757,
+      "step": 2890
+    },
+    {
+      "epoch": 5.0,
+      "step": 2890,
+      "total_flos": 6083127599923200.0,
+      "train_loss": 0.4380302508397086,
+      "train_runtime": 1381.1035,
+      "train_samples_per_second": 66.961,
+      "train_steps_per_second": 2.093
+    }
+  ],
+  "max_steps": 2890,
+  "num_train_epochs": 5,
+  "total_flos": 6083127599923200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44113396440b824d0b5a4ea5200b0fc83920e971a2d04314f402202765b3dc1
+size 2735