added model

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "harish/PT-UP-xlmR-ContextIncluded_IdiomExcluded-4_BEST",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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": "4.10.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f6eefe78f2afa03ac1d1d729643db963dd9d7a380d2ae90a503bc4a79f7f2b
+size 2224487441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b480c034a4be1383cee4dc162c8091940bcc61c9025aa4feb168287685e19589
+size 1112271305

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad48feab832b1ed3e993992097dfd066f008840491ad5445617f7ec52ba40c7a
+size 14593

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ed7209768c039efe0472d8b605a9f6470e66c061db35539b274e850c8f544a
+size 623

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": "harish/PT-UP-xlmR-ContextIncluded_IdiomExcluded-4_BEST", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6132865109901463,
+  "best_model_checkpoint": "OS_OUT/harish/PT-UP-xlmR-ContextIncluded_IdiomExcluded-4_BEST/TrueFalse-0/0/checkpoint-10",
+  "epoch": 5.0,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5054945349693298,
+      "eval_f1": 0.4448186316904772,
+      "eval_loss": 1.0858509540557861,
+      "eval_runtime": 0.7803,
+      "eval_samples_per_second": 349.868,
+      "eval_steps_per_second": 44.855,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5457875728607178,
+      "eval_f1": 0.5248267784316216,
+      "eval_loss": 0.7876102924346924,
+      "eval_runtime": 0.782,
+      "eval_samples_per_second": 349.108,
+      "eval_steps_per_second": 44.757,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5604395866394043,
+      "eval_f1": 0.561999123336614,
+      "eval_loss": 0.7128857970237732,
+      "eval_runtime": 0.798,
+      "eval_samples_per_second": 342.104,
+      "eval_steps_per_second": 43.859,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6007326245307922,
+      "eval_f1": 0.5950122936424307,
+      "eval_loss": 0.7449135184288025,
+      "eval_runtime": 0.7825,
+      "eval_samples_per_second": 348.874,
+      "eval_steps_per_second": 44.727,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6153846383094788,
+      "eval_f1": 0.6132865109901463,
+      "eval_loss": 0.7322821617126465,
+      "eval_runtime": 0.8163,
+      "eval_samples_per_second": 334.437,
+      "eval_steps_per_second": 42.876,
+      "step": 10
+    }
+  ],
+  "max_steps": 18,
+  "num_train_epochs": 9,
+  "total_flos": 17431107417600.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f3318f0337435ae5fce4eaa1f3386661f86a262cd8c80b45a37292d92b2e47
+size 2735