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:fd1c0665c29d81e309949e98f39d8a49ed04ebeeaabc3f424b1786e5610e9425
+size 2224487441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9e73fea1bf37889ca7916e931dd793a8ad7ddf5e402e9d49df14259ce7f3d5
+size 1112271305

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9210ef045109304fb4d440fbd8aee8a27e36d9221c3467c9f54e7b38427e53
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12799420259efb59c06fb1cd6fe51e32d793488edd192fc92a93c75f56339ab3
+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 +1,106 @@
+{
+  "best_metric": 0.6570678460213344,
+  "best_model_checkpoint": "FS_OUT/harish/PT-UP-xlmR-ContextIncluded_IdiomExcluded-4_BEST/TrueFalse-0/4/checkpoint-45",
+  "epoch": 9.0,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5567765831947327,
+      "eval_f1": 0.5578118336364079,
+      "eval_loss": 0.6907439827919006,
+      "eval_runtime": 0.7876,
+      "eval_samples_per_second": 346.644,
+      "eval_steps_per_second": 44.442,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5787546038627625,
+      "eval_f1": 0.4448845849320908,
+      "eval_loss": 0.665475606918335,
+      "eval_runtime": 0.7917,
+      "eval_samples_per_second": 344.817,
+      "eval_steps_per_second": 44.207,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.622710645198822,
+      "eval_f1": 0.5963622262791237,
+      "eval_loss": 0.6525125503540039,
+      "eval_runtime": 0.7838,
+      "eval_samples_per_second": 348.295,
+      "eval_steps_per_second": 44.653,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5970696210861206,
+      "eval_f1": 0.5985724185724186,
+      "eval_loss": 0.6665695309638977,
+      "eval_runtime": 0.7871,
+      "eval_samples_per_second": 346.827,
+      "eval_steps_per_second": 44.465,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.593406617641449,
+      "eval_f1": 0.5940832214099966,
+      "eval_loss": 0.6762897372245789,
+      "eval_runtime": 0.7899,
+      "eval_samples_per_second": 345.632,
+      "eval_steps_per_second": 44.312,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6336996555328369,
+      "eval_f1": 0.6314261706515927,
+      "eval_loss": 0.6941685676574707,
+      "eval_runtime": 0.7926,
+      "eval_samples_per_second": 344.418,
+      "eval_steps_per_second": 44.156,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6446886658668518,
+      "eval_f1": 0.645882102061817,
+      "eval_loss": 0.754807710647583,
+      "eval_runtime": 0.7972,
+      "eval_samples_per_second": 342.457,
+      "eval_steps_per_second": 43.905,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6446886658668518,
+      "eval_f1": 0.645882102061817,
+      "eval_loss": 0.7887275815010071,
+      "eval_runtime": 0.7852,
+      "eval_samples_per_second": 347.667,
+      "eval_steps_per_second": 44.573,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6556776762008667,
+      "eval_f1": 0.6570678460213344,
+      "eval_loss": 0.7924347519874573,
+      "eval_runtime": 0.7913,
+      "eval_samples_per_second": 345.022,
+      "eval_steps_per_second": 44.234,
+      "step": 45
+    }
+  ],
+  "max_steps": 45,
+  "num_train_epochs": 9,
+  "total_flos": 92351980431360.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22590c87fe17a093e4b23824fecbf3c085ec5e77257addd9b46f226254f87522
+size 2735