added model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "harish/PT-UP-xlmR-FalseTrue-0_0_BEST",
+  "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",
+  "transformers_version": "4.7.0.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:ba9cf9303786beb796379e56c1f1d43fbd1d7fec175add619090f240314b753a
+size 2224483455

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9840bcbfaf276a777e2322a03a21fca67f7412cd92f4851567cf4973f7d5a002
+size 1112269342

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c15b6ca556113eb978504491d45f96838fb401e78db184d3f9bb84a8357a6b
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f7bcf3e334e904b2712ac327cdfe83f934453bdfcfda1445f5cc66056e10b6
+size 623

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": "harish/PT-UP-xlmR-FalseTrue-0_0_BEST"}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.8789323285321096,
+  "best_model_checkpoint": "OS_OUT/harish/PT-UP-xlmR-FalseTrue-0_0_BEST/FalseTrue-0/2/checkpoint-18",
+  "epoch": 9.0,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6336996555328369,
+      "eval_f1": 0.6278853421710564,
+      "eval_loss": 1.0849474668502808,
+      "eval_runtime": 0.7985,
+      "eval_samples_per_second": 341.901,
+      "eval_steps_per_second": 43.834,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6996337175369263,
+      "eval_f1": 0.7003429567212002,
+      "eval_loss": 0.5072219371795654,
+      "eval_runtime": 0.7903,
+      "eval_samples_per_second": 345.433,
+      "eval_steps_per_second": 44.286,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7655677795410156,
+      "eval_f1": 0.7507642323997964,
+      "eval_loss": 0.47925040125846863,
+      "eval_runtime": 0.7908,
+      "eval_samples_per_second": 345.204,
+      "eval_steps_per_second": 44.257,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8131868243217468,
+      "eval_f1": 0.8096849683022662,
+      "eval_loss": 0.45054349303245544,
+      "eval_runtime": 0.791,
+      "eval_samples_per_second": 345.149,
+      "eval_steps_per_second": 44.25,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8351648449897766,
+      "eval_f1": 0.8353801154290916,
+      "eval_loss": 0.4265427887439728,
+      "eval_runtime": 0.7901,
+      "eval_samples_per_second": 345.511,
+      "eval_steps_per_second": 44.296,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8571428656578064,
+      "eval_f1": 0.8573294333718795,
+      "eval_loss": 0.38742759823799133,
+      "eval_runtime": 0.7896,
+      "eval_samples_per_second": 345.734,
+      "eval_steps_per_second": 44.325,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8644688725471497,
+      "eval_f1": 0.8640971847926557,
+      "eval_loss": 0.35351312160491943,
+      "eval_runtime": 0.7926,
+      "eval_samples_per_second": 344.433,
+      "eval_steps_per_second": 44.158,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8754578828811646,
+      "eval_f1": 0.8753319033800172,
+      "eval_loss": 0.33853575587272644,
+      "eval_runtime": 0.7916,
+      "eval_samples_per_second": 344.883,
+      "eval_steps_per_second": 44.216,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8791208863258362,
+      "eval_f1": 0.8789323285321096,
+      "eval_loss": 0.3337554633617401,
+      "eval_runtime": 0.7905,
+      "eval_samples_per_second": 345.343,
+      "eval_steps_per_second": 44.275,
+      "step": 18
+    }
+  ],
+  "max_steps": 18,
+  "num_train_epochs": 9,
+  "total_flos": 101857961258496.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7f7f32b6ac8aaf3ab1a0b5db4bbdef8fa286bb2eb3c68d7b434e4e1fd7bdae
+size 2479