added model

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "harish/PT-UP-xlmR-FalseFalse-0_0_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:e9152e1046d9eea9cbdf216ed71585ba90bbce01781b3c57685594305a45a002
+size 2224487441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb139126ed25fc8decd173c4bf8ba4300f51c2152d9eaca5bb9a31ab345f689
+size 1112271305

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f5f524f162424a8c94445a8f83ece9d1efce1ddd2f9913830313c9d4bd3276
+size 14593

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698a7aba416b810613af7bd65d48eaa5413e21e42f86b4db3ce7155829b39d18
+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-FalseFalse-0_0_BEST", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.6573426573426573,
+  "best_model_checkpoint": "OS_OUT/harish/PT-UP-xlmR-FalseFalse-0_0_BEST/FalseFalse-0/0/checkpoint-12",
+  "epoch": 6.0,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5311355590820312,
+      "eval_f1": 0.6049382716049383,
+      "eval_loss": 1.011836290359497,
+      "eval_runtime": 0.7598,
+      "eval_samples_per_second": 359.298,
+      "eval_steps_per_second": 46.064,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6043956279754639,
+      "eval_f1": 0.568,
+      "eval_loss": 0.671142041683197,
+      "eval_runtime": 0.7664,
+      "eval_samples_per_second": 356.204,
+      "eval_steps_per_second": 45.667,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6190476417541504,
+      "eval_f1": 0.5478260869565218,
+      "eval_loss": 0.6358144879341125,
+      "eval_runtime": 0.7706,
+      "eval_samples_per_second": 354.265,
+      "eval_steps_per_second": 45.419,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6263736486434937,
+      "eval_f1": 0.6015625,
+      "eval_loss": 0.6275585293769836,
+      "eval_runtime": 0.7711,
+      "eval_samples_per_second": 354.038,
+      "eval_steps_per_second": 45.39,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6410256624221802,
+      "eval_f1": 0.65,
+      "eval_loss": 0.6581979990005493,
+      "eval_runtime": 0.7584,
+      "eval_samples_per_second": 359.969,
+      "eval_steps_per_second": 46.15,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6410256624221802,
+      "eval_f1": 0.6573426573426573,
+      "eval_loss": 0.760171115398407,
+      "eval_runtime": 0.7597,
+      "eval_samples_per_second": 359.348,
+      "eval_steps_per_second": 46.07,
+      "step": 12
+    }
+  ],
+  "max_steps": 18,
+  "num_train_epochs": 9,
+  "total_flos": 20917328901120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e16b02194dead013a524b518910c8218b7ea313aea4953073c55e56604e523f
+size 2735