added data

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 sha256:43d4738057aea842c8f1157899d2037015e10d0ac8991af42dcd4a72d9e21fa4
+size 2224487441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5790156836db5e5066a0f39a3158dc6766c28aaf9df51e5f26309e3d7923219f
+size 1112271305

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49818527aead988a78aba3b44071fabe55bc0eb1ae5c3ca26900b6ea4852c3b6
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f936ab895e51bdf161e08ec4abc9119f741669d989197ed8805e7abcae9b2f4
+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 +1,96 @@
+{
+  "best_metric": 0.7989452316551693,
+  "best_model_checkpoint": "FS_OUT/harish/PT-UP-xlmR-FalseFalse-0_0_BEST/FalseFalse-0/2/checkpoint-40",
+  "epoch": 8.0,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6300366520881653,
+      "eval_f1": 0.6314656194864177,
+      "eval_loss": 0.6447749137878418,
+      "eval_runtime": 0.7731,
+      "eval_samples_per_second": 353.132,
+      "eval_steps_per_second": 45.273,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6813187003135681,
+      "eval_f1": 0.6795802519632642,
+      "eval_loss": 0.5641180872917175,
+      "eval_runtime": 0.7759,
+      "eval_samples_per_second": 351.861,
+      "eval_steps_per_second": 45.11,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7289377450942993,
+      "eval_f1": 0.7198230619283251,
+      "eval_loss": 0.5698391795158386,
+      "eval_runtime": 0.7786,
+      "eval_samples_per_second": 350.615,
+      "eval_steps_per_second": 44.951,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7289377450942993,
+      "eval_f1": 0.7299802761341222,
+      "eval_loss": 0.5229743719100952,
+      "eval_runtime": 0.7762,
+      "eval_samples_per_second": 351.719,
+      "eval_steps_per_second": 45.092,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7582417726516724,
+      "eval_f1": 0.7592382294429708,
+      "eval_loss": 0.5236229300498962,
+      "eval_runtime": 0.7877,
+      "eval_samples_per_second": 346.6,
+      "eval_steps_per_second": 44.436,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7655677795410156,
+      "eval_f1": 0.7641127492170192,
+      "eval_loss": 0.5164700150489807,
+      "eval_runtime": 0.7856,
+      "eval_samples_per_second": 347.517,
+      "eval_steps_per_second": 44.554,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.791208803653717,
+      "eval_f1": 0.7917637180095652,
+      "eval_loss": 0.5138589143753052,
+      "eval_runtime": 0.7752,
+      "eval_samples_per_second": 352.156,
+      "eval_steps_per_second": 45.148,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7985348105430603,
+      "eval_f1": 0.7989452316551693,
+      "eval_loss": 0.5282412767410278,
+      "eval_runtime": 0.7751,
+      "eval_samples_per_second": 352.197,
+      "eval_steps_per_second": 45.153,
+      "step": 40
+    }
+  ],
+  "max_steps": 45,
+  "num_train_epochs": 9,
+  "total_flos": 82090649272320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad440bbe38f3f6188e2115bcb09f97ac21459647ec005052cb30586a602b41ee
+size 2735