Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9159040316596587,
+    "eval_combined_score": 0.9019646623849604,
+    "eval_f1": 0.8880252931102622,
+    "eval_loss": 0.3268052935600281,
+    "eval_runtime": 106.0586,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 381.204,
+    "eval_steps_per_second": 47.653,
+    "train_loss": 0.1924241087868811,
+    "train_runtime": 13385.1324,
+    "train_samples": 363846,
+    "train_samples_per_second": 135.914,
+    "train_steps_per_second": 4.248
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "qqp",
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9159040316596587,
+    "eval_combined_score": 0.9019646623849604,
+    "eval_f1": 0.8880252931102622,
+    "eval_loss": 0.3268052935600281,
+    "eval_runtime": 106.0586,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 381.204,
+    "eval_steps_per_second": 47.653
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c606beb07bed1f4d689d6f6a6c5600d4fd0910dc573d47ba73792424c7de624
+size 498674093

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 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.1924241087868811,
+    "train_runtime": 13385.1324,
+    "train_samples": 363846,
+    "train_samples_per_second": 135.914,
+    "train_steps_per_second": 4.248
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.9159040316596587,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855",
+  "epoch": 5.0,
+  "global_step": 56855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.777760406488177e-05,
+      "loss": 0.3275,
+      "step": 11371
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8883502349740292,
+      "eval_combined_score": 0.8730347279011859,
+      "eval_f1": 0.8577192208283426,
+      "eval_loss": 0.2622373104095459,
+      "eval_runtime": 105.6916,
+      "eval_samples_per_second": 382.528,
+      "eval_steps_per_second": 47.818,
+      "step": 11371
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3333203048661326e-05,
+      "loss": 0.225,
+      "step": 22742
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9034380410586198,
+      "eval_combined_score": 0.8891589282275344,
+      "eval_f1": 0.874879815396449,
+      "eval_loss": 0.24025394022464752,
+      "eval_runtime": 105.7158,
+      "eval_samples_per_second": 382.44,
+      "eval_steps_per_second": 47.807,
+      "step": 22742
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.888802032440885e-06,
+      "loss": 0.171,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9104625278258719,
+      "eval_combined_score": 0.8967687316131944,
+      "eval_f1": 0.8830749354005168,
+      "eval_loss": 0.2317567765712738,
+      "eval_runtime": 106.0625,
+      "eval_samples_per_second": 381.19,
+      "eval_steps_per_second": 47.651,
+      "step": 34113
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.4444010162204425e-06,
+      "loss": 0.1315,
+      "step": 45484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9156814246846401,
+      "eval_combined_score": 0.9015178097880459,
+      "eval_f1": 0.8873541948914516,
+      "eval_loss": 0.27421835064888,
+      "eval_runtime": 106.1272,
+      "eval_samples_per_second": 380.958,
+      "eval_steps_per_second": 47.622,
+      "step": 45484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.107,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9159040316596587,
+      "eval_combined_score": 0.9019646623849604,
+      "eval_f1": 0.8880252931102622,
+      "eval_loss": 0.3268052935600281,
+      "eval_runtime": 106.2134,
+      "eval_samples_per_second": 380.649,
+      "eval_steps_per_second": 47.583,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "step": 56855,
+      "total_flos": 1.196648813106432e+17,
+      "train_loss": 0.1924241087868811,
+      "train_runtime": 13385.1324,
+      "train_samples_per_second": 135.914,
+      "train_steps_per_second": 4.248
+    }
+  ],
+  "max_steps": 56855,
+  "num_train_epochs": 5,
+  "total_flos": 1.196648813106432e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fcd259fc079b54178f00c834980a7dd49b3db8c7fd422dad98c21db16bc14a
+size 2671