Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8763222131814483,
+    "eval_loss": 0.38699284195899963,
+    "eval_runtime": 45.9076,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 214.169,
+    "eval_steps_per_second": 26.771,
+    "train_loss": 0.3447862050679392,
+    "train_runtime": 14914.656,
+    "train_samples": 392702,
+    "train_samples_per_second": 78.99,
+    "train_steps_per_second": 2.468
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8763222131814483,
+    "eval_loss": 0.38699284195899963,
+    "eval_runtime": 45.9076,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 214.169,
+    "eval_steps_per_second": 26.771
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1923614610d01538addf7d4739ac3ce4cdd4ca6ce29deae12e9fc7e6d32631f8
+size 498677165

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": 3.0,
+    "train_loss": 0.3447862050679392,
+    "train_runtime": 14914.656,
+    "train_samples": 392702,
+    "train_samples_per_second": 78.99,
+    "train_steps_per_second": 2.468
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8779419256240448,
+  "best_model_checkpoint": "./roberta_base/fine_tuned_models/checkpoint-36816",
+  "epoch": 3.0,
+  "global_step": 36816,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4814993662099355e-05,
+      "loss": 0.4891,
+      "step": 12272
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8625573102394295,
+      "eval_loss": 0.3779561519622803,
+      "eval_runtime": 45.6198,
+      "eval_samples_per_second": 215.148,
+      "eval_steps_per_second": 26.896,
+      "step": 12272
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.4074968310496775e-06,
+      "loss": 0.3181,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8757004584819155,
+      "eval_loss": 0.3620317280292511,
+      "eval_runtime": 45.5874,
+      "eval_samples_per_second": 215.301,
+      "eval_steps_per_second": 26.915,
+      "step": 24544
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2271,
+      "step": 36816
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8779419256240448,
+      "eval_loss": 0.38248324394226074,
+      "eval_runtime": 45.8275,
+      "eval_samples_per_second": 214.172,
+      "eval_steps_per_second": 26.774,
+      "step": 36816
+    },
+    {
+      "epoch": 3.0,
+      "step": 36816,
+      "total_flos": 7.74938740264658e+16,
+      "train_loss": 0.3447862050679392,
+      "train_runtime": 14914.656,
+      "train_samples_per_second": 78.99,
+      "train_steps_per_second": 2.468
+    }
+  ],
+  "max_steps": 36816,
+  "num_train_epochs": 3,
+  "total_flos": 7.74938740264658e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b7352ade12ad0d89ffe80c281d6aa7fe222bf20f2b127be31da052887ebe6f
+size 2671