Model import

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9acfce8999d7beea9c5bc64a1e3a24845dd3284e6dcb3268d92b10b7b2e93a2
+size 498683309

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d8162a4093e47b222902d6f1e867422a141be0d28d7e4a4889b3ad2fd4ae4d
+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 @@
+{"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, "name_or_path": "roberta-base"}

trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.9345950946320974,
+  "best_model_checkpoint": "../output/roberta-base-sst_bin/checkpoint-700",
+  "epoch": 3.225806451612903,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_f1": 0.9068620534601686,
+      "eval_loss": 0.2708713114261627,
+      "eval_precision": 0.9092790114821938,
+      "eval_recall": 0.9064683842721226,
+      "eval_runtime": 4.3371,
+      "eval_samples_per_second": 201.055,
+      "step": 100
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_f1": 0.9218539136302294,
+      "eval_loss": 0.22453300654888153,
+      "eval_precision": 0.9236269780824236,
+      "eval_recall": 0.9214869074682159,
+      "eval_runtime": 4.3383,
+      "eval_samples_per_second": 201.001,
+      "step": 200
+    },
+    {
+      "epoch": 1.38,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_f1": 0.9277248238707003,
+      "eval_loss": 0.26203280687332153,
+      "eval_precision": 0.9277451780122622,
+      "eval_recall": 0.9277069125199966,
+      "eval_runtime": 4.3399,
+      "eval_samples_per_second": 200.924,
+      "step": 300
+    },
+    {
+      "epoch": 1.84,
+      "eval_accuracy": 0.9288990825688074,
+      "eval_f1": 0.9288990825688074,
+      "eval_loss": 0.27323779463768005,
+      "eval_precision": 0.9292119222025764,
+      "eval_recall": 0.9292119222025764,
+      "eval_runtime": 4.3401,
+      "eval_samples_per_second": 200.916,
+      "step": 400
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.0783410138248848e-05,
+      "loss": 0.2545,
+      "step": 500
+    },
+    {
+      "epoch": 2.3,
+      "eval_accuracy": 0.9288990825688074,
+      "eval_f1": 0.928763802145097,
+      "eval_loss": 0.3416966497898102,
+      "eval_precision": 0.9303050804456754,
+      "eval_recall": 0.9284120569167298,
+      "eval_runtime": 4.3403,
+      "eval_samples_per_second": 200.908,
+      "step": 500
+    },
+    {
+      "epoch": 2.76,
+      "eval_accuracy": 0.9288990825688074,
+      "eval_f1": 0.9288256977356504,
+      "eval_loss": 0.250255286693573,
+      "eval_precision": 0.9293817476383266,
+      "eval_recall": 0.9286225477814263,
+      "eval_runtime": 4.3388,
+      "eval_samples_per_second": 200.976,
+      "step": 600
+    },
+    {
+      "epoch": 3.23,
+      "eval_accuracy": 0.9346330275229358,
+      "eval_f1": 0.9345950946320974,
+      "eval_loss": 0.3421626687049866,
+      "eval_precision": 0.9347459813507295,
+      "eval_recall": 0.9345057674496927,
+      "eval_runtime": 4.3413,
+      "eval_samples_per_second": 200.862,
+      "step": 700
+    }
+  ],
+  "max_steps": 1085,
+  "num_train_epochs": 5,
+  "total_flos": 2137477265246208,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b80c7696513ffa545c584d56f250d66edf7d982886ca7c3aacb56f5777ede26
+size 2159