Upload light files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7450fa90b7d03a21594d02601ac8dd84d5b41112416a372918c376939847ba78
+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-large"}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.8797919434527426,
+  "best_model_checkpoint": "result/clhaif-roberta-large-refse",
+  "epoch": 0.6963788300835655,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "eval_avg_sts": 0.8064963302246256,
+      "eval_sickr_spearman": 0.762082012728511,
+      "eval_stsb_spearman": 0.8509106477207403,
+      "step": 125
+    },
+    {
+      "epoch": 0.23,
+      "eval_avg_sts": 0.8452781032001684,
+      "eval_sickr_spearman": 0.8198200556739618,
+      "eval_stsb_spearman": 0.8707361507263751,
+      "step": 250
+    },
+    {
+      "epoch": 0.35,
+      "eval_avg_sts": 0.8271010163591597,
+      "eval_sickr_spearman": 0.7789582685609077,
+      "eval_stsb_spearman": 0.8752437641574118,
+      "step": 375
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.226245744351594e-05,
+      "loss": 7.5855,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "eval_avg_sts": 0.8293696081597453,
+      "eval_sickr_spearman": 0.7859766211341461,
+      "eval_stsb_spearman": 0.8727625951853443,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_avg_sts": 0.838054856261987,
+      "eval_sickr_spearman": 0.8025079656271157,
+      "eval_stsb_spearman": 0.8736017468968582,
+      "step": 625
+    },
+    {
+      "epoch": 0.7,
+      "eval_avg_sts": 0.8370776376044988,
+      "eval_sickr_spearman": 0.794363331756255,
+      "eval_stsb_spearman": 0.8797919434527426,
+      "step": 750
+    }
+  ],
+  "max_steps": 3231,
+  "num_train_epochs": 3,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6a5c4fd55a7a40f4a9472d9699eed64fd80002ecd350f4ea5366a92207f9ab
+size 2095