Upload 12 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "result/my-sup-simcse-robert-base",
+  "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": 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",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,12 @@
+epoch = 3.0
+eval_CR = 87.08
+eval_MPQA = 83.95
+eval_MR = 81.98
+eval_MRPC = 72.33
+eval_SST2 = 86.01
+eval_SUBJ = 94.08
+eval_TREC = 70.71
+eval_avg_sts = 0.7194451737065093
+eval_avg_transfer = 82.30571428571429
+eval_sickr_spearman = 0.7009749242348865
+eval_stsb_spearman = 0.737915423178132

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9d9d654384f7550e0213f95e93778782510242618b440f54b67df6db99bef1
+size 997280229

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84846e9549aeb19c2e07d77157c69ea1e1f2074f5a2b61e326ab3014c7b424c
+size 498649201

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c683d858a2ba1889c59dcbbddd01f89e510e802c6eceaa2ccd143b1fa7e042
+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"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 3.0
+train_runtime = 113.2803
+train_samples_per_second = 3.999

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 0.737915423178132,
+  "best_model_checkpoint": "result/my-sup-simcse-robert-base",
+  "epoch": 3.0,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.83,
+      "eval_avg_sts": 0.705034931467253,
+      "eval_sickr_spearman": 0.6842693229058995,
+      "eval_stsb_spearman": 0.7258005400286066,
+      "step": 125
+    },
+    {
+      "epoch": 1.66,
+      "eval_avg_sts": 0.7194451737065093,
+      "eval_sickr_spearman": 0.7009749242348865,
+      "eval_stsb_spearman": 0.737915423178132,
+      "step": 250
+    },
+    {
+      "epoch": 2.48,
+      "eval_avg_sts": 0.7050845142862847,
+      "eval_sickr_spearman": 0.6962160507354997,
+      "eval_stsb_spearman": 0.7139529778370697,
+      "step": 375
+    },
+    {
+      "epoch": 3.0,
+      "step": 453,
+      "train_runtime": 113.2803,
+      "train_samples_per_second": 3.999
+    }
+  ],
+  "max_steps": 453,
+  "num_train_epochs": 3,
+  "total_flos": 4156120134844416,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aca463af2126c3d2ab043826c9f3ec0092ef8d0205d8e3a99f7a0e19c48ffe2
+size 2031