Upload 10 files

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "/content/content/result/unsup-simcse-roberta-large-semeval2016-restaurants",
+  "_name_or_path": "/content/result/unsup-simcse-roberta-large-semeval2016-restaurants",
   "architectures": [
     "RobertaModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": null,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
@@ -20,8 +19,8 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.2.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265
-}
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc9a993e29f75c2e0d9c7e95bce77aabc5658ece8ed7c442fda17dea2eaf88a
+size 2843107653

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58520294003a324cfe203db57771736495a8299e4cfff2f0852388b4a10667e0
+size 627

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": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "princeton-nlp/unsup-simcse-roberta-large", "special_tokens_map_file": "/root/.cache/huggingface/transformers/6d59ec8e128c32fbf5663dad4484f60104c7f3b2520047fbaf57bc63b260e0fd.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 30.0
+train_runtime = 1919.7644
+train_samples_per_second = 0.5

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.8242545236101876,
+  "best_model_checkpoint": "/content/result/unsup-simcse-roberta-large-semeval2016-restaurants",
+  "epoch": 30.0,
+  "global_step": 960,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.91,
+      "eval_avg_sts": 0.7698010352632874,
+      "eval_sickr_spearman": 0.7266049923976835,
+      "eval_stsb_spearman": 0.8129970781288911,
+      "step": 125
+    },
+    {
+      "epoch": 7.81,
+      "eval_avg_sts": 0.7792034906317966,
+      "eval_sickr_spearman": 0.7348533254165491,
+      "eval_stsb_spearman": 0.8235536558470441,
+      "step": 250
+    },
+    {
+      "epoch": 11.72,
+      "eval_avg_sts": 0.7651583327248668,
+      "eval_sickr_spearman": 0.7195221820863151,
+      "eval_stsb_spearman": 0.8107944833634184,
+      "step": 375
+    },
+    {
+      "epoch": 15.62,
+      "learning_rate": 2.3958333333333334e-05,
+      "loss": 0.0019,
+      "step": 500
+    },
+    {
+      "epoch": 15.62,
+      "eval_avg_sts": 0.7728941176212885,
+      "eval_sickr_spearman": 0.7267549454963733,
+      "eval_stsb_spearman": 0.8190332897462036,
+      "step": 500
+    },
+    {
+      "epoch": 19.53,
+      "eval_avg_sts": 0.7803452705388955,
+      "eval_sickr_spearman": 0.7396146485021092,
+      "eval_stsb_spearman": 0.8210758925756817,
+      "step": 625
+    },
+    {
+      "epoch": 23.44,
+      "eval_avg_sts": 0.7784229361678052,
+      "eval_sickr_spearman": 0.7325913487254228,
+      "eval_stsb_spearman": 0.8242545236101876,
+      "step": 750
+    },
+    {
+      "epoch": 27.34,
+      "eval_avg_sts": 0.7792486791116137,
+      "eval_sickr_spearman": 0.7348576962467801,
+      "eval_stsb_spearman": 0.8236396619764472,
+      "step": 875
+    },
+    {
+      "epoch": 30.0,
+      "step": 960,
+      "train_runtime": 1919.7644,
+      "train_samples_per_second": 0.5
+    }
+  ],
+  "max_steps": 960,
+  "num_train_epochs": 30,
+  "total_flos": 8183872361005056,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d679af324eeda4c697af19c422195a5c98ca14d14593e4a2096cdb585bb7fd
+size 2107