Upload 10 files

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "/content/content/result/unsup-simcse-roberta-large-semeval2015-restaurants",
+  "_name_or_path": "/content/result/unsup-simcse-roberta-large-semeval2015-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 sha256:47afe8a496c33c3677030ee0c8c9d02dd668c8be61fc2847dad0611754218b6f
+size 2843107269

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816824eef0b30aca16c9c8bf778a070ad11132c4a3f7fb39b11b4a068742f12f
+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 = 1315.4897
+train_samples_per_second = 0.479

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.8174784417008615,
+  "best_model_checkpoint": "/content/result/unsup-simcse-roberta-large-semeval2015-restaurants",
+  "epoch": 30.0,
+  "global_step": 630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.95,
+      "eval_avg_sts": 0.7717928358908008,
+      "eval_sickr_spearman": 0.7292140418278018,
+      "eval_stsb_spearman": 0.8143716299538,
+      "step": 125
+    },
+    {
+      "epoch": 11.9,
+      "eval_avg_sts": 0.7791621837441685,
+      "eval_sickr_spearman": 0.7408459257874753,
+      "eval_stsb_spearman": 0.8174784417008615,
+      "step": 250
+    },
+    {
+      "epoch": 17.86,
+      "eval_avg_sts": 0.7722792956470997,
+      "eval_sickr_spearman": 0.7383406235364633,
+      "eval_stsb_spearman": 0.8062179677577361,
+      "step": 375
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 1.0317460317460318e-05,
+      "loss": 0.0021,
+      "step": 500
+    },
+    {
+      "epoch": 23.81,
+      "eval_avg_sts": 0.7703133775062114,
+      "eval_sickr_spearman": 0.7341789207212567,
+      "eval_stsb_spearman": 0.8064478342911661,
+      "step": 500
+    },
+    {
+      "epoch": 29.76,
+      "eval_avg_sts": 0.7706719031560307,
+      "eval_sickr_spearman": 0.7343738789619939,
+      "eval_stsb_spearman": 0.8069699273500677,
+      "step": 625
+    },
+    {
+      "epoch": 30.0,
+      "step": 630,
+      "train_runtime": 1315.4897,
+      "train_samples_per_second": 0.479
+    }
+  ],
+  "max_steps": 630,
+  "num_train_epochs": 30,
+  "total_flos": 5382182024773632,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30788ba4a0f336e040868da72d8dbebc7333a6cb7b34339aa8cc8e2dafd1440
+size 2107