eval-0.718

README.md

@@ -13,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test-mlm
 
-This model is a fine-tuned version of [/root/autodl-tmp/nbme/deberta-v3-large](https://huggingface.co//root/autodl-tmp/nbme/deberta-v3-large) on an unknown dataset.
+This model is a fine-tuned version of [ZZ99/deberta-v3-large-tapt](https://huggingface.co/ZZ99/deberta-v3-large-tapt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5185
-- Accuracy: 0.6987
+- Loss: 1.3692
+- Accuracy: 0.7180
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6986770866102621,
-    "eval_loss": 1.5184571743011475,
-    "eval_runtime": 50.0544,
+    "eval_accuracy": 0.7180157954865308,
+    "eval_loss": 1.3691895008087158,
+    "eval_runtime": 47.8255,
     "eval_samples": 794,
-    "eval_samples_per_second": 15.863,
-    "eval_steps_per_second": 1.998,
-    "perplexity": 4.565176487471998,
-    "train_loss": 1.5083582298156009,
-    "train_runtime": 7793.681,
+    "eval_samples_per_second": 16.602,
+    "eval_steps_per_second": 2.091,
+    "perplexity": 3.9321623891487576,
+    "train_loss": 1.0548812925209943,
+    "train_runtime": 7794.1827,
     "train_samples": 14828,
-    "train_samples_per_second": 5.708,
+    "train_samples_per_second": 5.707,
     "train_steps_per_second": 1.427
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/autodl-tmp/nbme/deberta-v3-large",
+  "_name_or_path": "ZZ99/deberta-v3-large-tapt",
   "architectures": [
     "NewDebertaV2ForMaskedLM"
   ],

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6986770866102621,
-    "eval_loss": 1.5184571743011475,
-    "eval_runtime": 50.0544,
+    "eval_accuracy": 0.7180157954865308,
+    "eval_loss": 1.3691895008087158,
+    "eval_runtime": 47.8255,
     "eval_samples": 794,
-    "eval_samples_per_second": 15.863,
-    "eval_steps_per_second": 1.998,
-    "perplexity": 4.565176487471998
+    "eval_samples_per_second": 16.602,
+    "eval_steps_per_second": 2.091,
+    "perplexity": 3.9321623891487576
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2f66fc7f71282ad9572e83c58abc6aa20f49951290f54bbc8c48b5b57654c7
+oid sha256:bbe4e67605ac34718bafb7684d144ba7006baf1dea461c31f4854256d610e2b7
 size 1740500457

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "vocab_type": "spm", "special_tokens_map_file": null, "name_or_path": "/root/autodl-tmp/nbme/deberta-v3-large", "sp_model_kwargs": {}, "tokenizer_class": "DebertaV2Tokenizer"}
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "vocab_type": "spm", "special_tokens_map_file": null, "name_or_path": "ZZ99/deberta-v3-large-tapt", "sp_model_kwargs": {}, "tokenizer_class": "DebertaV2Tokenizer"}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 1.5083582298156009,
-    "train_runtime": 7793.681,
+    "train_loss": 1.0548812925209943,
+    "train_runtime": 7794.1827,
     "train_samples": 14828,
-    "train_samples_per_second": 5.708,
+    "train_samples_per_second": 5.707,
     "train_steps_per_second": 1.427
 }

trainer_state.json

@@ -10,76 +10,76 @@
     {
       "epoch": 0.27,
       "learning_rate": 9.100800287743908e-06,
-      "loss": 2.8188,
+      "loss": 1.1859,
       "step": 1000
     },
     {
       "epoch": 0.54,
       "learning_rate": 8.201600575487818e-06,
-      "loss": 1.8053,
+      "loss": 1.095,
       "step": 2000
     },
     {
       "epoch": 0.81,
       "learning_rate": 7.3024008632317245e-06,
-      "loss": 1.5897,
+      "loss": 1.0536,
       "step": 3000
     },
     {
       "epoch": 1.08,
       "learning_rate": 6.403201150975632e-06,
-      "loss": 1.4814,
+      "loss": 1.0394,
       "step": 4000
     },
     {
       "epoch": 1.35,
       "learning_rate": 5.50400143871954e-06,
-      "loss": 1.3795,
+      "loss": 1.0087,
       "step": 5000
     },
     {
       "epoch": 1.62,
       "learning_rate": 4.604801726463448e-06,
-      "loss": 1.3396,
+      "loss": 1.0179,
       "step": 6000
     },
     {
       "epoch": 1.89,
       "learning_rate": 3.705602014207356e-06,
-      "loss": 1.2938,
+      "loss": 1.0191,
       "step": 7000
     },
     {
       "epoch": 2.16,
       "learning_rate": 2.806402301951264e-06,
-      "loss": 1.2645,
+      "loss": 1.0278,
       "step": 8000
     },
     {
       "epoch": 2.43,
       "learning_rate": 1.9072025896951715e-06,
-      "loss": 1.2359,
+      "loss": 1.0345,
       "step": 9000
     },
     {
       "epoch": 2.7,
       "learning_rate": 1.0080028774390793e-06,
-      "loss": 1.2172,
+      "loss": 1.0502,
       "step": 10000
     },
     {
       "epoch": 2.97,
       "learning_rate": 1.0880316518298715e-07,
-      "loss": 1.205,
+      "loss": 1.0697,
       "step": 11000
     },
     {
       "epoch": 3.0,
       "step": 11121,
       "total_flos": 4.147380631930061e+16,
-      "train_loss": 1.5083582298156009,
-      "train_runtime": 7793.681,
-      "train_samples_per_second": 5.708,
+      "train_loss": 1.0548812925209943,
+      "train_runtime": 7794.1827,
+      "train_samples_per_second": 5.707,
       "train_steps_per_second": 1.427
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a21949356dc8e894e20a5e23cc4b9ad03bab37ed07c14be91035a352f0b7a0a
+oid sha256:2cae7a945faaf8e89a4059074b4664e2594d2de7b82e3f3e0e2278326df623d1
 size 3119