End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: gpl-3.0
+base_model: ckiplab/bert-base-chinese
 tags:
 - generated_from_trainer
 model-index:
@@ -11,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [ckiplab/bert-base-chinese](https://huggingface.co/ckiplab/bert-base-chinese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.5963
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 100.0,
-    "eval_loss": 0.054326437413692474,
-    "eval_runtime": 3.844,
-    "eval_samples_per_second": 326.223,
-    "eval_steps_per_second": 3.382,
+    "eval_loss": 7.596293926239014,
+    "eval_runtime": 2.0803,
+    "eval_samples_per_second": 344.176,
+    "eval_steps_per_second": 2.884,
     "total_flos": 1.6588112479488e+16,
-    "train_loss": 0.4321923828125,
-    "train_runtime": 849.2414,
-    "train_samples_per_second": 147.661,
-    "train_steps_per_second": 1.884
+    "train_loss": 0.5603914216160775,
+    "train_runtime": 845.3181,
+    "train_samples_per_second": 148.347,
+    "train_steps_per_second": 1.893
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 100.0,
-    "eval_loss": 0.054326437413692474,
-    "eval_runtime": 3.844,
-    "eval_samples_per_second": 326.223,
-    "eval_steps_per_second": 3.382
+    "eval_loss": 7.596293926239014,
+    "eval_runtime": 2.0803,
+    "eval_samples_per_second": 344.176,
+    "eval_steps_per_second": 2.884
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 100.0,
     "total_flos": 1.6588112479488e+16,
-    "train_loss": 0.4321923828125,
-    "train_runtime": 849.2414,
-    "train_samples_per_second": 147.661,
-    "train_steps_per_second": 1.884
+    "train_loss": 0.5603914216160775,
+    "train_runtime": 845.3181,
+    "train_samples_per_second": 148.347,
+    "train_steps_per_second": 1.893
 }

trainer_state.json

@@ -10,33 +10,33 @@
   "log_history": [
     {
       "epoch": 31.25,
-      "grad_norm": 1.9496452808380127,
+      "grad_norm": 4.7310919761657715,
       "learning_rate": 3.4375e-05,
-      "loss": 1.2881,
+      "loss": 1.633,
       "step": 500
     },
     {
       "epoch": 62.5,
-      "grad_norm": 0.6210575699806213,
+      "grad_norm": 1.100446105003357,
       "learning_rate": 1.8750000000000002e-05,
-      "loss": 0.0667,
+      "loss": 0.1162,
       "step": 1000
     },
     {
       "epoch": 93.75,
-      "grad_norm": 0.8036883473396301,
+      "grad_norm": 0.6620476841926575,
       "learning_rate": 3.125e-06,
-      "loss": 0.0245,
+      "loss": 0.0385,
       "step": 1500
     },
     {
       "epoch": 100.0,
       "step": 1600,
       "total_flos": 1.6588112479488e+16,
-      "train_loss": 0.4321923828125,
-      "train_runtime": 849.2414,
-      "train_samples_per_second": 147.661,
-      "train_steps_per_second": 1.884
+      "train_loss": 0.5603914216160775,
+      "train_runtime": 845.3181,
+      "train_samples_per_second": 148.347,
+      "train_steps_per_second": 1.893
     }
   ],
   "logging_steps": 500,