End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_10_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_rand_10_v2_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6218195130880468
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_10_v2_qnli
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0601
-- Accuracy: 0.5973
+- Loss: 0.6458
+- Accuracy: 0.6218
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 7.0,
     "eval_accuracy": 0.6218195130880468,
     "eval_loss": 0.6458103060722351,
-    "eval_runtime": 1.5759,
+    "eval_runtime": 1.5854,
     "eval_samples": 5463,
-    "eval_samples_per_second": 3466.588,
-    "eval_steps_per_second": 13.96,
+    "eval_samples_per_second": 3445.79,
+    "eval_steps_per_second": 13.877,
     "total_flos": 1.922715369529651e+16,
-    "train_loss": 0.521182724158523,
-    "train_runtime": 397.0763,
+    "train_loss": 0.5211214391196647,
+    "train_runtime": 400.0726,
     "train_samples": 104743,
-    "train_samples_per_second": 13189.279,
-    "train_steps_per_second": 51.627
+    "train_samples_per_second": 13090.498,
+    "train_steps_per_second": 51.241
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "eval_accuracy": 0.6218195130880468,
     "eval_loss": 0.6458103060722351,
-    "eval_runtime": 1.5759,
+    "eval_runtime": 1.5854,
     "eval_samples": 5463,
-    "eval_samples_per_second": 3466.588,
-    "eval_steps_per_second": 13.96
+    "eval_samples_per_second": 3445.79,
+    "eval_steps_per_second": 13.877
 }

logs/events.out.tfevents.1745307862.s_005_m.2850172.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7df05aa0d17de1938ac4e3113f749dd4ad9a4e31f29a9ec9d1df041d468dfa
+size 363

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 1.922715369529651e+16,
-    "train_loss": 0.521182724158523,
-    "train_runtime": 397.0763,
+    "train_loss": 0.5211214391196647,
+    "train_runtime": 400.0726,
     "train_samples": 104743,
-    "train_samples_per_second": 13189.279,
-    "train_steps_per_second": 51.627
+    "train_samples_per_second": 13090.498,
+    "train_steps_per_second": 51.241
 }

trainer_state.json

@@ -20,9 +20,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.6201720666300568,
       "eval_loss": 0.6485046148300171,
-      "eval_runtime": 1.5703,
-      "eval_samples_per_second": 3478.947,
-      "eval_steps_per_second": 14.01,
+      "eval_runtime": 1.6382,
+      "eval_samples_per_second": 3334.701,
+      "eval_steps_per_second": 13.429,
       "step": 410
     },
     {
@@ -36,99 +36,99 @@
       "epoch": 2.0,
       "eval_accuracy": 0.6218195130880468,
       "eval_loss": 0.6458103060722351,
-      "eval_runtime": 1.5605,
-      "eval_samples_per_second": 3500.742,
-      "eval_steps_per_second": 14.098,
+      "eval_runtime": 1.5547,
+      "eval_samples_per_second": 3513.962,
+      "eval_steps_per_second": 14.151,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 2.3196091651916504,
+      "grad_norm": 2.337428569793701,
       "learning_rate": 4.7e-05,
-      "loss": 0.594,
+      "loss": 0.5941,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6238330587589237,
-      "eval_loss": 0.6675131916999817,
-      "eval_runtime": 1.5875,
-      "eval_samples_per_second": 3441.203,
-      "eval_steps_per_second": 13.858,
+      "eval_accuracy": 0.6231008603331503,
+      "eval_loss": 0.6681211590766907,
+      "eval_runtime": 1.5513,
+      "eval_samples_per_second": 3521.628,
+      "eval_steps_per_second": 14.182,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 2.5276989936828613,
+      "grad_norm": 2.5682601928710938,
       "learning_rate": 4.600000000000001e-05,
       "loss": 0.5378,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6183415705656233,
-      "eval_loss": 0.6989854574203491,
-      "eval_runtime": 1.5603,
-      "eval_samples_per_second": 3501.193,
-      "eval_steps_per_second": 14.1,
+      "eval_accuracy": 0.6198059674171701,
+      "eval_loss": 0.7004396915435791,
+      "eval_runtime": 1.5729,
+      "eval_samples_per_second": 3473.155,
+      "eval_steps_per_second": 13.987,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 3.2850587368011475,
+      "grad_norm": 3.3654308319091797,
       "learning_rate": 4.5e-05,
-      "loss": 0.4719,
+      "loss": 0.4716,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.613948380010983,
-      "eval_loss": 0.8101333975791931,
-      "eval_runtime": 1.5459,
-      "eval_samples_per_second": 3533.951,
-      "eval_steps_per_second": 14.232,
+      "eval_accuracy": 0.6159619256818598,
+      "eval_loss": 0.8119640946388245,
+      "eval_runtime": 1.567,
+      "eval_samples_per_second": 3486.19,
+      "eval_steps_per_second": 14.039,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 4.961696624755859,
+      "grad_norm": 5.089620590209961,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.4033,
+      "loss": 0.4032,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6086399414241259,
-      "eval_loss": 0.9288338422775269,
-      "eval_runtime": 1.5731,
-      "eval_samples_per_second": 3472.797,
-      "eval_steps_per_second": 13.985,
+      "eval_accuracy": 0.6075416437854658,
+      "eval_loss": 0.9388319253921509,
+      "eval_runtime": 1.592,
+      "eval_samples_per_second": 3431.577,
+      "eval_steps_per_second": 13.819,
       "step": 2460
     },
     {
       "epoch": 7.0,
-      "grad_norm": 5.6496782302856445,
+      "grad_norm": 5.411346435546875,
       "learning_rate": 4.3e-05,
-      "loss": 0.3409,
+      "loss": 0.3408,
       "step": 2870
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5980230642504119,
-      "eval_loss": 1.0519371032714844,
-      "eval_runtime": 1.5521,
-      "eval_samples_per_second": 3519.723,
-      "eval_steps_per_second": 14.174,
+      "eval_accuracy": 0.5972908658246385,
+      "eval_loss": 1.0600956678390503,
+      "eval_runtime": 1.5662,
+      "eval_samples_per_second": 3487.966,
+      "eval_steps_per_second": 14.046,
       "step": 2870
     },
     {
       "epoch": 7.0,
       "step": 2870,
       "total_flos": 1.922715369529651e+16,
-      "train_loss": 0.521182724158523,
-      "train_runtime": 397.0763,
-      "train_samples_per_second": 13189.279,
-      "train_steps_per_second": 51.627
+      "train_loss": 0.5211214391196647,
+      "train_runtime": 400.0726,
+      "train_samples_per_second": 13090.498,
+      "train_steps_per_second": 51.241
     }
   ],
   "logging_steps": 1,