End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_rand_100_v1_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6362804319970712
 ---
 
 <!-- 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. -->
 
 # bert_base_rand_100_v1_qnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2076
-- Accuracy: 0.6334
+- Loss: 0.6374
+- Accuracy: 0.6363
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.6370126304228446,
-    "eval_loss": 0.6337587833404541,
-    "eval_runtime": 3.4214,
+    "eval_accuracy": 0.6362804319970712,
+    "eval_loss": 0.6373825073242188,
+    "eval_runtime": 3.4251,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1596.692,
-    "eval_steps_per_second": 6.43,
+    "eval_samples_per_second": 1595.012,
+    "eval_steps_per_second": 6.423,
     "total_flos": 9.645664445050368e+16,
-    "train_loss": 0.43505343659829593,
-    "train_runtime": 1216.3776,
+    "train_loss": 0.4347643011538409,
+    "train_runtime": 1213.7649,
     "train_samples": 104743,
-    "train_samples_per_second": 4305.53,
-    "train_steps_per_second": 16.853
+    "train_samples_per_second": 4314.798,
+    "train_steps_per_second": 16.89
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.6370126304228446,
-    "eval_loss": 0.6337587833404541,
-    "eval_runtime": 3.4214,
+    "eval_accuracy": 0.6362804319970712,
+    "eval_loss": 0.6373825073242188,
+    "eval_runtime": 3.4251,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1596.692,
-    "eval_steps_per_second": 6.43
+    "eval_samples_per_second": 1595.012,
+    "eval_steps_per_second": 6.423
 }

logs/events.out.tfevents.1745184425.s_005_m.2815556.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba347e513db3b36536af978c358268ccdfeecfdd8519262155d1c78e84cab8ba
+size 363

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 9.645664445050368e+16,
-    "train_loss": 0.43505343659829593,
-    "train_runtime": 1216.3776,
+    "train_loss": 0.4347643011538409,
+    "train_runtime": 1213.7649,
     "train_samples": 104743,
-    "train_samples_per_second": 4305.53,
-    "train_steps_per_second": 16.853
+    "train_samples_per_second": 4314.798,
+    "train_steps_per_second": 16.89
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 820,
-  "best_metric": 0.6337587833404541,
+  "best_metric": 0.6373825073242188,
   "best_model_checkpoint": "bert_base_rand_100_v1_qnli/checkpoint-820",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -11,124 +11,124 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.0978119373321533,
+      "grad_norm": 2.113560676574707,
       "learning_rate": 4.9e-05,
       "loss": 0.6632,
       "step": 410
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6220025626944902,
-      "eval_loss": 0.6431590914726257,
-      "eval_runtime": 3.4725,
-      "eval_samples_per_second": 1573.217,
-      "eval_steps_per_second": 6.335,
+      "eval_accuracy": 0.6205381658429434,
+      "eval_loss": 0.643620491027832,
+      "eval_runtime": 3.5132,
+      "eval_samples_per_second": 1554.985,
+      "eval_steps_per_second": 6.262,
       "step": 410
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.5537503957748413,
+      "grad_norm": 1.5749682188034058,
       "learning_rate": 4.8e-05,
-      "loss": 0.6244,
+      "loss": 0.6248,
       "step": 820
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6370126304228446,
-      "eval_loss": 0.6337587833404541,
-      "eval_runtime": 3.4189,
-      "eval_samples_per_second": 1597.881,
-      "eval_steps_per_second": 6.435,
+      "eval_accuracy": 0.6362804319970712,
+      "eval_loss": 0.6373825073242188,
+      "eval_runtime": 3.4184,
+      "eval_samples_per_second": 1598.129,
+      "eval_steps_per_second": 6.436,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 2.911444664001465,
+      "grad_norm": 3.1714890003204346,
       "learning_rate": 4.7e-05,
-      "loss": 0.561,
+      "loss": 0.5616,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6351821343584111,
-      "eval_loss": 0.6733267903327942,
-      "eval_runtime": 3.4105,
-      "eval_samples_per_second": 1601.811,
-      "eval_steps_per_second": 6.451,
+      "eval_accuracy": 0.6390261760937214,
+      "eval_loss": 0.6837719082832336,
+      "eval_runtime": 3.4053,
+      "eval_samples_per_second": 1604.257,
+      "eval_steps_per_second": 6.46,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 3.900480270385742,
+      "grad_norm": 3.8961050510406494,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 0.4574,
+      "loss": 0.4586,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6468973091707853,
-      "eval_loss": 0.715512216091156,
-      "eval_runtime": 3.4192,
-      "eval_samples_per_second": 1597.753,
-      "eval_steps_per_second": 6.434,
+      "eval_accuracy": 0.6470803587772286,
+      "eval_loss": 0.7240437865257263,
+      "eval_runtime": 3.4148,
+      "eval_samples_per_second": 1599.799,
+      "eval_steps_per_second": 6.443,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 7.243943214416504,
+      "grad_norm": 7.140533924102783,
       "learning_rate": 4.5e-05,
-      "loss": 0.3358,
+      "loss": 0.3339,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6410397217645982,
-      "eval_loss": 0.864467203617096,
-      "eval_runtime": 3.416,
-      "eval_samples_per_second": 1599.235,
-      "eval_steps_per_second": 6.44,
+      "eval_accuracy": 0.6359143327841845,
+      "eval_loss": 0.831567108631134,
+      "eval_runtime": 3.4331,
+      "eval_samples_per_second": 1591.251,
+      "eval_steps_per_second": 6.408,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 6.885410308837891,
+      "grad_norm": 5.499217987060547,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.2353,
+      "loss": 0.2351,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.637195680029288,
-      "eval_loss": 1.0367809534072876,
-      "eval_runtime": 3.4173,
-      "eval_samples_per_second": 1598.617,
-      "eval_steps_per_second": 6.438,
+      "eval_accuracy": 0.6322533406553176,
+      "eval_loss": 1.0066131353378296,
+      "eval_runtime": 3.4113,
+      "eval_samples_per_second": 1601.464,
+      "eval_steps_per_second": 6.449,
       "step": 2460
     },
     {
       "epoch": 7.0,
-      "grad_norm": 8.375223159790039,
+      "grad_norm": 7.18892240524292,
       "learning_rate": 4.3e-05,
-      "loss": 0.1682,
+      "loss": 0.1661,
       "step": 2870
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.633534687900421,
-      "eval_loss": 1.0254089832305908,
-      "eval_runtime": 3.4225,
-      "eval_samples_per_second": 1596.224,
-      "eval_steps_per_second": 6.428,
+      "eval_accuracy": 0.6333516382939777,
+      "eval_loss": 1.2076168060302734,
+      "eval_runtime": 3.4291,
+      "eval_samples_per_second": 1593.149,
+      "eval_steps_per_second": 6.416,
       "step": 2870
     },
     {
       "epoch": 7.0,
       "step": 2870,
       "total_flos": 9.645664445050368e+16,
-      "train_loss": 0.43505343659829593,
-      "train_runtime": 1216.3776,
-      "train_samples_per_second": 4305.53,
-      "train_steps_per_second": 16.853
+      "train_loss": 0.4347643011538409,
+      "train_runtime": 1213.7649,
+      "train_samples_per_second": 4314.798,
+      "train_steps_per_second": 16.89
     }
   ],
   "logging_steps": 1,