End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_km_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: distilbert_km_100_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.04161454566059593
+    - name: Accuracy
+      type: accuracy
+      value: 0.6922339200973511
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_km_100_v1_cola
 
-This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8330
-- Matthews Correlation: 0.0623
-- Accuracy: 0.6242
+- Loss: 0.6169
+- Matthews Correlation: 0.0416
+- Accuracy: 0.6922
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6922339200973511,
     "eval_loss": 0.6169473528862,
     "eval_matthews_correlation": 0.04161454566059593,
-    "eval_runtime": 0.4447,
+    "eval_runtime": 0.4755,
     "eval_samples": 1043,
-    "eval_samples_per_second": 2345.648,
-    "eval_steps_per_second": 11.245,
+    "eval_samples_per_second": 2193.311,
+    "eval_steps_per_second": 10.514,
     "total_flos": 3964550540676096.0,
     "train_loss": 0.5012591065478926,
-    "train_runtime": 67.3665,
+    "train_runtime": 69.5503,
     "train_samples": 8551,
-    "train_samples_per_second": 6346.625,
-    "train_steps_per_second": 25.235
+    "train_samples_per_second": 6147.346,
+    "train_steps_per_second": 24.443
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6922339200973511,
     "eval_loss": 0.6169473528862,
     "eval_matthews_correlation": 0.04161454566059593,
-    "eval_runtime": 0.4447,
+    "eval_runtime": 0.4755,
     "eval_samples": 1043,
-    "eval_samples_per_second": 2345.648,
-    "eval_steps_per_second": 11.245
+    "eval_samples_per_second": 2193.311,
+    "eval_steps_per_second": 10.514
 }

logs/events.out.tfevents.1744905066.s_005_m.2758941.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad1b001412dc20cb91dc340308c1b248991ab3afad7c1f1cae402767ee5730f
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 3964550540676096.0,
     "train_loss": 0.5012591065478926,
-    "train_runtime": 67.3665,
+    "train_runtime": 69.5503,
     "train_samples": 8551,
-    "train_samples_per_second": 6346.625,
-    "train_steps_per_second": 25.235
+    "train_samples_per_second": 6147.346,
+    "train_steps_per_second": 24.443
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6249494552612305,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.4491,
-      "eval_samples_per_second": 2322.566,
-      "eval_steps_per_second": 11.134,
+      "eval_runtime": 0.4736,
+      "eval_samples_per_second": 2202.362,
+      "eval_steps_per_second": 10.558,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6922339200973511,
       "eval_loss": 0.6169473528862,
       "eval_matthews_correlation": 0.04161454566059593,
-      "eval_runtime": 0.4767,
-      "eval_samples_per_second": 2187.967,
-      "eval_steps_per_second": 10.489,
+      "eval_runtime": 0.4532,
+      "eval_samples_per_second": 2301.551,
+      "eval_steps_per_second": 11.033,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6759347915649414,
       "eval_loss": 0.6248862147331238,
       "eval_matthews_correlation": 0.011699922380397933,
-      "eval_runtime": 0.4547,
-      "eval_samples_per_second": 2293.723,
-      "eval_steps_per_second": 10.996,
+      "eval_runtime": 0.4365,
+      "eval_samples_per_second": 2389.408,
+      "eval_steps_per_second": 11.454,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.668264627456665,
       "eval_loss": 0.6789613962173462,
       "eval_matthews_correlation": 0.038543911507921406,
-      "eval_runtime": 0.4505,
-      "eval_samples_per_second": 2315.439,
-      "eval_steps_per_second": 11.1,
+      "eval_runtime": 0.444,
+      "eval_samples_per_second": 2348.877,
+      "eval_steps_per_second": 11.26,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6481304168701172,
       "eval_loss": 0.6883048415184021,
       "eval_matthews_correlation": 0.09717976180510585,
-      "eval_runtime": 0.4421,
-      "eval_samples_per_second": 2359.348,
-      "eval_steps_per_second": 11.31,
+      "eval_runtime": 0.47,
+      "eval_samples_per_second": 2219.285,
+      "eval_steps_per_second": 10.639,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6452540755271912,
       "eval_loss": 0.7564204335212708,
       "eval_matthews_correlation": 0.07687488069091071,
-      "eval_runtime": 0.462,
-      "eval_samples_per_second": 2257.566,
-      "eval_steps_per_second": 10.822,
+      "eval_runtime": 0.4442,
+      "eval_samples_per_second": 2347.831,
+      "eval_steps_per_second": 11.255,
       "step": 204
     },
     {
@@ -123,9 +123,9 @@
       "eval_accuracy": 0.6241610646247864,
       "eval_loss": 0.8330209255218506,
       "eval_matthews_correlation": 0.06232025777801515,
-      "eval_runtime": 0.4472,
-      "eval_samples_per_second": 2332.286,
-      "eval_steps_per_second": 11.181,
+      "eval_runtime": 0.448,
+      "eval_samples_per_second": 2327.951,
+      "eval_steps_per_second": 11.16,
       "step": 238
     },
     {
@@ -133,9 +133,9 @@
       "step": 238,
       "total_flos": 3964550540676096.0,
       "train_loss": 0.5012591065478926,
-      "train_runtime": 67.3665,
-      "train_samples_per_second": 6346.625,
-      "train_steps_per_second": 25.235
+      "train_runtime": 69.5503,
+      "train_samples_per_second": 6147.346,
+      "train_steps_per_second": 24.443
     }
   ],
   "logging_steps": 1,