End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_50_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: 0.8211605345048508
 ---
 
 <!-- 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. -->
 
 # distilbert_lda_50_v1_qnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6988
-- Accuracy: 0.7974
+- Loss: 0.4075
+- Accuracy: 0.8212
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.6933382749557495,
-    "eval_runtime": 2.2772,
+    "epoch": 7.0,
+    "eval_accuracy": 0.8211605345048508,
+    "eval_loss": 0.40745484828948975,
+    "eval_runtime": 2.3058,
     "eval_samples": 5463,
-    "eval_samples_per_second": 2398.986,
-    "eval_steps_per_second": 9.661,
-    "total_flos": 4.162509821227622e+16,
-    "train_loss": 0.6984581427845529,
-    "train_runtime": 603.2834,
+    "eval_samples_per_second": 2369.211,
+    "eval_steps_per_second": 9.541,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.2814387039025071,
+    "train_runtime": 709.1788,
     "train_samples": 104743,
-    "train_samples_per_second": 8681.077,
-    "train_steps_per_second": 33.981
+    "train_samples_per_second": 7384.809,
+    "train_steps_per_second": 28.907
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.6933382749557495,
-    "eval_runtime": 2.2772,
+    "epoch": 7.0,
+    "eval_accuracy": 0.8211605345048508,
+    "eval_loss": 0.40745484828948975,
+    "eval_runtime": 2.3058,
     "eval_samples": 5463,
-    "eval_samples_per_second": 2398.986,
-    "eval_steps_per_second": 9.661
+    "eval_samples_per_second": 2369.211,
+    "eval_steps_per_second": 9.541
 }

logs/events.out.tfevents.1733310363.ki-g0008.1206436.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f967565ea007541f9f7b555af6efc5f6e1038f888a637cc0dfae0287f1d46c5
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "total_flos": 4.162509821227622e+16,
-    "train_loss": 0.6984581427845529,
-    "train_runtime": 603.2834,
+    "epoch": 7.0,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.2814387039025071,
+    "train_runtime": 709.1788,
     "train_samples": 104743,
-    "train_samples_per_second": 8681.077,
-    "train_steps_per_second": 33.981
+    "train_samples_per_second": 7384.809,
+    "train_steps_per_second": 28.907
 }

trainer_state.json

@@ -1,117 +1,133 @@
 {
-  "best_metric": 0.6933382749557495,
-  "best_model_checkpoint": "distilbert_lda_50_v1_qnli/checkpoint-410",
-  "epoch": 6.0,
+  "best_metric": 0.40745484828948975,
+  "best_model_checkpoint": "distilbert_lda_50_v1_qnli/checkpoint-820",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 2460,
+  "global_step": 2870,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.1270582526922226,
-      "learning_rate": 0.00098,
-      "loss": 0.7249,
+      "grad_norm": 3.832184076309204,
+      "learning_rate": 4.9e-05,
+      "loss": 0.5532,
       "step": 410
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 2.2691,
-      "eval_samples_per_second": 2407.557,
-      "eval_steps_per_second": 9.695,
+      "eval_accuracy": 0.7627677100494233,
+      "eval_loss": 0.5176936984062195,
+      "eval_runtime": 2.289,
+      "eval_samples_per_second": 2386.653,
+      "eval_steps_per_second": 9.611,
       "step": 410
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.09046493470668793,
-      "learning_rate": 0.00096,
-      "loss": 0.6932,
+      "grad_norm": 3.9373576641082764,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4263,
       "step": 820
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 2.2549,
-      "eval_samples_per_second": 2422.742,
-      "eval_steps_per_second": 9.757,
+      "eval_accuracy": 0.8211605345048508,
+      "eval_loss": 0.40745484828948975,
+      "eval_runtime": 2.2919,
+      "eval_samples_per_second": 2383.66,
+      "eval_steps_per_second": 9.599,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.1270582526922226,
-      "learning_rate": 0.00094,
-      "loss": 0.6933,
+      "grad_norm": 4.5357537269592285,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3371,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 2.2708,
-      "eval_samples_per_second": 2405.723,
-      "eval_steps_per_second": 9.688,
+      "eval_accuracy": 0.8132894014277869,
+      "eval_loss": 0.4168780446052551,
+      "eval_runtime": 2.3267,
+      "eval_samples_per_second": 2347.919,
+      "eval_steps_per_second": 9.455,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.018296407535672188,
-      "learning_rate": 0.00092,
-      "loss": 0.6931,
+      "grad_norm": 5.284133434295654,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2505,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 2.3027,
-      "eval_samples_per_second": 2372.391,
-      "eval_steps_per_second": 9.554,
+      "eval_accuracy": 0.8116419549697969,
+      "eval_loss": 0.4765816330909729,
+      "eval_runtime": 2.3197,
+      "eval_samples_per_second": 2355.085,
+      "eval_steps_per_second": 9.484,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.047665297985076904,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6932,
+      "grad_norm": 4.09841251373291,
+      "learning_rate": 4.5e-05,
+      "loss": 0.18,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934648156166077,
-      "eval_runtime": 2.2699,
-      "eval_samples_per_second": 2406.754,
-      "eval_steps_per_second": 9.692,
+      "eval_accuracy": 0.7940691927512356,
+      "eval_loss": 0.6080189943313599,
+      "eval_runtime": 2.3468,
+      "eval_samples_per_second": 2327.804,
+      "eval_steps_per_second": 9.374,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.05455218255519867,
-      "learning_rate": 0.00088,
-      "loss": 0.6932,
+      "grad_norm": 5.979333400726318,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1275,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 2.2812,
-      "eval_samples_per_second": 2394.742,
-      "eval_steps_per_second": 9.644,
+      "eval_accuracy": 0.8120080541826835,
+      "eval_loss": 0.676863431930542,
+      "eval_runtime": 2.307,
+      "eval_samples_per_second": 2368.062,
+      "eval_steps_per_second": 9.536,
       "step": 2460
     },
     {
-      "epoch": 6.0,
-      "step": 2460,
-      "total_flos": 4.162509821227622e+16,
-      "train_loss": 0.6984581427845529,
-      "train_runtime": 603.2834,
-      "train_samples_per_second": 8681.077,
-      "train_steps_per_second": 33.981
+      "epoch": 7.0,
+      "grad_norm": 2.858701467514038,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0953,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7973640856672158,
+      "eval_loss": 0.6988027095794678,
+      "eval_runtime": 2.35,
+      "eval_samples_per_second": 2324.65,
+      "eval_steps_per_second": 9.362,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 4.856261458098893e+16,
+      "train_loss": 0.2814387039025071,
+      "train_runtime": 709.1788,
+      "train_samples_per_second": 7384.809,
+      "train_steps_per_second": 28.907
     }
   ],
   "logging_steps": 1,
@@ -140,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.162509821227622e+16,
+  "total_flos": 4.856261458098893e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null