End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_lda_100_v1_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8599554786049963
+    - name: F1
+      type: f1
+      value: 0.8240412704332154
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_100_v1_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4037
-- Accuracy: 0.8788
-- F1: 0.8427
-- Combined Score: 0.8608
+- Loss: 0.3133
+- Accuracy: 0.8600
+- F1: 0.8240
+- Combined Score: 0.8420
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 8.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6569345593452454,
-    "eval_runtime": 17.0276,
+    "epoch": 7.0,
+    "eval_accuracy": 0.8599554786049963,
+    "eval_combined_score": 0.8419983745191059,
+    "eval_f1": 0.8240412704332154,
+    "eval_loss": 0.31332626938819885,
+    "eval_runtime": 17.0752,
     "eval_samples": 40430,
-    "eval_samples_per_second": 2374.384,
-    "eval_steps_per_second": 9.279,
-    "total_flos": 1.927909325255639e+17,
-    "train_loss": 0.6596396455617226,
-    "train_runtime": 2840.4842,
+    "eval_samples_per_second": 2367.756,
+    "eval_steps_per_second": 9.253,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.20531803780299535,
+    "train_runtime": 2492.9036,
     "train_samples": 363846,
-    "train_samples_per_second": 6404.647,
-    "train_steps_per_second": 25.031
+    "train_samples_per_second": 7297.635,
+    "train_steps_per_second": 28.521
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 8.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6569345593452454,
-    "eval_runtime": 17.0276,
+    "epoch": 7.0,
+    "eval_accuracy": 0.8599554786049963,
+    "eval_combined_score": 0.8419983745191059,
+    "eval_f1": 0.8240412704332154,
+    "eval_loss": 0.31332626938819885,
+    "eval_runtime": 17.0752,
     "eval_samples": 40430,
-    "eval_samples_per_second": 2374.384,
-    "eval_steps_per_second": 9.279
+    "eval_samples_per_second": 2367.756,
+    "eval_steps_per_second": 9.253
 }

logs/events.out.tfevents.1733320516.ki-g0008.1206436.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161c26e77b1dff9fbe87b3ea7ff0c89103f93210b5458d38ac91257f581b1d80
+size 515

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 8.0,
-    "total_flos": 1.927909325255639e+17,
-    "train_loss": 0.6596396455617226,
-    "train_runtime": 2840.4842,
+    "epoch": 7.0,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.20531803780299535,
+    "train_runtime": 2492.9036,
     "train_samples": 363846,
-    "train_samples_per_second": 6404.647,
-    "train_steps_per_second": 25.031
+    "train_samples_per_second": 7297.635,
+    "train_steps_per_second": 28.521
 }

trainer_state.json

@@ -1,165 +1,147 @@
 {
-  "best_metric": 0.6569345593452454,
-  "best_model_checkpoint": "distilbert_lda_100_v1_qqp/checkpoint-4266",
-  "epoch": 8.0,
+  "best_metric": 0.31332626938819885,
+  "best_model_checkpoint": "distilbert_lda_100_v1_qqp/checkpoint-2844",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 11376,
+  "global_step": 9954,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.2662235498428345,
-      "learning_rate": 0.00098,
-      "loss": 0.667,
+      "grad_norm": 2.956484794616699,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4043,
       "step": 1422
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6585862040519714,
-      "eval_runtime": 16.9764,
-      "eval_samples_per_second": 2381.542,
-      "eval_steps_per_second": 9.307,
+      "eval_accuracy": 0.8511006678209251,
+      "eval_combined_score": 0.8251500670658996,
+      "eval_f1": 0.7991994663108739,
+      "eval_loss": 0.32754120230674744,
+      "eval_runtime": 17.107,
+      "eval_samples_per_second": 2363.359,
+      "eval_steps_per_second": 9.236,
       "step": 1422
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.10064509510993958,
-      "learning_rate": 0.00096,
-      "loss": 0.659,
+      "grad_norm": 4.963893413543701,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2918,
       "step": 2844
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6569439768791199,
-      "eval_runtime": 17.3915,
-      "eval_samples_per_second": 2324.697,
-      "eval_steps_per_second": 9.085,
+      "eval_accuracy": 0.8599554786049963,
+      "eval_combined_score": 0.8419983745191059,
+      "eval_f1": 0.8240412704332154,
+      "eval_loss": 0.31332626938819885,
+      "eval_runtime": 17.2399,
+      "eval_samples_per_second": 2345.134,
+      "eval_steps_per_second": 9.165,
       "step": 2844
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.05541796237230301,
-      "learning_rate": 0.00094,
-      "loss": 0.6585,
+      "grad_norm": 3.0235133171081543,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2305,
       "step": 4266
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6569345593452454,
-      "eval_runtime": 17.0052,
-      "eval_samples_per_second": 2377.504,
-      "eval_steps_per_second": 9.291,
+      "eval_accuracy": 0.8714568389809547,
+      "eval_combined_score": 0.852738415977335,
+      "eval_f1": 0.8340199929737153,
+      "eval_loss": 0.3146589696407318,
+      "eval_runtime": 17.2803,
+      "eval_samples_per_second": 2339.665,
+      "eval_steps_per_second": 9.143,
       "step": 4266
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.0837196335196495,
-      "learning_rate": 0.00092,
-      "loss": 0.6585,
+      "grad_norm": 3.2095916271209717,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.179,
       "step": 5688
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 17.1979,
-      "eval_samples_per_second": 2350.873,
-      "eval_steps_per_second": 9.187,
+      "eval_accuracy": 0.8760079149146673,
+      "eval_combined_score": 0.8519556894083102,
+      "eval_f1": 0.8279034639019532,
+      "eval_loss": 0.31782716512680054,
+      "eval_runtime": 17.1901,
+      "eval_samples_per_second": 2351.932,
+      "eval_steps_per_second": 9.191,
       "step": 5688
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.12371832132339478,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6585,
+      "grad_norm": 2.359029531478882,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1389,
       "step": 7110
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 16.9747,
-      "eval_samples_per_second": 2381.777,
-      "eval_steps_per_second": 9.308,
+      "eval_accuracy": 0.8804600544150384,
+      "eval_combined_score": 0.8585003961999769,
+      "eval_f1": 0.8365407379849155,
+      "eval_loss": 0.3524511456489563,
+      "eval_runtime": 17.2563,
+      "eval_samples_per_second": 2342.907,
+      "eval_steps_per_second": 9.156,
       "step": 7110
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.04144879803061485,
-      "learning_rate": 0.00088,
-      "loss": 0.6586,
+      "grad_norm": 2.7366631031036377,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1067,
       "step": 8532
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6577603816986084,
-      "eval_runtime": 17.1651,
-      "eval_samples_per_second": 2355.356,
-      "eval_steps_per_second": 9.205,
+      "eval_accuracy": 0.8782587187731882,
+      "eval_combined_score": 0.8595780276048511,
+      "eval_f1": 0.8408973364365141,
+      "eval_loss": 0.3905220925807953,
+      "eval_runtime": 17.273,
+      "eval_samples_per_second": 2340.65,
+      "eval_steps_per_second": 9.147,
       "step": 8532
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.050063714385032654,
-      "learning_rate": 0.00086,
-      "loss": 0.6585,
+      "grad_norm": 4.230625629425049,
+      "learning_rate": 4.3e-05,
+      "loss": 0.086,
       "step": 9954
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 17.1073,
-      "eval_samples_per_second": 2363.321,
-      "eval_steps_per_second": 9.236,
+      "eval_accuracy": 0.8788276032649023,
+      "eval_combined_score": 0.8607857401295461,
+      "eval_f1": 0.84274387699419,
+      "eval_loss": 0.4037318527698517,
+      "eval_runtime": 17.1931,
+      "eval_samples_per_second": 2351.532,
+      "eval_steps_per_second": 9.19,
       "step": 9954
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.11186650395393372,
-      "learning_rate": 0.00084,
-      "loss": 0.6586,
-      "step": 11376
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 17.0733,
-      "eval_samples_per_second": 2368.021,
-      "eval_steps_per_second": 9.254,
-      "step": 11376
-    },
-    {
-      "epoch": 8.0,
-      "step": 11376,
-      "total_flos": 1.927909325255639e+17,
-      "train_loss": 0.6596396455617226,
-      "train_runtime": 2840.4842,
-      "train_samples_per_second": 6404.647,
-      "train_steps_per_second": 25.031
+      "epoch": 7.0,
+      "step": 9954,
+      "total_flos": 1.686920659598684e+17,
+      "train_loss": 0.20531803780299535,
+      "train_runtime": 2492.9036,
+      "train_samples_per_second": 7297.635,
+      "train_steps_per_second": 28.521
     }
   ],
   "logging_steps": 1,
@@ -188,7 +170,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.927909325255639e+17,
+  "total_flos": 1.686920659598684e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null