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_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7355573637103336
 ---
 
 <!-- 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_mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9725
-- Accuracy: 0.7280
+- Loss: 0.6377
+- Accuracy: 0.7356
 
 ## Model description
 

all_results.json

@@ -1,22 +1,22 @@
 {
-    "epoch": 14.0,
-    "epoch_mm": 14.0,
-    "eval_accuracy": 0.3273560876209883,
-    "eval_accuracy_mm": 0.3295362082994304,
-    "eval_loss": 1.0962358713150024,
-    "eval_loss_mm": 1.0962363481521606,
-    "eval_runtime": 4.0763,
-    "eval_runtime_mm": 4.1679,
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7335710646968925,
+    "eval_accuracy_mm": 0.7355573637103336,
+    "eval_loss": 0.6567384004592896,
+    "eval_loss_mm": 0.6376878023147583,
+    "eval_runtime": 4.1853,
+    "eval_runtime_mm": 4.1351,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 2407.848,
-    "eval_samples_per_second_mm": 2358.953,
-    "eval_steps_per_second": 9.568,
-    "eval_steps_per_second_mm": 9.357,
-    "total_flos": 3.6414798065552794e+17,
-    "train_loss": 1.098874776140008,
-    "train_runtime": 5133.237,
+    "eval_samples_per_second": 2345.14,
+    "eval_samples_per_second_mm": 2377.695,
+    "eval_steps_per_second": 9.318,
+    "eval_steps_per_second_mm": 9.431,
+    "total_flos": 2.080845603745874e+17,
+    "train_loss": 0.479245346248383,
+    "train_runtime": 2964.6777,
     "train_samples": 392702,
-    "train_samples_per_second": 3825.091,
-    "train_steps_per_second": 14.942
+    "train_samples_per_second": 6623.013,
+    "train_steps_per_second": 25.871
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 14.0,
-    "epoch_mm": 14.0,
-    "eval_accuracy": 0.3273560876209883,
-    "eval_accuracy_mm": 0.3295362082994304,
-    "eval_loss": 1.0962358713150024,
-    "eval_loss_mm": 1.0962363481521606,
-    "eval_runtime": 4.0763,
-    "eval_runtime_mm": 4.1679,
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7335710646968925,
+    "eval_accuracy_mm": 0.7355573637103336,
+    "eval_loss": 0.6567384004592896,
+    "eval_loss_mm": 0.6376878023147583,
+    "eval_runtime": 4.1853,
+    "eval_runtime_mm": 4.1351,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 2407.848,
-    "eval_samples_per_second_mm": 2358.953,
-    "eval_steps_per_second": 9.568,
-    "eval_steps_per_second_mm": 9.357
+    "eval_samples_per_second": 2345.14,
+    "eval_samples_per_second_mm": 2377.695,
+    "eval_steps_per_second": 9.318,
+    "eval_steps_per_second_mm": 9.431
 }

logs/events.out.tfevents.1733316837.ki-g0008.1206436.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00754c53468f10e7a53cd947e5589583bbc1714d788402c752876b97f199bc8
+size 734

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 14.0,
-    "total_flos": 3.6414798065552794e+17,
-    "train_loss": 1.098874776140008,
-    "train_runtime": 5133.237,
+    "epoch": 8.0,
+    "total_flos": 2.080845603745874e+17,
+    "train_loss": 0.479245346248383,
+    "train_runtime": 2964.6777,
     "train_samples": 392702,
-    "train_samples_per_second": 3825.091,
-    "train_steps_per_second": 14.942
+    "train_samples_per_second": 6623.013,
+    "train_steps_per_second": 25.871
 }

trainer_state.json

@@ -1,245 +1,149 @@
 {
-  "best_metric": 1.0962358713150024,
-  "best_model_checkpoint": "distilbert_lda_50_v1_mnli/checkpoint-13806",
-  "epoch": 14.0,
+  "best_metric": 0.6567384004592896,
+  "best_model_checkpoint": "distilbert_lda_50_v1_mnli/checkpoint-4602",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 21476,
+  "global_step": 12272,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.02029508352279663,
-      "learning_rate": 0.00098,
-      "loss": 1.1024,
+      "grad_norm": 2.3023266792297363,
+      "learning_rate": 4.9e-05,
+      "loss": 0.8292,
       "step": 1534
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0992883443832397,
-      "eval_runtime": 4.1317,
-      "eval_samples_per_second": 2375.563,
-      "eval_steps_per_second": 9.439,
+      "eval_accuracy": 0.6905756495160469,
+      "eval_loss": 0.7242587208747864,
+      "eval_runtime": 4.1868,
+      "eval_samples_per_second": 2344.298,
+      "eval_steps_per_second": 9.315,
       "step": 1534
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.11782866716384888,
-      "learning_rate": 0.00096,
-      "loss": 1.0986,
+      "grad_norm": 1.6002289056777954,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6692,
       "step": 3068
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0987216234207153,
-      "eval_runtime": 4.138,
-      "eval_samples_per_second": 2371.933,
-      "eval_steps_per_second": 9.425,
+      "eval_accuracy": 0.7184921039225675,
+      "eval_loss": 0.6628246307373047,
+      "eval_runtime": 4.2185,
+      "eval_samples_per_second": 2326.655,
+      "eval_steps_per_second": 9.245,
       "step": 3068
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.038195185363292694,
-      "learning_rate": 0.00094,
-      "loss": 1.0987,
+      "grad_norm": 2.015767812728882,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5756,
       "step": 4602
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0989333391189575,
-      "eval_runtime": 4.1583,
-      "eval_samples_per_second": 2360.317,
-      "eval_steps_per_second": 9.379,
+      "eval_accuracy": 0.7335710646968925,
+      "eval_loss": 0.6567384004592896,
+      "eval_runtime": 4.2186,
+      "eval_samples_per_second": 2326.613,
+      "eval_steps_per_second": 9.245,
       "step": 4602
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.062206000089645386,
-      "learning_rate": 0.00092,
-      "loss": 1.0986,
+      "grad_norm": 2.5160274505615234,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4939,
       "step": 6136
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.10163414478302,
-      "eval_runtime": 4.0968,
-      "eval_samples_per_second": 2395.767,
-      "eval_steps_per_second": 9.52,
+      "eval_accuracy": 0.7320427916454406,
+      "eval_loss": 0.6775555610656738,
+      "eval_runtime": 4.1905,
+      "eval_samples_per_second": 2342.201,
+      "eval_steps_per_second": 9.307,
       "step": 6136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.07343439757823944,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 1.0985,
+      "grad_norm": 2.3854494094848633,
+      "learning_rate": 4.5e-05,
+      "loss": 0.414,
       "step": 7670
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0988649129867554,
-      "eval_runtime": 4.2047,
-      "eval_samples_per_second": 2334.293,
-      "eval_steps_per_second": 9.275,
+      "eval_accuracy": 0.7373408048904737,
+      "eval_loss": 0.6913235187530518,
+      "eval_runtime": 4.185,
+      "eval_samples_per_second": 2345.269,
+      "eval_steps_per_second": 9.319,
       "step": 7670
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.047856856137514114,
-      "learning_rate": 0.00088,
-      "loss": 1.0987,
+      "grad_norm": 2.9510507583618164,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3422,
       "step": 9204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0988649129867554,
-      "eval_runtime": 4.1454,
-      "eval_samples_per_second": 2367.71,
-      "eval_steps_per_second": 9.408,
+      "eval_accuracy": 0.7314314824248599,
+      "eval_loss": 0.7808761596679688,
+      "eval_runtime": 4.2144,
+      "eval_samples_per_second": 2328.947,
+      "eval_steps_per_second": 9.254,
       "step": 9204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.0791020318865776,
-      "learning_rate": 0.00086,
-      "loss": 1.0985,
+      "grad_norm": 2.713484048843384,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2807,
       "step": 10738
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.0968025922775269,
-      "eval_runtime": 4.0855,
-      "eval_samples_per_second": 2402.388,
-      "eval_steps_per_second": 9.546,
+      "eval_accuracy": 0.7349974528782476,
+      "eval_loss": 0.8293947577476501,
+      "eval_runtime": 4.1995,
+      "eval_samples_per_second": 2337.177,
+      "eval_steps_per_second": 9.287,
       "step": 10738
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.016667626798152924,
-      "learning_rate": 0.00084,
-      "loss": 1.0986,
+      "grad_norm": 3.71089506149292,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2292,
       "step": 12272
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.0990766286849976,
-      "eval_runtime": 4.2035,
-      "eval_samples_per_second": 2334.953,
-      "eval_steps_per_second": 9.278,
+      "eval_accuracy": 0.7279673968415691,
+      "eval_loss": 0.9724929928779602,
+      "eval_runtime": 4.2505,
+      "eval_samples_per_second": 2309.13,
+      "eval_steps_per_second": 9.175,
       "step": 12272
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.006651591043919325,
-      "learning_rate": 0.00082,
-      "loss": 1.0988,
-      "step": 13806
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0962358713150024,
-      "eval_runtime": 4.1757,
-      "eval_samples_per_second": 2350.501,
-      "eval_steps_per_second": 9.34,
-      "step": 13806
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.045499037951231,
-      "learning_rate": 0.0008,
-      "loss": 1.0986,
-      "step": 15340
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0992168188095093,
-      "eval_runtime": 4.1657,
-      "eval_samples_per_second": 2356.14,
-      "eval_steps_per_second": 9.362,
-      "step": 15340
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.009605828672647476,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 1.0986,
-      "step": 16874
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0990049839019775,
-      "eval_runtime": 4.099,
-      "eval_samples_per_second": 2394.463,
-      "eval_steps_per_second": 9.514,
-      "step": 16874
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.03646823763847351,
-      "learning_rate": 0.00076,
-      "loss": 1.0984,
-      "step": 18408
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.0990766286849976,
-      "eval_runtime": 4.3346,
-      "eval_samples_per_second": 2264.34,
-      "eval_steps_per_second": 8.997,
-      "step": 18408
-    },
-    {
-      "epoch": 13.0,
-      "grad_norm": 0.09090559184551239,
-      "learning_rate": 0.00074,
-      "loss": 1.0985,
-      "step": 19942
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.0965192317962646,
-      "eval_runtime": 4.2309,
-      "eval_samples_per_second": 2319.831,
-      "eval_steps_per_second": 9.218,
-      "step": 19942
-    },
-    {
-      "epoch": 14.0,
-      "grad_norm": 0.03515646234154701,
-      "learning_rate": 0.0007199999999999999,
-      "loss": 1.0988,
-      "step": 21476
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0987216234207153,
-      "eval_runtime": 4.0634,
-      "eval_samples_per_second": 2415.463,
-      "eval_steps_per_second": 9.598,
-      "step": 21476
-    },
-    {
-      "epoch": 14.0,
-      "step": 21476,
-      "total_flos": 3.6414798065552794e+17,
-      "train_loss": 1.098874776140008,
-      "train_runtime": 5133.237,
-      "train_samples_per_second": 3825.091,
-      "train_steps_per_second": 14.942
+      "epoch": 8.0,
+      "step": 12272,
+      "total_flos": 2.080845603745874e+17,
+      "train_loss": 0.479245346248383,
+      "train_runtime": 2964.6777,
+      "train_samples_per_second": 6623.013,
+      "train_steps_per_second": 25.871
     }
   ],
   "logging_steps": 1,
@@ -268,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.6414798065552794e+17,
+  "total_flos": 2.080845603745874e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null