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_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8291284403669725
 ---
 
 <!-- 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_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5851
-- Accuracy: 0.8177
+- Loss: 0.4006
+- Accuracy: 0.8291
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6954379081726074,
-    "eval_runtime": 0.377,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8291284403669725,
+    "eval_loss": 0.40057066082954407,
+    "eval_runtime": 0.3891,
     "eval_samples": 872,
-    "eval_samples_per_second": 2312.818,
-    "eval_steps_per_second": 10.609,
-    "total_flos": 4.014696074437325e+16,
-    "train_loss": 0.6891397867941295,
-    "train_runtime": 578.6042,
+    "eval_samples_per_second": 2240.942,
+    "eval_steps_per_second": 10.28,
+    "total_flos": 2.676464049624883e+16,
+    "train_loss": 0.16643811115110763,
+    "train_runtime": 389.8795,
     "train_samples": 67349,
-    "train_samples_per_second": 5819.954,
-    "train_steps_per_second": 22.814
+    "train_samples_per_second": 8637.157,
+    "train_steps_per_second": 33.857
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6954379081726074,
-    "eval_runtime": 0.377,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8291284403669725,
+    "eval_loss": 0.40057066082954407,
+    "eval_runtime": 0.3891,
     "eval_samples": 872,
-    "eval_samples_per_second": 2312.818,
-    "eval_steps_per_second": 10.609
+    "eval_samples_per_second": 2240.942,
+    "eval_steps_per_second": 10.28
 }

logs/events.out.tfevents.1733313437.ki-g0008.1206436.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3417e3286a782653b8e8946d1b3516e94d3bb53c2520a0d6e0f6d2caaa5e966c
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "total_flos": 4.014696074437325e+16,
-    "train_loss": 0.6891397867941295,
-    "train_runtime": 578.6042,
+    "epoch": 6.0,
+    "total_flos": 2.676464049624883e+16,
+    "train_loss": 0.16643811115110763,
+    "train_runtime": 389.8795,
     "train_samples": 67349,
-    "train_samples_per_second": 5819.954,
-    "train_steps_per_second": 22.814
+    "train_samples_per_second": 8637.157,
+    "train_steps_per_second": 33.857
 }

trainer_state.json

@@ -1,165 +1,117 @@
 {
-  "best_metric": 0.6954379081726074,
-  "best_model_checkpoint": "distilbert_lda_50_v1_sst2/checkpoint-1056",
-  "epoch": 9.0,
+  "best_metric": 0.40057066082954407,
+  "best_model_checkpoint": "distilbert_lda_50_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 2376,
+  "global_step": 1584,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.4881739616394043,
-      "learning_rate": 0.00098,
-      "loss": 0.7089,
+      "grad_norm": 8.42946720123291,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3785,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6971402168273926,
-      "eval_runtime": 0.3976,
-      "eval_samples_per_second": 2192.975,
-      "eval_steps_per_second": 10.06,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.40057066082954407,
+      "eval_runtime": 0.3872,
+      "eval_samples_per_second": 2251.83,
+      "eval_steps_per_second": 10.329,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.350206583738327,
-      "learning_rate": 0.00096,
-      "loss": 0.6871,
+      "grad_norm": 6.42087984085083,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2139,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.695724606513977,
-      "eval_runtime": 0.3768,
-      "eval_samples_per_second": 2314.264,
-      "eval_steps_per_second": 10.616,
+      "eval_accuracy": 0.8405963302752294,
+      "eval_loss": 0.42612364888191223,
+      "eval_runtime": 0.4877,
+      "eval_samples_per_second": 1787.91,
+      "eval_steps_per_second": 8.201,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.5072749257087708,
-      "learning_rate": 0.00094,
-      "loss": 0.6867,
+      "grad_norm": 5.889172554016113,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1523,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698914110660553,
-      "eval_runtime": 0.388,
-      "eval_samples_per_second": 2247.185,
-      "eval_steps_per_second": 10.308,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.4885922968387604,
+      "eval_runtime": 0.3795,
+      "eval_samples_per_second": 2297.458,
+      "eval_steps_per_second": 10.539,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.5293957591056824,
-      "learning_rate": 0.00092,
-      "loss": 0.6868,
+      "grad_norm": 5.110029220581055,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1085,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6954379081726074,
-      "eval_runtime": 0.373,
-      "eval_samples_per_second": 2337.899,
-      "eval_steps_per_second": 10.724,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 0.5391777753829956,
+      "eval_runtime": 0.3802,
+      "eval_samples_per_second": 2293.654,
+      "eval_steps_per_second": 10.521,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.16188092529773712,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6867,
+      "grad_norm": 0.9452471137046814,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0809,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6972835659980774,
-      "eval_runtime": 0.3778,
-      "eval_samples_per_second": 2307.995,
-      "eval_steps_per_second": 10.587,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.5835925340652466,
+      "eval_runtime": 0.3806,
+      "eval_samples_per_second": 2291.343,
+      "eval_steps_per_second": 10.511,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.0814874991774559,
-      "learning_rate": 0.00088,
-      "loss": 0.6866,
+      "grad_norm": 5.266055107116699,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0646,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698914110660553,
-      "eval_runtime": 0.3728,
-      "eval_samples_per_second": 2338.898,
-      "eval_steps_per_second": 10.729,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.5851426124572754,
+      "eval_runtime": 0.3834,
+      "eval_samples_per_second": 2274.1,
+      "eval_steps_per_second": 10.432,
       "step": 1584
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.1502029448747635,
-      "learning_rate": 0.00086,
-      "loss": 0.6862,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6969968676567078,
-      "eval_runtime": 0.3762,
-      "eval_samples_per_second": 2317.815,
-      "eval_steps_per_second": 10.632,
-      "step": 1848
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.050043512135744095,
-      "learning_rate": 0.00084,
-      "loss": 0.6866,
-      "step": 2112
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6970685124397278,
-      "eval_runtime": 0.3742,
-      "eval_samples_per_second": 2330.096,
-      "eval_steps_per_second": 10.689,
-      "step": 2112
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.18645544350147247,
-      "learning_rate": 0.00082,
-      "loss": 0.6867,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6969968676567078,
-      "eval_runtime": 0.382,
-      "eval_samples_per_second": 2282.808,
-      "eval_steps_per_second": 10.472,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "step": 2376,
-      "total_flos": 4.014696074437325e+16,
-      "train_loss": 0.6891397867941295,
-      "train_runtime": 578.6042,
-      "train_samples_per_second": 5819.954,
-      "train_steps_per_second": 22.814
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 2.676464049624883e+16,
+      "train_loss": 0.16643811115110763,
+      "train_runtime": 389.8795,
+      "train_samples_per_second": 8637.157,
+      "train_steps_per_second": 33.857
     }
   ],
   "logging_steps": 1,
@@ -188,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.014696074437325e+16,
+  "total_flos": 2.676464049624883e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null