End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_5_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: 0.8463302752293578
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_5_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4770
+- Loss: 0.3518
 - Accuracy: 0.8463
 
 ## Model description

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6939507126808167,
-    "eval_runtime": 0.3779,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8463302752293578,
+    "eval_loss": 0.35176724195480347,
+    "eval_runtime": 0.379,
     "eval_samples": 872,
-    "eval_samples_per_second": 2307.296,
-    "eval_steps_per_second": 10.584,
-    "total_flos": 3.1225413912290304e+16,
-    "train_loss": 0.6902871069970069,
-    "train_runtime": 450.9671,
+    "eval_samples_per_second": 2300.934,
+    "eval_steps_per_second": 10.555,
+    "total_flos": 2.676464049624883e+16,
+    "train_loss": 0.14276121361087066,
+    "train_runtime": 385.3319,
     "train_samples": 67349,
-    "train_samples_per_second": 7467.174,
-    "train_steps_per_second": 29.27
+    "train_samples_per_second": 8739.09,
+    "train_steps_per_second": 34.256
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6939507126808167,
-    "eval_runtime": 0.3779,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8463302752293578,
+    "eval_loss": 0.35176724195480347,
+    "eval_runtime": 0.379,
     "eval_samples": 872,
-    "eval_samples_per_second": 2307.296,
-    "eval_steps_per_second": 10.584
+    "eval_samples_per_second": 2300.934,
+    "eval_steps_per_second": 10.555
 }

logs/events.out.tfevents.1733313829.ki-g0008.1206098.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5728cbafacb9cb6b1dc1f4528c6f13201bb23445348951fe88032648e10a71d9
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 3.1225413912290304e+16,
-    "train_loss": 0.6902871069970069,
-    "train_runtime": 450.9671,
+    "epoch": 6.0,
+    "total_flos": 2.676464049624883e+16,
+    "train_loss": 0.14276121361087066,
+    "train_runtime": 385.3319,
     "train_samples": 67349,
-    "train_samples_per_second": 7467.174,
-    "train_steps_per_second": 29.27
+    "train_samples_per_second": 8739.09,
+    "train_steps_per_second": 34.256
 }

trainer_state.json

@@ -1,133 +1,117 @@
 {
-  "best_metric": 0.6939507126808167,
-  "best_model_checkpoint": "distilbert_lda_5_v1_sst2/checkpoint-528",
-  "epoch": 7.0,
+  "best_metric": 0.35176724195480347,
+  "best_model_checkpoint": "distilbert_lda_5_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1848,
+  "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": 1.6202912330627441,
-      "learning_rate": 0.00098,
-      "loss": 0.7107,
+      "grad_norm": 7.300721645355225,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3414,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6972835659980774,
-      "eval_runtime": 0.382,
-      "eval_samples_per_second": 2282.479,
-      "eval_steps_per_second": 10.47,
+      "eval_accuracy": 0.8463302752293578,
+      "eval_loss": 0.35176724195480347,
+      "eval_runtime": 0.3773,
+      "eval_samples_per_second": 2311.298,
+      "eval_steps_per_second": 10.602,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.21355657279491425,
-      "learning_rate": 0.00096,
-      "loss": 0.6885,
+      "grad_norm": 6.633228302001953,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1865,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6939507126808167,
-      "eval_runtime": 0.3791,
-      "eval_samples_per_second": 2300.381,
-      "eval_steps_per_second": 10.552,
+      "eval_accuracy": 0.8600917431192661,
+      "eval_loss": 0.35497570037841797,
+      "eval_runtime": 0.3782,
+      "eval_samples_per_second": 2305.767,
+      "eval_steps_per_second": 10.577,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.47229713201522827,
-      "learning_rate": 0.00094,
-      "loss": 0.6868,
+      "grad_norm": 3.8063089847564697,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1259,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6953662633895874,
-      "eval_runtime": 0.3859,
-      "eval_samples_per_second": 2259.69,
-      "eval_steps_per_second": 10.366,
+      "eval_accuracy": 0.8612385321100917,
+      "eval_loss": 0.408633828163147,
+      "eval_runtime": 0.379,
+      "eval_samples_per_second": 2301.086,
+      "eval_steps_per_second": 10.555,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.1830187439918518,
-      "learning_rate": 0.00092,
-      "loss": 0.6866,
+      "grad_norm": 6.068315505981445,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0881,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6973552107810974,
-      "eval_runtime": 0.3788,
-      "eval_samples_per_second": 2302.168,
-      "eval_steps_per_second": 10.56,
+      "eval_accuracy": 0.8497706422018348,
+      "eval_loss": 0.481966495513916,
+      "eval_runtime": 0.3822,
+      "eval_samples_per_second": 2281.556,
+      "eval_steps_per_second": 10.466,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.10979917645454407,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6865,
+      "grad_norm": 0.23764105141162872,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0658,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6972118616104126,
-      "eval_runtime": 0.3808,
-      "eval_samples_per_second": 2289.715,
-      "eval_steps_per_second": 10.503,
+      "eval_accuracy": 0.8612385321100917,
+      "eval_loss": 0.4614078998565674,
+      "eval_runtime": 0.3773,
+      "eval_samples_per_second": 2310.886,
+      "eval_steps_per_second": 10.6,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.0832272469997406,
-      "learning_rate": 0.00088,
-      "loss": 0.6866,
+      "grad_norm": 5.384342193603516,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.049,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6969968676567078,
-      "eval_runtime": 0.3779,
-      "eval_samples_per_second": 2307.472,
-      "eval_steps_per_second": 10.585,
+      "eval_accuracy": 0.8463302752293578,
+      "eval_loss": 0.47696468234062195,
+      "eval_runtime": 0.3821,
+      "eval_samples_per_second": 2282.095,
+      "eval_steps_per_second": 10.468,
       "step": 1584
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.14501214027404785,
-      "learning_rate": 0.00086,
-      "loss": 0.6863,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698842465877533,
-      "eval_runtime": 0.3825,
-      "eval_samples_per_second": 2279.681,
-      "eval_steps_per_second": 10.457,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "step": 1848,
-      "total_flos": 3.1225413912290304e+16,
-      "train_loss": 0.6902871069970069,
-      "train_runtime": 450.9671,
-      "train_samples_per_second": 7467.174,
-      "train_steps_per_second": 29.27
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 2.676464049624883e+16,
+      "train_loss": 0.14276121361087066,
+      "train_runtime": 385.3319,
+      "train_samples_per_second": 8739.09,
+      "train_steps_per_second": 34.256
     }
   ],
   "logging_steps": 1,
@@ -156,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1225413912290304e+16,
+  "total_flos": 2.676464049624883e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null