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_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5090252707581228
 ---
 
 <!-- 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_5_v1_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4545
-- Accuracy: 0.5199
+- Loss: 0.6961
+- Accuracy: 0.5090
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6915614008903503,
-    "eval_runtime": 0.135,
+    "epoch": 8.0,
+    "eval_accuracy": 0.5090252707581228,
+    "eval_loss": 0.6961374878883362,
+    "eval_runtime": 0.1357,
     "eval_samples": 277,
-    "eval_samples_per_second": 2051.606,
-    "eval_steps_per_second": 14.813,
-    "total_flos": 1979062935920640.0,
-    "train_loss": 0.7172688285509745,
-    "train_runtime": 49.8636,
+    "eval_samples_per_second": 2041.519,
+    "eval_steps_per_second": 14.74,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.46914870738983155,
+    "train_runtime": 32.4978,
     "train_samples": 2490,
-    "train_samples_per_second": 2496.812,
-    "train_steps_per_second": 10.027
+    "train_samples_per_second": 3831.025,
+    "train_steps_per_second": 15.386
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6915614008903503,
-    "eval_runtime": 0.135,
+    "epoch": 8.0,
+    "eval_accuracy": 0.5090252707581228,
+    "eval_loss": 0.6961374878883362,
+    "eval_runtime": 0.1357,
     "eval_samples": 277,
-    "eval_samples_per_second": 2051.606,
-    "eval_steps_per_second": 14.813
+    "eval_samples_per_second": 2041.519,
+    "eval_steps_per_second": 14.74
 }

logs/events.out.tfevents.1733313349.ki-g0008.1206098.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c91b4be82da4d115eab490f4ebdb2d18dfe4294ec8d561a875a2524e5e4e6b
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "total_flos": 1979062935920640.0,
-    "train_loss": 0.7172688285509745,
-    "train_runtime": 49.8636,
+    "epoch": 8.0,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.46914870738983155,
+    "train_runtime": 32.4978,
     "train_samples": 2490,
-    "train_samples_per_second": 2496.812,
-    "train_steps_per_second": 10.027
+    "train_samples_per_second": 3831.025,
+    "train_steps_per_second": 15.386
 }

trainer_state.json

@@ -1,213 +1,149 @@
 {
-  "best_metric": 0.6915614008903503,
-  "best_model_checkpoint": "distilbert_lda_5_v1_rte/checkpoint-70",
-  "epoch": 12.0,
+  "best_metric": 0.6961374878883362,
+  "best_model_checkpoint": "distilbert_lda_5_v1_rte/checkpoint-30",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.5855181813240051,
-      "learning_rate": 0.00098,
-      "loss": 0.9449,
+      "grad_norm": 2.3214802742004395,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7504,
       "step": 10
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.7021801471710205,
-      "eval_runtime": 0.1254,
-      "eval_samples_per_second": 2209.06,
-      "eval_steps_per_second": 15.95,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7092382311820984,
+      "eval_runtime": 0.1294,
+      "eval_samples_per_second": 2141.351,
+      "eval_steps_per_second": 15.461,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.4455162584781647,
-      "learning_rate": 0.00096,
-      "loss": 0.7042,
+      "grad_norm": 1.0456618070602417,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6796,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6999943852424622,
-      "eval_runtime": 0.1299,
-      "eval_samples_per_second": 2133.087,
-      "eval_steps_per_second": 15.401,
+      "eval_accuracy": 0.516245487364621,
+      "eval_loss": 0.7038653492927551,
+      "eval_runtime": 0.1272,
+      "eval_samples_per_second": 2177.108,
+      "eval_steps_per_second": 15.719,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.8011177182197571,
-      "learning_rate": 0.00094,
-      "loss": 0.7004,
+      "grad_norm": 1.003218650817871,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6429,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.691927969455719,
-      "eval_runtime": 0.1312,
-      "eval_samples_per_second": 2111.997,
-      "eval_steps_per_second": 15.249,
+      "eval_accuracy": 0.5090252707581228,
+      "eval_loss": 0.6961374878883362,
+      "eval_runtime": 0.129,
+      "eval_samples_per_second": 2146.522,
+      "eval_steps_per_second": 15.498,
       "step": 30
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.39011821150779724,
-      "learning_rate": 0.00092,
-      "loss": 0.6962,
+      "grad_norm": 1.37013840675354,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5697,
       "step": 40
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6929433941841125,
-      "eval_runtime": 0.1287,
-      "eval_samples_per_second": 2152.24,
-      "eval_steps_per_second": 15.54,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.7390656471252441,
+      "eval_runtime": 0.1247,
+      "eval_samples_per_second": 2221.135,
+      "eval_steps_per_second": 16.037,
       "step": 40
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.33056044578552246,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6965,
+      "grad_norm": 1.7822569608688354,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4539,
       "step": 50
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6995571851730347,
-      "eval_runtime": 0.1316,
-      "eval_samples_per_second": 2104.975,
-      "eval_steps_per_second": 15.198,
+      "eval_accuracy": 0.5306859205776173,
+      "eval_loss": 0.8573698997497559,
+      "eval_runtime": 0.1268,
+      "eval_samples_per_second": 2185.207,
+      "eval_steps_per_second": 15.778,
       "step": 50
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.3222827613353729,
-      "learning_rate": 0.00088,
-      "loss": 0.6965,
+      "grad_norm": 5.516984939575195,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3105,
       "step": 60
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6917728781700134,
-      "eval_runtime": 0.129,
-      "eval_samples_per_second": 2146.95,
-      "eval_steps_per_second": 15.501,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 1.0425331592559814,
+      "eval_runtime": 0.126,
+      "eval_samples_per_second": 2197.919,
+      "eval_steps_per_second": 15.869,
       "step": 60
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.2771111726760864,
-      "learning_rate": 0.00086,
-      "loss": 0.6947,
+      "grad_norm": 5.505280017852783,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2107,
       "step": 70
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6915614008903503,
-      "eval_runtime": 0.1383,
-      "eval_samples_per_second": 2002.531,
-      "eval_steps_per_second": 14.459,
+      "eval_accuracy": 0.5054151624548736,
+      "eval_loss": 1.4041368961334229,
+      "eval_runtime": 0.1276,
+      "eval_samples_per_second": 2171.224,
+      "eval_steps_per_second": 15.677,
       "step": 70
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.3152952194213867,
-      "learning_rate": 0.00084,
-      "loss": 0.6949,
+      "grad_norm": 3.022568941116333,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1354,
       "step": 80
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6938458681106567,
-      "eval_runtime": 0.1301,
-      "eval_samples_per_second": 2129.334,
-      "eval_steps_per_second": 15.374,
+      "eval_accuracy": 0.51985559566787,
+      "eval_loss": 1.4544810056686401,
+      "eval_runtime": 0.1345,
+      "eval_samples_per_second": 2058.888,
+      "eval_steps_per_second": 14.866,
       "step": 80
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.508091390132904,
-      "learning_rate": 0.00082,
-      "loss": 0.6948,
-      "step": 90
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.699120044708252,
-      "eval_runtime": 0.1297,
-      "eval_samples_per_second": 2135.915,
-      "eval_steps_per_second": 15.422,
-      "step": 90
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.13915003836154938,
-      "learning_rate": 0.0008,
-      "loss": 0.6957,
-      "step": 100
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6919844150543213,
-      "eval_runtime": 0.1283,
-      "eval_samples_per_second": 2159.75,
-      "eval_steps_per_second": 15.594,
-      "step": 100
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.2669129967689514,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6941,
-      "step": 110
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6955804228782654,
-      "eval_runtime": 0.1281,
-      "eval_samples_per_second": 2162.358,
-      "eval_steps_per_second": 15.613,
-      "step": 110
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.15157711505889893,
-      "learning_rate": 0.00076,
-      "loss": 0.6944,
-      "step": 120
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6934651136398315,
-      "eval_runtime": 0.1305,
-      "eval_samples_per_second": 2122.658,
-      "eval_steps_per_second": 15.326,
-      "step": 120
-    },
-    {
-      "epoch": 12.0,
-      "step": 120,
-      "total_flos": 1979062935920640.0,
-      "train_loss": 0.7172688285509745,
-      "train_runtime": 49.8636,
-      "train_samples_per_second": 2496.812,
-      "train_steps_per_second": 10.027
+      "epoch": 8.0,
+      "step": 80,
+      "total_flos": 1319375290613760.0,
+      "train_loss": 0.46914870738983155,
+      "train_runtime": 32.4978,
+      "train_samples_per_second": 3831.025,
+      "train_steps_per_second": 15.386
     }
   ],
   "logging_steps": 1,
@@ -236,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1979062935920640.0,
+  "total_flos": 1319375290613760.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null