End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_100_v1_book_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5270758122743683
 ---
 
 <!-- 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_100_v1_book_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1_book) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1421
-- Accuracy: 0.5415
+- Loss: 0.6902
+- Accuracy: 0.5271
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6901934742927551,
+    "eval_runtime": 0.1285,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2155.242,
+    "eval_steps_per_second": 15.561,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.5446511417627334,
+    "train_runtime": 23.7456,
+    "train_samples": 2490,
+    "train_samples_per_second": 5243.072,
+    "train_steps_per_second": 21.057
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6901934742927551,
+    "eval_runtime": 0.1285,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2155.242,
+    "eval_steps_per_second": 15.561
+}

logs/events.out.tfevents.1733767407.ki-g0009.1845686.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe6e9a49a8366a196cb14843a4830b1c6a6ec87f681c144d27a30cf10beb859
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.5446511417627334,
+    "train_runtime": 23.7456,
+    "train_samples": 2490,
+    "train_samples_per_second": 5243.072,
+    "train_steps_per_second": 21.057
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6901934742927551,
+  "best_model_checkpoint": "distilbert_lda_100_v1_book_rte/checkpoint-30",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "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": 0.37823545932769775,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7006,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 0.6935356259346008,
+      "eval_runtime": 0.0902,
+      "eval_samples_per_second": 3071.564,
+      "eval_steps_per_second": 22.177,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3537502884864807,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6908,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.51985559566787,
+      "eval_loss": 0.6907716989517212,
+      "eval_runtime": 0.1084,
+      "eval_samples_per_second": 2554.219,
+      "eval_steps_per_second": 18.442,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.510235071182251,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6809,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6901934742927551,
+      "eval_runtime": 0.0873,
+      "eval_samples_per_second": 3174.699,
+      "eval_steps_per_second": 22.922,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9909873604774475,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6542,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.6958836317062378,
+      "eval_runtime": 0.0888,
+      "eval_samples_per_second": 3121.064,
+      "eval_steps_per_second": 22.535,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.276339054107666,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5813,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.555956678700361,
+      "eval_loss": 0.7287077903747559,
+      "eval_runtime": 0.0975,
+      "eval_samples_per_second": 2840.683,
+      "eval_steps_per_second": 20.51,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.013831615447998,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4761,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5631768953068592,
+      "eval_loss": 0.7502124309539795,
+      "eval_runtime": 0.0887,
+      "eval_samples_per_second": 3121.961,
+      "eval_steps_per_second": 22.541,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.732637882232666,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3513,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5776173285198556,
+      "eval_loss": 0.8904139399528503,
+      "eval_runtime": 0.0928,
+      "eval_samples_per_second": 2985.155,
+      "eval_steps_per_second": 21.553,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.108197212219238,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2219,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 1.1421412229537964,
+      "eval_runtime": 0.09,
+      "eval_samples_per_second": 3076.909,
+      "eval_steps_per_second": 22.216,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "step": 80,
+      "total_flos": 1319375290613760.0,
+      "train_loss": 0.5446511417627334,
+      "train_runtime": 23.7456,
+      "train_samples_per_second": 5243.072,
+      "train_steps_per_second": 21.057
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1319375290613760.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}