End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_5_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_5_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: 0.5812274368231047
 ---
 
 <!-- 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_book_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1_book) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1483
-- Accuracy: 0.5848
+- Loss: 0.6748
+- Accuracy: 0.5812
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5812274368231047,
+    "eval_loss": 0.6747588515281677,
+    "eval_runtime": 0.1304,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2123.788,
+    "eval_steps_per_second": 15.334,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.49908527731895447,
+    "train_runtime": 23.1463,
+    "train_samples": 2490,
+    "train_samples_per_second": 5378.828,
+    "train_steps_per_second": 21.602
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5812274368231047,
+    "eval_loss": 0.6747588515281677,
+    "eval_runtime": 0.1304,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2123.788,
+    "eval_steps_per_second": 15.334
+}

logs/events.out.tfevents.1733761988.ki-g0009.1845686.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce0de93ae099022f2be54e656c96767f3a2d22162ece172052ea79d2d74c3c2
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1319375290613760.0,
+    "train_loss": 0.49908527731895447,
+    "train_runtime": 23.1463,
+    "train_samples": 2490,
+    "train_samples_per_second": 5378.828,
+    "train_steps_per_second": 21.602
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6747588515281677,
+  "best_model_checkpoint": "distilbert_lda_5_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": 1.3656349182128906,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7084,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.700727641582489,
+      "eval_runtime": 0.0928,
+      "eval_samples_per_second": 2984.043,
+      "eval_steps_per_second": 21.545,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4563600718975067,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6894,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6886704564094543,
+      "eval_runtime": 0.0886,
+      "eval_samples_per_second": 3126.405,
+      "eval_steps_per_second": 22.573,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6420542597770691,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6725,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5812274368231047,
+      "eval_loss": 0.6747588515281677,
+      "eval_runtime": 0.0919,
+      "eval_samples_per_second": 3014.424,
+      "eval_steps_per_second": 21.765,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.2448971271514893,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6047,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5812274368231047,
+      "eval_loss": 0.7341934442520142,
+      "eval_runtime": 0.0884,
+      "eval_samples_per_second": 3133.032,
+      "eval_steps_per_second": 22.621,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.820317268371582,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5014,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.8410080671310425,
+      "eval_runtime": 0.0894,
+      "eval_samples_per_second": 3098.184,
+      "eval_steps_per_second": 22.37,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.13090991973877,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3728,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6101083032490975,
+      "eval_loss": 0.8730283379554749,
+      "eval_runtime": 0.0998,
+      "eval_samples_per_second": 2776.417,
+      "eval_steps_per_second": 20.046,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.186768054962158,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2546,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5956678700361011,
+      "eval_loss": 1.0909957885742188,
+      "eval_runtime": 0.1007,
+      "eval_samples_per_second": 2749.465,
+      "eval_steps_per_second": 19.852,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.9953765869140625,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1889,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5848375451263538,
+      "eval_loss": 1.148336410522461,
+      "eval_runtime": 0.089,
+      "eval_samples_per_second": 3112.702,
+      "eval_steps_per_second": 22.474,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "step": 80,
+      "total_flos": 1319375290613760.0,
+      "train_loss": 0.49908527731895447,
+      "train_runtime": 23.1463,
+      "train_samples_per_second": 5378.828,
+      "train_steps_per_second": 21.602
+    }
+  ],
+  "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
+}