End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_50_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_50_v1_book_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7891578519121237
 ---
 
 <!-- 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_book_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1_book) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8023
-- Accuracy: 0.7903
+- Loss: 0.5241
+- Accuracy: 0.7892
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7843097300050943,
+    "eval_accuracy_mm": 0.7891578519121237,
+    "eval_loss": 0.5418533682823181,
+    "eval_loss_mm": 0.5241080522537231,
+    "eval_runtime": 4.25,
+    "eval_runtime_mm": 4.1709,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2309.386,
+    "eval_samples_per_second_mm": 2357.297,
+    "eval_steps_per_second": 9.176,
+    "eval_steps_per_second_mm": 9.351,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3574085956757507,
+    "train_runtime": 2655.9238,
+    "train_samples": 392702,
+    "train_samples_per_second": 7392.946,
+    "train_steps_per_second": 28.879
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7843097300050943,
+    "eval_accuracy_mm": 0.7891578519121237,
+    "eval_loss": 0.5418533682823181,
+    "eval_loss_mm": 0.5241080522537231,
+    "eval_runtime": 4.25,
+    "eval_runtime_mm": 4.1709,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2309.386,
+    "eval_samples_per_second_mm": 2357.297,
+    "eval_steps_per_second": 9.176,
+    "eval_steps_per_second_mm": 9.351
+}

logs/events.out.tfevents.1733774170.ki-g0008.150368.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9e663309a4f7ede6267399b3d27b7cd52273593bb5aaa73d9274334e8aac8b
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3574085956757507,
+    "train_runtime": 2655.9238,
+    "train_samples": 392702,
+    "train_samples_per_second": 7392.946,
+    "train_steps_per_second": 28.879
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.5418533682823181,
+  "best_model_checkpoint": "distilbert_lda_50_v1_book_mnli/checkpoint-3068",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 10738,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2750277519226074,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6972,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7672949566989302,
+      "eval_loss": 0.5769084692001343,
+      "eval_runtime": 4.3374,
+      "eval_samples_per_second": 2262.873,
+      "eval_steps_per_second": 8.992,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.248551368713379,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5103,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7843097300050943,
+      "eval_loss": 0.5418533682823181,
+      "eval_runtime": 4.4484,
+      "eval_samples_per_second": 2206.435,
+      "eval_steps_per_second": 8.767,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.602325677871704,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4037,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7866530820173204,
+      "eval_loss": 0.565662682056427,
+      "eval_runtime": 4.4644,
+      "eval_samples_per_second": 2198.497,
+      "eval_steps_per_second": 8.736,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.847217082977295,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3143,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7947019867549668,
+      "eval_loss": 0.6038748025894165,
+      "eval_runtime": 4.3041,
+      "eval_samples_per_second": 2280.367,
+      "eval_steps_per_second": 9.061,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.0149447917938232,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2422,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7900152827305145,
+      "eval_loss": 0.6403793692588806,
+      "eval_runtime": 4.2083,
+      "eval_samples_per_second": 2332.303,
+      "eval_steps_per_second": 9.267,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.697627544403076,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1859,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7872643912379012,
+      "eval_loss": 0.7667628526687622,
+      "eval_runtime": 4.4282,
+      "eval_samples_per_second": 2216.48,
+      "eval_steps_per_second": 8.807,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.5282509326934814,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1482,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7903209373408049,
+      "eval_loss": 0.8023476600646973,
+      "eval_runtime": 4.5936,
+      "eval_samples_per_second": 2136.685,
+      "eval_steps_per_second": 8.49,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "step": 10738,
+      "total_flos": 1.8207399032776397e+17,
+      "train_loss": 0.3574085956757507,
+      "train_runtime": 2655.9238,
+      "train_samples_per_second": 7392.946,
+      "train_steps_per_second": 28.879
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 76700,
+  "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": 1.8207399032776397e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}