End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_20_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_20_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: 0.7886493083807974
 ---
 
 <!-- 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_20_v1_book_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1_book) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7587
-- Accuracy: 0.7882
+- Loss: 0.5334
+- Accuracy: 0.7886
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7890983188996434,
+    "eval_accuracy_mm": 0.7886493083807974,
+    "eval_loss": 0.5409021973609924,
+    "eval_loss_mm": 0.5334087014198303,
+    "eval_runtime": 4.2462,
+    "eval_runtime_mm": 4.2345,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2311.455,
+    "eval_samples_per_second_mm": 2321.859,
+    "eval_steps_per_second": 9.185,
+    "eval_steps_per_second_mm": 9.21,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3593115150251298,
+    "train_runtime": 2646.1923,
+    "train_samples": 392702,
+    "train_samples_per_second": 7420.134,
+    "train_steps_per_second": 28.985
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7890983188996434,
+    "eval_accuracy_mm": 0.7886493083807974,
+    "eval_loss": 0.5409021973609924,
+    "eval_loss_mm": 0.5334087014198303,
+    "eval_runtime": 4.2462,
+    "eval_runtime_mm": 4.2345,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2311.455,
+    "eval_samples_per_second_mm": 2321.859,
+    "eval_steps_per_second": 9.185,
+    "eval_steps_per_second_mm": 9.21
+}

logs/events.out.tfevents.1733766494.ki-g0008.150368.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677d7cd96a96f0c43ee035e119c192cf8959321a032964a0efd77f727125abd6
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3593115150251298,
+    "train_runtime": 2646.1923,
+    "train_samples": 392702,
+    "train_samples_per_second": 7420.134,
+    "train_steps_per_second": 28.985
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.5409021973609924,
+  "best_model_checkpoint": "distilbert_lda_20_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": 2.5330288410186768,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7024,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7646459500764137,
+      "eval_loss": 0.5842658281326294,
+      "eval_runtime": 4.3578,
+      "eval_samples_per_second": 2252.258,
+      "eval_steps_per_second": 8.949,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.305652141571045,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5147,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7890983188996434,
+      "eval_loss": 0.5409021973609924,
+      "eval_runtime": 4.3076,
+      "eval_samples_per_second": 2278.506,
+      "eval_steps_per_second": 9.054,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.426408052444458,
+      "learning_rate": 4.7e-05,
+      "loss": 0.407,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7910341314314824,
+      "eval_loss": 0.5485309362411499,
+      "eval_runtime": 4.5464,
+      "eval_samples_per_second": 2158.847,
+      "eval_steps_per_second": 8.578,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.034677028656006,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3142,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.789302088639837,
+      "eval_loss": 0.6063764691352844,
+      "eval_runtime": 4.3943,
+      "eval_samples_per_second": 2233.584,
+      "eval_steps_per_second": 8.875,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.319906711578369,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2419,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7875700458481916,
+      "eval_loss": 0.6936997771263123,
+      "eval_runtime": 4.3472,
+      "eval_samples_per_second": 2257.795,
+      "eval_steps_per_second": 8.971,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.0567739009857178,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1866,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7874681609780948,
+      "eval_loss": 0.7424802184104919,
+      "eval_runtime": 4.3189,
+      "eval_samples_per_second": 2272.577,
+      "eval_steps_per_second": 9.03,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.2307686805725098,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1483,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7881813550687723,
+      "eval_loss": 0.7587445974349976,
+      "eval_runtime": 4.2598,
+      "eval_samples_per_second": 2304.108,
+      "eval_steps_per_second": 9.155,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "step": 10738,
+      "total_flos": 1.8207399032776397e+17,
+      "train_loss": 0.3593115150251298,
+      "train_runtime": 2646.1923,
+      "train_samples_per_second": 7420.134,
+      "train_steps_per_second": 28.985
+    }
+  ],
+  "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
+}