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_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7843775427176566
 ---
 
 <!-- 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_mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8225
-- Accuracy: 0.7847
+- Loss: 0.5376
+- Accuracy: 0.7844
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7807437595517066,
+    "eval_accuracy_mm": 0.7843775427176566,
+    "eval_loss": 0.5515223741531372,
+    "eval_loss_mm": 0.5376002788543701,
+    "eval_runtime": 3.0737,
+    "eval_runtime_mm": 3.0706,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3193.234,
+    "eval_samples_per_second_mm": 3201.995,
+    "eval_steps_per_second": 12.688,
+    "eval_steps_per_second_mm": 12.701,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3683101322247254,
+    "train_runtime": 1824.7695,
+    "train_samples": 392702,
+    "train_samples_per_second": 10760.318,
+    "train_steps_per_second": 42.033
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "epoch_mm": 7.0,
+    "eval_accuracy": 0.7807437595517066,
+    "eval_accuracy_mm": 0.7843775427176566,
+    "eval_loss": 0.5515223741531372,
+    "eval_loss_mm": 0.5376002788543701,
+    "eval_runtime": 3.0737,
+    "eval_runtime_mm": 3.0706,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3193.234,
+    "eval_samples_per_second_mm": 3201.995,
+    "eval_steps_per_second": 12.688,
+    "eval_steps_per_second_mm": 12.701
+}

logs/events.out.tfevents.1733769878.ki-g0009.1845686.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52416a958b44bdbc3426b308082b67e2e3ebc2257f7ec79c4657e0b6dfb2a76
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.8207399032776397e+17,
+    "train_loss": 0.3683101322247254,
+    "train_runtime": 1824.7695,
+    "train_samples": 392702,
+    "train_samples_per_second": 10760.318,
+    "train_steps_per_second": 42.033
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.5515223741531372,
+  "best_model_checkpoint": "distilbert_lda_100_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": 2.60382342338562,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7044,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7563932755985736,
+      "eval_loss": 0.5977848172187805,
+      "eval_runtime": 3.0636,
+      "eval_samples_per_second": 3203.75,
+      "eval_steps_per_second": 12.73,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2005040645599365,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5255,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7807437595517066,
+      "eval_loss": 0.5515223741531372,
+      "eval_runtime": 3.0787,
+      "eval_samples_per_second": 3188.022,
+      "eval_steps_per_second": 12.668,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.5877318382263184,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4196,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7879775853285788,
+      "eval_loss": 0.5754101276397705,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 3156.631,
+      "eval_steps_per_second": 12.543,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.74764084815979,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3274,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7889964340295467,
+      "eval_loss": 0.6202009916305542,
+      "eval_runtime": 3.0789,
+      "eval_samples_per_second": 3187.857,
+      "eval_steps_per_second": 12.667,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.0883874893188477,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2518,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7923586347427407,
+      "eval_loss": 0.666239321231842,
+      "eval_runtime": 3.1435,
+      "eval_samples_per_second": 3122.326,
+      "eval_steps_per_second": 12.407,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.3877968788146973,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1948,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7855323484462557,
+      "eval_loss": 0.7695251107215881,
+      "eval_runtime": 3.0638,
+      "eval_samples_per_second": 3203.564,
+      "eval_steps_per_second": 12.729,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.0762624740600586,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1547,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7847172694854814,
+      "eval_loss": 0.8225114345550537,
+      "eval_runtime": 3.0287,
+      "eval_samples_per_second": 3240.65,
+      "eval_steps_per_second": 12.877,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "step": 10738,
+      "total_flos": 1.8207399032776397e+17,
+      "train_loss": 0.3683101322247254,
+      "train_runtime": 1824.7695,
+      "train_samples_per_second": 10760.318,
+      "train_steps_per_second": 42.033
+    }
+  ],
+  "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
+}