End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_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: 0.7589503661513426
 ---
 
 <!-- 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. -->
 
 # bert_tiny_lda_100_v1_book_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8576
-- Accuracy: 0.7496
+- Loss: 0.6109
+- Accuracy: 0.7590
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.7494651044319919,
+    "eval_accuracy_mm": 0.7589503661513426,
+    "eval_loss": 0.6237662434577942,
+    "eval_loss_mm": 0.6108659505844116,
+    "eval_runtime": 3.0164,
+    "eval_runtime_mm": 2.9988,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3253.909,
+    "eval_samples_per_second_mm": 3278.646,
+    "eval_steps_per_second": 12.929,
+    "eval_steps_per_second_mm": 13.005,
+    "total_flos": 9.268524907513344e+16,
+    "train_loss": 0.46838148797610074,
+    "train_runtime": 1960.9442,
+    "train_samples": 392702,
+    "train_samples_per_second": 10013.084,
+    "train_steps_per_second": 39.114
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.7494651044319919,
+    "eval_accuracy_mm": 0.7589503661513426,
+    "eval_loss": 0.6237662434577942,
+    "eval_loss_mm": 0.6108659505844116,
+    "eval_runtime": 3.0164,
+    "eval_runtime_mm": 2.9988,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3253.909,
+    "eval_samples_per_second_mm": 3278.646,
+    "eval_steps_per_second": 12.929,
+    "eval_steps_per_second_mm": 13.005
+}

logs/events.out.tfevents.1733845431.ki-g0008.684565.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507353b430c4796697adb41dc8d43aeb8eb913114bc298ecbf14582878469440
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 9.268524907513344e+16,
+    "train_loss": 0.46838148797610074,
+    "train_runtime": 1960.9442,
+    "train_samples": 392702,
+    "train_samples_per_second": 10013.084,
+    "train_steps_per_second": 39.114
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.6237662434577942,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_book_mnli/checkpoint-6136",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 13806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0562517642974854,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7993,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7059602649006622,
+      "eval_loss": 0.6937502026557922,
+      "eval_runtime": 3.1334,
+      "eval_samples_per_second": 3132.346,
+      "eval_steps_per_second": 12.446,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.114716053009033,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6472,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7342842587875701,
+      "eval_loss": 0.6425073742866516,
+      "eval_runtime": 3.0988,
+      "eval_samples_per_second": 3167.354,
+      "eval_steps_per_second": 12.586,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.1429429054260254,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5649,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.74793683138054,
+      "eval_loss": 0.6276543140411377,
+      "eval_runtime": 3.0359,
+      "eval_samples_per_second": 3232.988,
+      "eval_steps_per_second": 12.846,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.27493953704834,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4986,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7494651044319919,
+      "eval_loss": 0.6237662434577942,
+      "eval_runtime": 3.0906,
+      "eval_samples_per_second": 3175.716,
+      "eval_steps_per_second": 12.619,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.513547420501709,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4399,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7544574630667346,
+      "eval_loss": 0.6532984972000122,
+      "eval_runtime": 3.1037,
+      "eval_samples_per_second": 3162.309,
+      "eval_steps_per_second": 12.565,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.5992519855499268,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3857,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7527254202750892,
+      "eval_loss": 0.7153750658035278,
+      "eval_runtime": 3.1035,
+      "eval_samples_per_second": 3162.54,
+      "eval_steps_per_second": 12.566,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.377389907836914,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3351,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.757208354559348,
+      "eval_loss": 0.7138446569442749,
+      "eval_runtime": 3.078,
+      "eval_samples_per_second": 3188.756,
+      "eval_steps_per_second": 12.671,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.1899678707122803,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2914,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7533367294956699,
+      "eval_loss": 0.7700338959693909,
+      "eval_runtime": 3.0368,
+      "eval_samples_per_second": 3232.026,
+      "eval_steps_per_second": 12.842,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.912041664123535,
+      "learning_rate": 4.1e-05,
+      "loss": 0.2533,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7495669893020886,
+      "eval_loss": 0.8575912117958069,
+      "eval_runtime": 3.0725,
+      "eval_samples_per_second": 3194.509,
+      "eval_steps_per_second": 12.693,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "step": 13806,
+      "total_flos": 9.268524907513344e+16,
+      "train_loss": 0.46838148797610074,
+      "train_runtime": 1960.9442,
+      "train_samples_per_second": 10013.084,
+      "train_steps_per_second": 39.114
+    }
+  ],
+  "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": 9.268524907513344e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}