End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_20_v1_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5053999633900788
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_20_v1_qnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6933
 - Accuracy: 0.5054

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6933382749557495,
+    "eval_runtime": 3.491,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1564.864,
+    "eval_steps_per_second": 6.302,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.7020159961731454,
+    "train_runtime": 1044.8612,
+    "train_samples": 104743,
+    "train_samples_per_second": 5012.293,
+    "train_steps_per_second": 19.62
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6933382749557495,
+    "eval_runtime": 3.491,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1564.864,
+    "eval_steps_per_second": 6.302
+}

logs/events.out.tfevents.1732641497.ki-g0008.2136969.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e69f4db1f7ba5360afe9cef4f358f86996df3a8b6a6a40e7f4767bc59c0aba2
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.7020159961731454,
+    "train_runtime": 1044.8612,
+    "train_samples": 104743,
+    "train_samples_per_second": 5012.293,
+    "train_steps_per_second": 19.62
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.6933382749557495,
+  "best_model_checkpoint": "bert_base_lda_20_v1_qnli/checkpoint-410",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12706193327903748,
+      "learning_rate": 0.00098,
+      "loss": 0.7463,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.5554,
+      "eval_samples_per_second": 1536.551,
+      "eval_steps_per_second": 6.188,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09045995026826859,
+      "learning_rate": 0.00096,
+      "loss": 0.6932,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.4846,
+      "eval_samples_per_second": 1567.745,
+      "eval_steps_per_second": 6.313,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1270582526922226,
+      "learning_rate": 0.00094,
+      "loss": 0.6932,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.5053,
+      "eval_samples_per_second": 1558.508,
+      "eval_steps_per_second": 6.276,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.01812651753425598,
+      "learning_rate": 0.00092,
+      "loss": 0.6931,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.4781,
+      "eval_samples_per_second": 1570.686,
+      "eval_steps_per_second": 6.325,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.047646842896938324,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6931,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6934648156166077,
+      "eval_runtime": 3.5198,
+      "eval_samples_per_second": 1552.085,
+      "eval_steps_per_second": 6.25,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.05455218255519867,
+      "learning_rate": 0.00088,
+      "loss": 0.6932,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.5682,
+      "eval_samples_per_second": 1531.045,
+      "eval_steps_per_second": 6.166,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "step": 2460,
+      "total_flos": 8.267712381471744e+16,
+      "train_loss": 0.7020159961731454,
+      "train_runtime": 1044.8612,
+      "train_samples_per_second": 5012.293,
+      "train_steps_per_second": 19.62
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "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": 8.267712381471744e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}