End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/bert_base_train_book_ent_15p_s_init
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_train_book_ent_15p_s_init_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_train_book_ent_15p_s_init_wnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6859
+- Loss: 0.6849
 - Accuracy: 0.5634
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6848593354225159,
+    "eval_runtime": 0.0732,
+    "eval_samples": 71,
+    "eval_samples_per_second": 970.217,
+    "eval_steps_per_second": 13.665,
+    "total_flos": 584764320537600.0,
+    "train_loss": 0.6998025803338914,
+    "train_runtime": 22.999,
+    "train_samples": 635,
+    "train_samples_per_second": 1380.493,
+    "train_steps_per_second": 6.522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6848593354225159,
+    "eval_runtime": 0.0732,
+    "eval_samples": 71,
+    "eval_samples_per_second": 970.217,
+    "eval_steps_per_second": 13.665
+}

logs/events.out.tfevents.1745519525.ki-g0008.3436350.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead1b40b2f2f3ae5ab5c15cb3952a1f8aea7b48d8c5f7279bbc184d64cbd0ad2
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 584764320537600.0,
+    "train_loss": 0.6998025803338914,
+    "train_runtime": 22.999,
+    "train_samples": 635,
+    "train_samples_per_second": 1380.493,
+    "train_steps_per_second": 6.522
+}

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 6,
+  "best_metric": 0.6848593354225159,
+  "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_wnli/checkpoint-6",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9552319049835205,
+      "learning_rate": 4.933333333333334e-05,
+      "loss": 0.7049,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.6941022872924805,
+      "eval_runtime": 0.0568,
+      "eval_samples_per_second": 1250.669,
+      "eval_steps_per_second": 17.615,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1868820190429688,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.7016,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6848593354225159,
+      "eval_runtime": 0.0563,
+      "eval_samples_per_second": 1260.036,
+      "eval_steps_per_second": 17.747,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.71503084897995,
+      "learning_rate": 4.7333333333333336e-05,
+      "loss": 0.7019,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.69140625,
+      "eval_runtime": 0.0558,
+      "eval_samples_per_second": 1271.327,
+      "eval_steps_per_second": 17.906,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8658474683761597,
+      "learning_rate": 4.633333333333333e-05,
+      "loss": 0.6938,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7015296220779419,
+      "eval_runtime": 0.0557,
+      "eval_samples_per_second": 1274.952,
+      "eval_steps_per_second": 17.957,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7237994074821472,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.6971,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.697073221206665,
+      "eval_runtime": 0.0564,
+      "eval_samples_per_second": 1259.641,
+      "eval_steps_per_second": 17.741,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0709381103515625,
+      "learning_rate": 4.433333333333334e-05,
+      "loss": 0.6948,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6891505718231201,
+      "eval_runtime": 0.0572,
+      "eval_samples_per_second": 1242.098,
+      "eval_steps_per_second": 17.494,
+      "step": 18
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8299973607063293,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.7045,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6859046220779419,
+      "eval_runtime": 0.0558,
+      "eval_samples_per_second": 1272.598,
+      "eval_steps_per_second": 17.924,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "step": 21,
+      "total_flos": 584764320537600.0,
+      "train_loss": 0.6998025803338914,
+      "train_runtime": 22.999,
+      "train_samples_per_second": 1380.493,
+      "train_steps_per_second": 6.522
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "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": 584764320537600.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}