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_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
@@ -16,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_train_book_ent_15p_s_init_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6932
+- Loss: 0.6928
 - Accuracy: 0.5054
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6928256154060364,
+    "eval_runtime": 4.6207,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1182.284,
+    "eval_steps_per_second": 4.761,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.6958341645031441,
+    "train_runtime": 1153.5282,
+    "train_samples": 104743,
+    "train_samples_per_second": 4540.114,
+    "train_steps_per_second": 17.772
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6928256154060364,
+    "eval_runtime": 4.6207,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1182.284,
+    "eval_steps_per_second": 4.761
+}

logs/events.out.tfevents.1745512872.ki-g0008.3436350.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c82fd07187806ef1a2dfa84bd045fbabcfb781a77e53f7bfba76807dee23cc7
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.6958341645031441,
+    "train_runtime": 1153.5282,
+    "train_samples": 104743,
+    "train_samples_per_second": 4540.114,
+    "train_steps_per_second": 17.772
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 410,
+  "best_metric": 0.6928256154060364,
+  "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_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": 2.6589386463165283,
+      "learning_rate": 4.900243902439024e-05,
+      "loss": 0.6973,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6928256154060364,
+      "eval_runtime": 4.6142,
+      "eval_samples_per_second": 1183.95,
+      "eval_steps_per_second": 4.768,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1992162466049194,
+      "learning_rate": 4.8002439024390246e-05,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6954562067985535,
+      "eval_runtime": 4.6225,
+      "eval_samples_per_second": 1181.833,
+      "eval_steps_per_second": 4.759,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4169254302978516,
+      "learning_rate": 4.700243902439024e-05,
+      "loss": 0.6957,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6980332136154175,
+      "eval_runtime": 4.6457,
+      "eval_samples_per_second": 1175.926,
+      "eval_steps_per_second": 4.736,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.994229793548584,
+      "learning_rate": 4.600243902439025e-05,
+      "loss": 0.6956,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931659579277039,
+      "eval_runtime": 4.6359,
+      "eval_samples_per_second": 1178.403,
+      "eval_steps_per_second": 4.746,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0654411315917969,
+      "learning_rate": 4.500243902439025e-05,
+      "loss": 0.6954,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 4.6434,
+      "eval_samples_per_second": 1176.507,
+      "eval_steps_per_second": 4.738,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.196447491645813,
+      "learning_rate": 4.400243902439024e-05,
+      "loss": 0.6951,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6932117342948914,
+      "eval_runtime": 4.6641,
+      "eval_samples_per_second": 1171.299,
+      "eval_steps_per_second": 4.717,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "step": 2460,
+      "total_flos": 8.267712381471744e+16,
+      "train_loss": 0.6958341645031441,
+      "train_runtime": 1153.5282,
+      "train_samples_per_second": 4540.114,
+      "train_steps_per_second": 17.772
+    }
+  ],
+  "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
+}