End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_train_book_ent_15p_inv
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tinybert_train_book_ent_15p_inv_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6911764705882353
+    - name: F1
+      type: f1
+      value: 0.7967741935483871
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinybert_train_book_ent_15p_inv_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_ent_15p_inv](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_ent_15p_inv) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_ent_15p_inv](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_ent_15p_inv) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8915
-- Accuracy: 0.6740
-- F1: 0.7734
-- Combined Score: 0.7237
+- Loss: 0.5824
+- Accuracy: 0.6912
+- F1: 0.7968
+- Combined Score: 0.7440
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7439753320683111,
+    "eval_f1": 0.7967741935483871,
+    "eval_loss": 0.5824070572853088,
+    "eval_runtime": 0.1816,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2246.872,
+    "eval_steps_per_second": 11.014,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4657690184456961,
+    "train_runtime": 22.5099,
+    "train_samples": 3668,
+    "train_samples_per_second": 8147.52,
+    "train_steps_per_second": 33.319
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7439753320683111,
+    "eval_f1": 0.7967741935483871,
+    "eval_loss": 0.5824070572853088,
+    "eval_runtime": 0.1816,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2246.872,
+    "eval_steps_per_second": 11.014
+}

logs/events.out.tfevents.1744169757.ki-g0008.1517121.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f830dac6933489adbac20952c3f17ec5c57cf7374ca76f107046e9dca98a533
+size 507

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4657690184456961,
+    "train_runtime": 22.5099,
+    "train_samples": 3668,
+    "train_samples_per_second": 8147.52,
+    "train_steps_per_second": 33.319
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.5824070572853088,
+  "best_model_checkpoint": "tinybert_train_book_ent_15p_inv_mrpc/checkpoint-30",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9117701649665833,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6271,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7603485838779958,
+      "eval_f1": 0.8148148148148149,
+      "eval_loss": 0.6072375178337097,
+      "eval_runtime": 0.1885,
+      "eval_samples_per_second": 2163.997,
+      "eval_steps_per_second": 10.608,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4351258277893066,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5897,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7439753320683111,
+      "eval_f1": 0.7967741935483871,
+      "eval_loss": 0.5824070572853088,
+      "eval_runtime": 0.2121,
+      "eval_samples_per_second": 1923.366,
+      "eval_steps_per_second": 9.428,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1977477073669434,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5555,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7156862745098039,
+      "eval_combined_score": 0.7696972405983671,
+      "eval_f1": 0.8237082066869301,
+      "eval_loss": 0.6068498492240906,
+      "eval_runtime": 0.1753,
+      "eval_samples_per_second": 2326.95,
+      "eval_steps_per_second": 11.407,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.7320971488952637,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5055,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7271952259164536,
+      "eval_f1": 0.7681159420289856,
+      "eval_loss": 0.6074116826057434,
+      "eval_runtime": 0.1914,
+      "eval_samples_per_second": 2131.207,
+      "eval_steps_per_second": 10.447,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.920226812362671,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4197,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7396476072946662,
+      "eval_f1": 0.7832167832167833,
+      "eval_loss": 0.6649504899978638,
+      "eval_runtime": 0.1954,
+      "eval_samples_per_second": 2087.576,
+      "eval_steps_per_second": 10.233,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.858860492706299,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3231,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6764705882352942,
+      "eval_combined_score": 0.726370887337986,
+      "eval_f1": 0.7762711864406779,
+      "eval_loss": 0.8156278729438782,
+      "eval_runtime": 0.1706,
+      "eval_samples_per_second": 2391.911,
+      "eval_steps_per_second": 11.725,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.400638103485107,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2398,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7237218993219094,
+      "eval_f1": 0.7734241908006815,
+      "eval_loss": 0.8914933800697327,
+      "eval_runtime": 0.1735,
+      "eval_samples_per_second": 2351.474,
+      "eval_steps_per_second": 11.527,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.4657690184456961,
+      "train_runtime": 22.5099,
+      "train_samples_per_second": 8147.52,
+      "train_steps_per_second": 33.319
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 673316591603712.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}