End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tinybert_base_train_book_ent_15p_s_init_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7009803921568627
+    - name: F1
+      type: f1
+      value: 0.8038585209003215
 ---
 
 <!-- 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_base_train_book_ent_15p_s_init_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7486
-- Accuracy: 0.6789
-- F1: 0.7835
-- Combined Score: 0.7312
+- Loss: 0.5788
+- Accuracy: 0.7010
+- F1: 0.8039
+- Combined Score: 0.7524
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7009803921568627,
+    "eval_combined_score": 0.7524194565285921,
+    "eval_f1": 0.8038585209003215,
+    "eval_loss": 0.5787975788116455,
+    "eval_runtime": 0.2441,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1671.268,
+    "eval_steps_per_second": 8.192,
+    "total_flos": 507738681741312.0,
+    "train_loss": 0.5309564317975726,
+    "train_runtime": 26.6717,
+    "train_samples": 3668,
+    "train_samples_per_second": 6876.205,
+    "train_steps_per_second": 28.12
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7009803921568627,
+    "eval_combined_score": 0.7524194565285921,
+    "eval_f1": 0.8038585209003215,
+    "eval_loss": 0.5787975788116455,
+    "eval_runtime": 0.2441,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1671.268,
+    "eval_steps_per_second": 8.192
+}

logs/events.out.tfevents.1745504220.ki-g0008.3436350.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94e1c47155e657c86098bc3b31b155996acf4663676899d4130f5b48eb101ac
+size 507

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 507738681741312.0,
+    "train_loss": 0.5309564317975726,
+    "train_runtime": 26.6717,
+    "train_samples": 3668,
+    "train_samples_per_second": 6876.205,
+    "train_steps_per_second": 28.12
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5787975788116455,
+  "best_model_checkpoint": "tinybert_base_train_book_ent_15p_s_init_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": 0.916682779788971,
+      "learning_rate": 4.906666666666667e-05,
+      "loss": 0.626,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.748077548554967,
+      "eval_f1": 0.8025276461295419,
+      "eval_loss": 0.5948342680931091,
+      "eval_runtime": 0.2461,
+      "eval_samples_per_second": 1657.768,
+      "eval_steps_per_second": 8.126,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.384405493736267,
+      "learning_rate": 4.806666666666667e-05,
+      "loss": 0.5902,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7524194565285921,
+      "eval_f1": 0.8038585209003215,
+      "eval_loss": 0.5787975788116455,
+      "eval_runtime": 0.2436,
+      "eval_samples_per_second": 1675.043,
+      "eval_steps_per_second": 8.211,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9498925805091858,
+      "learning_rate": 4.706666666666667e-05,
+      "loss": 0.5641,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7555019022534386,
+      "eval_f1": 0.8149253731343283,
+      "eval_loss": 0.6337752938270569,
+      "eval_runtime": 0.2411,
+      "eval_samples_per_second": 1692.349,
+      "eval_steps_per_second": 8.296,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.267024040222168,
+      "learning_rate": 4.606666666666667e-05,
+      "loss": 0.5567,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7398835373075405,
+      "eval_f1": 0.7885906040268457,
+      "eval_loss": 0.5952854752540588,
+      "eval_runtime": 0.2443,
+      "eval_samples_per_second": 1669.849,
+      "eval_steps_per_second": 8.186,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.532133102416992,
+      "learning_rate": 4.5066666666666667e-05,
+      "loss": 0.5118,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7419698142414861,
+      "eval_f1": 0.7927631578947368,
+      "eval_loss": 0.6026850938796997,
+      "eval_runtime": 0.2435,
+      "eval_samples_per_second": 1675.473,
+      "eval_steps_per_second": 8.213,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.633739709854126,
+      "learning_rate": 4.406666666666667e-05,
+      "loss": 0.4615,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.7293849046467902,
+      "eval_f1": 0.7773972602739726,
+      "eval_loss": 0.6785858869552612,
+      "eval_runtime": 0.2236,
+      "eval_samples_per_second": 1825.083,
+      "eval_steps_per_second": 8.946,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.333436965942383,
+      "learning_rate": 4.3066666666666665e-05,
+      "loss": 0.4065,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.678921568627451,
+      "eval_combined_score": 0.7311963215038082,
+      "eval_f1": 0.7834710743801653,
+      "eval_loss": 0.7485843896865845,
+      "eval_runtime": 0.2545,
+      "eval_samples_per_second": 1602.908,
+      "eval_steps_per_second": 7.857,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 507738681741312.0,
+      "train_loss": 0.5309564317975726,
+      "train_runtime": 26.6717,
+      "train_samples_per_second": 6876.205,
+      "train_steps_per_second": 28.12
+    }
+  ],
+  "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": 507738681741312.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}