End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-2_H-512_A-8
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-512_A-8_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4507042253521127
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_uncased_L-2_H-512_A-8_wnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7724
-- Accuracy: 0.2958
+- Loss: 0.7026
+- Accuracy: 0.4507
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7026298642158508,
+    "eval_runtime": 0.0361,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1965.284,
+    "eval_steps_per_second": 27.68,
+    "total_flos": 38445612963840.0,
+    "train_loss": 0.6945502228207059,
+    "train_runtime": 6.1777,
+    "train_samples": 635,
+    "train_samples_per_second": 5139.486,
+    "train_steps_per_second": 24.281
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7026298642158508,
+    "eval_runtime": 0.0361,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1965.284,
+    "eval_steps_per_second": 27.68
+}

logs/events.out.tfevents.1733343977.ki-g0008.1764072.51

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a638fbfdb8d559860c271e6f7a10f380e5c2c9b6c07cff07a4c517f2f710e0
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 38445612963840.0,
+    "train_loss": 0.6945502228207059,
+    "train_runtime": 6.1777,
+    "train_samples": 635,
+    "train_samples_per_second": 5139.486,
+    "train_steps_per_second": 24.281
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.7026298642158508,
+  "best_model_checkpoint": "bert_uncased_L-2_H-512_A-8_wnli/checkpoint-3",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.546919584274292,
+      "learning_rate": 4.9e-05,
+      "loss": 0.709,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.7026298642158508,
+      "eval_runtime": 0.0333,
+      "eval_samples_per_second": 2131.954,
+      "eval_steps_per_second": 30.028,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9109190106391907,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6989,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4084507042253521,
+      "eval_loss": 0.7127256989479065,
+      "eval_runtime": 0.0349,
+      "eval_samples_per_second": 2034.693,
+      "eval_steps_per_second": 28.658,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8286433219909668,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6959,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.323943661971831,
+      "eval_loss": 0.7356405854225159,
+      "eval_runtime": 0.0345,
+      "eval_samples_per_second": 2060.313,
+      "eval_steps_per_second": 29.018,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0639235973358154,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.692,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.30985915492957744,
+      "eval_loss": 0.7548967003822327,
+      "eval_runtime": 0.0352,
+      "eval_samples_per_second": 2014.31,
+      "eval_steps_per_second": 28.371,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0856434106826782,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6833,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.28169014084507044,
+      "eval_loss": 0.7648547291755676,
+      "eval_runtime": 0.0343,
+      "eval_samples_per_second": 2072.14,
+      "eval_steps_per_second": 29.185,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.3245850801467896,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6881,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.29577464788732394,
+      "eval_loss": 0.7724470496177673,
+      "eval_runtime": 0.0331,
+      "eval_samples_per_second": 2141.875,
+      "eval_steps_per_second": 30.167,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "step": 18,
+      "total_flos": 38445612963840.0,
+      "train_loss": 0.6945502228207059,
+      "train_runtime": 6.1777,
+      "train_samples_per_second": 5139.486,
+      "train_steps_per_second": 24.281
+    }
+  ],
+  "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": 38445612963840.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}