End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MNLI
       type: glue
       config: mnli
       split: validation_matched
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.3544574630667346
+      value: 0.3522172497965826
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_mnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0986
-- Accuracy: 0.3545
+- Loss: 1.0983
+- Accuracy: 0.3522
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 15.0,
+    "epoch_mm": 15.0,
+    "eval_accuracy": 0.3544574630667346,
+    "eval_accuracy_mm": 0.3522172497965826,
+    "eval_loss": 1.0982866287231445,
+    "eval_loss_mm": 1.098288893699646,
+    "eval_runtime": 11.3752,
+    "eval_runtime_mm": 11.3674,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 862.843,
+    "eval_samples_per_second_mm": 864.931,
+    "eval_steps_per_second": 3.429,
+    "eval_steps_per_second_mm": 3.431,
+    "train_loss": 1.0986910359541369,
+    "train_runtime": 20364.3039,
+    "train_samples": 392702,
+    "train_samples_per_second": 964.192,
+    "train_steps_per_second": 3.766
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 15.0,
+    "epoch_mm": 15.0,
+    "eval_accuracy": 0.3544574630667346,
+    "eval_accuracy_mm": 0.3522172497965826,
+    "eval_loss": 1.0982866287231445,
+    "eval_loss_mm": 1.098288893699646,
+    "eval_runtime": 11.3752,
+    "eval_runtime_mm": 11.3674,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 862.843,
+    "eval_samples_per_second_mm": 864.931,
+    "eval_steps_per_second": 3.429,
+    "eval_steps_per_second_mm": 3.431
+}

logs/events.out.tfevents.1677779244.serv-3317.65116.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a71bca39ae4f91dc966112438c60800ea7990b12b0e414b16120db43808c889
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "train_loss": 1.0986910359541369,
+    "train_runtime": 20364.3039,
+    "train_samples": 392702,
+    "train_samples_per_second": 964.192,
+    "train_steps_per_second": 3.766
+}

trainer_state.json

@@ -0,0 +1,250 @@
+{
+  "best_metric": 1.0982866287231445,
+  "best_model_checkpoint": "hBERTv2_mnli/checkpoint-15340",
+  "epoch": 15.0,
+  "global_step": 23010,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.90013037809648e-05,
+      "loss": 1.0992,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0996192693710327,
+      "eval_runtime": 11.4609,
+      "eval_samples_per_second": 856.391,
+      "eval_steps_per_second": 3.403,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.80013037809648e-05,
+      "loss": 1.0988,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.098758578300476,
+      "eval_runtime": 11.4241,
+      "eval_samples_per_second": 859.146,
+      "eval_steps_per_second": 3.414,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.70013037809648e-05,
+      "loss": 1.0987,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.098650336265564,
+      "eval_runtime": 11.3879,
+      "eval_samples_per_second": 861.881,
+      "eval_steps_per_second": 3.425,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.60013037809648e-05,
+      "loss": 1.0986,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986592769622803,
+      "eval_runtime": 11.4873,
+      "eval_samples_per_second": 854.425,
+      "eval_steps_per_second": 3.395,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.50013037809648e-05,
+      "loss": 1.0987,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0984472036361694,
+      "eval_runtime": 11.4054,
+      "eval_samples_per_second": 860.558,
+      "eval_steps_per_second": 3.419,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.40013037809648e-05,
+      "loss": 1.0987,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986328125,
+      "eval_runtime": 11.4628,
+      "eval_samples_per_second": 856.251,
+      "eval_steps_per_second": 3.402,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3001303780964804e-05,
+      "loss": 1.0986,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0986063480377197,
+      "eval_runtime": 11.4244,
+      "eval_samples_per_second": 859.13,
+      "eval_steps_per_second": 3.414,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.20039113428944e-05,
+      "loss": 1.0987,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0986063480377197,
+      "eval_runtime": 11.4277,
+      "eval_samples_per_second": 858.877,
+      "eval_steps_per_second": 3.413,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.10045632333768e-05,
+      "loss": 1.0986,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.098358392715454,
+      "eval_runtime": 11.4149,
+      "eval_samples_per_second": 859.839,
+      "eval_steps_per_second": 3.417,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.000456323337679e-05,
+      "loss": 1.0986,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0982866287231445,
+      "eval_runtime": 11.4072,
+      "eval_samples_per_second": 860.424,
+      "eval_steps_per_second": 3.419,
+      "step": 15340
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9004563233376796e-05,
+      "loss": 1.0987,
+      "step": 16874
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986417531967163,
+      "eval_runtime": 11.4708,
+      "eval_samples_per_second": 855.65,
+      "eval_steps_per_second": 3.4,
+      "step": 16874
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.800456323337679e-05,
+      "loss": 1.0987,
+      "step": 18408
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0983929634094238,
+      "eval_runtime": 11.4592,
+      "eval_samples_per_second": 856.517,
+      "eval_steps_per_second": 3.403,
+      "step": 18408
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.7004563233376795e-05,
+      "loss": 1.0986,
+      "step": 19942
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0983316898345947,
+      "eval_runtime": 11.4401,
+      "eval_samples_per_second": 857.948,
+      "eval_steps_per_second": 3.409,
+      "step": 19942
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.600456323337679e-05,
+      "loss": 1.0986,
+      "step": 21476
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0983843803405762,
+      "eval_runtime": 11.4436,
+      "eval_samples_per_second": 857.683,
+      "eval_steps_per_second": 3.408,
+      "step": 21476
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 3.50045632333768e-05,
+      "loss": 1.0986,
+      "step": 23010
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.3544574630667346,
+      "eval_loss": 1.0986328125,
+      "eval_runtime": 11.4531,
+      "eval_samples_per_second": 856.97,
+      "eval_steps_per_second": 3.405,
+      "step": 23010
+    },
+    {
+      "epoch": 15.0,
+      "step": 23010,
+      "total_flos": 7.33692663127081e+17,
+      "train_loss": 1.0986910359541369,
+      "train_runtime": 20364.3039,
+      "train_samples_per_second": 964.192,
+      "train_steps_per_second": 3.766
+    }
+  ],
+  "max_steps": 76700,
+  "num_train_epochs": 50,
+  "total_flos": 7.33692663127081e+17,
+  "trial_name": null,
+  "trial_params": null
+}