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: 0.3273560876209883
+      value: 0.3295362082994304
 ---
 
 <!-- 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. -->
 
 # add_BERT_24_mnli
 
-This model is a fine-tuned version of [gokuls/add_bert_12_layer_model_complete_training_new](https://huggingface.co/gokuls/add_bert_12_layer_model_complete_training_new) on the glue dataset.
+This model is a fine-tuned version of [gokuls/add_bert_12_layer_model_complete_training_new](https://huggingface.co/gokuls/add_bert_12_layer_model_complete_training_new) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0986
-- Accuracy: 0.3274
+- Accuracy: 0.3295
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.3273560876209883,
+    "eval_accuracy_mm": 0.3295362082994304,
+    "eval_loss": 1.098607063293457,
+    "eval_loss_mm": 1.0986051559448242,
+    "eval_runtime": 18.573,
+    "eval_runtime_mm": 18.6409,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 528.455,
+    "eval_samples_per_second_mm": 527.442,
+    "eval_steps_per_second": 4.146,
+    "eval_steps_per_second_mm": 4.131,
+    "train_loss": 1.0991917665015438,
+    "train_runtime": 20728.3509,
+    "train_samples": 392702,
+    "train_samples_per_second": 947.258,
+    "train_steps_per_second": 7.4
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.3273560876209883,
+    "eval_accuracy_mm": 0.3295362082994304,
+    "eval_loss": 1.098607063293457,
+    "eval_loss_mm": 1.0986051559448242,
+    "eval_runtime": 18.573,
+    "eval_runtime_mm": 18.6409,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 528.455,
+    "eval_samples_per_second_mm": 527.442,
+    "eval_steps_per_second": 4.146,
+    "eval_steps_per_second_mm": 4.131
+}

logs/events.out.tfevents.1686938362.serv-3317.1852327.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df0dae4f51514eb85daa12117f36c695b28f0921b9740b7e38842b07adeebaa
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 1.0991917665015438,
+    "train_runtime": 20728.3509,
+    "train_samples": 392702,
+    "train_samples_per_second": 947.258,
+    "train_steps_per_second": 7.4
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 1.098607063293457,
+  "best_model_checkpoint": "add_BERT_24_mnli/checkpoint-12272",
+  "epoch": 9.0,
+  "global_step": 27612,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 1.1032,
+      "step": 3068
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0993977785110474,
+      "eval_runtime": 18.7596,
+      "eval_samples_per_second": 523.198,
+      "eval_steps_per_second": 4.105,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 1.0988,
+      "step": 6136
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986474752426147,
+      "eval_runtime": 18.7682,
+      "eval_samples_per_second": 522.959,
+      "eval_steps_per_second": 4.103,
+      "step": 6136
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 1.0987,
+      "step": 9204
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986655950546265,
+      "eval_runtime": 18.7095,
+      "eval_samples_per_second": 524.599,
+      "eval_steps_per_second": 4.116,
+      "step": 9204
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 1.0988,
+      "step": 12272
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.098607063293457,
+      "eval_runtime": 18.7295,
+      "eval_samples_per_second": 524.039,
+      "eval_steps_per_second": 4.111,
+      "step": 12272
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 1.0987,
+      "step": 15340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986140966415405,
+      "eval_runtime": 18.7195,
+      "eval_samples_per_second": 524.319,
+      "eval_steps_per_second": 4.113,
+      "step": 15340
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 1.0986,
+      "step": 18408
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986219644546509,
+      "eval_runtime": 18.741,
+      "eval_samples_per_second": 523.719,
+      "eval_steps_per_second": 4.109,
+      "step": 18408
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 1.0986,
+      "step": 21476
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.098610281944275,
+      "eval_runtime": 18.7043,
+      "eval_samples_per_second": 524.746,
+      "eval_steps_per_second": 4.117,
+      "step": 21476
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 1.0986,
+      "step": 24544
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.31818644931227713,
+      "eval_loss": 1.0986121892929077,
+      "eval_runtime": 18.7343,
+      "eval_samples_per_second": 523.907,
+      "eval_steps_per_second": 4.11,
+      "step": 24544
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.28e-05,
+      "loss": 1.0986,
+      "step": 27612
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3273560876209883,
+      "eval_loss": 1.0986137390136719,
+      "eval_runtime": 18.7418,
+      "eval_samples_per_second": 523.695,
+      "eval_steps_per_second": 4.108,
+      "step": 27612
+    },
+    {
+      "epoch": 9.0,
+      "step": 27612,
+      "total_flos": 5.0478948198383616e+17,
+      "train_loss": 1.0991917665015438,
+      "train_runtime": 20728.3509,
+      "train_samples_per_second": 947.258,
+      "train_steps_per_second": 7.4
+    }
+  ],
+  "max_steps": 153400,
+  "num_train_epochs": 50,
+  "total_flos": 5.0478948198383616e+17,
+  "trial_name": null,
+  "trial_params": null
+}