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-128_A-2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-128_A-2_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7112489829129374
 ---
 
 <!-- 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-128_A-2_mnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7059
-- Accuracy: 0.7147
+- Loss: 0.6901
+- Accuracy: 0.7112
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 16.0,
+    "epoch_mm": 16.0,
+    "eval_accuracy": 0.7063678043810494,
+    "eval_accuracy_mm": 0.7112489829129374,
+    "eval_loss": 0.6966096758842468,
+    "eval_loss_mm": 0.6901494860649109,
+    "eval_runtime": 3.0139,
+    "eval_runtime_mm": 3.0078,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3256.594,
+    "eval_samples_per_second_mm": 3268.863,
+    "eval_steps_per_second": 12.94,
+    "eval_steps_per_second_mm": 12.966,
+    "total_flos": 3992627397378048.0,
+    "train_loss": 0.6793889937220527,
+    "train_runtime": 2308.8944,
+    "train_samples": 392702,
+    "train_samples_per_second": 8504.114,
+    "train_steps_per_second": 33.219
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 16.0,
+    "epoch_mm": 16.0,
+    "eval_accuracy": 0.7063678043810494,
+    "eval_accuracy_mm": 0.7112489829129374,
+    "eval_loss": 0.6966096758842468,
+    "eval_loss_mm": 0.6901494860649109,
+    "eval_runtime": 3.0139,
+    "eval_runtime_mm": 3.0078,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3256.594,
+    "eval_samples_per_second_mm": 3268.863,
+    "eval_steps_per_second": 12.94,
+    "eval_steps_per_second_mm": 12.966
+}

logs/events.out.tfevents.1733348933.ki-g0008.1759256.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74abe54e4de15adba3e04291e6854e5d54e0e1a81906e5507e09037592094f8c
+size 746

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 16.0,
+    "total_flos": 3992627397378048.0,
+    "train_loss": 0.6793889937220527,
+    "train_runtime": 2308.8944,
+    "train_samples": 392702,
+    "train_samples_per_second": 8504.114,
+    "train_steps_per_second": 33.219
+}

trainer_state.json

@@ -0,0 +1,307 @@
+{
+  "best_metric": 0.6966096758842468,
+  "best_model_checkpoint": "bert_uncased_L-2_H-128_A-2_mnli/checkpoint-16874",
+  "epoch": 16.0,
+  "eval_steps": 500,
+  "global_step": 24544,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.641183853149414,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9155,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6342333163525217,
+      "eval_loss": 0.8197218775749207,
+      "eval_runtime": 3.1144,
+      "eval_samples_per_second": 3151.502,
+      "eval_steps_per_second": 12.523,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0699892044067383,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8189,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6625573102394294,
+      "eval_loss": 0.7689471244812012,
+      "eval_runtime": 3.0712,
+      "eval_samples_per_second": 3195.829,
+      "eval_steps_per_second": 12.699,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7944191694259644,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7747,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6760061130922058,
+      "eval_loss": 0.7416538596153259,
+      "eval_runtime": 3.0841,
+      "eval_samples_per_second": 3182.445,
+      "eval_steps_per_second": 12.645,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8538000583648682,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7449,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6851757514009169,
+      "eval_loss": 0.7284622192382812,
+      "eval_runtime": 3.0649,
+      "eval_samples_per_second": 3202.403,
+      "eval_steps_per_second": 12.725,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.2576873302459717,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7198,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.693428425878757,
+      "eval_loss": 0.7110932469367981,
+      "eval_runtime": 3.0825,
+      "eval_samples_per_second": 3184.117,
+      "eval_steps_per_second": 12.652,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2374134063720703,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6996,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6977075904228223,
+      "eval_loss": 0.7117594480514526,
+      "eval_runtime": 3.0866,
+      "eval_samples_per_second": 3179.874,
+      "eval_steps_per_second": 12.635,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.3460779190063477,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6812,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7030056036678554,
+      "eval_loss": 0.7004757523536682,
+      "eval_runtime": 3.0836,
+      "eval_samples_per_second": 3182.923,
+      "eval_steps_per_second": 12.647,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.158047914505005,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6649,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7043301069791136,
+      "eval_loss": 0.6981356739997864,
+      "eval_runtime": 3.0881,
+      "eval_samples_per_second": 3178.334,
+      "eval_steps_per_second": 12.629,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.4495298862457275,
+      "learning_rate": 4.1e-05,
+      "loss": 0.6491,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7036169128884361,
+      "eval_loss": 0.7056555151939392,
+      "eval_runtime": 3.0711,
+      "eval_samples_per_second": 3195.888,
+      "eval_steps_per_second": 12.699,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.2467546463012695,
+      "learning_rate": 4e-05,
+      "loss": 0.6358,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7076923076923077,
+      "eval_loss": 0.698304295539856,
+      "eval_runtime": 3.0715,
+      "eval_samples_per_second": 3195.477,
+      "eval_steps_per_second": 12.697,
+      "step": 15340
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.603757619857788,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.6224,
+      "step": 16874
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7063678043810494,
+      "eval_loss": 0.6966096758842468,
+      "eval_runtime": 3.0786,
+      "eval_samples_per_second": 3188.18,
+      "eval_steps_per_second": 12.668,
+      "step": 16874
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.9877541065216064,
+      "learning_rate": 3.8e-05,
+      "loss": 0.6109,
+      "step": 18408
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7145185939887927,
+      "eval_loss": 0.7001488208770752,
+      "eval_runtime": 3.1144,
+      "eval_samples_per_second": 3151.457,
+      "eval_steps_per_second": 12.522,
+      "step": 18408
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 2.9254136085510254,
+      "learning_rate": 3.7e-05,
+      "loss": 0.5994,
+      "step": 19942
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.7112582781456953,
+      "eval_loss": 0.7014375329017639,
+      "eval_runtime": 3.0536,
+      "eval_samples_per_second": 3214.286,
+      "eval_steps_per_second": 12.772,
+      "step": 19942
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 2.3332672119140625,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5872,
+      "step": 21476
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.7084055017829852,
+      "eval_loss": 0.7061210870742798,
+      "eval_runtime": 3.0601,
+      "eval_samples_per_second": 3207.409,
+      "eval_steps_per_second": 12.745,
+      "step": 21476
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.173841953277588,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5779,
+      "step": 23010
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.716760061130922,
+      "eval_loss": 0.7053535580635071,
+      "eval_runtime": 3.016,
+      "eval_samples_per_second": 3254.334,
+      "eval_steps_per_second": 12.931,
+      "step": 23010
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.5497801303863525,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.5681,
+      "step": 24544
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.7147223637289862,
+      "eval_loss": 0.7059070467948914,
+      "eval_runtime": 3.034,
+      "eval_samples_per_second": 3234.976,
+      "eval_steps_per_second": 12.854,
+      "step": 24544
+    },
+    {
+      "epoch": 16.0,
+      "step": 24544,
+      "total_flos": 3992627397378048.0,
+      "train_loss": 0.6793889937220527,
+      "train_runtime": 2308.8944,
+      "train_samples_per_second": 8504.114,
+      "train_steps_per_second": 33.219
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 76700,
+  "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": 3992627397378048.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}