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-256_A-4
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-256_A-4_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8211009174311926
 ---
 
 <!-- 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-256_A-4_sst2
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-256_A-4](https://huggingface.co/google/bert_uncased_L-2_H-256_A-4) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-256_A-4](https://huggingface.co/google/bert_uncased_L-2_H-256_A-4) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5187
-- Accuracy: 0.8326
+- Loss: 0.4074
+- Accuracy: 0.8211
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8211009174311926,
+    "eval_loss": 0.40743663907051086,
+    "eval_runtime": 0.3039,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2869.079,
+    "eval_steps_per_second": 13.161,
+    "total_flos": 1192173351527424.0,
+    "train_loss": 0.23822046461559476,
+    "train_runtime": 191.9714,
+    "train_samples": 67349,
+    "train_samples_per_second": 17541.413,
+    "train_steps_per_second": 68.76
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8211009174311926,
+    "eval_loss": 0.40743663907051086,
+    "eval_runtime": 0.3039,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2869.079,
+    "eval_steps_per_second": 13.161
+}

logs/events.out.tfevents.1733333065.ki-g0008.1764072.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c698510b0a8fa0e2796713c53dbdebe92e79e04b8575f9253423e5409531fe
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1192173351527424.0,
+    "train_loss": 0.23822046461559476,
+    "train_runtime": 191.9714,
+    "train_samples": 67349,
+    "train_samples_per_second": 17541.413,
+    "train_steps_per_second": 68.76
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.40743663907051086,
+  "best_model_checkpoint": "bert_uncased_L-2_H-256_A-4_sst2/checkpoint-528",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1848,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.376885890960693,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4405,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 0.41945868730545044,
+      "eval_runtime": 0.306,
+      "eval_samples_per_second": 2849.234,
+      "eval_steps_per_second": 13.07,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.9676666259765625,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2935,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.40743663907051086,
+      "eval_runtime": 0.2939,
+      "eval_samples_per_second": 2967.419,
+      "eval_steps_per_second": 13.612,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.570894241333008,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2371,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.42405587434768677,
+      "eval_runtime": 0.2923,
+      "eval_samples_per_second": 2983.543,
+      "eval_steps_per_second": 13.686,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.769681930541992,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2044,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.4573158919811249,
+      "eval_runtime": 0.2898,
+      "eval_samples_per_second": 3009.426,
+      "eval_steps_per_second": 13.805,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.537114143371582,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1805,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 0.4635075628757477,
+      "eval_runtime": 0.2906,
+      "eval_samples_per_second": 3000.771,
+      "eval_steps_per_second": 13.765,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.772435188293457,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.163,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8325688073394495,
+      "eval_loss": 0.49149924516677856,
+      "eval_runtime": 0.4558,
+      "eval_samples_per_second": 1913.094,
+      "eval_steps_per_second": 8.776,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.723846435546875,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1486,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8325688073394495,
+      "eval_loss": 0.5186809301376343,
+      "eval_runtime": 0.2897,
+      "eval_samples_per_second": 3009.624,
+      "eval_steps_per_second": 13.806,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "step": 1848,
+      "total_flos": 1192173351527424.0,
+      "train_loss": 0.23822046461559476,
+      "train_runtime": 191.9714,
+      "train_samples_per_second": 17541.413,
+      "train_steps_per_second": 68.76
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 13200,
+  "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": 1192173351527424.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}