End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-4_H-128_A-2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-128_A-2_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8130733944954128
 ---
 
 <!-- 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-4_H-128_A-2_sst2
 
-This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4869
-- Accuracy: 0.8222
+- Loss: 0.4254
+- Accuracy: 0.8131
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.8130733944954128,
+    "eval_loss": 0.4253731071949005,
+    "eval_runtime": 0.2993,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2913.92,
+    "eval_steps_per_second": 13.367,
+    "total_flos": 754242524273664.0,
+    "train_loss": 0.26212185561054885,
+    "train_runtime": 260.6206,
+    "train_samples": 67349,
+    "train_samples_per_second": 12920.89,
+    "train_steps_per_second": 50.648
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.8130733944954128,
+    "eval_loss": 0.4253731071949005,
+    "eval_runtime": 0.2993,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2913.92,
+    "eval_steps_per_second": 13.367
+}

logs/events.out.tfevents.1733338770.ki-g0008.1764072.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78290ba296aaf8a6b8c2898fc4d5576d48af7b30fb34d836b1de0dfd96e098f3
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 754242524273664.0,
+    "train_loss": 0.26212185561054885,
+    "train_runtime": 260.6206,
+    "train_samples": 67349,
+    "train_samples_per_second": 12920.89,
+    "train_steps_per_second": 50.648
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.4253731071949005,
+  "best_model_checkpoint": "bert_uncased_L-4_H-128_A-2_sst2/checkpoint-1056",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.3465471267700195,
+      "learning_rate": 4.9e-05,
+      "loss": 0.497,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7786697247706422,
+      "eval_loss": 0.4756825268268585,
+      "eval_runtime": 0.3049,
+      "eval_samples_per_second": 2860.362,
+      "eval_steps_per_second": 13.121,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.5109405517578125,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3535,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.4270114600658417,
+      "eval_runtime": 0.2966,
+      "eval_samples_per_second": 2939.669,
+      "eval_steps_per_second": 13.485,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.689140796661377,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2951,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.42806658148765564,
+      "eval_runtime": 0.3092,
+      "eval_samples_per_second": 2820.531,
+      "eval_steps_per_second": 12.938,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.24284553527832,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2539,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 0.4253731071949005,
+      "eval_runtime": 0.3016,
+      "eval_samples_per_second": 2891.35,
+      "eval_steps_per_second": 13.263,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.972127914428711,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2259,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.434358149766922,
+      "eval_runtime": 0.3064,
+      "eval_samples_per_second": 2845.702,
+      "eval_steps_per_second": 13.054,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.203221797943115,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2048,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.4487341344356537,
+      "eval_runtime": 0.3066,
+      "eval_samples_per_second": 2843.967,
+      "eval_steps_per_second": 13.046,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.583701133728027,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1892,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.4820203483104706,
+      "eval_runtime": 0.2989,
+      "eval_samples_per_second": 2917.167,
+      "eval_steps_per_second": 13.381,
+      "step": 1848
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 8.318140029907227,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1754,
+      "step": 2112
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8348623853211009,
+      "eval_loss": 0.4953659474849701,
+      "eval_runtime": 0.3207,
+      "eval_samples_per_second": 2718.717,
+      "eval_steps_per_second": 12.471,
+      "step": 2112
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 10.092487335205078,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1643,
+      "step": 2376
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.4868989884853363,
+      "eval_runtime": 0.3235,
+      "eval_samples_per_second": 2695.399,
+      "eval_steps_per_second": 12.364,
+      "step": 2376
+    },
+    {
+      "epoch": 9.0,
+      "step": 2376,
+      "total_flos": 754242524273664.0,
+      "train_loss": 0.26212185561054885,
+      "train_runtime": 260.6206,
+      "train_samples_per_second": 12920.89,
+      "train_steps_per_second": 50.648
+    }
+  ],
+  "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": 754242524273664.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}