End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tinybert_base_train_book_ent_15p_s_init_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8371559633027523
 ---
 
 <!-- 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. -->
 
 # tinybert_base_train_book_ent_15p_s_init_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5464
-- Accuracy: 0.8360
+- Loss: 0.4233
+- Accuracy: 0.8372
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8371559633027523,
+    "eval_loss": 0.42326632142066956,
+    "eval_runtime": 0.4562,
+    "eval_samples": 872,
+    "eval_samples_per_second": 1911.424,
+    "eval_steps_per_second": 8.768,
+    "total_flos": 9322707872572416.0,
+    "train_loss": 0.2009547892070952,
+    "train_runtime": 356.0592,
+    "train_samples": 67349,
+    "train_samples_per_second": 9457.557,
+    "train_steps_per_second": 37.072
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8371559633027523,
+    "eval_loss": 0.42326632142066956,
+    "eval_runtime": 0.4562,
+    "eval_samples": 872,
+    "eval_samples_per_second": 1911.424,
+    "eval_steps_per_second": 8.768
+}

logs/events.out.tfevents.1745508118.ki-g0008.3436350.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba67fb12d472eb1bfdd469198c1bf85cf9c05d9f18a035c1c2cc85669a1e020
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 9322707872572416.0,
+    "train_loss": 0.2009547892070952,
+    "train_runtime": 356.0592,
+    "train_samples": 67349,
+    "train_samples_per_second": 9457.557,
+    "train_steps_per_second": 37.072
+}

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 528,
+  "best_metric": 0.42326632142066956,
+  "best_model_checkpoint": "tinybert_base_train_book_ent_15p_s_init_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": 8.234528541564941,
+      "learning_rate": 4.9003787878787885e-05,
+      "loss": 0.4327,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 0.42891594767570496,
+      "eval_runtime": 0.4846,
+      "eval_samples_per_second": 1799.371,
+      "eval_steps_per_second": 8.254,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.003406524658203,
+      "learning_rate": 4.800378787878788e-05,
+      "loss": 0.2697,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8371559633027523,
+      "eval_loss": 0.42326632142066956,
+      "eval_runtime": 0.5716,
+      "eval_samples_per_second": 1525.65,
+      "eval_steps_per_second": 6.998,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.7203593254089355,
+      "learning_rate": 4.7003787878787884e-05,
+      "loss": 0.201,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 0.44505876302719116,
+      "eval_runtime": 0.4616,
+      "eval_samples_per_second": 1889.032,
+      "eval_steps_per_second": 8.665,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.59065055847168,
+      "learning_rate": 4.600378787878788e-05,
+      "loss": 0.1604,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8451834862385321,
+      "eval_loss": 0.4601452648639679,
+      "eval_runtime": 0.4782,
+      "eval_samples_per_second": 1823.658,
+      "eval_steps_per_second": 8.365,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.951050758361816,
+      "learning_rate": 4.5003787878787876e-05,
+      "loss": 0.1338,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.475068598985672,
+      "eval_runtime": 0.4604,
+      "eval_samples_per_second": 1894.142,
+      "eval_steps_per_second": 8.689,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.206764221191406,
+      "learning_rate": 4.4003787878787885e-05,
+      "loss": 0.1116,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.5976091027259827,
+      "eval_runtime": 0.4585,
+      "eval_samples_per_second": 1901.705,
+      "eval_steps_per_second": 8.723,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 11.474570274353027,
+      "learning_rate": 4.300378787878788e-05,
+      "loss": 0.0973,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8360091743119266,
+      "eval_loss": 0.5464378595352173,
+      "eval_runtime": 0.4503,
+      "eval_samples_per_second": 1936.314,
+      "eval_steps_per_second": 8.882,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "step": 1848,
+      "total_flos": 9322707872572416.0,
+      "train_loss": 0.2009547892070952,
+      "train_runtime": 356.0592,
+      "train_samples_per_second": 9457.557,
+      "train_steps_per_second": 37.072
+    }
+  ],
+  "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": 9322707872572416.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}