End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_train_book_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tinybert_train_book_v2_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.763120423108218
 ---
 
 <!-- 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_train_book_v2_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_v2](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_v2) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_v2](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7525
-- Accuracy: 0.7624
+- Loss: 0.5840
+- Accuracy: 0.7631
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7577177789098319,
+    "eval_accuracy_mm": 0.763120423108218,
+    "eval_loss": 0.6048181056976318,
+    "eval_loss_mm": 0.5839571356773376,
+    "eval_runtime": 3.0264,
+    "eval_runtime_mm": 3.0155,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3243.136,
+    "eval_samples_per_second_mm": 3260.492,
+    "eval_steps_per_second": 12.887,
+    "eval_steps_per_second_mm": 12.933,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.4677888803096607,
+    "train_runtime": 1742.9254,
+    "train_samples": 392702,
+    "train_samples_per_second": 11265.6,
+    "train_steps_per_second": 44.006
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7577177789098319,
+    "eval_accuracy_mm": 0.763120423108218,
+    "eval_loss": 0.6048181056976318,
+    "eval_loss_mm": 0.5839571356773376,
+    "eval_runtime": 3.0264,
+    "eval_runtime_mm": 3.0155,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3243.136,
+    "eval_samples_per_second_mm": 3260.492,
+    "eval_steps_per_second": 12.887,
+    "eval_steps_per_second_mm": 12.933
+}

logs/events.out.tfevents.1738236316.ki-g0008.245006.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436201e6a0dc01f5995fbfe97b32445b527e170767a0432fda3326e3f3f2bf17
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.4677888803096607,
+    "train_runtime": 1742.9254,
+    "train_samples": 392702,
+    "train_samples_per_second": 11265.6,
+    "train_steps_per_second": 44.006
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6048181056976318,
+  "best_model_checkpoint": "tinybert_train_book_v2_mnli/checkpoint-4602",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 12272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.3192458152770996,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7774,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7187977585328579,
+      "eval_loss": 0.666066586971283,
+      "eval_runtime": 3.1975,
+      "eval_samples_per_second": 3069.538,
+      "eval_steps_per_second": 12.197,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0783512592315674,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6247,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7500764136525726,
+      "eval_loss": 0.6113393902778625,
+      "eval_runtime": 3.3146,
+      "eval_samples_per_second": 2961.111,
+      "eval_steps_per_second": 11.766,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2522432804107666,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5397,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7577177789098319,
+      "eval_loss": 0.6048181056976318,
+      "eval_runtime": 3.4015,
+      "eval_samples_per_second": 2885.489,
+      "eval_steps_per_second": 11.466,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.7355704307556152,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4702,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7657666836474784,
+      "eval_loss": 0.6142801642417908,
+      "eval_runtime": 3.0282,
+      "eval_samples_per_second": 3241.228,
+      "eval_steps_per_second": 12.879,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.552318811416626,
+      "learning_rate": 4.5e-05,
+      "loss": 0.409,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7654610290371879,
+      "eval_loss": 0.6275655627250671,
+      "eval_runtime": 3.4437,
+      "eval_samples_per_second": 2850.144,
+      "eval_steps_per_second": 11.325,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.787414073944092,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3531,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7641365257259297,
+      "eval_loss": 0.6843419671058655,
+      "eval_runtime": 3.0824,
+      "eval_samples_per_second": 3184.223,
+      "eval_steps_per_second": 12.653,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.5224530696868896,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3063,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7648497198166072,
+      "eval_loss": 0.7110432386398315,
+      "eval_runtime": 3.2277,
+      "eval_samples_per_second": 3040.843,
+      "eval_steps_per_second": 12.083,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.977783679962158,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2619,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7624044829342843,
+      "eval_loss": 0.7525456547737122,
+      "eval_runtime": 3.081,
+      "eval_samples_per_second": 3185.632,
+      "eval_steps_per_second": 12.658,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "step": 12272,
+      "total_flos": 8.238688806678528e+16,
+      "train_loss": 0.4677888803096607,
+      "train_runtime": 1742.9254,
+      "train_samples_per_second": 11265.6,
+      "train_steps_per_second": 44.006
+    }
+  ],
+  "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": 8.238688806678528e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}