End of training

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+all_results.json filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
+full_predict_tr_results.json filter=lfs diff=lfs merge=lfs -text
+predict_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: albert/albert-base-v2
 tags:
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: squad_albert_finetuned4
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_albert_finetuned4
 
-This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a773f26bff0deed5819434ff30e02e9c4a68966d7ca60cb03921a2b922c99b
+size 17471502

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015484f15de446817f0aad4e90db0b3b6c0d2e2794d22118774eec8c35c38ed7
+size 65688368

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 84.05865657521286,
+    "eval_f1": 90.94001917546326,
+    "eval_runtime": 36.9087,
+    "eval_samples": 10808,
+    "eval_samples_per_second": 292.83,
+    "eval_steps_per_second": 36.604
+}

full_predict_tr_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00cf23957091b96e75a41cb5a21f69cb29f94187165374e53a63d9e6b1fdfa6
+size 15587234

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015484f15de446817f0aad4e90db0b3b6c0d2e2794d22118774eec8c35c38ed7
+size 65688368

predict_tr_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_tr": 88638,
+    "test_exact_match": 79.27944382926746,
+    "test_f1": 90.81739314452958,
+    "test_runtime": 303.6453,
+    "test_samples_per_second": 291.913,
+    "test_steps_per_second": 36.49
+}

predict_val_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_val": 10808,
+    "test_exact_match": 84.05865657521286,
+    "test_f1": 90.94001917546326,
+    "test_runtime": 35.4654,
+    "test_samples_per_second": 304.747,
+    "test_steps_per_second": 38.093
+}

runs/Feb09_15-37-45_xgpi3/events.out.tfevents.1739088176.xgpi3.6318.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e58b8aac50aaf6a5b1206ea88127f96b69a35d970b42df0aee2953f4299043d
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2936196213553152.0,
+    "train_loss": 0.8232728455217709,
+    "train_runtime": 1379.4371,
+    "train_samples": 88638,
+    "train_samples_per_second": 128.513,
+    "train_steps_per_second": 2.678
+}

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3694,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2707092582566324,
+      "grad_norm": 21.4527587890625,
+      "learning_rate": 2.5939361126150515e-05,
+      "loss": 1.2393,
+      "step": 500
+    },
+    {
+      "epoch": 0.5414185165132648,
+      "grad_norm": 19.001697540283203,
+      "learning_rate": 2.187872225230103e-05,
+      "loss": 0.9569,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8121277747698972,
+      "grad_norm": 13.545599937438965,
+      "learning_rate": 1.7818083378451544e-05,
+      "loss": 0.8955,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0828370330265296,
+      "grad_norm": 14.762840270996094,
+      "learning_rate": 1.3757444504602057e-05,
+      "loss": 0.7921,
+      "step": 2000
+    },
+    {
+      "epoch": 1.353546291283162,
+      "grad_norm": 23.409305572509766,
+      "learning_rate": 9.696805630752573e-06,
+      "loss": 0.6574,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6242555495397943,
+      "grad_norm": 15.587923049926758,
+      "learning_rate": 5.636166756903086e-06,
+      "loss": 0.6549,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8949648077964265,
+      "grad_norm": 14.118770599365234,
+      "learning_rate": 1.5755278830536005e-06,
+      "loss": 0.6304,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "step": 3694,
+      "total_flos": 2936196213553152.0,
+      "train_loss": 0.8232728455217709,
+      "train_runtime": 1379.4371,
+      "train_samples_per_second": 128.513,
+      "train_steps_per_second": 2.678
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3694,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2936196213553152.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}