End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-base-banking77-pt2
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.2882
 
 ## Model description
 
@@ -40,7 +42,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 640
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 10
 
 ### Training results
 

logs/events.out.tfevents.1702227000.07df5a8b60a1.2585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fd0f274d60d2b02e3f867847b550b0b73ce4905bf94570b51a2f06fe209739
+size 5224

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdf21c65e42ecf425af13ee6cb1bc584fb68ab844200b542e0174b7ee5e4cb4
+oid sha256:6729e64018ebc5616c73c83749f191be7b30355301edcf01b4dc16b751c61810
 size 497814144

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 4.375,
+  "best_metric": 6.288247108459473,
+  "best_model_checkpoint": "bert-base-banking77-pt2/checkpoint-10",
+  "epoch": 8.875,
   "eval_steps": 10,
-  "global_step": 7,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,13 +25,36 @@
       "train_runtime": 0.0348,
       "train_samples_per_second": 201109.164,
       "train_steps_per_second": 201.109
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 3.5e-05,
+      "loss": 7.1176,
+      "step": 10
+    },
+    {
+      "epoch": 8.88,
+      "eval_loss": 6.288247108459473,
+      "eval_runtime": 12.385,
+      "eval_samples_per_second": 80.743,
+      "eval_steps_per_second": 2.584,
+      "step": 10
+    },
+    {
+      "epoch": 8.88,
+      "step": 10,
+      "total_flos": 410228490240000.0,
+      "train_loss": 2.135270118713379,
+      "train_runtime": 92.0794,
+      "train_samples_per_second": 108.602,
+      "train_steps_per_second": 0.109
     }
   ],
   "logging_steps": 10,
-  "max_steps": 7,
-  "num_train_epochs": 7,
+  "max_steps": 10,
+  "num_train_epochs": 10,
   "save_steps": 10,
-  "total_flos": 286376067072000.0,
+  "total_flos": 410228490240000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3120a79b950bf9a79bef5fab066d940b2c8afce2622e34f82e0c5edb68126598
+oid sha256:dd8fdabe3ce8b5faf7d270d98467375c27a1b24feaf5108409ab4e5f05f2e744
 size 4600