End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 3.2330
+- Loss: 2.1050
 
 ## Model description
 
@@ -40,15 +40,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 19.3915       | 1.0   | 10   | 4.2030          |
-| 3.99          | 2.0   | 20   | 3.7262          |
-| 3.2015        | 3.0   | 30   | 3.2330          |
+| 17.0348       | 1.0   | 10   | 4.3278          |
+| 4.1755        | 2.0   | 20   | 2.9010          |
+| 2.9516        | 3.0   | 30   | 2.5815          |
+| 2.4828        | 4.0   | 40   | 2.1538          |
+| 2.2802        | 5.0   | 50   | 2.1050          |
 
 
 ### Framework versions

logs/events.out.tfevents.1702138955.62a1e4c74a80.28401.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5f353f9d084001096c13f26013c816671962fd60eb5c2c0760cae1f789696d
+size 4875

logs/events.out.tfevents.1702139054.62a1e4c74a80.28401.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5069f98d12f22e25e1049e38192074bd667536db10532b34d4edf6482ba9c900
+size 4875

logs/events.out.tfevents.1702139174.62a1e4c74a80.28401.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e403265c55d3c3eb8d0f425593ba6bf252c3e364275781004e5702e030d6261b
+size 4875

logs/events.out.tfevents.1702139233.62a1e4c74a80.28401.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843dff6f2fd5e5ba3d8d35e5a913419b97ddecfeefe219fc11106bb10953a8bd
+size 4875

logs/events.out.tfevents.1702139307.62a1e4c74a80.28401.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d122bbf63137c1fa2ecd72a3ae33f6a4277f431b5adbf2c6395f63a0a50efcf5
+size 4875

logs/events.out.tfevents.1702139405.62a1e4c74a80.28401.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b421831a980d159a229620cdc1e8aef91a7c68bfac8809892dc798744d22f7a
+size 4875

logs/events.out.tfevents.1702139462.62a1e4c74a80.28401.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf4af6c1f07596102a2c8c1b874be46de28c88fe23b2403d2db7bfdb302ed95
+size 4875

logs/events.out.tfevents.1702139569.62a1e4c74a80.42734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10573f1c578060c8a7fe7a63532c3c57c7f594549f6e9abe28d61f0b0878901f
+size 4875

logs/events.out.tfevents.1702139738.62a1e4c74a80.42734.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862b59d537c3087970dda4eb9cb0c43c58ef9783742940b6a7c60c3fd50dc0de
+size 4609

logs/events.out.tfevents.1702139834.62a1e4c74a80.42734.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f34eda1d1492413ee3260d01c6ee127a9048f449b1c66d607a578a0021ed865
+size 4609

logs/events.out.tfevents.1702139869.62a1e4c74a80.42734.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9965faac42822f0f8dd6b916c3421c4eef98c2f81716cc53a8cd84cb30bd5061
+size 4609

logs/events.out.tfevents.1702139961.62a1e4c74a80.42734.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb78934330590605c7e6c40d2e76cd06c6e526687f8e070e4836d7305b0716f
+size 4606

logs/events.out.tfevents.1702140138.62a1e4c74a80.42734.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d331a24dc9a532716744ac508481766b12cfb51fc86ddac9464f97d6a5c276
+size 4606

logs/events.out.tfevents.1702140238.62a1e4c74a80.42734.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144e0bfbd3ee6def3d3b70dd254dcf318d6522605997aa8c59b542a091b4046a
+size 4606

logs/events.out.tfevents.1702140298.62a1e4c74a80.42734.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4dc6c185b3fcd0c7c041bfcbf5217c38518795ebe2da4eb4d824d8bf031f504
+size 4606

logs/events.out.tfevents.1702140363.62a1e4c74a80.42734.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04157d0d4f2197967f760ef4efbc4616f70239cbc5707c7e167a64d87c1266ec
+size 4606

logs/events.out.tfevents.1702140378.62a1e4c74a80.42734.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cac25fa574b929b1709021b730dc363484aa419ae45cc7a721d311d1b2562c
+size 4606

logs/events.out.tfevents.1702140407.62a1e4c74a80.42734.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6154844b860859f9b3651ba14e82d5d4a430de14bf1b477a8894ef939ded591b
+size 6900

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88ed9b657a61945ca24ea5091d4c155db10756fe037cc5b74535e0209d21b87
+oid sha256:09037655973ebe73f63dc99bf71b69df1b21e4ed23b2b929dd5d59a3c929ef1f
 size 497814144

trainer_state.json

@@ -1,70 +1,98 @@
 {
-  "best_metric": 3.2330009937286377,
-  "best_model_checkpoint": "bert-base-banking77-pt2/checkpoint-30",
-  "epoch": 3.0,
+  "best_metric": 2.105010747909546,
+  "best_model_checkpoint": "bert-base-banking77-pt2/checkpoint-50",
+  "epoch": 5.0,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 19.3915,
+      "learning_rate": 4e-05,
+      "loss": 17.0348,
       "step": 10
     },
     {
       "epoch": 1.0,
-      "eval_loss": 4.202950954437256,
-      "eval_runtime": 0.2436,
-      "eval_samples_per_second": 41.048,
-      "eval_steps_per_second": 8.21,
+      "eval_loss": 4.327815055847168,
+      "eval_runtime": 0.2279,
+      "eval_samples_per_second": 43.887,
+      "eval_steps_per_second": 8.777,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "learning_rate": 1.6666666666666667e-05,
-      "loss": 3.99,
+      "learning_rate": 3e-05,
+      "loss": 4.1755,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_loss": 3.726235866546631,
-      "eval_runtime": 0.2518,
-      "eval_samples_per_second": 39.71,
-      "eval_steps_per_second": 7.942,
+      "eval_loss": 2.9009530544281006,
+      "eval_runtime": 0.1465,
+      "eval_samples_per_second": 68.244,
+      "eval_steps_per_second": 13.649,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.0,
-      "loss": 3.2015,
+      "learning_rate": 2e-05,
+      "loss": 2.9516,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "eval_loss": 3.2330009937286377,
-      "eval_runtime": 0.1321,
-      "eval_samples_per_second": 75.687,
-      "eval_steps_per_second": 15.137,
+      "eval_loss": 2.581455707550049,
+      "eval_runtime": 0.1718,
+      "eval_samples_per_second": 58.205,
+      "eval_steps_per_second": 11.641,
       "step": 30
     },
     {
-      "epoch": 3.0,
-      "step": 30,
-      "total_flos": 1959690240000.0,
-      "train_loss": 0.0,
-      "train_runtime": 0.2088,
-      "train_samples_per_second": 143.66,
-      "train_steps_per_second": 143.66
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 2.4828,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.1537680625915527,
+      "eval_runtime": 0.1261,
+      "eval_samples_per_second": 79.287,
+      "eval_steps_per_second": 15.857,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 2.2802,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.105010747909546,
+      "eval_runtime": 0.1259,
+      "eval_samples_per_second": 79.453,
+      "eval_steps_per_second": 15.891,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "step": 50,
+      "total_flos": 3266150400000.0,
+      "train_loss": 5.784983711242676,
+      "train_runtime": 46.2198,
+      "train_samples_per_second": 1.082,
+      "train_steps_per_second": 1.082
     }
   ],
   "logging_steps": 10,
-  "max_steps": 30,
-  "num_train_epochs": 3,
+  "max_steps": 50,
+  "num_train_epochs": 5,
   "save_steps": 10,
-  "total_flos": 1959690240000.0,
+  "total_flos": 3266150400000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d2e3efd73c0549af05ba602fe17d6f289b9221ec1a605cec415e1fe2103ddf
+oid sha256:f0e816bb628d55636c013287b128c2af89853b6c5e028b9f9192a3db21dc0f9f
 size 4600