Training in progress, epoch 1

README.md

@@ -5,18 +5,18 @@ base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
-- name: Se124M500KInfKeyValue
+- name: Se124M500KInfSimple
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Se124M500KInfKeyValue
+# Se124M500KInfSimple
 
 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: 0.5125
+- Loss: 0.4475
 
 ## Model description
 
@@ -41,16 +41,42 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.1379        | 1.0   | 7890  | 0.5277          |
-| 0.1328        | 2.0   | 15780 | 0.5159          |
-| 0.1316        | 3.0   | 23670 | 0.5125          |
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.1287        | 1.0   | 8317   | 0.5023          |
+| 0.1249        | 2.0   | 16634  | 0.4836          |
+| 0.1214        | 3.0   | 24951  | 0.4746          |
+| 0.1225        | 4.0   | 33268  | 0.4691          |
+| 0.1212        | 5.0   | 41585  | 0.4653          |
+| 0.1192        | 6.0   | 49902  | 0.4625          |
+| 0.1203        | 7.0   | 58219  | 0.4595          |
+| 0.1182        | 8.0   | 66536  | 0.4579          |
+| 0.117         | 9.0   | 74853  | 0.4565          |
+| 0.1184        | 10.0  | 83170  | 0.4543          |
+| 0.1165        | 11.0  | 91487  | 0.4539          |
+| 0.116         | 12.0  | 99804  | 0.4528          |
+| 0.117         | 13.0  | 108121 | 0.4515          |
+| 0.1161        | 14.0  | 116438 | 0.4512          |
+| 0.1149        | 15.0  | 124755 | 0.4510          |
+| 0.1157        | 16.0  | 133072 | 0.4503          |
+| 0.1162        | 17.0  | 141389 | 0.4497          |
+| 0.1155        | 18.0  | 149706 | 0.4497          |
+| 0.115         | 19.0  | 158023 | 0.4496          |
+| 0.1156        | 20.0  | 166340 | 0.4488          |
+| 0.1156        | 21.0  | 174657 | 0.4492          |
+| 0.114         | 22.0  | 182974 | 0.4483          |
+| 0.1122        | 23.0  | 191291 | 0.4488          |
+| 0.1134        | 24.0  | 199608 | 0.4480          |
+| 0.114         | 25.0  | 207925 | 0.4476          |
+| 0.1159        | 26.0  | 216242 | 0.4481          |
+| 0.115         | 27.0  | 224559 | 0.4475          |
+| 0.1145        | 28.0  | 232876 | 0.4475          |
+| 0.1141        | 29.0  | 241193 | 0.4477          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2edd1ac6046eb1727376c50e98f07a81d1245986962273f81f91b833390dc013
+oid sha256:d3d2425931099ef58f09edd41ff08a773f3e0fd2614129d42d246960f2c1456d
 size 309974336

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.5125296115875244,
-    "eval_runtime": 335.8616,
-    "eval_samples_per_second": 160.786,
-    "eval_steps_per_second": 5.026,
-    "perplexity": 1.6695090673895705,
-    "total_flos": 4.964450408556134e+16,
-    "train_loss": 0.14119057995788548,
-    "train_runtime": 2419.9093,
-    "train_samples_per_second": 312.97,
-    "train_steps_per_second": 9.781
+    "epoch": 29.0,
+    "eval_loss": 0.4475274682044983,
+    "eval_runtime": 362.3481,
+    "eval_samples_per_second": 157.114,
+    "eval_steps_per_second": 4.912,
+    "perplexity": 1.5644392736681412,
+    "total_flos": 5.058807603414958e+17,
+    "train_loss": 0.11824046083851339,
+    "train_runtime": 25872.5126,
+    "train_samples_per_second": 514.295,
+    "train_steps_per_second": 16.073
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.5125296115875244,
-    "eval_runtime": 335.8616,
-    "eval_samples_per_second": 160.786,
-    "eval_steps_per_second": 5.026,
-    "perplexity": 1.6695090673895705
+    "epoch": 29.0,
+    "eval_loss": 0.4475274682044983,
+    "eval_runtime": 362.3481,
+    "eval_samples_per_second": 157.114,
+    "eval_steps_per_second": 4.912,
+    "perplexity": 1.5644392736681412
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 4.964450408556134e+16,
-    "train_loss": 0.14119057995788548,
-    "train_runtime": 2419.9093,
-    "train_samples_per_second": 312.97,
-    "train_steps_per_second": 9.781
+    "epoch": 29.0,
+    "total_flos": 5.058807603414958e+17,
+    "train_loss": 0.11824046083851339,
+    "train_runtime": 25872.5126,
+    "train_samples_per_second": 514.295,
+    "train_steps_per_second": 16.073
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1ce96f12de9b1ff1cb809b16cb4dde0102780a08f892825fada3abcdc64a4e
+oid sha256:48bc8a9c586835ebf2b8d61c7e3abec9bc92d1b305ab61f047fb443adf7100bb
 size 5432