Training in progress, epoch 1

README.md

@@ -5,18 +5,18 @@ base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
-- name: Se124M500KInfSimple
+- name: Se124M500KInfMinimalist
   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. -->
 
-# Se124M500KInfSimple
+# Se124M500KInfMinimalist
 
 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: 0.4881
+- Loss: 0.5700
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.1297        | 1.0   | 8317  | 0.5045          |
-| 0.1268        | 2.0   | 16634 | 0.4917          |
-| 0.1248        | 3.0   | 24951 | 0.4881          |
+| 0.1527        | 1.0   | 7035  | 0.5857          |
+| 0.1485        | 2.0   | 14070 | 0.5736          |
+| 0.1468        | 3.0   | 21105 | 0.5700          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3360775adf5f55e02c895bb86a2f0084bd76052a208ddc57fe87e155454e90b7
+oid sha256:174011ec29c75f08221ec92842e4013a8813fa8f56d81400054624f388b4bd5a
 size 309974336

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.48813220858573914,
-    "eval_runtime": 355.5361,
-    "eval_samples_per_second": 160.124,
-    "eval_steps_per_second": 5.007,
-    "perplexity": 1.6292702392482226,
-    "total_flos": 5.233249244912026e+16,
-    "train_loss": 0.13553106638144063,
-    "train_runtime": 2552.5753,
-    "train_samples_per_second": 312.769,
-    "train_steps_per_second": 9.775
+    "eval_loss": 0.5699824094772339,
+    "eval_runtime": 299.7106,
+    "eval_samples_per_second": 160.628,
+    "eval_steps_per_second": 5.022,
+    "perplexity": 1.7682359469654831,
+    "total_flos": 4.426734746743603e+16,
+    "train_loss": 0.15721422936277518,
+    "train_runtime": 2145.6584,
+    "train_samples_per_second": 314.741,
+    "train_steps_per_second": 9.836
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.48813220858573914,
-    "eval_runtime": 355.5361,
-    "eval_samples_per_second": 160.124,
-    "eval_steps_per_second": 5.007,
-    "perplexity": 1.6292702392482226
+    "eval_loss": 0.5699824094772339,
+    "eval_runtime": 299.7106,
+    "eval_samples_per_second": 160.628,
+    "eval_steps_per_second": 5.022,
+    "perplexity": 1.7682359469654831
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 5.233249244912026e+16,
-    "train_loss": 0.13553106638144063,
-    "train_runtime": 2552.5753,
-    "train_samples_per_second": 312.769,
-    "train_steps_per_second": 9.775
+    "total_flos": 4.426734746743603e+16,
+    "train_loss": 0.15721422936277518,
+    "train_runtime": 2145.6584,
+    "train_samples_per_second": 314.741,
+    "train_steps_per_second": 9.836
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e7e48074b9d4a9223c7ec1f8f3c14b6667da1c3552646e4edae6dada307e73
+oid sha256:14adea7788f43e13aaa6b202e5725e7097a04f0103eec6f02fba4affe48f9053
 size 5432