Model save

README.md

@@ -1,22 +1,22 @@
 ---
 library_name: peft
 license: mit
-base_model: gpt2
+base_model: gpt2-medium
 tags:
 - generated_from_trainer
 model-index:
-- name: Se124M10KInfPrompt_WT_EOS
+- name: Se124M100KInfPrompt_WT_EOS_medium
   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. -->
 
-# Se124M10KInfPrompt_WT_EOS
+# Se124M100KInfPrompt_WT_EOS_medium
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0978
+- Loss: 0.7127
 
 ## Model description
 
@@ -44,28 +44,57 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.2645        | 0.5970 | 20   | 2.8750          |
-| 3.0103        | 1.1791 | 40   | 2.6534          |
-| 2.7014        | 1.7761 | 60   | 2.3720          |
-| 2.3851        | 2.3582 | 80   | 2.1090          |
-| 2.1288        | 2.9552 | 100  | 1.8650          |
-| 1.9062        | 3.5373 | 120  | 1.6703          |
-| 1.739         | 4.1194 | 140  | 1.5153          |
-| 1.6033        | 4.7164 | 160  | 1.3879          |
-| 1.5039        | 5.2985 | 180  | 1.2845          |
-| 1.4219        | 5.8955 | 200  | 1.2122          |
-| 1.357         | 6.4776 | 220  | 1.1649          |
-| 1.3201        | 7.0597 | 240  | 1.1304          |
-| 1.2923        | 7.6567 | 260  | 1.1101          |
-| 1.2831        | 8.2388 | 280  | 1.1035          |
-| 1.2715        | 8.8358 | 300  | 1.1007          |
-| 1.2721        | 9.4179 | 320  | 1.0986          |
+| 2.8652        | 0.0655 | 20   | 2.6742          |
+| 2.6735        | 0.1309 | 40   | 2.4205          |
+| 2.3498        | 0.1964 | 60   | 2.0554          |
+| 1.9542        | 0.2619 | 80   | 1.6239          |
+| 1.5661        | 0.3273 | 100  | 1.2791          |
+| 1.3052        | 0.3928 | 120  | 1.0776          |
+| 1.1291        | 0.4583 | 140  | 0.9537          |
+| 1.0151        | 0.5237 | 160  | 0.8837          |
+| 0.9431        | 0.5892 | 180  | 0.8324          |
+| 0.8821        | 0.6547 | 200  | 0.8044          |
+| 0.8536        | 0.7201 | 220  | 0.7846          |
+| 0.8371        | 0.7856 | 240  | 0.7712          |
+| 0.8281        | 0.8511 | 260  | 0.7628          |
+| 0.8077        | 0.9165 | 280  | 0.7553          |
+| 0.8013        | 0.9820 | 300  | 0.7501          |
+| 0.7948        | 1.0458 | 320  | 0.7447          |
+| 0.783         | 1.1113 | 340  | 0.7394          |
+| 0.7727        | 1.1768 | 360  | 0.7372          |
+| 0.777         | 1.2422 | 380  | 0.7331          |
+| 0.7711        | 1.3077 | 400  | 0.7309          |
+| 0.7642        | 1.3732 | 420  | 0.7289          |
+| 0.7631        | 1.4386 | 440  | 0.7267          |
+| 0.7581        | 1.5041 | 460  | 0.7250          |
+| 0.7606        | 1.5696 | 480  | 0.7233          |
+| 0.7578        | 1.6350 | 500  | 0.7223          |
+| 0.7562        | 1.7005 | 520  | 0.7208          |
+| 0.7497        | 1.7660 | 540  | 0.7195          |
+| 0.7508        | 1.8314 | 560  | 0.7179          |
+| 0.7476        | 1.8969 | 580  | 0.7168          |
+| 0.7503        | 1.9624 | 600  | 0.7165          |
+| 0.7414        | 2.0262 | 620  | 0.7164          |
+| 0.7425        | 2.0917 | 640  | 0.7159          |
+| 0.7451        | 2.1571 | 660  | 0.7146          |
+| 0.7452        | 2.2226 | 680  | 0.7147          |
+| 0.7446        | 2.2881 | 700  | 0.7138          |
+| 0.7437        | 2.3535 | 720  | 0.7140          |
+| 0.7397        | 2.4190 | 740  | 0.7131          |
+| 0.7426        | 2.4845 | 760  | 0.7130          |
+| 0.7421        | 2.5499 | 780  | 0.7127          |
+| 0.7408        | 2.6154 | 800  | 0.7135          |
+| 0.7413        | 2.6809 | 820  | 0.7135          |
+| 0.7404        | 2.7463 | 840  | 0.7131          |
+| 0.7373        | 2.8118 | 860  | 0.7128          |
+| 0.7451        | 2.8773 | 880  | 0.7134          |
+| 0.7407        | 2.9427 | 900  | 0.7127          |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 9.716417910447761,
+    "epoch": 2.9918166939443536,
     "eval_loss": 1.0977526903152466,
     "eval_runtime": 1.7342,
     "eval_samples_per_second": 1054.072,
     "eval_steps_per_second": 16.722,
     "perplexity": 2.9974223129878887,
-    "total_flos": 5406457244811264.0,
-    "train_loss": 1.8237198396162553,
-    "train_runtime": 182.316,
-    "train_samples_per_second": 467.759,
-    "train_steps_per_second": 1.81
+    "total_flos": 5.437860691102925e+16,
+    "train_loss": 0.9607737994584881,
+    "train_runtime": 2198.2213,
+    "train_samples_per_second": 106.683,
+    "train_steps_per_second": 0.416
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.716417910447761,
-    "total_flos": 5406457244811264.0,
-    "train_loss": 1.8237198396162553,
-    "train_runtime": 182.316,
-    "train_samples_per_second": 467.759,
-    "train_steps_per_second": 1.81
+    "epoch": 2.9918166939443536,
+    "total_flos": 5.437860691102925e+16,
+    "train_loss": 0.9607737994584881,
+    "train_runtime": 2198.2213,
+    "train_samples_per_second": 106.683,
+    "train_steps_per_second": 0.416
 }