Model save

README.md

@@ -1,15 +1,15 @@
----
-base_model: bigscience/bloomz-560m
-library_name: peft
-license: bigscience-bloom-rail-1.0
-tags:
-- trl
-- sft
-- generated_from_trainer
-model-index:
-- name: bloom_ts2
-  results: []
----
+---
+base_model: bigscience/bloomz-560m
+library_name: peft
+license: bigscience-bloom-rail-1.0
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: bloom_ts2
+  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. -->
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.0056
+- Loss: 4.7031
 
 ## Model description
 
@@ -51,17 +51,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.105         | 1.0   | 25   | 4.3496          |
-| 4.7363        | 2.0   | 50   | 4.1841          |
-| 4.528         | 3.0   | 75   | 4.0786          |
-| 4.4779        | 4.0   | 100  | 4.0237          |
-| 4.5107        | 5.0   | 125  | 4.0056          |
+| 4.9365        | 1.0   | 25   | 4.6211          |
+| 4.7031        | 2.0   | 50   | 4.6562          |
+| 4.7573        | 3.0   | 75   | 4.6953          |
+| 4.3525        | 4.0   | 100  | 4.7031          |
+| 4.8447        | 5.0   | 125  | 4.7031          |
 
 
 ### Framework versions
 
 - PEFT 0.12.0
 - Transformers 4.44.2
-- Pytorch 2.4.0+cu121
+- Pytorch 2.2.1
 - Datasets 3.0.0
 - Tokenizers 0.19.1

runs/Sep15_20-39-30_LAPTOP-1QK69S9G/events.out.tfevents.1726412986.LAPTOP-1QK69S9G.4776.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecab320f1fdd5b0bf96c4a66e3a4904ff379f2cea1b36e7afcb083198668c188
-size 32248
+oid sha256:efc2bf25763516a28808b24d7ae5744d0a216d5ae30beff77d9d881c3f12356d
+size 32862