Completed epoch 4

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.7790
+- Loss: 4.6578
 
 ## Model description
 
@@ -49,17 +49,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 26.9686       | 0.32   | 100  | 5.6473          |
-| 20.7043       | 0.64   | 200  | 5.1898          |
-| 19.3176       | 0.96   | 300  | 4.9661          |
-| 18.0682       | 1.2784 | 400  | 4.8781          |
-| 17.5367       | 1.5984 | 500  | 4.8027          |
-| 17.3323       | 1.9184 | 600  | 4.7790          |
+| 17.5854       | 0.32   | 100  | 4.8255          |
+| 16.9758       | 0.64   | 200  | 4.7656          |
+| 16.4608       | 0.96   | 300  | 4.6877          |
+| 14.761        | 1.2784 | 400  | 4.7266          |
+| 14.5481       | 1.5984 | 500  | 4.6778          |
+| 14.7485       | 1.9184 | 600  | 4.6578          |
 
 
 ### Framework versions
 
-- Transformers 4.47.1
+- Transformers 4.48.2
 - Pytorch 2.5.1+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -5,7 +5,7 @@
   "model_type": "xlstm",
   "pad_token_id": 151643,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.2",
   "xlstm_cfg": {
     "_block_map": "1,0,1,0,1,0,1,0,1,0,1,0,1,0",
     "add_embedding_dropout": false,

events.out.tfevents.1738959286.ba07c9a9650d.3222.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c95a5f4c0f93bc9847f6fab06dc322a5c85c3e96f8a613beab4d2805964fc7
+size 1035358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9765ccdb2e84cb04be86e9949bbf8200ba92af8a437e8ae588f63bc236ffec5c
+oid sha256:68cf9fe198fbb61b277bf4c504e9e5256b61c256c3efc82aa7e0e8b60d20453a
 size 2661593144