Model save

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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8022
+- Loss: 4.0885
 
 ## Model description
 
@@ -44,15 +44,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 4.75          | 0.1280 | 1000 | 4.7368          |
-| 4.3175        | 0.2560 | 2000 | 4.2998          |
-| 4.1447        | 0.3840 | 3000 | 4.1426          |
-| 4.0202        | 0.5120 | 4000 | 4.0230          |
-| 3.9294        | 0.6400 | 5000 | 3.9186          |
-| 3.8586        | 0.7680 | 6000 | 3.8424          |
-| 3.8007        | 0.8959 | 7000 | 3.8022          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.7547        | 0.32  | 1000 | 4.7084          |
+| 4.3024        | 0.64  | 2000 | 4.2576          |
+| 4.1338        | 0.96  | 3000 | 4.0885          |
 
 
 ### Framework versions

config.json

@@ -5,9 +5,9 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_unified.UnifiedModelConfig",
-    "AutoModel": "modeling_unified.UnifiedModel",
-    "AutoModelForCausalLM": "modeling_unified.UnifiedModel"
+    "AutoConfig": "configuration_neollm.NeoLLMConfig",
+    "AutoModel": "modeling_neollm.NeoLLMModel",
+    "AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM"
   },
   "dropout_rate": 0.1,
   "dtype": "bfloat16",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62cd7d9ec2951daafd43197c6a44edf21f7825ebbd07e2e68e9be1647489c2b6
+oid sha256:91a55249ceb22eb712612f2255ca5a7ee2fe464da0580eb69d60bda5737ceb42
 size 250512472

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564e47598a4f1d370d6f25e4ef232753dcc16a3820474c3416e7f1e02c8388df
-size 5969
+oid sha256:1a91aabf3d6c07af2c87fce84e2311facefa29045b5c3f146148e1fd1fa584b9
+size 5585