ninagroot/babyllamatest

README.md

@@ -13,7 +13,7 @@ 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: 3.9293
+- Loss: 3.4868
 
 ## Model description
 
@@ -46,26 +46,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 217.7542      | 1.0   | 69   | 169.6833        |
-| 140.0595      | 2.0   | 138  | 102.3135        |
-| 64.7821       | 3.0   | 207  | 47.4496         |
-| 26.8103       | 4.0   | 276  | 19.3383         |
-| 12.782        | 5.0   | 345  | 12.0085         |
-| 9.8432        | 6.0   | 414  | 8.0061          |
-| 6.9448        | 7.0   | 483  | 6.6308          |
-| 6.1985        | 8.0   | 552  | 6.0272          |
-| 5.3316        | 9.0   | 621  | 5.6098          |
-| 4.7103        | 10.0  | 690  | 5.0774          |
-| 4.3456        | 11.0  | 759  | 4.8933          |
-| 4.1052        | 12.0  | 828  | 4.6336          |
-| 4.0201        | 13.0  | 897  | 4.4522          |
-| 3.7028        | 14.0  | 966  | 4.2817          |
-| 3.4861        | 15.0  | 1035 | 4.1521          |
-| 3.3937        | 16.0  | 1104 | 4.0707          |
-| 3.2937        | 17.0  | 1173 | 3.9879          |
-| 3.2748        | 18.0  | 1242 | 3.9467          |
-| 3.2268        | 19.0  | 1311 | 3.9353          |
-| 3.1461        | 20.0  | 1380 | 3.9293          |
+| 16.2182       | 1.0   | 393  | 13.7445         |
+| 6.1598        | 2.0   | 786  | 6.7784          |
+| 5.094         | 3.0   | 1179 | 5.4728          |
+| 4.2823        | 4.0   | 1572 | 4.9842          |
+| 3.7105        | 5.0   | 1965 | 4.6118          |
+| 3.3325        | 6.0   | 2358 | 4.4379          |
+| 3.1282        | 7.0   | 2751 | 4.2705          |
+| 2.9706        | 8.0   | 3144 | 4.0921          |
+| 2.8795        | 9.0   | 3537 | 3.9575          |
+| 2.5869        | 10.0  | 3930 | 3.8738          |
+| 2.6449        | 11.0  | 4323 | 3.8033          |
+| 2.4537        | 12.0  | 4716 | 3.7222          |
+| 2.4489        | 13.0  | 5109 | 3.6770          |
+| 2.237         | 14.0  | 5502 | 3.6201          |
+| 2.2934        | 15.0  | 5895 | 3.5597          |
+| 2.2597        | 16.0  | 6288 | 3.5336          |
+| 2.2667        | 17.0  | 6681 | 3.5108          |
+| 2.2947        | 18.0  | 7074 | 3.4935          |
+| 2.1618        | 19.0  | 7467 | 3.4894          |
+| 2.2033        | 20.0  | 7860 | 3.4868          |
 
 
 ### Framework versions

config.json

@@ -24,5 +24,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.1",
   "use_cache": true,
-  "vocab_size": 4312
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ccdb44254ef68be2db7f409e2555a42b7bf2111a213da449857b19375dce7e5
-size 185517896
+oid sha256:18587d669e316d918d29fef1f1c52079e33a2b167f33c3ccd433d7cd84931186
+size 298928096

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b13b0c38155039527a0899d7e7fd8f62fc72ce5bcb791e539c84eab61b13ab
+oid sha256:42dba10b5115a01d6be8e65830dfd27ac82bb1251d44e3f697c99e87edbab09d
 size 4984