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: 3.9805
+- Loss: 3.9293
 
 ## Model description
 
@@ -46,31 +46,31 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 208.1439      | 1.0   | 69   | 168.7479        |
-| 137.7666      | 2.0   | 138  | 104.4204        |
-| 64.4054       | 3.0   | 207  | 42.3502         |
-| 26.5661       | 4.0   | 276  | 19.2662         |
-| 14.7544       | 5.0   | 345  | 12.7249         |
-| 10.2813       | 6.0   | 414  | 8.5354          |
-| 6.9142        | 7.0   | 483  | 7.3827          |
-| 6.1554        | 8.0   | 552  | 6.4836          |
-| 5.3557        | 9.0   | 621  | 5.5994          |
-| 4.8551        | 10.0  | 690  | 5.4054          |
-| 4.7462        | 11.0  | 759  | 4.9582          |
-| 4.1657        | 12.0  | 828  | 4.7667          |
-| 4.0338        | 13.0  | 897  | 4.4520          |
-| 3.8436        | 14.0  | 966  | 4.2957          |
-| 3.6859        | 15.0  | 1035 | 4.2060          |
-| 3.4503        | 16.0  | 1104 | 4.0957          |
-| 3.4381        | 17.0  | 1173 | 4.0400          |
-| 3.2315        | 18.0  | 1242 | 4.0068          |
-| 3.2559        | 19.0  | 1311 | 3.9848          |
-| 3.3044        | 20.0  | 1380 | 3.9805          |
+| 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          |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
+- Transformers 4.39.1
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -22,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.39.1",
   "use_cache": true,
   "vocab_size": 4312
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.39.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9925d491ca799897f70b48245759259ad5d64b36d4b976076a474865f3e75683
+oid sha256:8ccdb44254ef68be2db7f409e2555a42b7bf2111a213da449857b19375dce7e5
 size 185517896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72472d90ccb6353e373291e39e33b128c9244c2d501fc745a44c17b455cf604
-size 4792
+oid sha256:72b13b0c38155039527a0899d7e7fd8f62fc72ce5bcb791e539c84eab61b13ab
+size 4984