ninagroot/Llama-360Mtest

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: 5.9655
+- Loss: 7.3725
 
 ## Model description
 
@@ -48,24 +48,25 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.89  | 2    | 8.5679          |
-| No log        | 1.78  | 4    | 8.5182          |
-| No log        | 2.67  | 6    | 8.4304          |
-| No log        | 4.0   | 9    | 8.2278          |
-| No log        | 4.89  | 11   | 8.0473          |
-| No log        | 5.78  | 13   | 7.8459          |
-| No log        | 6.67  | 15   | 7.6372          |
-| No log        | 8.0   | 18   | 7.3787          |
-| 7.9918        | 8.89  | 20   | 7.1956          |
-| 7.9918        | 9.78  | 22   | 7.0644          |
-| 7.9918        | 10.67 | 24   | 6.9150          |
-| 7.9918        | 12.0  | 27   | 6.7280          |
-| 7.9918        | 12.89 | 29   | 6.5960          |
-| 7.9918        | 13.78 | 31   | 6.4792          |
-| 7.9918        | 14.67 | 33   | 6.3487          |
-| 7.9918        | 16.0  | 36   | 6.1616          |
-| 7.9918        | 16.89 | 38   | 6.0606          |
-| 6.3677        | 17.78 | 40   | 5.9655          |
+| No log        | 0.94  | 2    | 11.0486         |
+| No log        | 1.88  | 4    | 10.9834         |
+| No log        | 2.82  | 6    | 10.8679         |
+| No log        | 3.76  | 8    | 10.7046         |
+| No log        | 4.71  | 10   | 10.4956         |
+| No log        | 5.65  | 12   | 10.2361         |
+| No log        | 6.59  | 14   | 9.9249          |
+| No log        | 8.0   | 17   | 9.4434          |
+| No log        | 8.94  | 19   | 9.1960          |
+| 10.3432       | 9.88  | 21   | 8.9986          |
+| 10.3432       | 10.82 | 23   | 8.8144          |
+| 10.3432       | 11.76 | 25   | 8.6667          |
+| 10.3432       | 12.71 | 27   | 8.5072          |
+| 10.3432       | 13.65 | 29   | 8.3409          |
+| 10.3432       | 14.59 | 31   | 8.1751          |
+| 10.3432       | 16.0  | 34   | 7.8970          |
+| 10.3432       | 16.94 | 36   | 7.6996          |
+| 10.3432       | 17.88 | 38   | 7.5270          |
+| 8.1799        | 18.82 | 40   | 7.3725          |
 
 
 ### Framework versions

config.json

@@ -15,7 +15,7 @@
   "num_attention_heads": 8,
   "num_hidden_layers": 24,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
+  "pad_token_id": 50256,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -24,5 +24,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "use_cache": true,
-  "vocab_size": 4312
+  "vocab_size": 50257
 }

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 0,
+  "pad_token_id": 50256,
   "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd7d3b9032857420cb3030328c76375a6bb5f32b36c42f25f16f07a6eccf4255
-size 1344172280
+oid sha256:81d0b4ce55886a4159484e3695f3dcd58f19abc0eecdf0bb8527cb2e06d5da7d
+size 1720553864

runs/Mar20_14-44-38_gcn37.local.snellius.surf.nl/events.out.tfevents.1710942287.gcn37.local.snellius.surf.nl.950453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12998fbcdfa2cddd62d2995ead76c39238c54725ab7a0a595070bcc0e667aef
+size 10035

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854943628158b4953c8db55688afec58f9d4beac612540e46ff06bd58dd3e71c
+oid sha256:8602f336bb4ad74eb3e84c33958f37677008e74be29d1b73d0f234013e985f87
 size 4728