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: 4.2709
+- Loss: 4.6344
 
 ## Model description
 
@@ -41,16 +41,20 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 3
+- num_epochs: 7
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.5887        | 1.0   | 42   | 4.8016          |
-| 2.1371        | 2.0   | 84   | 4.1574          |
-| 1.4171        | 3.0   | 126  | 4.2709          |
+| 4.5524        | 1.0   | 42   | 4.7852          |
+| 2.1679        | 2.0   | 84   | 4.1345          |
+| 1.4522        | 3.0   | 126  | 4.2880          |
+| 0.9328        | 4.0   | 168  | 4.4565          |
+| 0.5606        | 5.0   | 210  | 4.6031          |
+| 0.3514        | 6.0   | 252  | 4.6564          |
+| 0.2839        | 7.0   | 294  | 4.6344          |
 
 
 ### Framework versions

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<|endoftext|>": 4425
+  "<|endoftext|>": 12214
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794d95504e6c3eeb2e6c93a841abb188804e4df3d50372c54871dd40f3cebc5b
+oid sha256:581986c8393aab378ba562c2e1515606e5f06fcb1b3cd14bf03d7ba824cd0bce
 size 1408905504

runs/Apr10_10-05-43_gcn25.local.snellius.surf.nl/events.out.tfevents.1712736350.gcn25.local.snellius.surf.nl.3450425.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a97c13cf5683e2ae68ec4aca9efb88f8fe74582b0174cd40aff4086bf539675
+size 9729

tokenizer_config.json

@@ -1,10 +1,34 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12214": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e320fb248b2a7f327332399d659f25a2c7c8f78a3631c7a187c353d17322f0
+oid sha256:3ed61a658032aee43721b02ee38be59a2bf2b6b2a5447552875f86900ad7932e
 size 4984