lakshyaag/llama38binstruct-summary-tldrlegal

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0867
+- Loss: 1.8731
 
 ## Model description
 
@@ -46,16 +46,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 0.03
-- training_steps: 100
+- training_steps: 150
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.519         | 1.25  | 25   | 1.6759          |
-| 0.4363        | 2.5   | 50   | 1.7830          |
-| 0.1865        | 3.75  | 75   | 1.9570          |
-| 0.1076        | 5.0   | 100  | 2.0867          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6074        | 1.1905 | 25   | 1.2061          |
+| 0.6597        | 2.3810 | 50   | 1.3782          |
+| 0.2859        | 3.5714 | 75   | 1.5552          |
+| 0.1349        | 4.7619 | 100  | 1.8426          |
+| 0.068         | 5.9524 | 125  | 1.8918          |
+| 0.039         | 7.1429 | 150  | 1.8731          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
     "q_proj",
-    "o_proj",
-    "k_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj",
-    "down_proj"
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d319f5954c3413802fbb924b03589e7454cc56e37ff8881d88d756ba742f61
+oid sha256:b3284408eda2e6fbce5055680326f0e99f1de010fb787b7bf81ea5b5556cdb76
 size 167832240

runs/Jun15_03-55-27_03854b07a572/events.out.tfevents.1718423733.03854b07a572.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b574967d768e01ba47b80002ec3ee30cdc3b110825f555179f9ea4f977c9ea
+size 10841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a160a351c4560734e62e6fba61a4474f0b8f571d8f3ffb95a6f22c5d9ecd222
+oid sha256:a0a8f5d7b5c25a665bad36c003903f15d6fc2fc3db8189e1f627b95282d9d532
 size 5432