HuggingFaceTB/SmolLM-360M-Instruct

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0979
+- Loss: 2.0409
 
 ## Model description
 
@@ -40,24 +40,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
+- num_devices: 8
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
-- total_eval_batch_size: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.1319        | 0.9880 | 41   | 2.0979          |
+| 2.3444        | 0.9524 | 10   | 2.3038          |
+| 2.2609        | 2.0    | 21   | 2.1919          |
+| 2.1732        | 2.9524 | 31   | 2.1334          |
+| 2.1255        | 4.0    | 42   | 2.0941          |
+| 2.0831        | 4.9524 | 52   | 2.0632          |
+| 2.0563        | 5.7143 | 60   | 2.0409          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "o_proj",
     "gate_proj",
     "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
     "down_proj",
-    "q_proj"
+    "v_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:d80fa55a96409d6595e0f792589a79de124eb42f9a34027b26b1c5caf68d437e
+oid sha256:e0216683abaa9c920d78c4c5a90aed2f701cdb4ae4b481dc09618211a026e35d
 size 17426248

runs/Aug28_12-28-25_algo-2/events.out.tfevents.1724848122.algo-2.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd83f35209d4359fa660148c448c0d88a28d93d6ce79706482a2789df07ac8e
+size 8594

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8767dcfa891e294a477c1427a36cacd1062a407291969d81ed9b60519f9db3b
+oid sha256:d57dd6dc0a640f00c6f19e312c5fd1fd07932eb590221acbbcd4acbb9a2c7ba0
 size 5240