Model save

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # tinyllama-1.1b-sft-lora
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -35,8 +37,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
 - train_batch_size: 2
-- eval_batch_size: 8
-- seed: 42
+- eval_batch_size: 2
+- seed: 4234
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 4
 - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
@@ -46,6 +48,19 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0889 | 2    | nan             |
+| No log        | 0.1778 | 4    | nan             |
+| 0.0           | 0.2667 | 6    | nan             |
+| 0.0           | 0.3556 | 8    | nan             |
+| 0.0           | 0.4444 | 10   | nan             |
+| 0.0           | 0.5333 | 12   | nan             |
+| 0.0           | 0.6222 | 14   | nan             |
+| 0.0           | 0.7111 | 16   | nan             |
+| 0.0           | 0.8    | 18   | nan             |
+| 0.0           | 0.8889 | 20   | nan             |
+| 0.0           | 0.9778 | 22   | nan             |
 
 
 ### Framework versions

final/adapter_config.json

@@ -24,10 +24,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "k_proj",
     "v_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

final/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d286ac1636133aa1c97535c746a54976137ef2982b3e4f0e000b82e39a04d3
+oid sha256:f33b1949d363deee8e767a06946963c25989518590fbfee36034d690e70df386
 size 9034304

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d456bc1ea3b44bf033be7fcdb402df397ef1eb85631edcaf712667d4796c8b6e
+oid sha256:bb2ee265ee5cf93495055060630e51285cfa78e7806b3e6ee0032eae18868177
 size 5713