Model save

README.md

@@ -2,9 +2,6 @@
 base_model: meta-llama/Llama-2-7b-hf
 library_name: peft
 license: llama2
-metrics:
-- accuracy
-- rouge
 tags:
 - generated_from_trainer
 model-index:
@@ -19,11 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 22.2205
-- Accuracy: 0.0
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
+- Loss: 23.5375
+- Model Preparation Time: 0.004
 
 ## Model description
 
@@ -43,14 +37,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 2
-- gradient_accumulation_steps: 32
-- total_train_batch_size: 128
-- total_eval_batch_size: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
@@ -59,10 +51,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Rouge1 | Rouge2 | Rougel |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:------:|:------:|
-| 26.5755       | 1.4222 | 10   | 23.5886         | 0.0      | 0.0    | 0.0    | 0.0    |
-| 25.4247       | 2.8444 | 20   | 22.2188         | 0.0      | 0.0    | 0.0    | 0.0    |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "k_proj",
-    "o_proj"
+    "q_proj",
+    "o_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 sha256:8326d3eed650affbe81ffa53bff6fc680ced295403e17ea8b55584c64e43add3
+oid sha256:a2457729b52d52469a66d0f65048f18c84365279d82e4c680ed5e604178053a1
 size 33588528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b897f974aa01181b03ec48fc3d8d4170320a1f49e8b062290a5a0cde4e885f93
+oid sha256:f0599077019008d8ec165d91974bfe87bc63f25386042319df08054a1534a819
 size 5304