End of training

README.md

@@ -65,7 +65,7 @@ lora_model_dir: null
 lora_r: 32
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 100
+max_steps: 200
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/0c389fe694d49e2c_train_data.json
 model_type: AutoModelForCausalLM
@@ -83,7 +83,7 @@ tf32: false
 tokenizer_type: AutoTokenizer
 train_on_inputs: false
 trust_remote_code: true
-val_set_size: 0.02
+val_set_size: 0.1
 wandb_entity: null
 wandb_mode: online
 wandb_name: 8258b119-6362-4754-9e34-cdd215dba50b
@@ -130,17 +130,17 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 100
+- training_steps: 200
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.5019        | 0.0004 | 1    | nan             |
-| 2.3903        | 0.0100 | 25   | nan             |
-| 2.9039        | 0.0199 | 50   | nan             |
-| 2.4618        | 0.0299 | 75   | nan             |
-| 1.779         | 0.0398 | 100  | nan             |
+| 4.2027        | 0.0004 | 1    | nan             |
+| 2.7534        | 0.0217 | 50   | nan             |
+| 1.7026        | 0.0434 | 100  | nan             |
+| 2.3272        | 0.0650 | 150  | nan             |
+| 2.5038        | 0.0867 | 200  | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "gate_proj",
-    "o_proj",
     "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
     "q_proj",
     "k_proj"
   ],

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:479d3eef82ce226f70d01e323bbec796aa6fa19cd7fd64dd349d734b9f409782
+oid sha256:316e70f9b3f4f0a73b768477122e631b34b1aab87bef3c37e176ad310169a558
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4bae772233d95878af6c79ca0786e029c5b928ca1ddac881139ef2dd842e35f
+oid sha256:8c7999ded8de52ab72cb7097e1002a337b6415095697681252714d881491b44b
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06327c333702c90c3c2773755c7143c276c333539c2f472aeb955071203f580
+oid sha256:2a0f802361e7d4ff965c2243609680b1fcf327f5a2f5e825bea35cfb3727ce91
 size 6776