End of training

README.md

@@ -47,7 +47,7 @@ flash_attention: false
 fp16: null
 fsdp: null
 fsdp_config: null
-gradient_accumulation_steps: 4
+gradient_accumulation_steps: 1
 gradient_checkpointing: true
 group_by_length: false
 hub_model_id: nblinh63/c15eea94-310b-4df8-b4a4-ca8f6c1a7aab
@@ -67,7 +67,7 @@ lora_r: 16
 lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 10
-micro_batch_size: 2
+micro_batch_size: 1
 mlflow_experiment_name: /tmp/2437198224a470c0_train_data.json
 model_type: AutoModelForCausalLM
 num_epochs: 1
@@ -123,11 +123,9 @@ 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: 1
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
 - 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
@@ -137,7 +135,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.0112 | 10   | nan             |
+| 0.0           | 0.0014 | 10   | nan             |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce564cadad4549387ddbf7f4177a3652cd00cc904cc5197a0bad3871250559e
+oid sha256:eb5a181c1642c83b6fa5c53eca6b3f22aae90f6d66f5ebe2d6681a96c3977cad
 size 275494090

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494f0bc6d731581c53b687ca50d7736e706164cbceee2e0271e1be64407c3b27
+oid sha256:5cc995a168185b66da21b5d111b5f6dd4c087187a6bb307703a19893040eb1fd
 size 275341720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625bdaeaa249f50b6bc662f91dbddd37ed10355d0f4a7be16a19a93738dd71d9
+oid sha256:54fa189f91ee8a9b701d32c0e946fcb512221c24b19c7dc9e7af62744d52bc02
 size 6776