End of training

README.md

@@ -47,7 +47,7 @@ flash_attention: true
 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: nblinh63/395bda4d-4035-47c7-9550-1f2977bb55d3
@@ -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/5238526693fb2e82_train_data.json
 model_type: AutoModelForCausalLM
 num_epochs: 1
@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6994
+- Loss: 3.8126
 
 ## Model description
 
@@ -125,11 +125,9 @@ 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
@@ -139,7 +137,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 3.5197        | 0.0017 | 10   | 2.6994          |
+| 4.4013        | 0.0002 | 10   | 3.8126          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bd407d59ffd17bb51b587cb156ee300897c9168ffd7133b96b177af5404eec
+oid sha256:cb082aff772c33d961204a180dafea9c358faadc0381d1f77f48dac5c5bfbb44
 size 101834682

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d62f84e036feae092305c1701ec163765a2beb9754c18be5f494434f774bc47
+oid sha256:1cf18823b417f9fd583037d8c61abe93adbec260a1295cea794603f0629a5cbb
 size 101752088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181320dbe3a06dc2543ec59d562e6f78b916b60af8e889d64a321965e18e5306
+oid sha256:14f5fe38cf0db07db6dd3e88fc90e63160bab952b33e1ba62b35683431cf5712
 size 6776