End of training

README.md

@@ -66,11 +66,11 @@ lora_model_dir: null
 lora_r: 32
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 100
+max_steps: 300
 micro_batch_size: 1
 mlflow_experiment_name: /tmp/a8d492346672a1c8_train_data.json
 model_type: AutoModelForCausalLM
-num_epochs: 4
+num_epochs: 12
 optimizer: adamw_bnb_8bit
 output_dir: miner_id_24
 pad_to_sequence_len: true
@@ -103,7 +103,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3402
+- Loss: 1.0501
 
 ## Model description
 
@@ -131,17 +131,25 @@ 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: 300
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 3.7335        | 0.0029 | 1    | 3.8303          |
-| 1.6115        | 0.0729 | 25   | 2.3264          |
-| 0.952         | 0.1458 | 50   | 1.4975          |
-| 1.9603        | 0.2187 | 75   | 1.3585          |
-| 1.434         | 0.2915 | 100  | 1.3402          |
+| 1.5917        | 0.0729 | 25   | 2.3094          |
+| 0.9143        | 0.1458 | 50   | 1.4404          |
+| 1.7505        | 0.2187 | 75   | 1.2449          |
+| 1.2376        | 0.2915 | 100  | 1.1931          |
+| 1.2788        | 0.3644 | 125  | 1.1278          |
+| 1.4158        | 0.4373 | 150  | 1.0998          |
+| 0.9088        | 0.5102 | 175  | 1.0870          |
+| 1.1591        | 0.5831 | 200  | 1.0699          |
+| 1.0273        | 0.6560 | 225  | 1.0602          |
+| 1.9042        | 0.7289 | 250  | 1.0567          |
+| 0.9941        | 0.8017 | 275  | 1.0524          |
+| 1.1544        | 0.8746 | 300  | 1.0501          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
     "gate_proj",
     "up_proj",
+    "q_proj",
     "down_proj",
     "o_proj",
-    "v_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276ad78cd1e7cec305cda80c44d587d1b2f2a40c8fd77b008d3ed30b28d3cf69
+oid sha256:9e6ee602386a820be0e08e0dc35ba90ab1e8d13d11507992be368693a2f48e46
 size 319977674

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7211c6973eef28e52bea4d96a74846e994ad7ebb2c1bccd845772d42aa497ee6
+oid sha256:0e0ea1556d29c6d79e48933779339bb1a59db98e44cdb9697922abeb465b0322
 size 319876032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f8188926fa47a0c6a507ee13a218f5419bcf03d5cb9408289fcb2ae6e89945
+oid sha256:f1dafb245219169482eca522df88859feac6a8e53af11c374d72d3c6395fdc05
 size 6776