End of training

README.md

@@ -65,11 +65,11 @@ 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/74aeb5c63551d548_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
@@ -77,7 +77,7 @@ resume_from_checkpoint: null
 s2_attention: null
 sample_packing: false
 saves_per_epoch: 1
-sequence_len: 512
+sequence_len: 1024
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -102,7 +102,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-64k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-64k) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8454
+- Loss: 0.6145
 
 ## Model description
 
@@ -130,17 +130,25 @@ 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 |
 |:-------------:|:------:|:----:|:---------------:|
-| 15.4853       | 0.0015 | 1    | 1.9837          |
-| 8.258         | 0.0367 | 25   | 1.0133          |
-| 7.0325        | 0.0735 | 50   | 0.8924          |
-| 6.9895        | 0.1102 | 75   | 0.8511          |
-| 7.1211        | 0.1470 | 100  | 0.8454          |
+| 14.7383       | 0.0015 | 1    | 1.9144          |
+| 8.0433        | 0.0367 | 25   | 0.9946          |
+| 6.8449        | 0.0735 | 50   | 0.8665          |
+| 6.4117        | 0.1102 | 75   | 0.8008          |
+| 6.4906        | 0.1470 | 100  | 0.7581          |
+| 5.5423        | 0.1837 | 125  | 0.7179          |
+| 5.578         | 0.2205 | 150  | 0.6876          |
+| 5.5843        | 0.2572 | 175  | 0.6619          |
+| 6.4463        | 0.2940 | 200  | 0.6412          |
+| 5.6181        | 0.3307 | 225  | 0.6261          |
+| 5.3514        | 0.3674 | 250  | 0.6183          |
+| 5.4112        | 0.4042 | 275  | 0.6149          |
+| 5.4528        | 0.4409 | 300  | 0.6145          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "k_proj",
+    "q_proj",
     "v_proj",
+    "gate_proj",
     "o_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj",
-    "q_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:bc2698401e8cc057934f6debafdaefc3d1e5e0e2b8711c0d48f61f8edc5d3c4c
+oid sha256:2df17193a0b542d5e4326bfbc1341a74b6238a7449ba37ec376caa16d91d342e
 size 319977674

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c7ffcdfad33df1cf046b9db21453d068d6adc4f740c1d0d7ff1ecacf1e065e
+oid sha256:35656d9085a51766893b24b905720d7dc9ce544f08c759bb4aebdcd999bc9ab0
 size 319876032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8f1aff6635a8458ab5bd24faa152d26d89204bb8abb69225ac232788b454ef
+oid sha256:fa69054571f1c99cb1154155ef9a003552fe538354e88fc75855c4f706c16dd5
 size 6776