Training in progress, step 416

README.md

@@ -68,7 +68,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 20
+max_steps: 1
 micro_batch_size: 32
 mlflow_experiment_name: /tmp/0258260fff514215_train_data.json
 model_type: AutoModelForCausalLM
@@ -76,7 +76,7 @@ num_epochs: 100
 optimizer: adamw_bnb_8bit
 output_dir: miner_id_24
 pad_to_sequence_len: true
-resume_from_checkpoint: null
+resume_from_checkpoint: /workspace/hub_repo/last-checkpoint
 s2_attention: null
 sample_packing: false
 save_steps: 
@@ -105,6 +105,8 @@ xformers_attention: null
 # miner_id_24
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1909
 
 ## Model description
 
@@ -132,10 +134,20 @@ 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: 100
-- training_steps: 20
+- training_steps: 1
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0021 | 1    | 5.5854          |
+| 2.5076        | 0.1101 | 52   | 0.4229          |
+| 0.2709        | 0.2201 | 104  | 0.2650          |
+| 0.2372        | 0.3302 | 156  | 0.2207          |
+| 0.197         | 0.4402 | 208  | 0.2383          |
+| 0.1677        | 0.5503 | 260  | 0.2076          |
+| 0.1963        | 0.6603 | 312  | 0.2016          |
+| 0.192         | 0.7704 | 364  | 0.1909          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd5fda799e3ba244dbd889af6da84501e01e2b084f2a3eec154f96218b137d0
+oid sha256:56892c2e428e2dd943f947b12324750662f045fbdd73ae86cb320c6eb5b55993
 size 80881450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947ff4a4575d16fd3c1d22fe57bafb0495b146c3593b2a18672461845c2b7795
+oid sha256:64111459bd770687db8d0214abc9e53e654b6ccf6ffd2089f35d3c0b5bbfcf9a
 size 80792096

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41baabe19c02cb862e889e8ebd5d5c46c223ccfc1a8a900c2d1c568de6eb7bd8
+oid sha256:d10e94c5db75a378dd2c821d2ebbe48fdd9ed9a8df5086eac228838cf23623d2
 size 6776