End of training

README.md

@@ -2,6 +2,8 @@
 license: mit
 base_model: HuggingFaceH4/zephyr-7b-beta
 tags:
+- trl
+- sft
 - generated_from_trainer
 model-index:
 - name: results
@@ -14,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4427
 
 ## Model description
 
@@ -32,22 +36,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.00025
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6943        | 0.5   | 50   | 0.6478          |
+| 0.5485        | 1.0   | 100  | 0.5314          |
+| 0.4163        | 1.5   | 150  | 0.5019          |
+| 0.3924        | 2.0   | 200  | 0.4376          |
+| 0.3311        | 2.5   | 250  | 0.4994          |
+| 0.3167        | 3.0   | 300  | 0.4327          |
+| 0.2694        | 3.5   | 350  | 0.4408          |
+| 0.2475        | 4.0   | 400  | 0.4265          |
+| 0.2271        | 4.5   | 450  | 0.4136          |
+| 0.2442        | 5.0   | 500  | 0.4427          |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.15.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
 - Tokenizers 0.15.0

adapter_config.json

@@ -8,22 +8,25 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "k_proj",
     "gate_proj",
-    "lm_head",
-    "o_proj",
-    "up_proj",
+    "down_proj",
     "v_proj",
+    "lm_head",
     "q_proj",
-    "k_proj"
+    "up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5701a850b69273fd6de4fb92eda1fce0545db3dc90dfc5d76639e4f94fb197
-size 340225224
+oid sha256:58e3fdb5aa32dc3a8a2dd57e1299106de3bf884740d094031e8c7145d9a54ec1
+size 609389712

runs/Jan11_12-37-09_5d222086593d/events.out.tfevents.1704976633.5d222086593d.1277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556218a73b0d6c5177448be6b6f1bc052431811b43c112bbe313fe25d9016b68
+size 10758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9bfc5bcdbb4b1fae5217bade55644c28cf155c640f95c5d2080d02c2b0434a9
+oid sha256:4dc57440d1e5bcd20812a9240c6a6c764ec380ed8a6876257a888d0334df6f54
 size 4536