nelkh/pgd_lora_8bits_mistral_1_r2_e10_

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4637
+- Loss: 0.3707
 
 ## Model description
 
@@ -42,16 +42,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 20
-- num_epochs: 3
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.3046        | 1.0   | 90   | 0.9798          |
-| 0.6382        | 2.0   | 180  | 0.5166          |
-| 0.4762        | 3.0   | 270  | 0.4637          |
+| 2.2656        | 1.0   | 90   | 0.8020          |
+| 0.5399        | 2.0   | 180  | 0.4374          |
+| 0.4287        | 3.0   | 270  | 0.4115          |
+| 0.4052        | 4.0   | 360  | 0.3926          |
+| 0.3858        | 5.0   | 450  | 0.3802          |
+| 0.3756        | 6.0   | 540  | 0.3757          |
+| 0.3699        | 7.0   | 630  | 0.3717          |
+| 0.366         | 8.0   | 720  | 0.3712          |
+| 0.3626        | 9.0   | 810  | 0.3702          |
+| 0.3607        | 10.0  | 900  | 0.3707          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,13 +16,13 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "v_proj",
-    "k_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694edf81fba5ea034b1d99bcdb7d5d72c65dc894c7bb515711ea0df470f8e7e1
-size 27301384
+oid sha256:f9991c1446cd255278b21f28a6e80fefe47faa0f5e7bb118c3058a89151601a0
+size 6849416

runs/Jul24_08-16-49_19c3b9d08bc5/events.out.tfevents.1721809029.19c3b9d08bc5.237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46845b26346d6be9a48ab11d643cf5fba3bee9e8b4eb7def88ef2df50000fb8
+size 10532

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cc3aabf6f5c853fbe54c122ee6380542f7702f83e22c5a6905ef55354d7434
+oid sha256:c77869c9678b3b7dfffd551ac7f37345217ba31b3d01986a4694956da1e7e210
 size 5112