End of training

README.md

@@ -5,18 +5,23 @@ tags:
 - generated_from_trainer
 base_model: mistralai/Mixtral-8x7B-v0.1
 model-index:
-- name: pawan2411/semMixtral-LoRA
+- name: pawan2411/semMixtral2-LoRA
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# pawan2411/semMixtral-LoRA
+# pawan2411/semMixtral2-LoRA
 
 This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3446
+- eval_loss: 1.5055
+- eval_runtime: 24.5456
+- eval_samples_per_second: 4.074
+- eval_steps_per_second: 0.53
+- epoch: 3.38
+- step: 850
 
 ## Model description
 
@@ -44,27 +49,9 @@ 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: 1
-- training_steps: 300
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.4717        | 0.1   | 25   | 1.4328          |
-| 1.409         | 0.2   | 50   | 1.3987          |
-| 1.4058        | 0.3   | 75   | 1.3804          |
-| 1.3436        | 0.4   | 100  | 1.3703          |
-| 1.3548        | 0.5   | 125  | 1.3611          |
-| 1.32          | 0.6   | 150  | 1.3558          |
-| 1.3892        | 0.7   | 175  | 1.3509          |
-| 1.384         | 0.8   | 200  | 1.3483          |
-| 1.3442        | 0.89  | 225  | 1.3467          |
-| 1.3692        | 0.99  | 250  | 1.3461          |
-| 1.2944        | 1.09  | 275  | 1.3448          |
-| 1.3064        | 1.19  | 300  | 1.3446          |
-
-
 ### Framework versions
 
 - PEFT 0.7.2.dev0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "w3",
-    "lm_head",
-    "k_proj",
-    "w1",
-    "q_proj",
     "w2",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "lm_head",
+    "w1",
+    "k_proj",
+    "w3",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461bedc1948471d2d5dde9f465715cf1353c69a9f7f2e16b1750214b22750a83
-size 2450168296
+oid sha256:628c7597c4a99fe39bfab7e0110d4a1bf501a842a32de3576eed80d7b5a62017
+size 2450198808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbad49e0ace1b9c957d37096206464b7873943598b40b362f10366017d9a11bc
+oid sha256:6d598c73bf3e41511624db1a92a59136fb9889345244229ee58884caa8027b1d
 size 4728