ashishpatel26/opt-6.1b-lora

README.md

@@ -1,9 +1,9 @@
 ---
-license: bigscience-bloom-rail-1.0
+license: other
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: bigscience/bloomz-560m
+base_model: facebook/opt-1.3b
 model-index:
 - name: outputs
   results: []
@@ -12,10 +12,10 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/carlosslocar0/huggingface/runs/30e4dqt1)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/carlosslocar0/huggingface/runs/rdwmof3i)
 # outputs
 
-This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
 
 ## Model description
 
@@ -44,6 +44,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
 - training_steps: 200
+- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "bigscience/bloomz-560m",
+  "base_model_name_or_path": "facebook/opt-1.3b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,7 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408f23bfdfd74d474c8f7420aea0f1fbc76421370cefbe5df6d0793d45fe2df5
-size 6298560
+oid sha256:4bb847ea1a78da7669b6295d4517b8500df31886a57ed891a3ec0ee148305c52
+size 12596472

runs/May25_06-33-52_e3a9dd922337/events.out.tfevents.1716618833.e3a9dd922337.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a7b14cf2dd062b9c898244402325b1fdf287a91ae4aae559f22de82888a5fd
+size 7406

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5e603c8c12f8829ca7eb8528e117bb6738176b7145ad8c4f3751d02de15d7c
+oid sha256:6a58c776d266c43c01f78e07822ddd4c9edc97de5c899411955ee81e149b4ca9
 size 5112