tuhinatripathi/gemma2b-lpr-5k

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on the None dataset.
+This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on an unknown dataset.
 
 ## Model description
 
@@ -37,15 +37,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 3407
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 200
-- num_epochs: 1
+- lr_scheduler_warmup_steps: 5
+- training_steps: 240
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -16,16 +16,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "q_proj",
+    "o_proj",
     "down_proj",
     "k_proj",
-    "gate_proj",
-    "o_proj",
     "up_proj",
+    "q_proj",
+    "gate_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1c76c5a586628ba2982a2ce20de8a65a2e4a0a10b4fd97ffcb6295c9e79aec
-size 39256456
+oid sha256:7e1b3fed12110bfba1668f65fb039c64f2eabb700f189820995aaf8da3573ff1
+size 78480072

runs/May13_17-09-36_d79fc51216f5/events.out.tfevents.1715620184.d79fc51216f5.1477.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec57ec10e8e6cd960c4c064b79cf92d9d90bd615266190eeb32fb1f30d2ecf4
+size 5750

runs/May13_17-59-12_d79fc51216f5/events.out.tfevents.1715623170.d79fc51216f5.1477.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfdbb3b68e427109f5c2e84720bf40ac70654eb06a41280a7a64debf8f1cbf2
+size 5122

runs/May13_18-09-58_d79fc51216f5/events.out.tfevents.1715623825.d79fc51216f5.16931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851466dd5d4b775bf1cbc91d69712253d3a5413a698ac13aec8d539daa0ca9d3
+size 5894

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62aac1caf8a9d4c3f0bbcea6f3b568dc4c31697217cfb0a518a27db2e4da992a
-size 17518624
+oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2f05601b021a3bd3f68a895fdf4e7a91b218c0e03fd940b4435da1bc7d1eb5
+oid sha256:ad292d6eab00c56afa98369b7f0c5d8befeb7905e17752487c16c748ed12618a
 size 4984