Upload task output instructtest1334test1234test1234test12334

README.md

@@ -81,10 +81,10 @@ trust_remote_code: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: test1334test1234test1234test12334
+wandb_name: instructtest1334test1234test1234test12334
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: test1334test1234test1234test12334
+wandb_runid: instructtest1334test1234test1234test12334
 warmup_steps: 0
 weight_decay: 0.0
 xformers_attention: null
@@ -97,7 +97,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [samoline/b7447218-27e6-491c-b3ab-ea03a5b93541](https://huggingface.co/samoline/b7447218-27e6-491c-b3ab-ea03a5b93541) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8255
+- Loss: 0.8261
 
 ## Model description
 
@@ -130,7 +130,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5794        | 0.0084 | 1    | 0.8255          |
+| 0.5794        | 0.0084 | 1    | 0.8261          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "v_proj",
-    "o_proj",
-    "k_proj",
     "up_proj",
+    "k_proj",
     "down_proj",
+    "v_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66c2f8bfa778dfa1a84917bad1b705d01d065960c4a8890926445024c6a9ab3
+oid sha256:d9887c789e1b8c473a8b4ca8d8782006ee31e9409aff9af8b8a14955be211dff
 size 22624970

checkpoint-1/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "v_proj",
-    "o_proj",
-    "k_proj",
     "up_proj",
+    "k_proj",
     "down_proj",
+    "v_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-1/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5b3691795bf6bd58bcf9ca4274750a059d196df416cb1960dafc8226ba0be5
+oid sha256:e43c34ff207fd3074b49d5fd4f002f67e3769e3658eb2a1b133c46e90ce21d94
 size 22573704

checkpoint-1/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae23796d9b0133b5c99efd15115659635f24f6383319defabebffd5736df559
+oid sha256:ce93b8d86fadd8e6454d9a6661cc2fce00a1502d154dc7d2eb74db3866c3925f
 size 11710970

checkpoint-1/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52bb4a1f680991b39471f7bea45681a2b21ef2121ba1ad028e04d7edc135f0f
+oid sha256:7f6d4a6f3773b907ac1538b67c4fa544962eb5b1fc06aa0e7c5a313a547dc052
 size 14244

checkpoint-1/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.008421052631578947,
-      "grad_norm": 0.4095326066017151,
+      "grad_norm": 0.42370617389678955,
       "learning_rate": 0.0,
       "loss": 0.5794,
       "step": 1
     },
     {
       "epoch": 0.008421052631578947,
-      "eval_loss": 0.8254684209823608,
-      "eval_runtime": 1.1752,
-      "eval_samples_per_second": 42.545,
-      "eval_steps_per_second": 21.272,
+      "eval_loss": 0.8261134624481201,
+      "eval_runtime": 1.1415,
+      "eval_samples_per_second": 43.801,
+      "eval_steps_per_second": 21.901,
       "step": 1
     }
   ],

checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1cf165f6578d67dcaddc6087d65a0d404260662712b04399eef2021f5e0ed5
+oid sha256:8065f5a864b80993ab1beab427b139b642e1c31a0a8f2d96defab61f080c3fbd
 size 6776