Upload folder using huggingface_hub

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj",
-    "c_attn"
+    "c_attn",
+    "c_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205639d5518ad2635d9ff85e240ab7adfbd53cf6f4c0097ed416a8006ec3642e
+oid sha256:fcee55c3a6d095844c13e6a1581a2569d65629e5c9661351260c110844a17d6e
 size 121915776

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae78663a89944488c3ea13511b18dfa4680ad21cedaec2830b047347e158ad53
+oid sha256:98807b528de929625c704eee6ff4a8b7bfac94972a6461f0e8fd9e071223f266
 size 243883194

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90200101f953921312744293ee71aa8aba7266377b4396e665a0d441571c9ab9
+oid sha256:183eb4d88f2758914294124886d1c48746eb117c394992417d09a86ef7c6fed1
 size 14244

trainer_state.json

@@ -11,199 +11,199 @@
     {
       "epoch": 0.03,
       "learning_rate": 1.3333333333333333e-05,
-      "loss": 2.5901,
+      "loss": 2.6262,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.9987954562051724e-05,
-      "loss": 1.6054,
+      "loss": 1.6549,
       "step": 4
     },
     {
       "epoch": 0.09,
       "learning_rate": 1.989176509964781e-05,
-      "loss": 1.637,
+      "loss": 1.6926,
       "step": 6
     },
     {
       "epoch": 0.12,
       "learning_rate": 1.9700312531945444e-05,
-      "loss": 1.5457,
+      "loss": 1.6159,
       "step": 8
     },
     {
       "epoch": 0.15,
       "learning_rate": 1.941544065183021e-05,
-      "loss": 1.2591,
+      "loss": 1.3612,
       "step": 10
     },
     {
       "epoch": 0.18,
       "learning_rate": 1.9039892931234434e-05,
-      "loss": 1.5811,
+      "loss": 1.7452,
       "step": 12
     },
     {
       "epoch": 0.21,
       "learning_rate": 1.8577286100002723e-05,
-      "loss": 2.0195,
+      "loss": 2.2381,
       "step": 14
     },
     {
       "epoch": 0.24,
       "learning_rate": 1.803207531480645e-05,
-      "loss": 2.6436,
+      "loss": 3.1504,
       "step": 16
     },
     {
       "epoch": 0.27,
       "learning_rate": 1.7409511253549592e-05,
-      "loss": 2.0522,
+      "loss": 2.0864,
       "step": 18
     },
     {
       "epoch": 0.3,
       "learning_rate": 1.6715589548470187e-05,
-      "loss": 1.5437,
+      "loss": 1.5856,
       "step": 20
     },
     {
       "epoch": 0.33,
       "learning_rate": 1.5956993044924334e-05,
-      "loss": 1.5208,
+      "loss": 1.5722,
       "step": 22
     },
     {
       "epoch": 0.36,
       "learning_rate": 1.5141027441932217e-05,
-      "loss": 1.5031,
+      "loss": 1.5654,
       "step": 24
     },
     {
       "epoch": 0.39,
       "learning_rate": 1.4275550934302822e-05,
-      "loss": 1.5096,
+      "loss": 1.5932,
       "step": 26
     },
     {
       "epoch": 0.42,
       "learning_rate": 1.3368898533922202e-05,
-      "loss": 1.7672,
+      "loss": 1.9197,
       "step": 28
     },
     {
       "epoch": 0.45,
       "learning_rate": 1.242980179903264e-05,
-      "loss": 2.1739,
+      "loss": 2.3697,
       "step": 30
     },
     {
       "epoch": 0.48,
       "learning_rate": 1.1467304744553618e-05,
-      "loss": 2.5344,
+      "loss": 2.975,
       "step": 32
     },
     {
       "epoch": 0.51,
       "learning_rate": 1.0490676743274181e-05,
-      "loss": 2.4945,
+      "loss": 2.5185,
       "step": 34
     },
     {
       "epoch": 0.54,
       "learning_rate": 9.50932325672582e-06,
-      "loss": 1.9292,
+      "loss": 1.9642,
       "step": 36
     },
     {
       "epoch": 0.57,
       "learning_rate": 8.532695255446384e-06,
-      "loss": 1.5841,
+      "loss": 1.6161,
       "step": 38
     },
     {
       "epoch": 0.6,
       "learning_rate": 7.570198200967363e-06,
-      "loss": 1.4861,
+      "loss": 1.5248,
       "step": 40
     },
     {
       "epoch": 0.63,
       "learning_rate": 6.631101466077801e-06,
-      "loss": 1.37,
+      "loss": 1.4393,
       "step": 42
     },
     {
       "epoch": 0.66,
       "learning_rate": 5.724449065697182e-06,
-      "loss": 1.7151,
+      "loss": 1.823,
       "step": 44
     },
     {
       "epoch": 0.69,
       "learning_rate": 4.858972558067784e-06,
-      "loss": 2.0653,
+      "loss": 2.1982,
       "step": 46
     },
     {
       "epoch": 0.72,
       "learning_rate": 4.043006955075667e-06,
-      "loss": 2.5185,
+      "loss": 3.0005,
       "step": 48
     },
     {
       "epoch": 0.75,
       "learning_rate": 3.284410451529816e-06,
-      "loss": 2.799,
+      "loss": 2.8139,
       "step": 50
     },
     {
       "epoch": 0.78,
       "learning_rate": 2.5904887464504115e-06,
-      "loss": 1.6359,
+      "loss": 1.6601,
       "step": 52
     },
     {
       "epoch": 0.81,
       "learning_rate": 1.967924685193552e-06,
-      "loss": 1.3921,
+      "loss": 1.4221,
       "step": 54
     },
     {
       "epoch": 0.84,
       "learning_rate": 1.4227138999972801e-06,
-      "loss": 1.6824,
+      "loss": 1.7112,
       "step": 56
     },
     {
       "epoch": 0.86,
       "learning_rate": 9.601070687655667e-07,
-      "loss": 1.5013,
+      "loss": 1.5428,
       "step": 58
     },
     {
       "epoch": 0.89,
       "learning_rate": 5.845593481697931e-07,
-      "loss": 1.4693,
+      "loss": 1.5406,
       "step": 60
     },
     {
       "epoch": 0.92,
       "learning_rate": 2.996874680545603e-07,
-      "loss": 1.7278,
+      "loss": 1.8368,
       "step": 62
     },
     {
       "epoch": 0.95,
       "learning_rate": 1.0823490035218986e-07,
-      "loss": 2.3428,
+      "loss": 2.6137,
       "step": 64
     },
     {
       "epoch": 0.98,
       "learning_rate": 1.2045437948275952e-08,
-      "loss": 1.5258,
+      "loss": 1.5788,
       "step": 66
     }
   ],
@@ -212,7 +212,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 4665930355777536.0,
+  "total_flos": 4694799827656704.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9653fc37f15f43deaa9493115e12b71d00caae59a1a8db756d1f8243d0afe89c
+oid sha256:21bcb8c36870e5182a02c55ede2a08d2d61a08d449827fd961caac1d2a3e60c7
 size 4728