Training in progress, step 7100

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:829e114ab5a9e821c62f695524a70db8ca49a86641b2859ce77fb48a06a52662
+oid sha256:f7994cd2bdb16f74437b3f74bb9b30d22b607685dff2fbbddd6503caf3ecfc9c
 size 500897101

{checkpoint-6700 → checkpoint-7000/adapter_model}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-6700 → checkpoint-7000/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb96297919ffccc23a8f48a581a3185b03d83d73a72799941d2f235cad389d3
+oid sha256:829e114ab5a9e821c62f695524a70db8ca49a86641b2859ce77fb48a06a52662
 size 500897101

{checkpoint-6700/adapter_model → checkpoint-7100}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-6700/adapter_model → checkpoint-7100}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb96297919ffccc23a8f48a581a3185b03d83d73a72799941d2f235cad389d3
+oid sha256:f7994cd2bdb16f74437b3f74bb9b30d22b607685dff2fbbddd6503caf3ecfc9c
 size 500897101

{checkpoint-6700 → checkpoint-7100}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62cd6479e017b9a26c6526efc05511bbf9df9083364daa29ee80aa0a5dfd359
+oid sha256:08bb8b622161de17af40582eb3ed678e87e25a018cf69b2de05646628dfca429
 size 1001752701

{checkpoint-6700 → checkpoint-7100}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b849a067e4f8461499fff8af86ebd00e3d3bf92cc824ac056b45ce1c6f1c291d
+oid sha256:23c8a5bc289147cb5929165f36a3fc53769326cf76122f4e6c3653db9207d22b
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f7d4c58f6339b6807226b0366cd9b4808e6973c1c8a248799f75b54a950a71
+oid sha256:13d75987ce8c09a29b765dd85cdd96b7a9a16698e6e223be594288e44b77c0ef
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfb08b6b4d0f86655bf2077164aac4e21f12609b7e13eaf1b85093e2bd5b575
+oid sha256:9194e62944ef0d0d95beb53e67dd3ad85f824a5c4c4367f1ae922d8f0252511a
 size 27789

{checkpoint-6700 → checkpoint-7100}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee65fa4fe3df5dd0784bb0ffd9f8c43572441235f5f1584cd7e48ca6d391b3b
+oid sha256:e8b2f0d2bdab9bb6a53039c3d6d49fe1efd65d83e7c14abc55131fd39c7a8087
 size 27789

{checkpoint-6700 → checkpoint-7100}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81c59c719504cb60451e827226d5c96dd0d7b2c2029c662831e8cefda2c54c4
+oid sha256:5afbd024ed5e83de312b869416218e006a8c440bcfa8eb583f35096bfb0c4720
 size 27789

{checkpoint-6700 → checkpoint-7100}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f42032bd3037f0ed187573de33bf981a8759d22c266510058950f3fe7fedd84
+oid sha256:0cab3d1d84a4ad05749470c8f5dc01e60bfcb95467f434ca95e7e4ea22f5d250
 size 27789

{checkpoint-6700 → checkpoint-7100}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6568983fb50a48df14df5e018a2b846aa35270eca396c9cde88d8e926a2b7e9e
+oid sha256:97044b073aa474e262f429ff1b481848b303cc0cfb213657542fc577a8f0b9fd
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63f3fa6b0e3996d213ddad5511a17eca0c4465010e640447f4b694b1b0964e2
+oid sha256:574b4b605f5956d0c7871af3ec3d18dbf8d8e7ed9b553e22b08e100a70e567fa
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bda1b1d8e9e2ec530f144ce7f12db517bc8a9fc24f2dada873ec9a52da5a86e
+oid sha256:40164a2ca96b5ba33c934479558b3008f70a14394bc47f822b3d87cfe904a19e
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2376f635219a3647dc4c0e776c0a3111a0130b027a88d2ccb50344af206de2d4
+oid sha256:e5f952d85ac6565b75dbbb768259288b5b0dd464f3cb12806854d43d36838e07
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6a7fccb0aa5e4d85e4648b63853053ae8aaa55e6c9b6a833460f775d1fe07e
+oid sha256:86c477a0ba385b263d319ebf01a2681a100d7e5c60aaec444e59be567c2e2eab
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cfd7753ba250ce6a1634c239e3256daf18c248cc833b55bb6b9e6ce312d51f
+oid sha256:dadf17ecf19fb0e7d5796316055a7f6a2ff58b559ee65fb247152209c0f58e0c
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c755eb589e46f504ec1fa833022df48b211aa54b7f5ff4f0f1a446258e9f93
+oid sha256:54df0035f6989468f459c9adfac4aab9e79d3416ce505281cf38f0c89b6df8d0
 size 27772

{checkpoint-6700 → checkpoint-7100}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2635059e555f5db3a1c952c755fa2e418c4d0df4b1ef65c28677fc28d92db24d
+oid sha256:697f5513e941f30e44819a138ad4df97f3c4871e837c83e79cd6dcfa2561da90
 size 27772

{checkpoint-6700 → checkpoint-7100}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e004103cf4786af8b81629072cde0f9b18441c01ffdcd8cae42df8cd38f3d412
+oid sha256:28d2cff1b78513eaa3664c14381155eeb1b4cabe349547de751fa001fc41f348
 size 627

{checkpoint-6700 → checkpoint-7100}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5979061651803024,
-  "global_step": 6700,
+  "epoch": 2.7530050407134548,
+  "global_step": 7100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1638,11 +1638,115 @@
       "learning_rate": 8.757144409503359e-06,
       "loss": 0.765,
       "step": 6700
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.34590363821306e-06,
+      "loss": 0.7713,
+      "step": 6725
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.944131909713859e-06,
+      "loss": 0.7631,
+      "step": 6750
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.551870732174416e-06,
+      "loss": 0.767,
+      "step": 6775
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.169160631201566e-06,
+      "loss": 0.7692,
+      "step": 6800
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.796041145653553e-06,
+      "loss": 0.7677,
+      "step": 6825
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.432550823555128e-06,
+      "loss": 0.7706,
+      "step": 6850
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.078727218115043e-06,
+      "loss": 0.7678,
+      "step": 6875
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.734606883846338e-06,
+      "loss": 0.7717,
+      "step": 6900
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.40022537278978e-06,
+      "loss": 0.7701,
+      "step": 6925
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.07561723084089e-06,
+      "loss": 0.7694,
+      "step": 6950
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.7608159941809e-06,
+      "loss": 0.7659,
+      "step": 6975
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.455854185812047e-06,
+      "loss": 0.7639,
+      "step": 7000
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 0.8055068850517273,
+      "eval_runtime": 58.7443,
+      "eval_samples_per_second": 12.427,
+      "eval_steps_per_second": 0.902,
+      "step": 7000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.160763312197513e-06,
+      "loss": 0.7724,
+      "step": 7025
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.875573860006421e-06,
+      "loss": 0.7696,
+      "step": 7050
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.6003152929641624e-06,
+      "loss": 0.7625,
+      "step": 7075
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.335016048808437e-06,
+      "loss": 0.7733,
+      "step": 7100
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.885490295679274e+19,
+  "total_flos": 3.0575605849301975e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-6700 → checkpoint-7100}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e85009bca9623c846e630c294adb80ecbcd9e720da8da9f9ee5311b562908b91
+oid sha256:1c2f4cc723c65538de12d445f71a30b1610b702bfe771edb2385636bb8724bfd
 size 4027