Training in progress, step 7200

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7994cd2bdb16f74437b3f74bb9b30d22b607685dff2fbbddd6503caf3ecfc9c
+oid sha256:b4ed435f77b8aaa468d0a026e8247b6e75dcc7152deb57502bce336e2ea4128e
 size 500897101

{checkpoint-6800 → checkpoint-7100/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-6800 → checkpoint-7100/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caee01e1da9f7e92223499414f8bb25b28ea34daf6fb927c9bd869dcba2559fd
+oid sha256:f7994cd2bdb16f74437b3f74bb9b30d22b607685dff2fbbddd6503caf3ecfc9c
 size 500897101

{checkpoint-6800/adapter_model → checkpoint-7200}/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-6800/adapter_model → checkpoint-7200}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caee01e1da9f7e92223499414f8bb25b28ea34daf6fb927c9bd869dcba2559fd
+oid sha256:b4ed435f77b8aaa468d0a026e8247b6e75dcc7152deb57502bce336e2ea4128e
 size 500897101

{checkpoint-6800 → checkpoint-7200}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8797c2a2a21d3c99399832b3c5e9972ada7dec6e83cff5de4273cfa1c8c9f7
+oid sha256:58080885ae3c7e810fac9015f40f367426ce410c7f99ba7b48feda9529653b88
 size 1001752701

{checkpoint-6800 → checkpoint-7200}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a69b101b534038a0d1cd30c8b1e9841f687d0b3b07df6d02b3916e19b719c2
+oid sha256:e78a8c7990f0b5fabbe6277b9b978a79ef9d902e28f476c9e2d7ad38be8f683c
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e8706d00c08c82d30b24671bce72e1fd88ccda2d435bfc8570ef4280b40d47
+oid sha256:d7b8c7955910d1e491c12afee87720b150c2f84104325ab9c838c1295ee23834
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f82da6b92d2dd42eda022db14fa263f4d03e28910c03bf4e97c967f1d893d8f
+oid sha256:b248c3f8c2f9ee32893e76f2912253473328a82703a9e9cf774a7ddf60d42191
 size 27789

{checkpoint-6800 → checkpoint-7200}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864477484049b3efdc98311c8185fa709645f956dfcbc5f22f55344bde84d440
+oid sha256:80b4aace0601254c95160262eebbc86921bdf994e5b06ee7d3f592a180f3f4da
 size 27789

{checkpoint-6800 → checkpoint-7200}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b26c1496ef4023f2612561635f505e587abbdb9e2a946f7d90f08aaa3337aa4
+oid sha256:dbfecac90c68b3c7960f23f0a5c624343b34de925fd36e8f1553794649032b92
 size 27789

{checkpoint-6800 → checkpoint-7200}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c96078789fb495fd632c506d1671752f888d28d828331ac9ab1506089b50ed
+oid sha256:c3aaab3904ce6b40c88c9ba5f75918dcc2286b14b28ff6f552b1e33426b307a4
 size 27789

{checkpoint-6800 → checkpoint-7200}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e915fcf4dd8f755df46cb9e5050aaae8b843699fa9edd019950564b2fda05c
+oid sha256:7cea57a52a03e3e2ba53900bfa4f24480bd064ae5ee54082744c8d66479e3392
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e81ee1af73dd375865e86e8bf7e0efc15b3d4e65d58ca9f4d3ed4d33561879b
+oid sha256:183c5a8964dcebb4403f961f817d27e57f34a8aca9d588c50a976a55c7fd2dcc
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9150b049fc2e88708149ace562a8a4c9fef4ae5ea0bb2b8a584401d2abf84b2
+oid sha256:72dde9fbb9f6a3d30beec6e7a6a331f1c07cc41bc3e421c95d5fc51337163858
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9632ffce62364279230205690bdfad30fc16e17ef6a0f7efacfbeb73e2b1496
+oid sha256:240e0b564b5f72f61c5e9bf130c09d6b7a884041c6817f283c0db8dce9514c6d
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0510fe79de24ae1d1cce464b86e9ee2bc9d2fa77099fb7dc30a7866117bd6e7
+oid sha256:c3e782243547e75d21ba55dd4adfc01fec8df179ac5853e510085d873d508172
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c084b8f84126bddadb7fcd64d22191438d565af4562b1fa9ef192f15ed39f43
+oid sha256:a862e45bf9cf553270045d741a8187da4668bf889c171749a617824d14d63917
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3c330abb87810692a9b735e5edfdf7a74760562ee2e69753f40e14ef0d2404
+oid sha256:e864e9ec63d970372488da3e89af0a1ea00e3da41e08446b93c1ddc621af475d
 size 27772

{checkpoint-6800 → checkpoint-7200}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002d98d8a4fb73f32df6d2c88a43fb21668bf0821b126886c8586170e99c43d9
+oid sha256:4d8cdcdaf9565ca7ffc01e41e6463d0c5d0aaca2ff165ca019aaa7bb751b870e
 size 27772

{checkpoint-6800 → checkpoint-7200}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89396b89609adca20f26c9861c9dcc008dc9de0fbc3e7816552f07bbb0b807a7
+oid sha256:d125f3dfa4d0989c607da131ae73674dff5736961f5c5c505915b427cba21012
 size 627

{checkpoint-6800 → checkpoint-7200}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6366808840635905,
-  "global_step": 6800,
+  "epoch": 2.791779759596743,
+  "global_step": 7200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1662,11 +1662,115 @@
       "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
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.0797035363512193e-06,
+      "loss": 0.7685,
+      "step": 7125
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.834404132647128e-06,
+      "loss": 0.769,
+      "step": 7150
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.5991431802683262e-06,
+      "loss": 0.7647,
+      "step": 7175
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.3739449846862826e-06,
+      "loss": 0.7634,
+      "step": 7200
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.928513074136613e+19,
+  "total_flos": 3.100665541573791e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-6800 → checkpoint-7200}/training_args.bin

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