Training in progress, step 6400

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a03009057bc17a55fb03559fceee9416e58df44f2b8cad404853c77ef5e25ff
+oid sha256:90226543ac07d2ffe305a17c9351436408a800fb2798a5a37995d29cfa11cdec
 size 500897101

{checkpoint-6000 → checkpoint-6300/adapter_model}/adapter_config.json

@@ -14,12 +14,12 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
     "up_proj",
     "gate_proj",
+    "down_proj",
     "q_proj",
+    "k_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

{checkpoint-6000 → checkpoint-6300/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb9d05e18d21539814aa33a75bcd59ecfa1423d749f7def1fa099eac295c773
+oid sha256:7a03009057bc17a55fb03559fceee9416e58df44f2b8cad404853c77ef5e25ff
 size 500897101

{checkpoint-6000/adapter_model → checkpoint-6400}/adapter_config.json

@@ -14,12 +14,12 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
     "up_proj",
     "gate_proj",
+    "down_proj",
     "q_proj",
+    "k_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

{checkpoint-6000/adapter_model → checkpoint-6400}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb9d05e18d21539814aa33a75bcd59ecfa1423d749f7def1fa099eac295c773
+oid sha256:90226543ac07d2ffe305a17c9351436408a800fb2798a5a37995d29cfa11cdec
 size 500897101

{checkpoint-6000 → checkpoint-6400}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2ecc4ddee7391368ca2bdf883b52a142b3223ddd7c27bca7244bd2de3bcddb
+oid sha256:498cd6646ca27d259b758938350aa23c6521abf4c2e2e7ad5c89c29393ef9c1f
 size 1001752701

{checkpoint-6000 → checkpoint-6400}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc24f1aa55fed05f1395ad2ed79cf05eb52b6ecc0baa24742036645b43faed9a
+oid sha256:28dca7865869f4b6acc2f12dccd0fb29d6ef17a6e533975d532c1cf6e37e11d2
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd27831189358f6a62977ee2eaf1b805123377bd30c694f0260768c08c73954
+oid sha256:6e95bbfc662c04f7d23d557ef4f14e26a584a804cd946876565cd79d3d1e5395
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35941e4f7d06780895f1a79a56ff5c4378292f6ce6bd12fc5b07e69724583728
+oid sha256:3a2dbf6e4afff30fb600631c828f6c4c1912077153655c0461e63ffb7c879162
 size 27789

{checkpoint-6000 → checkpoint-6400}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed503aec51f41855765482332db02edad2f64c1f84d01addcf0bb9777d98e33a
+oid sha256:5d5da328b9e2cfadac7217a3b12ebdf223bce01441fbb5a17edda72c92eeff44
 size 27789

{checkpoint-6000 → checkpoint-6400}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794be6d7653f4e3a617847df5f3466cd27e58c0fe6720fe54daac78fc2b957b3
+oid sha256:3a6396a02b3c9fddf0f353e31c8917f8cc7ea2204873bd2f4e0c28162e34ae43
 size 27789

{checkpoint-6000 → checkpoint-6400}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787c5cf322d2f5c9b4401cf5a1ee788314c3b0a9b62adb194e310d0e488e6a01
+oid sha256:26c3b73c9edd077374308e10afe3bc005239a39405fc2b10ee7113b60e422175
 size 27789

{checkpoint-6000 → checkpoint-6400}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8ddf4d9464f9f9e2f65e5f602469d549730a86cdea5aeebf632abac52e2e7e
+oid sha256:08c5ca5a5628b5625b372e5488a7dee8c4f85acbb5354ff6d66f2598a5588c2b
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f06a9c27fbf30d7ffa33a768c437fa0acdb24b8ab9c8b350036ee30534cc87
+oid sha256:21a349f1d80528bfaed715a90e1ab0cc38dcbe474a5753e02758e4de13823c66
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb4d07e81dd9a7d8e8f1e36bf075c260c77ff9df9ae50349f3e7cf63f188c79
+oid sha256:75aa1cbfd6e20ff25a627f7aabdabf69a55c2919dbb6f0133b93d94a03326d25
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1385cb52df53e1ad178f15b0c5c370c5544fd6d8ad2d70836280b53fdb12dce
+oid sha256:c3767f9dbacf7f7a87c95de7127c5a2e9cede78d6705a5058e7c152a0c95be20
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d99a2b8968570e031e0424a32e609efbd36648cb10e1a6a433d86dd846f6d51
+oid sha256:6736745fefc84acda69d21cca4210db1f2401990416ab7e86d4b97098b677a94
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d90f2793c0b89d8fc097ed1e2e79c2dce00f7ae4b893c1240cd6664cc419eb0
+oid sha256:5c8fad12f554df98e8ba12231bfa25343972f0990eb9688e02db0ecc021980e7
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020a7c57e51633fe41e2ad1d5636383a5f62fa61c16b20d12d5869f55850a7f1
+oid sha256:602e5b7b74cd1c25d9273dbce9513df4d9b1b8f459502b8973c5bc8ca815aeb9
 size 27772

{checkpoint-6000 → checkpoint-6400}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c4d1cef0517bd38d2881b2355b42ca7ef85e4a7d0e88cede6f3065dfea9556
+oid sha256:185367afc7f2b90a34c4a5da4f23b94cb09be4dbc5724516759fc2da4c464581
 size 27772

{checkpoint-6000 → checkpoint-6400}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d28d8e21aab77031305d6f6264051b275f871e4d54bbf04a21e88a4fbbdfa50
+oid sha256:12e968b9fe43b01b005367c0524e704d117f3484589d1270b46af1f5c106a7eb
 size 627

{checkpoint-6000 → checkpoint-6400}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3264831329972857,
-  "global_step": 6000,
+  "epoch": 2.481582008530438,
+  "global_step": 6400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1470,11 +1470,107 @@
       "eval_samples_per_second": 12.516,
       "eval_steps_per_second": 0.909,
       "step": 6000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.3262147229821984e-05,
+      "loss": 0.7679,
+      "step": 6025
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.2614391037483983e-05,
+      "loss": 0.7704,
+      "step": 6050
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.1974629770324106e-05,
+      "loss": 0.7661,
+      "step": 6075
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1342929523880416e-05,
+      "loss": 0.7652,
+      "step": 6100
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0719355560884246e-05,
+      "loss": 0.765,
+      "step": 6125
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.010397230451766e-05,
+      "loss": 0.7704,
+      "step": 6150
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.9496843331757784e-05,
+      "loss": 0.767,
+      "step": 6175
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8898031366808467e-05,
+      "loss": 0.7654,
+      "step": 6200
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.830759827462004e-05,
+      "loss": 0.7753,
+      "step": 6225
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.7725605054497906e-05,
+      "loss": 0.7725,
+      "step": 6250
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7152111833800522e-05,
+      "loss": 0.7698,
+      "step": 6275
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.6587177861727454e-05,
+      "loss": 0.7703,
+      "step": 6300
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.6030861503198204e-05,
+      "loss": 0.7658,
+      "step": 6325
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.548322023282235e-05,
+      "loss": 0.7677,
+      "step": 6350
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.4944310628961666e-05,
+      "loss": 0.7694,
+      "step": 6375
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.4414188367884907e-05,
+      "loss": 0.7668,
+      "step": 6400
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.584169133228268e+19,
+  "total_flos": 2.7563086736728785e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-6000 → checkpoint-6400}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c008d25bfaf7bb9a08aab93c029ae5c61570d5e3604fc9ca9ea2654e60b13cd6
+oid sha256:e85009bca9623c846e630c294adb80ecbcd9e720da8da9f9ee5311b562908b91
 size 4027