Training in progress, step 6800

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb96297919ffccc23a8f48a581a3185b03d83d73a72799941d2f235cad389d3
+oid sha256:caee01e1da9f7e92223499414f8bb25b28ea34daf6fb927c9bd869dcba2559fd
 size 500897101

{checkpoint-6400 → checkpoint-6700/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90226543ac07d2ffe305a17c9351436408a800fb2798a5a37995d29cfa11cdec
+oid sha256:bcb96297919ffccc23a8f48a581a3185b03d83d73a72799941d2f235cad389d3
 size 500897101

{checkpoint-6400/adapter_model → checkpoint-6800}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90226543ac07d2ffe305a17c9351436408a800fb2798a5a37995d29cfa11cdec
+oid sha256:caee01e1da9f7e92223499414f8bb25b28ea34daf6fb927c9bd869dcba2559fd
 size 500897101

{checkpoint-6400 → checkpoint-6800}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498cd6646ca27d259b758938350aa23c6521abf4c2e2e7ad5c89c29393ef9c1f
+oid sha256:4a8797c2a2a21d3c99399832b3c5e9972ada7dec6e83cff5de4273cfa1c8c9f7
 size 1001752701

{checkpoint-6400 → checkpoint-6800}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dca7865869f4b6acc2f12dccd0fb29d6ef17a6e533975d532c1cf6e37e11d2
+oid sha256:76a69b101b534038a0d1cd30c8b1e9841f687d0b3b07df6d02b3916e19b719c2
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e95bbfc662c04f7d23d557ef4f14e26a584a804cd946876565cd79d3d1e5395
+oid sha256:f5e8706d00c08c82d30b24671bce72e1fd88ccda2d435bfc8570ef4280b40d47
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2dbf6e4afff30fb600631c828f6c4c1912077153655c0461e63ffb7c879162
+oid sha256:8f82da6b92d2dd42eda022db14fa263f4d03e28910c03bf4e97c967f1d893d8f
 size 27789

{checkpoint-6400 → checkpoint-6800}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5da328b9e2cfadac7217a3b12ebdf223bce01441fbb5a17edda72c92eeff44
+oid sha256:864477484049b3efdc98311c8185fa709645f956dfcbc5f22f55344bde84d440
 size 27789

{checkpoint-6400 → checkpoint-6800}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6396a02b3c9fddf0f353e31c8917f8cc7ea2204873bd2f4e0c28162e34ae43
+oid sha256:4b26c1496ef4023f2612561635f505e587abbdb9e2a946f7d90f08aaa3337aa4
 size 27789

{checkpoint-6400 → checkpoint-6800}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c3b73c9edd077374308e10afe3bc005239a39405fc2b10ee7113b60e422175
+oid sha256:f3c96078789fb495fd632c506d1671752f888d28d828331ac9ab1506089b50ed
 size 27789

{checkpoint-6400 → checkpoint-6800}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c5ca5a5628b5625b372e5488a7dee8c4f85acbb5354ff6d66f2598a5588c2b
+oid sha256:61e915fcf4dd8f755df46cb9e5050aaae8b843699fa9edd019950564b2fda05c
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a349f1d80528bfaed715a90e1ab0cc38dcbe474a5753e02758e4de13823c66
+oid sha256:1e81ee1af73dd375865e86e8bf7e0efc15b3d4e65d58ca9f4d3ed4d33561879b
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75aa1cbfd6e20ff25a627f7aabdabf69a55c2919dbb6f0133b93d94a03326d25
+oid sha256:f9150b049fc2e88708149ace562a8a4c9fef4ae5ea0bb2b8a584401d2abf84b2
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3767f9dbacf7f7a87c95de7127c5a2e9cede78d6705a5058e7c152a0c95be20
+oid sha256:b9632ffce62364279230205690bdfad30fc16e17ef6a0f7efacfbeb73e2b1496
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6736745fefc84acda69d21cca4210db1f2401990416ab7e86d4b97098b677a94
+oid sha256:f0510fe79de24ae1d1cce464b86e9ee2bc9d2fa77099fb7dc30a7866117bd6e7
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8fad12f554df98e8ba12231bfa25343972f0990eb9688e02db0ecc021980e7
+oid sha256:3c084b8f84126bddadb7fcd64d22191438d565af4562b1fa9ef192f15ed39f43
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602e5b7b74cd1c25d9273dbce9513df4d9b1b8f459502b8973c5bc8ca815aeb9
+oid sha256:7a3c330abb87810692a9b735e5edfdf7a74760562ee2e69753f40e14ef0d2404
 size 27772

{checkpoint-6400 → checkpoint-6800}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185367afc7f2b90a34c4a5da4f23b94cb09be4dbc5724516759fc2da4c464581
+oid sha256:002d98d8a4fb73f32df6d2c88a43fb21668bf0821b126886c8586170e99c43d9
 size 27772

{checkpoint-6400 → checkpoint-6800}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e968b9fe43b01b005367c0524e704d117f3484589d1270b46af1f5c106a7eb
+oid sha256:89396b89609adca20f26c9861c9dcc008dc9de0fbc3e7816552f07bbb0b807a7
 size 627

{checkpoint-6400 → checkpoint-6800}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.481582008530438,
-  "global_step": 6400,
+  "epoch": 2.6366808840635905,
+  "global_step": 6800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1566,11 +1566,107 @@
       "learning_rate": 1.4414188367884907e-05,
       "loss": 0.7668,
       "step": 6400
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.3892908218015654e-05,
+      "loss": 0.7662,
+      "step": 6425
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.3380524034274122e-05,
+      "loss": 0.7689,
+      "step": 6450
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.2877088752513189e-05,
+      "loss": 0.7694,
+      "step": 6475
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2382654384049475e-05,
+      "loss": 0.7714,
+      "step": 6500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1897272010289884e-05,
+      "loss": 0.7701,
+      "step": 6525
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1420991777454315e-05,
+      "loss": 0.7628,
+      "step": 6550
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.0953862891394795e-05,
+      "loss": 0.7661,
+      "step": 6575
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.0495933612511976e-05,
+      "loss": 0.7729,
+      "step": 6600
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0047251250769175e-05,
+      "loss": 0.772,
+      "step": 6625
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.60786216080466e-06,
+      "loss": 0.7702,
+      "step": 6650
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.177811737142627e-06,
+      "loss": 0.7711,
+      "step": 6675
+    },
+    {
+      "epoch": 2.6,
+      "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
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.7563086736728785e+19,
+  "total_flos": 2.928513074136613e+19,
   "trial_name": null,
   "trial_params": null
 }