Training in progress, step 2700

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56dc05e4b75a13b83ba7370f0c76297d690a74a3feda12d5b102e996353b81b9
+oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
 size 500897101

{checkpoint-2300 → checkpoint-2600/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccafc4bd14ec4e43b1042a0590cd94ede59a0a46b3af2268942333e14f009fe
+oid sha256:56dc05e4b75a13b83ba7370f0c76297d690a74a3feda12d5b102e996353b81b9
 size 500897101

{checkpoint-2300/adapter_model → checkpoint-2700}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccafc4bd14ec4e43b1042a0590cd94ede59a0a46b3af2268942333e14f009fe
+oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
 size 500897101

{checkpoint-2300 → checkpoint-2700}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09875d8710c0b256d70a45b6165795297947cc066fffefa4eadde4a7e74447b5
+oid sha256:1e6581d1b0c10687bb3a3bc5ccd55dd7742012f93950a83aa87e181175ba0dae
 size 1001752701

{checkpoint-2300 → checkpoint-2700}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d32bef7d638b8934d561d4bfad1a900fc4e2c41552b753e806e0029fc74fe58
+oid sha256:f207e68632bac90f957ee4b69848b1b3bf1823589f0084ffda5fe51a062cda66
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d7e27372a96cbe26696b4d82834096fe258ad20f726deb5cafafff231c413a
+oid sha256:22862d05c3516b301c0029fcde0e8d61ec3a7a699c06f10b45b2038d258705bf
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9806ad8996ad73655276c702e9bf582d2f26f57c2055304271731c76fc61448
+oid sha256:ce953efa19f78d1504d60b13e76d782935e5997327dfbb7ccffdc0d67cd8ce63
 size 27789

{checkpoint-2300 → checkpoint-2700}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2304ae934a1ca1b566d82fc3b91a900f5a0e57004ba7c3747d3680c9bf7994a2
+oid sha256:f1474d4132d013009328b51314e14a4557202e7a03fe1c5dd72c4bee493ebc32
 size 27789

{checkpoint-2300 → checkpoint-2700}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095ef2621d7ad17b6d8b81bd18ce2b6fe2c178312e1e8ba1a86de571c45e2de5
+oid sha256:d397934e98e2af089f95cd3ebfbb6349d0d5379338b81dcdd71225e616b7d2d4
 size 27789

{checkpoint-2300 → checkpoint-2700}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9e9be373c3ebb63188ca728493103bb092268d7b6fcf92e0a89b09894cd715
+oid sha256:1c5aad35bbee83cb807b5f372f846229966f29c49d44cb351799da3e78c3739b
 size 27789

{checkpoint-2300 → checkpoint-2700}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c239354dbdd86d563374469538b584871ae2a28594f5ff63b8abde299fdbf2b
+oid sha256:54f1ed3e8d7bf0d86bd6d9acac91b9cfaabc266a2ecb5c2e05b800f5fb314129
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214c1bd964accc3329ceb0082946ac028de6fff1d26af23610d5e72192f25e06
+oid sha256:01f289536347abba01b49789dfbc3e30589b75cea2b08c3d776318c525f868ad
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51ae82338efebd3f9959ec89be63f51f4fd7447d7c81b0d5ced4b15d1471971
+oid sha256:203e94cac471cc2d7046694caa3b10e20010a25498536913b857d68ce1af2d43
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e425296388d7987a837bfc17bf8521aaffafc95bfdaa4ed71a252a8ee6e4785
+oid sha256:03a357f3ee8bad9901505c5f66d44c603f13d92ab451726200a0ee872b5550ca
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c0480d1aa56b841109174fd836fb9e139546505439291aa5228bd8284cd42d
+oid sha256:632d1189cca460782dd94b618a185a39301197e1ac0644b87bc12e7d639eb0db
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9cf82ee205afbfaca239c8f3606beac9926d4f89934cfba78fc70c7965c04c
+oid sha256:6c082c3485e7cf0ad8b46608970b89a1aec712ccf501f38bb2fbacfb0063ff84
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f54cc251e64fc43ea7906bcda268979b7ccf5730ecf572e5f7e35696eaef1fc
+oid sha256:f661148a14bf7645d198ffbee78fd27e53207bc2df14b4ac8eaf8cb1ec10b9d2
 size 27772

{checkpoint-2300 → checkpoint-2700}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411f28f7aa334979626223b80737ac45d841073b4663a97895d7c8a8a90716d4
+oid sha256:302a97fe98bf1022f079fb5f4731e03dbd6c8c435be26dfdcac5c3191c75b913
 size 27772

{checkpoint-2300 → checkpoint-2700}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a4eb98896140d186e72cc6934fa7664ebaea1f79a33825c5ffebfaf2a088e1
+oid sha256:165954622b82d5ed3c4b0d29e582a52b9368810b632d35b84ef87387e9f95006
 size 627

{checkpoint-2300 → checkpoint-2700}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8918185343156262,
-  "global_step": 2300,
+  "epoch": 1.0469174098487786,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -550,11 +550,107 @@
       "learning_rate": 0.0001596989478162339,
       "loss": 0.8334,
       "step": 2300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015888044520055106,
+      "loss": 0.8352,
+      "step": 2325
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015805585948026852,
+      "loss": 0.823,
+      "step": 2350
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000157225275845659,
+      "loss": 0.8293,
+      "step": 2375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015638878010665672,
+      "loss": 0.8289,
+      "step": 2400
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015554645868399205,
+      "loss": 0.832,
+      "step": 2425
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015469839860026308,
+      "loss": 0.8294,
+      "step": 2450
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001538446874709452,
+      "loss": 0.8281,
+      "step": 2475
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015298541349533925,
+      "loss": 0.8314,
+      "step": 2500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015212066544745926,
+      "loss": 0.831,
+      "step": 2525
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015125053266686124,
+      "loss": 0.8319,
+      "step": 2550
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015037510504941303,
+      "loss": 0.8259,
+      "step": 2575
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014949447303800695,
+      "loss": 0.8133,
+      "step": 2600
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014860872761321593,
+      "loss": 0.8139,
+      "step": 2625
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00014771796028389405,
+      "loss": 0.804,
+      "step": 2650
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001468222630777225,
+      "loss": 0.8011,
+      "step": 2675
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00014592172853170193,
+      "loss": 0.8037,
+      "step": 2700
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 9.906168731933868e+18,
+  "total_flos": 1.1628331844604264e+19,
   "trial_name": null,
   "trial_params": null
 }