Training in progress, step 2800

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
+oid sha256:2ea36cf8e55409a14da3fc648b1dfbd6758083b72318e4742d7d9efc2963c331
 size 500897101

{checkpoint-2400 → checkpoint-2700/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a78f07f6c25ff3a384ba787025398b099c4ded28cf5a456badfb2abdeac5d61
+oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
 size 500897101

{checkpoint-2400/adapter_model → checkpoint-2800}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a78f07f6c25ff3a384ba787025398b099c4ded28cf5a456badfb2abdeac5d61
+oid sha256:2ea36cf8e55409a14da3fc648b1dfbd6758083b72318e4742d7d9efc2963c331
 size 500897101

{checkpoint-2400 → checkpoint-2800}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442f0fed82ae5467ffbfbea1da70c37dc0aa8f203aa2acc1af02f5551c32b764
+oid sha256:4ad547cbbf1779bc43d5f541ea80ff23dfadca360f5b7fbe6b9210bdabd5b0a3
 size 1001752701

{checkpoint-2400 → checkpoint-2800}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25acea38e8d5bd8784604757d457a14328f73f9d42017801732c3673ffcbfc19
+oid sha256:54ceaf70d5ffe3e642b177d8e34d1f05742963af64a1bcc361535a9360b397c4
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3505b23dfaf76f0323c2ce25bb39a0407b98df2fa7f7f93ac6e58b365baaf761
+oid sha256:9607a8c2ef03708a5690aea65c1585d4ddbd8e01d7e279a5781ba30e8f1917ff
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96eb3af611e5c6385bb1c8067036789858b5ea043db87fec2ad208b395fffc57
+oid sha256:8681f4b5196d1fde8691794cb783ea1dab72c5077dbcf5394c6998bd4136e731
 size 27789

{checkpoint-2400 → checkpoint-2800}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb10515bb0a74ed81dcf9a34118607a62c4ccb79c19d815ce2d4bdb2d1592d9
+oid sha256:fd6cb0b4fef9e193eda245bff5fbcc8df9769fc61966e5f1cdf256150779c1da
 size 27789

{checkpoint-2400 → checkpoint-2800}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fbdd560259eca962bf8c98ba80f05b15bff2710d82866301aa92e4d53e6796
+oid sha256:b66ef66b2b0e1dce0083092ba63e49bdf210999432342b9c2a3993ca381ca353
 size 27789

{checkpoint-2400 → checkpoint-2800}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77df3ee11bff786b83de93e9a70beacac88e03056ae7179237d27b9de8bea35
+oid sha256:5cec3ba0fdf94eca1cdf6294a4f5fddb5e3c4f431222a020f6b0acac68bcd0b2
 size 27789

{checkpoint-2400 → checkpoint-2800}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766dffdd000bec26f59585fd09f364b34726c28f571693e392e5ad0bcc023f25
+oid sha256:1c53913af6dbe6026773029476e95c35bab12c198a7f90d679010f0fd21198df
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7057ffcb1d3910adbeb89bdb03cf4db72e06b97d19d39d45a5fe88814dc8fd
+oid sha256:811ad146e12ad4449d58b59f6fcb92f298ffd443e1a43261d70a55e3eb6343d9
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b19904fa5333a4aafd38d77ad2ee464c195a29f00b1ba0693aff3710185b33
+oid sha256:d5da3f408ca3cd0e89a66524e7f4846e322256ba24237784526bdc51b9ede18b
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6ca6b609b5c555ef0a17f2d40c5a0ac1a71bb332d258ec785e0a74ff79d3df
+oid sha256:4c659f82e6a038ab94307ae424a29fedf3767fe4eabecd42c8ea9b1fb19e36fc
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27777665ad4b9dc253fdd2761e1c9d90b9e208f74c07efc1915794ca03143b09
+oid sha256:3d5c97078c0cd3e6af8628033620fd2ade2aea530684443c37b10455b6826ae1
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32c2e57af55e62f6ebb560ee9f279e7a2d4cf944db5c350acc71b49224172b1
+oid sha256:7dd4ff6e318b6e48ea5386ceaf02104c9a56c201311646c4a4e1f4c3be379fe7
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b4976b266fb6cb141d47782aeb00f44806fb3e77fd565e3b1d784d985b712c
+oid sha256:31d89de68577a860ceffdb664eb8eb7a44e5a8dd6aa62c351c0caf7b931e6a02
 size 27772

{checkpoint-2400 → checkpoint-2800}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3562833238738c3d7b0e7d94f70e453b7694fc096cd6651e5e76b9fc45a3ed
+oid sha256:76b3e7281559d95415194847aba99c3c754c2f0ad8f10ac4eb274f044a763cf1
 size 27772

{checkpoint-2400 → checkpoint-2800}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f85b645b3956f71e88b844e74e8a1785c175b8f1cad016ae6807e31a99fe657c
+oid sha256:0008ae7bce85f92437f0e149969fba2477d40c35a55a3a590f361670b6eb7290
 size 627

{checkpoint-2400 → checkpoint-2800}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9305932531989143,
-  "global_step": 2400,
+  "epoch": 1.0856921287320667,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -574,11 +574,107 @@
       "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
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014501644968259212,
+      "loss": 0.8063,
+      "step": 2725
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014410652005730025,
+      "loss": 0.8155,
+      "step": 2750
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014319203366321826,
+      "loss": 0.8066,
+      "step": 2775
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001422730849785107,
+      "loss": 0.8091,
+      "step": 2800
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 1.0337240915667583e+19,
+  "total_flos": 1.205858669606155e+19,
   "trial_name": null,
   "trial_params": null
 }