Training in progress, step 360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ce6cecdd314dff17b644147b3388cb5111b549d613ac5c68bdbdf5b9fdee40
+oid sha256:bf6bc89ed515c11edca157585cc4d08f3b032c0ffd4314aa79333ca1f3c8d512
 size 18091656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49cd53400e0a47159989aa1c77c8379561a427dfe9dfc1b0094c1fcaf788b7df
+oid sha256:8084acbc3ed18c5405e1dae91524a8683c3de78b48f0c9f04ed0d349a7c73286
 size 36192998

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4c58634faaaf2fb0eeb91e473e7b93896c3a9652f663d387a8d5fb6f43e7d2
+oid sha256:6184eeaad9b63225dc77ef2ebed37b3393eb958bf1b0036e48dd0dd4dce8d3e8
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57aa4fb3e97b079d1ad911bf7d37d534bb625378be9778ebb012c06b4d7e99cc
+oid sha256:b023e2a6d269c0076aa102ee08abf897f3861f92ad6f8e6c141a2add64f168fc
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a952c2e65d35ff62cb12b1f44329829277d5ed82f3d4b456abd568196b60a7
+oid sha256:0cc15daee6eb8334e4ef77378d3160328ff03a12360233ca932fdc7422e74a5c
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa234d2834072dafe4b1a2bbcd33db2d2f07041dcdbd1740fb2502aaf8a2fbe2
+oid sha256:1799d707236b96f35b0a65f363960fd5940a5fdfa4742f09a2e63a97bbd9dc57
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f672ca888e1d40971fbc5f6ca9c9fbf26c349778491acbb6d14b2591deef0eac
+oid sha256:b12d1bdab4d9b46cb08e585841e7243af006aa3bab548a59d48e6556aeddac40
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec566273622194d0477a7520f381463a85cbca503e3d8bf85a39683e530a83d
+oid sha256:a6bf839b2526d77010bd7aa679f8e366e5d97bb7f4d317d2d1da257b8178f8e4
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a5df562c029883190dad4fc757a124ade431b1e7ad179f4a2c1dea51a68973
+oid sha256:55273bfecbe6270bcc0713428d0aef85b6f753e4a96acc6a4ba319abd3048438
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30f4e64a39ddfe0cd45836a729f4974c4326800cec624251db6d6ab0e9fc5d2
+oid sha256:212b99b6d3d9b2cedd149518a5819f7b601ae13b9e1660a64dbe679fa815027c
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ba300eb50af5f07dfdf5f9c8ec3b31766e55d5d321cd8570f14309b439775d
+oid sha256:8546ece63abe39ed6d5eb52d3760f17bec10518134f71da680520ffc565f9e9f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.037914691943128,
+  "epoch": 6.796208530805687,
   "eval_steps": 200,
-  "global_step": 320,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,34 @@
       "learning_rate": 0.0001950050699546116,
       "loss": 2.5373,
       "step": 320
+    },
+    {
+      "epoch": 6.2274881516587675,
+      "grad_norm": 2.4172613620758057,
+      "learning_rate": 0.00019459278837999046,
+      "loss": 2.3316,
+      "step": 330
+    },
+    {
+      "epoch": 6.4170616113744074,
+      "grad_norm": 0.724682092666626,
+      "learning_rate": 0.00019416463127609656,
+      "loss": 2.5669,
+      "step": 340
+    },
+    {
+      "epoch": 6.606635071090047,
+      "grad_norm": 0.4259670674800873,
+      "learning_rate": 0.00019372067050063438,
+      "loss": 2.4148,
+      "step": 350
+    },
+    {
+      "epoch": 6.796208530805687,
+      "grad_norm": 1.5209062099456787,
+      "learning_rate": 0.00019326098056364222,
+      "loss": 2.4746,
+      "step": 360
     }
   ],
   "logging_steps": 10,
@@ -266,7 +294,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.806803648937984e+16,
+  "total_flos": 5.410483850969088e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null