Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c582e34b740c2ab84777b72c509a0e97c269aac69112da8e8698713a54feeae8
+oid sha256:66bb7c33619160a5e48850e0b483d5a81d1997be023b014dbf19adda41b6beca
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ccefb6bcb213e033c6d906dfab3f18aaf2958fcc017bb013b20f4d401e0fe3
+oid sha256:ae0e93e739b1f1ad537a3aac7e3afc2fbd66a15c103bba4b06e45f4891d59c55
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5134bfc96a8a009684ec48127ff4fc03b2f2e61a0fbe126a34bef4ab7025231
+oid sha256:b29318a353e9804a8c1ab05eea178ef167bea993ccfea56e96ee92575c188598
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.936785474108944,
+  "epoch": 2.1304640215198387,
   "eval_steps": 50,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -653,6 +653,69 @@
       "learning_rate": 5.709035061653494e-06,
       "loss": 23.4895,
       "step": 90
+    },
+    {
+      "epoch": 1.9583053127101546,
+      "grad_norm": 18.024465560913086,
+      "learning_rate": 4.635649805813696e-06,
+      "loss": 26.1946,
+      "step": 91
+    },
+    {
+      "epoch": 1.9798251513113652,
+      "grad_norm": 25.951337814331055,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 24.1037,
+      "step": 92
+    },
+    {
+      "epoch": 2.0013449899125755,
+      "grad_norm": 27.450637817382812,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 21.865,
+      "step": 93
+    },
+    {
+      "epoch": 2.0228648285137862,
+      "grad_norm": 17.74875259399414,
+      "learning_rate": 2.072255970174258e-06,
+      "loss": 19.4987,
+      "step": 94
+    },
+    {
+      "epoch": 2.0443846671149966,
+      "grad_norm": 20.335710525512695,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 15.9349,
+      "step": 95
+    },
+    {
+      "epoch": 2.0659045057162073,
+      "grad_norm": 19.2858829498291,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 18.5274,
+      "step": 96
+    },
+    {
+      "epoch": 2.0874243443174176,
+      "grad_norm": 16.66928482055664,
+      "learning_rate": 5.198657283805279e-07,
+      "loss": 16.2938,
+      "step": 97
+    },
+    {
+      "epoch": 2.108944182918628,
+      "grad_norm": 16.087203979492188,
+      "learning_rate": 2.311999700154027e-07,
+      "loss": 18.4087,
+      "step": 98
+    },
+    {
+      "epoch": 2.1304640215198387,
+      "grad_norm": 17.201932907104492,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 23.99,
+      "step": 99
     }
   ],
   "logging_steps": 1,
@@ -672,7 +735,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7332406838951936e+17,
+  "total_flos": 5.206564752284713e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null