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:e69737468e1fb1de5e564342fde461863038f68a28839425a4fc340178859c00
+oid sha256:febf45a969f1743db71679e87f2e8dd5c3e45e9ccc3eba79ee60d62799fcb233
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634f8f84cb5240eda635a68a792f143e946460abcf5b35abd8e7894bb714d806
+oid sha256:8f76adb2ec4a4f22259261ad1c2af20873bd2ec873d46b2a398ce43b24317099
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5c78d2865422c8a71f9b08eee49ec4800d53dad218f6b85a4d1663cb3c95cb
+oid sha256:139992acb92d13c33e1e3be34ed67bfdc6c2e95d411ffea68d2d0ea31dc94825
 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": 1.2126315789473685,
+  "epoch": 1.3338947368421052,
   "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": 1.2346,
       "step": 90
+    },
+    {
+      "epoch": 1.2261052631578948,
+      "grad_norm": 0.6364325284957886,
+      "learning_rate": 4.635649805813696e-06,
+      "loss": 1.3149,
+      "step": 91
+    },
+    {
+      "epoch": 1.2395789473684211,
+      "grad_norm": 0.6105322241783142,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 1.2594,
+      "step": 92
+    },
+    {
+      "epoch": 1.2530526315789474,
+      "grad_norm": 0.6162554621696472,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 1.277,
+      "step": 93
+    },
+    {
+      "epoch": 1.2665263157894737,
+      "grad_norm": 0.5331520438194275,
+      "learning_rate": 2.072255970174258e-06,
+      "loss": 1.2193,
+      "step": 94
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5716810822486877,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 1.4455,
+      "step": 95
+    },
+    {
+      "epoch": 1.2934736842105263,
+      "grad_norm": 0.56926029920578,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 1.291,
+      "step": 96
+    },
+    {
+      "epoch": 1.3069473684210526,
+      "grad_norm": 0.5255064964294434,
+      "learning_rate": 5.198657283805279e-07,
+      "loss": 1.2986,
+      "step": 97
+    },
+    {
+      "epoch": 1.320421052631579,
+      "grad_norm": 0.5318115949630737,
+      "learning_rate": 2.311999700154027e-07,
+      "loss": 1.2152,
+      "step": 98
+    },
+    {
+      "epoch": 1.3338947368421052,
+      "grad_norm": 0.5788165330886841,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 1.4851,
+      "step": 99
     }
   ],
   "logging_steps": 1,
@@ -672,7 +735,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.500747528732672e+16,
+  "total_flos": 8.25082228160594e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null