Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49d74a21c9de4957df85ff3d5da7ab77e561aa8097ff2aa90937236812ddf5a
+oid sha256:a11b9310008671c3363f4d5c24dd1ce2d0a44993f8ca8a21c44a570dd5fb9b4b
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bc5d7f250a29484cb11644e9c6bdb27e7569607b8207b8f5e90054bdb57733
+oid sha256:7f8ef5b9081f7bbcfbd44e0c9da0cd59c37c4009fe2a98bb3a83b51934b4a714
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10c1e950ccc3ca6ce28644d055ede3dfe6763dec3f800e5ed80a1dc9e119762
+oid sha256:45226a9cf86da3e155e17d7054bcd08c887c2590dcdc9e3592a57d62031be887
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.547645125958379,
+  "epoch": 0.8214676889375685,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,41 @@
       "learning_rate": 9.794023256786919e-05,
       "loss": 1.5251,
       "step": 1000
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 2.4210712909698486,
+      "learning_rate": 9.693844960047051e-05,
+      "loss": 1.4886,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6571741511500547,
+      "grad_norm": 2.1745235919952393,
+      "learning_rate": 9.574612596698522e-05,
+      "loss": 1.4715,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7119386637458927,
+      "grad_norm": 2.216663360595703,
+      "learning_rate": 9.436810175355263e-05,
+      "loss": 1.4191,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7667031763417306,
+      "grad_norm": 2.010982036590576,
+      "learning_rate": 9.280997087419733e-05,
+      "loss": 1.4411,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8214676889375685,
+      "grad_norm": 2.0168168544769287,
+      "learning_rate": 9.107805836304658e-05,
+      "loss": 1.4264,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -96,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.845362695616594e+17,
+  "total_flos": 7.241672688292332e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null