Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3dc6c515ee0f4f4109aa6b772e7096ba0fd9660f9b48198877e1f3349b50df
+oid sha256:052ac46bf7d2d1b44a241a06bdec78d42ac63064330fee549a6aaebbdb276cd7
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6420f56b769015f931e16e49f064a093d314d846a8d84417e4cd4ef3e3c9a988
+oid sha256:a7fa1f4a02ff4376a50d9c6e5afe72a0356a2cdfa5181b3383f0dafcc246394f
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f905070f344ff5757d2e5f48fcda24ded17f953888429aa8e5791b2828fc54a
+oid sha256:8add635ab6b081112ff7d255bb9a21a69af8460dd1de7ddf6c5c5d319e909536
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9654250144958496,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 0.9631500840187073,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 5.445,
       "eval_steps_per_second": 0.683,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.8352,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.9631500840187073,
+      "eval_runtime": 354.7367,
+      "eval_samples_per_second": 5.441,
+      "eval_steps_per_second": 0.682,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.936315915975148e+17,
+  "total_flos": 6.220289728654295e+17,
   "trial_name": null,
   "trial_params": null
 }