Training in progress, step 3300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2136a32fb2b9890a71924e493b715e1dea24c94d0a82fb2c22adbbd3dfd8a4c5
+oid sha256:72a9b3238f128bf1dbe68749e2830687ee771e8e6997bd21936fbd8c9e9d69b8
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4382891ea1c877de16959a801736498d104584758891e25a8472f399a72f737d
+oid sha256:2f80c684412745d5b933bb172431b91e4aa8432bebc668f5e5bb93fb386fb459
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea25f12ee5fbb106a39c36fad6a74dfd973d58cc647034eaab7ed6408694269e
+oid sha256:c63d6d6384d612982216f57b7930ead02ff385875d3d4426f2a6519af4c21380
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
+oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9038098454475403,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 4.266666666666667,
+  "best_metric": 0.9004936218261719,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 4.4,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,6 +455,20 @@
       "eval_samples_per_second": 2.455,
       "eval_steps_per_second": 0.308,
       "step": 3200
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0002,
+      "loss": 0.7049,
+      "step": 3300
+    },
+    {
+      "epoch": 4.4,
+      "eval_loss": 0.9004936218261719,
+      "eval_runtime": 777.3844,
+      "eval_samples_per_second": 2.483,
+      "eval_steps_per_second": 0.311,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
@@ -462,7 +476,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 8.288385958299648e+17,
+  "total_flos": 8.547856629710438e+17,
   "trial_name": null,
   "trial_params": null
 }