Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:085a2ebfd04a3809d12b0e3db225b58bc970a83b1089d0a63600fcfc200ecdba
+oid sha256:2136a32fb2b9890a71924e493b715e1dea24c94d0a82fb2c22adbbd3dfd8a4c5
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bdab217ef76511669f78840feecc999ecc4aaa34ffbda530e89db33f056d9c5
+oid sha256:4382891ea1c877de16959a801736498d104584758891e25a8472f399a72f737d
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b02564141f65d6796fc22bd626e526e8aed02bce0651ca616957fae586fbe037
+oid sha256:ea25f12ee5fbb106a39c36fad6a74dfd973d58cc647034eaab7ed6408694269e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
+oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9039433002471924,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 4.133333333333334,
+  "best_metric": 0.9038098454475403,
+  "best_model_checkpoint": "./outputs/checkpoint-3200",
+  "epoch": 4.266666666666667,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -441,6 +441,20 @@
       "eval_samples_per_second": 2.461,
       "eval_steps_per_second": 0.309,
       "step": 3100
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.0002,
+      "loss": 0.6886,
+      "step": 3200
+    },
+    {
+      "epoch": 4.27,
+      "eval_loss": 0.9038098454475403,
+      "eval_runtime": 786.1544,
+      "eval_samples_per_second": 2.455,
+      "eval_steps_per_second": 0.308,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
@@ -448,7 +462,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 8.029294478933606e+17,
+  "total_flos": 8.288385958299648e+17,
   "trial_name": null,
   "trial_params": null
 }