Training in progress, epoch 14, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d129595fae7d6a599b3385944328c2ca5a535960773b57f6793b5d9302d90b4b
+oid sha256:8755cbe7e2398d1959416d6feb911384858a351204adb4f45a8e698f8710fd55
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15dd934ee573a4e96c2e6c32fd035d243501c3f44f5e51d002ee25e6a40619d0
+oid sha256:f66a5ce1a780e3e1ff27f566dc0f0ffc09cedbb81984f67263cfbe2c21bb457c
 size 60252034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efb80898d149eb1b696384fcec14a440610378f5ac9545b1364e732b1989466
+oid sha256:235ab0e10f5c7cdfbbd49cc3926a6ca3af658975caba14cd01311559832e2b6e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd6d49e54c475078e98e61f59f66d9d4d233cbd00636e275a4c3ce7ac559441f
+oid sha256:7bbd78e2bc5c115f006119ec58fcb69b8d548f43ab2f01e37b0763759baab3bc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.997987927565392,
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 3225,
+  "global_step": 3474,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "learning_rate": 0.0002,
       "loss": 0.1706,
       "step": 3200
+    },
+    {
+      "epoch": 13.299798792756539,
+      "grad_norm": 0.42144036293029785,
+      "learning_rate": 0.0002,
+      "loss": 0.1563,
+      "step": 3300
+    },
+    {
+      "epoch": 13.702213279678068,
+      "grad_norm": 0.40393030643463135,
+      "learning_rate": 0.0002,
+      "loss": 0.1555,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
@@ -250,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.8613350330649805e+17,
+  "total_flos": 5.235863557546967e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null