Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ee44e26614e9447cfc27e0cef1c1714b58eb3cf11f85f2a9f6325340a2ddb3
+oid sha256:94f60540ceba67b43edb961d9eb68ceeb8df14ff6b8a52a2435f2d6f547b8032
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b4bbdcdf6591cfc85935d6cfca6406fe6dc98fd94d9cd842aaa67c9217d071
+oid sha256:9be048dbcb5cff8f9e3dcee217ddeb6360f254536160be606b4b70ca5c2ea750
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4776aa4ae2f79df395fd23658707cbcd26ae09b7f65f95efe553922891ee4cd
+oid sha256:49538dce3facebf1422d6e704db43c3d118b4ba238927a55894a7f6c90e7b58f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3021882772445679,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 1.2918113470077515,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 43.582,
       "eval_steps_per_second": 5.453,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.2619,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 1.2918113470077515,
+      "eval_runtime": 143.9692,
+      "eval_samples_per_second": 43.579,
+      "eval_steps_per_second": 5.453,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.967030879005655e+17,
+  "total_flos": 2.026581552041902e+17,
   "trial_name": null,
   "trial_params": null
 }