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:bb1da2691117a813be6ae26cb3daa8864abe45045c7990797c31520b6d743733
+oid sha256:97ee44e26614e9447cfc27e0cef1c1714b58eb3cf11f85f2a9f6325340a2ddb3
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7bb1f8f6c217720084827862416a413498808180e969bdd7c3619ce2f15d098
+oid sha256:a4b4bbdcdf6591cfc85935d6cfca6406fe6dc98fd94d9cd842aaa67c9217d071
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084132876d83624f29d3863ed0c0b0e930fe3b7a99f53b6167286f214214e720
+oid sha256:b4776aa4ae2f79df395fd23658707cbcd26ae09b7f65f95efe553922891ee4cd
 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": 1.3148905038833618,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 2.3315118397085612,
+  "best_metric": 1.3021882772445679,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 2.4043715846994536,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,13 +455,27 @@
       "eval_samples_per_second": 42.473,
       "eval_steps_per_second": 5.314,
       "step": 3200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.28,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.3021882772445679,
+      "eval_runtime": 143.959,
+      "eval_samples_per_second": 43.582,
+      "eval_steps_per_second": 5.453,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.9074327262757683e+17,
+  "total_flos": 1.967030879005655e+17,
   "trial_name": null,
   "trial_params": null
 }