Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7689f33151bd82adef3fbdd806f0a896151ad5ded514487710f21184e1a66f
+oid sha256:d6fc019d1368053f0a7c135d63807237026e16f10bf02cc74877d19973f90204
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f2782ade138c5a2770b8fa3c20889fa7d2d170607dda48aaf8cf35717e1190
+oid sha256:881fda66a673ef30018b4385380fb9fb212e1963649f1ce0750132944ada5361
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
+oid sha256:648a063f91ae3ab228fd410ffbd4321ad14a00c1e969d3c92bcd911e862ae5e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00020433966360582879,
+  "epoch": 0.000255424579507286,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 33.779,
       "eval_steps_per_second": 16.89,
       "step": 4
+    },
+    {
+      "epoch": 0.000255424579507286,
+      "grad_norm": 1.7061797380447388,
+      "learning_rate": 5e-05,
+      "loss": 2.3663,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3283829787721728.0,
+  "total_flos": 4104787234652160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null