Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2560cdbdf6decf7486ab4e1f6eeadce5f5b39946700775d12c98e13fbb5ce97e
+oid sha256:d68e9027e4bf97c6414927857b028d829eb6d43f1177daa97e6d9ecbe020ada6
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2dffcc4677ce980d5ae9b8fc65a181f5ae010f61dd89cd75c8f3b263528968a
+oid sha256:ff64a2874d26d23ab1be0b1a33a748a78ea59280cf4eb2b58783447cfc07be51
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49593839f9d1f47c098855c411ae242b6ae0da44eb823919bbad1cbb6de79de6
+oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000749063670411985,
+  "epoch": 0.0008322929671244278,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 394.221,
       "eval_steps_per_second": 197.15,
       "step": 9
+    },
+    {
+      "epoch": 0.0008322929671244278,
+      "grad_norm": 0.13933014869689941,
+      "learning_rate": 0.0002,
+      "loss": 6.9371,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 22082033664.0,
+  "total_flos": 24389111808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null