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:dbd930926d4b53c0f3cc88a0f47484fcf6ea4e738add79dd4e4349564420a32d
+oid sha256:9e3150263ad93b79a5dbaec0360ce17ef232342d3fe120547453c8a2e642b49f
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3291c5a6d95ccbcdd769d8239706f3e9ff859038c05a2fdab2be8d746e12ec
+oid sha256:ae9d24941ec909652e2d04c01e854d084c8e08ef41e39cd1fdb8c9af929fbc2b
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7aff96afc5f824b7ed5aecc135005bf3f081ddcf459ff2ffbdc421f0310581
+oid sha256:e9477cb77af51c30771492f0c32c4c8e2f41808701e1aa27e3b2b1ae6a671b1d
 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": 0.02727272727272727,
+  "epoch": 0.030303030303030304,
   "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": 20.08,
       "eval_steps_per_second": 10.112,
       "step": 9
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.899142265319824,
+      "learning_rate": 0.0002,
+      "loss": 1.3746,
+      "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": 738043798487040.0,
+  "total_flos": 820048664985600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null