Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf6dadc2b817ce3e4c7103f12f6a7b8179d96c57e4892ceb88f68707c566e74
+oid sha256:980082cfe73cd305f89c53d61b68dbb44917121fa761529d35ec2aff4c854af3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150b994b316b5ab6b941b5d4fdb5e6457202e21a9159d476d44c830d75ca4cb9
+oid sha256:32fc2e77c8f1bcf925cad70a8a9d19e2c28cd467a2d7e6349406ef1cc7d3a9eb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a99d972e0aab172de95cae715f9773a3c20fa17f6164a2ad191ea3725b43fd4
+oid sha256:ee1d1b668fe428c6b9252e79d5553c0e2b5f88aee38d1dc78172da9e448d459d
 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": 0.0007503908285565399,
+  "epoch": 0.0008337675872850443,
   "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": 26.274,
       "eval_steps_per_second": 13.137,
       "step": 9
+    },
+    {
+      "epoch": 0.0008337675872850443,
+      "grad_norm": 2.564300775527954,
+      "learning_rate": 0.0002,
+      "loss": 6.6296,
+      "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": 1547311779938304.0,
+  "total_flos": 1750905435193344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null