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:d0dcf89e4bc8e9a03ec2412af43ca7340ad82c033dc543649c99d62039f35ba6
+oid sha256:7c09a619b09dc76ea1b7dd47b7880aa5b7c41088668e9d6692f1f5e7197e2233
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87016bec416f33d16bec87880b86c9fea190ab9b48de9e1d5ce5dad52000bcc0
+oid sha256:5775e5005bb305e40c0f6cee347485f788913a61ffdd7d1fddd264a95d7aad38
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f428c8a6a024f6338900342bc9c5ff40c342f28b297a96dfc6c96a2bb31282f
+oid sha256:4604a4b5237b87986eb44e035d79c1465c0958193ad1bb8451bd8a32011c9813
 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": 0.0011090231354548535,
+  "epoch": 0.0012322479282831705,
   "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": 30.388,
       "eval_steps_per_second": 15.198,
       "step": 9
+    },
+    {
+      "epoch": 0.0012322479282831705,
+      "grad_norm": 2.2186131477355957,
+      "learning_rate": 0.0002,
+      "loss": 6.7451,
+      "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": 537430264381440.0,
+  "total_flos": 597144738201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null