Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f37d4c9fb93dd101d43f3381339e0c9a88fbf8baf396242a7852eb935d8e667
+oid sha256:af4367142514015d008a95c745276518acdb9a7703320ddf23ad7cdaa8385ec7
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c28e5ebd873c455c98e0419c426388f9dcc9cb06be8991c0a6bde5132021d2
+oid sha256:2c0b8984e8341cd5fbaffde64aea71f47fa6ab6b05c8004104b443694684efd7
 size 111078

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f3828ea52b194ed76e01c62f9f5be77b2bd9f9cfe728db3d9d8cc44a4f67a8
+oid sha256:d53389285e1a574b35c681421511ed4fd865190d0dbcc7ca577aba5847d929e5
 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": 0.04591836734693878,
+  "epoch": 0.05102040816326531,
   "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": 125.907,
       "eval_steps_per_second": 62.953,
       "step": 9
+    },
+    {
+      "epoch": 0.05102040816326531,
+      "grad_norm": 0.07752110809087753,
+      "learning_rate": 0.0002,
+      "loss": 10.3777,
+      "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": 470722019328.0,
+  "total_flos": 523024465920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null