Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c72db1a8c6d897d4c7f6f5f804cb8873cc75a8dba2eb8dfc30539189c9d8e05
+oid sha256:f17b9066d12808bc99c28a640e8b33c078abd521d7a2779211556cffd834ac7c
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865c5ab14612cc223e8430e3ccd016a170becca1cc8880464e6b4be013e1d5be
+oid sha256:c3c21d04893708a6ee7e011232e7816a29011fe2b652906a6a368c8e1b01a8f5
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f265840a5150193d3089ed9739f00e8318829b81ae0dcb8186108f545b3b4269
+oid sha256:6fc88aa7d187ecce791a5d80237fdf79fddd543842bd123369abd444b26734b2
 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": 0.001764792391783911,
+  "epoch": 0.0019608804353154568,
   "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": 58.068,
       "eval_steps_per_second": 29.034,
       "step": 9
+    },
+    {
+      "epoch": 0.0019608804353154568,
+      "grad_norm": 0.8966437578201294,
+      "learning_rate": 0.0002,
+      "loss": 2.0806,
+      "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": 432981927788544.0,
+  "total_flos": 481091030876160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null