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:b5ca5432170be897e6379e8a6ae195dc940dd90d609901e4ef9d3ef81345caeb
+oid sha256:2c3a5db71f46aa629d08de54d483e712b4b35ddf583f0e29bedb70faec6d7a81
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4748a63c4ea29e7cb103beac6792012d481fbfca18fa8cfa20fd78a57aabbaa
+oid sha256:65da58ccc03279d09d0cd5c3e672ccee7256e6e710980950026ef6eb4a6c5b0f
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
+oid sha256:7182179a8a7aba8a5eeabfede23ca4be12f62c10f09d621d492038f5f2795122
 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": 0.0002737788323332801,
+  "epoch": 0.00030419870259253346,
   "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": 53.265,
       "eval_steps_per_second": 26.633,
       "step": 9
+    },
+    {
+      "epoch": 0.00030419870259253346,
+      "grad_norm": 1.2982311248779297,
+      "learning_rate": 0.0002,
+      "loss": 3.3955,
+      "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": 80134347423744.0,
+  "total_flos": 89038163804160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null