Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73846cbe0ebf9596d831c55e5f624796fbdca57d56812761bf6e9e0bd9de0efc
+oid sha256:7e5fbcb0959e2022640eaa87bb5c5e004460f44ca4bded4a72fdca16799bf720
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a13594a7c481de2bb76cb1757cf01a136d11d369e964453ed15adae029df82
+oid sha256:6b6a38be174ca1fe8f661a9862551673faa893a289eb3f9ae013717a33155c52
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082044c9ebc4d75fd1a91516a3ec97fa3a443503223b674e9f9e897d6e964942
+oid sha256:943594a2b4f73cf5f181b71c371a1e12ae8c1c3104df810c9e0971d3d5427b2d
 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": 0.00044108457796782535,
+  "epoch": 0.0004900939755198059,
   "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": 9.7,
       "eval_steps_per_second": 4.85,
       "step": 9
+    },
+    {
+      "epoch": 0.0004900939755198059,
+      "grad_norm": 0.5418856739997864,
+      "learning_rate": 0.0002,
+      "loss": 0.3945,
+      "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": 3537906035589120.0,
+  "total_flos": 3960342577152000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null