Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da4768de4c5132093d1e026fa7f3615558477cbe1ed744b1593c53e3568d249
+oid sha256:c637fea77d64b69317676cf6cff9be8e14ff00d97ff2908982353c856adba333
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fdd062e563bdb1668485e6e852a75e1c2b9e4ec534a412359fc90fc6ef2d4a
+oid sha256:21adf8590eb13ff6a2f617e6590a0ecf6023fae4e955c5eb3ba4ee3a2e64f62c
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb91e2e45c651d389a1f4a7175eaa9b1cb7c3752127424640499fdf51987e759
+oid sha256:2cd40db2a30439bddcbee41ef58cd13a17ffe2dbf0b0a533f0b6bac4c3e0b859
 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": 0.026373626373626374,
+  "epoch": 0.029304029304029304,
   "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": 58.429,
       "eval_steps_per_second": 29.214,
       "step": 9
+    },
+    {
+      "epoch": 0.029304029304029304,
+      "grad_norm": 11.693865776062012,
+      "learning_rate": 0.0002,
+      "loss": 10.0381,
+      "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": 587654391398400.0,
+  "total_flos": 652949323776000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null