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:e860bf0515fd077598000b645c16894a72c856acda2e727e0a2ccef96fe1ad61
+oid sha256:dc991484d8af2405b2e75a70a11dd147f01b60fd7180fadd9a0159fc4af70de9
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4af30bd1bb5e26a4eb16973a47ead61fb8cdb6975b0a3c99f3f210281c91252
+oid sha256:36cbbbcb86337a7b2c65fe18f25a8dbecbb35e24ebbbc1bbe46cc0279c8fb712
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9c008c53bd43dddd700dd53d4fc40b32330d14b9af4a071419d30caa919a84
+oid sha256:64e0ad38cb6a9b260214ff2448dfe536ce9e17e756d9b5261cd852e5d2e99acb
 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": 0.0001334930305513633,
+  "epoch": 0.00014832558950151478,
   "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": 11.828,
       "eval_steps_per_second": 5.914,
       "step": 9
+    },
+    {
+      "epoch": 0.00014832558950151478,
+      "grad_norm": 1385.4351806640625,
+      "learning_rate": 0.0002,
+      "loss": 94.7189,
+      "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": 80435610648576.0,
+  "total_flos": 89372900720640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null