Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70fdda0557ed81baedb1ab86da3de4d7996cb20a05b406e06eebfc4f994edd0c
+oid sha256:4bee6dbb2e23c7148434d939bb6dbfaa38a1b2791e9916006f9fe7fda22b6a37
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86096d1138ea845baeba49d6556d7ca988b15980a2b01409d1949bd76bcaaccf
+oid sha256:535b89042720e16935a1fc208914785b74e91c278611248d7c887811c591ba9c
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e465eb0265e76c1c3121bcc183ba1f1604238c641718592811ee2b5b90c7fa47
+oid sha256:880d8ee051caa52ccc0af4171bce0128e02a876287da8e6c32faeb315d1c8044
 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": 0.00032841321680745865,
+  "epoch": 0.0003649035742305096,
   "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": 17.397,
       "eval_steps_per_second": 8.699,
       "step": 9
+    },
+    {
+      "epoch": 0.0003649035742305096,
+      "grad_norm": 1.4207048416137695,
+      "learning_rate": 0.0002,
+      "loss": 1.775,
+      "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": 1953769004728320.0,
+  "total_flos": 2164987275509760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null