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:b9217aba7328276fea07e6e324f20da4951c03797c61a364d8aa26e81cdafc62
+oid sha256:258c9346e9ce1aa45e1de3b80cba87193dd45e4cc5e2dd86384015e460dcd8c3
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d19c0cbfe35c843886c00da8004cf4429f2e97491c11042b4f0b349616013a
+oid sha256:d1f3a18707787df5d1f877795213676c1cd4dba9cfb228b8a3456b43e8ed7aff
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b26abbf1b59934080d069888ddc280966a21772b32c06587e6b149de3c91db2
+oid sha256:fe5d40862c830b3663935b6a2f0e4f2ae08afca37762fc890317d5bd9d190ee1
 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": 0.003673469387755102,
+  "epoch": 0.004081632653061225,
   "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": 24.841,
       "eval_steps_per_second": 12.421,
       "step": 9
+    },
+    {
+      "epoch": 0.004081632653061225,
+      "grad_norm": 1.365379810333252,
+      "learning_rate": 0.0002,
+      "loss": 3.1071,
+      "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": 3280726162145280.0,
+  "total_flos": 3566006697984000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null