Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510379b32e19db4e6757807083c49b7c2b65510101005ccf010c1cbf5239fbfa
+oid sha256:4a4ddf9d39000fe6559bb91d8c3c36858f4f23e3f44125b12196ca57e4b36d63
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fffd611f6cb9a5b4473f60760c6ff4e8a260472bcf99d3501ab2d174690f43f
+oid sha256:a66a098b798ffcdac26d79c4f3908c8ace05bd2bcb898f3e0708fbe2f097610d
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db79c5cc5439263656db6134fa199281305040d42833f95cc5ecf73b101d7d07
+oid sha256:13045082dd395ff23ec01ea62abb7ab1984d0af8f8c2441c419760ff666be782
 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": 0.00871881811576653,
+  "epoch": 0.009687575684185032,
   "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": 228.78,
       "eval_steps_per_second": 114.653,
       "step": 9
+    },
+    {
+      "epoch": 0.009687575684185032,
+      "grad_norm": 2065.03759765625,
+      "learning_rate": 0.0002,
+      "loss": 77.5755,
+      "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": 9967478243328.0,
+  "total_flos": 11074975825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null