Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d94f1b6964c9fb80268ed5ff9064c5d750fb7fc9facbcb3350bbb539017d0c
+oid sha256:f9ecc4032f5566e48556b3f59c52039848ad14291fa280ced0531f5d0e256551
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abe7c14fb4db64ebf0aadd93754b08ee21448ee07268e140ef6c742d147d541
+oid sha256:4e95faf0e053595f414ced81954d1610a4885741d482dcb117eba8eb2319d479
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
+oid sha256:01f1e74501df1fbd31ea6589ac46c9040a3cc3de26625df68c126260a6c260a0
 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": 0.00025280011235560547,
+  "epoch": 0.00028088901372845055,
   "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": 33.08,
       "eval_steps_per_second": 16.54,
       "step": 9
+    },
+    {
+      "epoch": 0.00028088901372845055,
+      "grad_norm": 0.6545543074607849,
+      "learning_rate": 0.0002,
+      "loss": 2.058,
+      "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": 1568372441481216.0,
+  "total_flos": 1829767848394752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null