Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c56735a7f8a43bfdba20a2a378685af49491f51f381dffe031b2a2c5c647a7
+oid sha256:9b8ff0acf70a6046120f6fabc669ea7a74104783835f661dd1c09188bb0df3f7
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d87f0465583729fd8e5b748c1f702336dd96b5ae20193ba19de4680ee7f1ba
+oid sha256:32f493156293df82d6584a8dbd356e9c2bad071c2f45c8aec01d595a32ae30b9
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8016c26e84c1fd30f5896ac536aafb4523282bedddb725e30fbede86af7cd838
+oid sha256:5836d9315d97c755aed4ba71d1de248550d31aee8ca072cde8cf52f9ceb8f8f1
 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": 0.0035703659625111574,
+  "epoch": 0.0039670732916790635,
   "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": 145.615,
       "eval_steps_per_second": 72.807,
       "step": 9
+    },
+    {
+      "epoch": 0.0039670732916790635,
+      "grad_norm": 16.79721450805664,
+      "learning_rate": 0.0002,
+      "loss": 13.2189,
+      "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": 24413938384896.0,
+  "total_flos": 27067627339776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null