Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7c8729c75d5c73c996d65dd44feeecd12f36c6903951d658e7943f47fc5d9d
+oid sha256:f9e4887a4763bfa398b14bbbf0681138286ee61599ce5c30526a38b3d205f7dc
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2288ae55ac0b7126dc6f0515a77f6a8e2f60432c34a8d880c9f4c70e38c86f8d
+oid sha256:0f53c7fb520c29acd43143ac0eafd7def75c454bb60f8f4b6896d41703a095a2
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7de5e176fa2b8e5251ff118b880d34c6853f1576b9191071b2557ae455b984
+oid sha256:ebdc0a587da84cff6f6ddab5cdbc0c4fe3bf1a6f2cf15d07068052f512b5eb16
 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": 0.03908794788273615,
+  "epoch": 0.04343105320304017,
   "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": 5.682,
       "eval_steps_per_second": 2.87,
       "step": 9
+    },
+    {
+      "epoch": 0.04343105320304017,
+      "grad_norm": 1.3310284614562988,
+      "learning_rate": 0.0002,
+      "loss": 3.4842,
+      "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": 5620012406538240.0,
+  "total_flos": 6253253241077760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null