Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b07b173d7cd6fe787b2236fe00c72a431aef3f4251b7f43d9a57832d9710095
+oid sha256:586eedd6b8bfef1c79f60a373114f633bc266f6e8e6fec6460491adeecb7e549
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a7c72dad384c11a070c5c37402aea05165a4fb4e9cd65219e3afe6f9f6a9db
+oid sha256:fbacc8fc09fcf0846f50a69b9b43185d7820d222f1ec9ddd655468692c9a0c46
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7113b4ddb953686a19c918f6a7688101b24bc7cc26d2b0fb2a2b9afb4381aaed
+oid sha256:3bfdf591814dafb58fbed6eb038d855a52ef8ffd37af8d5a199008bec3e7e73b
 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": 0.003808314820691844,
+  "epoch": 0.004231460911879826,
   "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": 2.511,
       "eval_steps_per_second": 1.257,
       "step": 9
+    },
+    {
+      "epoch": 0.004231460911879826,
+      "grad_norm": 2.5473413467407227,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "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": 1.1866151483080704e+16,
+  "total_flos": 1.318461275897856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null