Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7108c12ecb0bea707b20e316fe4c5e0f34340c9f6a117beaad1fcde594900c08
+oid sha256:2667d826070b3e4e83d72923767472e50c0fc3cd0f48a4674a897b0f216e147a
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317a41fe06905c18f6addc82f99f210d00d45100708b0d4333be8f6f12cf5582
+oid sha256:7695d94f407b8aa64de51ba8239069b0999487f2d8a97ca6b1c9491a47f46023
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0860148a5490b599e99944483a9c384219ff285d2e241ac00d74f0d5a768e3
+oid sha256:8fc0118d9a21cd15a57e8be6dd818341632c2768b618f4ed64002d6ce6e01761
 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": 0.0002510250188268764,
+  "epoch": 0.0002789166875854182,
   "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": 58.654,
       "eval_steps_per_second": 29.329,
       "step": 9
+    },
+    {
+      "epoch": 0.0002789166875854182,
+      "grad_norm": 2.935885429382324,
+      "learning_rate": 0.0002,
+      "loss": 5.2923,
+      "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": 515370733535232.0,
+  "total_flos": 567654720995328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null