Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03991258c12f067eb8f6740c658c5d4a9ec018d59b089be0af48b0e7d92cbd8e
+oid sha256:beeb85f3a0ff62bbfab4bc0aba25a49160a65b9c46893708d0115fa2236e8c63
 size 7586384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9dc8ade88be6ada5888525aed5c6287020dc5d8f90fa89dc1db77673849bde
+oid sha256:648e2403a63a98aad4f2fa79d1842a751ffca3849bb17f08aab13fa90d829d39
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252ee14cb440203dbc9a036ce807d18ac00757efdc7beb446e076604019f4754
+oid sha256:07a2282370ce14042f09fb52cfd203e1f906932348c4490fd7c50dbae1816301
 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": 0.018072289156626505,
+  "epoch": 0.020080321285140562,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 36.084,
       "eval_steps_per_second": 18.042,
       "step": 9
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 0.9044764637947083,
+      "learning_rate": 0.0002,
+      "loss": 10.5242,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 49122314551296.0,
+  "total_flos": 54432835043328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null