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:f5f115f7f6fcc83c099aefb6e8f1e51ad33462bea235974d09586e694a739710
+oid sha256:63a3fe137e7182175a5fcfe63ff07c513d7baec0c09f5eaf32443ed66a09c65d
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab574ca104a7f65a9bfd784422e2bb3ccb8bceaca653644bc4e1f3477e2b02ac
+oid sha256:7601d7e3350e290564f9bbc0f7d991161c3ebbc161185ed2cafc01c019d5d3dc
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bceb7de99ff7b17d6ec7d794e86c7f9fba87fb5bd36c827c120924e029007a1
+oid sha256:b70f29a81cab5749b7acb47c2046572b3022dd01b41109c8e1baa88cfd573b4b
 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": 0.00511727078891258,
+  "epoch": 0.005685856432125089,
   "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": 27.92,
       "eval_steps_per_second": 13.979,
       "step": 9
+    },
+    {
+      "epoch": 0.005685856432125089,
+      "grad_norm": 3.7585558891296387,
+      "learning_rate": 0.0002,
+      "loss": 12.125,
+      "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": 1404380642715648.0,
+  "total_flos": 1548419682994176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null