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:b6f05ca6b5c548e1523a60d420f1494556c9f1f9603be9d688b89f6a952e8fb1
+oid sha256:6568ba74acab48ceda82b306ae84b72812295a6711c20673f1307c2133cce5eb
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476ea86efae19fce14debbd2ea3a6ecc0f8779bbb220a0a5788a6a8f9af33035
+oid sha256:bd98681be6bb9f6171383a164667afbb273114000d956be351eb086da04e991e
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed657ca35a3b26ab39201e05f010d681b5d27ca2e383b370948911cf5bec9601
+oid sha256:d57765ccdbd3b79c135f681da7122fdba173117294579537d75e298a46d06671
 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": 0.001918669722325854,
+  "epoch": 0.0021318552470287267,
   "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": 17.81,
       "eval_steps_per_second": 8.91,
       "step": 9
+    },
+    {
+      "epoch": 0.0021318552470287267,
+      "grad_norm": 0.8884080648422241,
+      "learning_rate": 0.0002,
+      "loss": 1.0179,
+      "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": 291868432662528.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null