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:cecb9e1afd8934e0b1fe5909c4043ae3d0ec5889ce94695eb56744e9bcc4e6dc
+oid sha256:066466ef7fc9b6c1638130155e2c18dd441c334389085da8048388bcdf68da90
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11bacbb148416ea423d68261d2732f806e9eb1ff020d78c5bfb3194d29ebf4a
+oid sha256:d1a97e5660c395b6de8f1da81bf7c22aaadc959e64f42ebcd7fbd3ef08b99c5a
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74e3c925ceec40baf5d508fc3d6ea8a468f31ee20a14f9330a7ee79c304b1d4
+oid sha256:1d4d6f0339a64145471a731f39983c4abd2c3231f0b38c2e13cc0df069dada1e
 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": 0.00021305809384025378,
+  "epoch": 0.00023673121537805974,
   "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": 53.53,
       "eval_steps_per_second": 26.767,
       "step": 9
+    },
+    {
+      "epoch": 0.00023673121537805974,
+      "grad_norm": 6.127230167388916,
+      "learning_rate": 0.0002,
+      "loss": 3.2116,
+      "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": 440530014044160.0,
+  "total_flos": 489477793382400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null