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:a3f16f01d8918a7c95cd4f92a2ba359b54e2c5b487436cbf16a85abd23ad7aeb
+oid sha256:26764406ee907df978eda620b150cd583aceda946e9af1523a28256338a71344
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25661b373f3575f6c916de9fdaa7e8d0b2ccd137c1dd184799285fac6772066
+oid sha256:ce5b5918ae8c751e0dcc1f124d036db76be29a6570fd2389eb11a2077c8a72a7
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e430790c418395df8ca73708b8c4c3a500f2ad56804e8db2527f4c5b2ee2f2c1
+oid sha256:ac4e86bf3065dfb74b37ddedb5b2b3b3d63257bd53c18a0384f379447d9f9455
 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": 0.0008439807759934357,
+  "epoch": 0.0009377564177704841,
   "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": 84.694,
       "eval_steps_per_second": 42.347,
       "step": 9
+    },
+    {
+      "epoch": 0.0009377564177704841,
+      "grad_norm": 2.9032371044158936,
+      "learning_rate": 0.0002,
+      "loss": 6.6547,
+      "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": 403861344878592.0,
+  "total_flos": 443125642297344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null