Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e08ea5759b66d68b5826a946960f85335011cdec364cf2189e65ea3c0fc5d2
+oid sha256:3d3e09b9d7348c570e0a7d2725359abe309e56823d1361c1adeeeb39e801ba4b
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d069c41bee9c14120e492b516678e115e099a38367bb38a8af363f11f7626ed1
+oid sha256:c6e54cb8bc64f0f7f56469675ec0047091d88219ddaf8829c738b41a9d942672
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3eb98feac32b720f92b1df3b665b261d47c67a4e3c3c062aadf23be87a370f
+oid sha256:f8c5fde4f720089952bd5c71bba2c4452e80f1ff0f1aa546016bdaa69acd2d03
 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": 0.007733619763694952,
+  "epoch": 0.008592910848549946,
   "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": 82.509,
       "eval_steps_per_second": 41.254,
       "step": 9
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 0.9625266790390015,
+      "learning_rate": 0.0002,
+      "loss": 9.5679,
+      "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": 38200890359808.0,
+  "total_flos": 42445433733120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null