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:ebce020e97bb7a4a1f7921ece1e76e7b39843dbfff849f01e2f1673feb633451
+oid sha256:9be19ad538ab57082ddf526fa2140e94fd10e33a970a6ca35346d0f83b241a2e
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8a595b1c6ba334f1c3e577bdbea70f8fa2fbcd56244ec5eb272104c48a7410
+oid sha256:0595face5fe2def58dfb57776595344e85c1b4d6a40b08e1fd6a1ff22dd3a7fe
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bee0f47e046288a8ab410015fc2b2510b7d505ae807cb056407e3f2c1143e
+oid sha256:87b368c128ea0a3e3249112be27647c1e5cf6b066033174cae0f792ccb2e0084
 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": 0.0002578519500053719,
+  "epoch": 0.00028650216667263544,
   "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": 102.439,
       "eval_steps_per_second": 51.223,
       "step": 9
+    },
+    {
+      "epoch": 0.00028650216667263544,
+      "grad_norm": 0.6823318004608154,
+      "learning_rate": 0.0002,
+      "loss": 0.9904,
+      "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": 61726770855936.0,
+  "total_flos": 68585300951040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null