Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403e8208eb019a015cf36218295ee7f6276332a066bfb844d55b064d39d64a0f
+oid sha256:e2641721ed729094c533535256996e70164536230283aebd106aca853eb3897e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246a78029073e8446722f693a3e08bf4cf5d726801817d474f4430feab7c7b6c
+oid sha256:ff0b32b1aece4c0ffff589cb7604093642f8914676c8e3fd7183ab035f898456
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882f931c75a63dbadf1613ab2f34ceb65bcdc210992aa9cbd7ce762e1fde05cb
+oid sha256:98a7acd013371135d9845339eb6cd85e24b0200154b4675f28546f4b6720db19
 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": 0.0035499457647174834,
+  "epoch": 0.0039443841830194264,
   "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": 5.173,
       "eval_steps_per_second": 2.587,
       "step": 9
+    },
+    {
+      "epoch": 0.0039443841830194264,
+      "grad_norm": 4.624992370605469,
+      "learning_rate": 0.0002,
+      "loss": 2.1407,
+      "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": 2891001316245504.0,
+  "total_flos": 3216747943428096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null