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:b0978e6dfdee6c1d5c08e4146f034d90571c321b2a6ab132fd0a4661d17dc045
+oid sha256:dea2a4c9e97d44c813013e29e18d359d82fbb607751b97634c63df0660900965
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e98551e0e2155e1f520a71a99bdc6620ab4a26fee1ca6b70a563f1816d531e1
+oid sha256:e9d77080132f031be59c3d76c41ca2f76fed828e1058bb5c328ff262dc546a8d
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215659ca3bf8cc95ac7f721ab7c95f29349357dfed8b3e1cd548301b28ff57a7
+oid sha256:aff656d6341c09caaea4e0f2ef1c5bce6a6bed15ad4771b0229b2451f64ca789
 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": 0.001052970253590336,
+  "epoch": 0.0011699669484337067,
   "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": 20.041,
       "eval_steps_per_second": 10.023,
       "step": 9
+    },
+    {
+      "epoch": 0.0011699669484337067,
+      "grad_norm": 4.809872627258301,
+      "learning_rate": 0.0002,
+      "loss": 2.8174,
+      "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": 1898464096026624.0,
+  "total_flos": 2103703457759232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null