Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b54d16f76b9868594915a7b166f3d0d360bb02a4d925dea46a2da54d1cf2f9
+oid sha256:3b4c0d0a9db87544e63da2ab6095b47ee9db2b8733c33e2160e7b0b38bd9386f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c891b6ce9a7bf11db263c652735b7cae19dced12e97a43a02207d96a353fa9
+oid sha256:bd6ed775fe19889ee79580fe2b20b6ea2472060770bf0d749861a17b041886c3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a99d972e0aab172de95cae715f9773a3c20fa17f6164a2ad191ea3725b43fd4
+oid sha256:b7bbb9e6b1248c3560ef0c4d2a18853bb3b1d23161e5fbf5d045daee6827a56f
 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": 0.001463057790782736,
+  "epoch": 0.0016256197675363732,
   "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": 27.465,
       "eval_steps_per_second": 13.738,
       "step": 9
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "grad_norm": 1.4648605585098267,
+      "learning_rate": 0.0002,
+      "loss": 3.3775,
+      "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": 1547296479117312.0,
+  "total_flos": 1710169792708608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null