Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69af10d130d9d9984eb5e4b353201f99e39a67aa1671a0a85777503fc38217a8
+oid sha256:fd6e6b0c4383a6e6d969c94cfc512a62fb5dcc6553e0be9dfada110268a3c9f3
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb610c61361b2687d0600b86bd4bf6b08886b63d5f841083cf3aca9031c8ae49
+oid sha256:6cfae5148d777f55a506f3b1d9ca51c9b19236efd0c4ec7658a35a4b40dc19e0
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
+oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
 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": 0.010404624277456647,
+  "epoch": 0.011560693641618497,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 21.776,
       "eval_steps_per_second": 10.918,
       "step": 9
+    },
+    {
+      "epoch": 0.011560693641618497,
+      "grad_norm": 9.691489219665527,
+      "learning_rate": 0.0002,
+      "loss": 3.651,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 80134347423744.0,
+  "total_flos": 89038163804160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null