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:e4a225986b20ec4d2a54b452531c0c7e978397c48122af459ed98e4654b30d4f
+oid sha256:581522bbc127711ca20dd8286582e028b55ff41743b95b6ef3409b5fb9a29442
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6037abdcea64219b04e55eac3249296aa6a8df6e52fd30684bac4129377a3e4
+oid sha256:17a60486137e6acac2b697ad8bf52b5e854416ea85e4595fc2c11b1044dccc8e
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0917c9df0e2fed3551649f7fd31c403419b920ce0eca0ea2185844965b01ce
+oid sha256:c56618ea608aa96fead1e4bd33f77c9af27927b14f7670f63239831a514f62fe
 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": 0.0023833167825223437,
+  "epoch": 0.0026481297583581596,
   "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": 39.53,
       "eval_steps_per_second": 19.765,
       "step": 9
+    },
+    {
+      "epoch": 0.0026481297583581596,
+      "grad_norm": 0.8304316401481628,
+      "learning_rate": 0.0002,
+      "loss": 0.9792,
+      "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": 795401414246400.0,
+  "total_flos": 893296972922880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null