Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6341f1c762452e203b953fecfb3edd7fd7b09fd38eed053cc5662dd231d92ffd
+oid sha256:918d9f5c41c3d5ad6d471d183ef01730fe22ae2ce35a3daae4853ead14c7309c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ff1fd1810e89c643c0b7d2fe809ea8f6a5246d46b9625dcc13b99399d9d22b
+oid sha256:d38433fe896813e0715a713e07cfc837ffcd7e73bf5396a7f11059f4034b746f
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f962f3aeee84895d12d77fcc89b352232c7e33129610fc6571d50b4a4c4806
+oid sha256:ba2c71fa1735005a0fac0d669cc222fad36906855093f4399a0c8d6b1dae0f56
 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": 0.03444976076555024,
+  "epoch": 0.03827751196172249,
   "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": 10.657,
       "eval_steps_per_second": 5.328,
       "step": 9
+    },
+    {
+      "epoch": 0.03827751196172249,
+      "grad_norm": 0.44957005977630615,
+      "learning_rate": 0.0002,
+      "loss": 1.3155,
+      "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": 5699169775779840.0,
+  "total_flos": 6332410861977600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null