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:bc0cc769d1a91784e3b80f3902d1f12d4aefa011d39e129a5508c6ace33f8150
+oid sha256:80788c77ecd26210445fb69c3eddddf82dc7bbd4c6e17e7b98814a17a91c6166
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caf4731ad322a5823daf5ff9b599a49728b5d91e724b85fe5a5d3b0a2344b1c
+oid sha256:e2665d00e2f15be902ac317a487aef131ff6f69c1b0156d89f3d026ca3c52363
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
+oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
 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": 0.00025280011235560547,
+  "epoch": 0.00028088901372845055,
   "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": 304.095,
       "eval_steps_per_second": 152.047,
       "step": 9
+    },
+    {
+      "epoch": 0.00028088901372845055,
+      "grad_norm": 0.6684051752090454,
+      "learning_rate": 0.0002,
+      "loss": 44.4089,
+      "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": 147083231232.0,
+  "total_flos": 163961634816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null