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:ec346d1a772e23473646096535616c7ae18363cff13e77734bd9c60af8ce0b5d
+oid sha256:23ea3d4335f553e3da2002a5b861a3b451f69367fcf2764bc3d2ebdc16103c53
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06f868c90e216083538a612b5788c11247942bcd7dfeb4bf1a5fc3d6e2b107f
+oid sha256:d58d1ae8c0320986858c457d9ee5fc4b43751d1b99fb3ee8a7f5df9cd0a9e7a5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27b9270eed978938fb264ff9eb30405bf39917e9b19434c0a83e81afe9c8968
+oid sha256:84b4b93b80f2f863f1227b74a2459863279ee895de0abcfd4b5921551e484253
 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": 0.005550416281221091,
+  "epoch": 0.006167129201356768,
   "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": 25.87,
       "eval_steps_per_second": 12.954,
       "step": 9
+    },
+    {
+      "epoch": 0.006167129201356768,
+      "grad_norm": 0.793143093585968,
+      "learning_rate": 0.0002,
+      "loss": 3.3745,
+      "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": 2280226390278144.0,
+  "total_flos": 2483818032267264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null