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:ea876285a3915b8a283ee916de125b2d34ca5e8b296814d41646b1f31676b87c
+oid sha256:4de3a33b350a2d07867ce8c940ef73c0e641417396694d5da7cb2c6edead3b91
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1224f0f286c788a3cf65c5420f86925edc7a938fb0080035303fa8777079f5a2
+oid sha256:8aa1f05f6021d763cc5bc3789920747f813024e635cc4314e907a00ef3b15585
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
+oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
 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": 0.023936170212765957,
+  "epoch": 0.026595744680851064,
   "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": 50.801,
       "eval_steps_per_second": 25.56,
       "step": 9
+    },
+    {
+      "epoch": 0.026595744680851064,
+      "grad_norm": 0.05749232694506645,
+      "learning_rate": 0.0002,
+      "loss": 10.3787,
+      "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": 177799987200.0,
+  "total_flos": 193963622400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null