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:bd35f99d23a23dba28a434690342bb34e9ba9399a24a0684b530676cc2b0233f
+oid sha256:d25b76d36756846355d863df08eaac6c8edd24f6227af35c278e2c41db1c1c38
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c86691227abf0cc47ec9cb95a80a9c870ce6d3d2753c6e75e2b288b7b2a968
+oid sha256:8c313bfb17083780919a47e3a5fa8324a9e03e390c7946aecc4d68806e033f60
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcb1a37e33a0ac1e0105c4bc27e66617878bcbe64a668414cad41720b65f0d0
+oid sha256:ec6db30ee73f05bb409f30e8156512f9a9ef8f23341ed53323a7a650159f75ec
 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": 0.0001724435247456458,
+  "epoch": 0.00019160391638405088,
   "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": 46.564,
       "eval_steps_per_second": 23.282,
       "step": 9
+    },
+    {
+      "epoch": 0.00019160391638405088,
+      "grad_norm": 2.964939594268799,
+      "learning_rate": 0.0002,
+      "loss": 19.1079,
+      "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": 19100445179904.0,
+  "total_flos": 21222716866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null