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:e1f8ecc8054e63d9c6fb1829b5b02a32e8d845c5b8d6bb6d259d43344cabe9af
+oid sha256:76d84744c9bdb7a15dcedaa39bd3201d05a1d9e11465b613da4635d261dd537d
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64342d41f393bf778566987beb2141833f89aaceafedfa3aca4732431c0ea674
+oid sha256:dadd0cccc48bca87b00e771304eeb1bec7a3b2bcfb6058d7b7c1bcee5bf24e07
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c97bc565cd4fb8a42b76a6ece2fcb3dd5e28308569908026f4f891351c64fa
+oid sha256:5362d71581ed76e40890e79da234f75746e87029b0ba7feb51524fd6b9831e6b
 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": 0.000244555249106694,
+  "epoch": 0.00027172805456299334,
   "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": 17.833,
       "eval_steps_per_second": 8.917,
       "step": 9
+    },
+    {
+      "epoch": 0.00027172805456299334,
+      "grad_norm": 1.940193772315979,
+      "learning_rate": 0.0002,
+      "loss": 5.2021,
+      "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": 2962191695216640.0,
+  "total_flos": 3344409978470400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null