Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec44069222cc3b94a45375c3d70aa8256f35ab34c1a16b270438dee9fe34e7f
+oid sha256:1c97312d3af314006bf73853bb26194a69571ad39149c195011b1589501040a2
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52fd454f943f6ce859e6f24fabe08df8be5fe4b2ae5a43e46dfec53b83b3fb5
+oid sha256:14c087f6c2ecbc4c0f813e7a46340bc47b680a97b6e7ea781e8ff8b4d8561a19
 size 45221242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df47f74fc65ae82ce71309b28037be288c0c25786f593d6ecf20815ba938920b
+oid sha256:28743bd7e41bbe24cb4b44d738beff4cf83f8d1ac2e3ab9153e4d6b7b2986cd1
 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": 0.012517385257301807,
+  "epoch": 0.013908205841446454,
   "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": 29.895,
       "eval_steps_per_second": 29.895,
       "step": 9
+    },
+    {
+      "epoch": 0.013908205841446454,
+      "grad_norm": 0.8026168346405029,
+      "learning_rate": 0.0002,
+      "loss": 0.8507,
+      "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": 234531877552128.0,
+  "total_flos": 258586429095936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null