Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407ce1504b4278637e59db1cb89ec2aa43ec237ec82de0209db931d5e40482ff
+oid sha256:cc1eb55e84af521e1ab0bac902adc052184867b155b0136979eac69add8854e0
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552fd7735fcad3a55b07a9c4fb1a4b1c45b81b81b98c439f32bf13174bd6fee0
+oid sha256:2e318a961335917aee3ef0968e8276dcd0e29727ea1931ae43261ea89e0b2708
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250f97136bb82e04ee10e4c62496f30c964b276f4f885a1cd4fd399051d1a491
+oid sha256:94071748f62332148254f203c71f7325ea56cde7ad2faca34274a6e63d38b5df
 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": 0.0016550963174106939,
+  "epoch": 0.0018389959082341042,
   "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": 20.728,
       "eval_steps_per_second": 10.364,
       "step": 9
+    },
+    {
+      "epoch": 0.0018389959082341042,
+      "grad_norm": 0.3872000277042389,
+      "learning_rate": 0.0002,
+      "loss": 1.1082,
+      "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": 1209571780853760.0,
+  "total_flos": 1353080297226240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null