Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e392b092eab174fe8893a606c083e7fa88d4a609eb04e3b96ed5370d3e6d511
+oid sha256:24d6da595248fae2523711f101b6869f0ad098a24f2a4d9c10314ba700afd466
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be0646c1c88ccaaa1f6830a797935a91e876612c121058e60bb730dc49a77fcc
+oid sha256:094f837299cbd05a4db0458d5286b45dc4a21fde6f5bebdc8ad91e13ff895f64
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4269677e3d335673fbcee71e5b78f83433b7173960adf0a51d212c7727af18
+oid sha256:0115a51802b9fbbc4b35b5253182300acdb5f38e83f59ae76d850f9880396752
 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": 0.0007394322803269934,
+  "epoch": 0.0008215914225855482,
   "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": 4.275,
       "eval_steps_per_second": 4.275,
       "step": 9
+    },
+    {
+      "epoch": 0.0008215914225855482,
+      "grad_norm": 1.9233784675598145,
+      "learning_rate": 0.0002,
+      "loss": 0.6987,
+      "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": 6902049253883904.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null