Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d9c854ac884deaebb06958d75bbaced8fcdab623670e5fb82d9cd9cc8d6774
+oid sha256:f3290ebf59a7c7c17345a561946847733c97d5bb1b2a57638649d79adc35ce1c
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ba55df101b9a5e2ba36923b1bc94b71e44232c2f57bfcba4da9c7b035e917a
+oid sha256:804508b051edecc8d5dec4a16d81d82135071a2a49bfadbabbfd87252c01f931
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e4abb5d8f838d7298d0da53d751603c0e159cddd8e50398726666cfef25317
+oid sha256:f06dc400444691b20cd0161805e955b193c9256e8e96477d1c3f4ece92014368
 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": 0.009018036072144289,
+  "epoch": 0.01002004008016032,
   "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": 13.643,
       "eval_steps_per_second": 6.838,
       "step": 9
+    },
+    {
+      "epoch": 0.01002004008016032,
+      "grad_norm": 1.0714696645736694,
+      "learning_rate": 0.0002,
+      "loss": 4.1267,
+      "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": 5647185236459520.0,
+  "total_flos": 6274650262732800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null