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:b9fdcd9bfa83e7e753fedaad6821701e608a2897c768b6d5663c76111568a2b3
+oid sha256:5bda37b6251963a1a892895169e07e500c7e1b66688b2c1260be3d0ce5abf745
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07b40521996e4d6e3d3822e1bd5c8c062972ddf6429bf36ca6c79d7548c9219
+oid sha256:2b56ca204094da7df11289b2aa871a9ac08ca4c1530ff2169798af8176447898
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d0903aa420d18f253df95cd1ed6a8bc8082a9eea91eb682a120fc88792e0ac
+oid sha256:45e4abb5d8f838d7298d0da53d751603c0e159cddd8e50398726666cfef25317
 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": 0.003247924936845904,
+  "epoch": 0.003608805485384338,
   "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": 15.258,
       "eval_steps_per_second": 7.636,
       "step": 9
+    },
+    {
+      "epoch": 0.003608805485384338,
+      "grad_norm": 4.192689895629883,
+      "learning_rate": 0.0002,
+      "loss": 5.7959,
+      "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": 5135049645096960.0,
+  "total_flos": 5705610716774400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null