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:ce487d910e74e4a3ac24e931d75fb7cf1257c26f81f4b645ba54e8206b554b36
+oid sha256:2239d6f4b7881336868a07c9cf3ef300b02addaf73deef9d0e8f1d1a0a441861
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f14919fc0fd2a9a0509148c4ef9696c1b4eb1f9d1302c6f07dcd25f38bf5a42
+oid sha256:b39b5a6f8c166804a97f55427101a1c52edb2cded285e87eb9fe04e91d4294c0
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc470492a838a1187e04ee046b639f8c9a5027c3c8d3a9f2791682eb7df7e881
+oid sha256:680f5b3c4ec45e8602ead895aca2a12993a9213489503574020100d1d917b14c
 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": 0.0005747952291995977,
+  "epoch": 0.0006386613657773307,
   "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": 20.966,
       "eval_steps_per_second": 10.484,
       "step": 9
+    },
+    {
+      "epoch": 0.0006386613657773307,
+      "grad_norm": 2.048513412475586,
+      "learning_rate": 0.0002,
+      "loss": 2.6492,
+      "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": 1353981232152576.0,
+  "total_flos": 1468725404368896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null