Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a97713d08cce0de8b3517917b5a0b9632d4ebb3f59fd2ea32c04a88c7239b28
+oid sha256:ee98c61a863540e695b8383828e07af5c606304ffb7c4911780477b7f329aa60
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2b7c8896c627223ddf87f733fb7c339bbfd4279de82eb5e19eb42e1540c371
+oid sha256:c00066527d5c5e85abb78f3c02fb1c8233e575547019d6e45828cacb632b647e
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
+oid sha256:7ece6b3cf12ab3425c1775b1dafa9dd975d0c94122e55acd5be3596d4a99c259
 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": 0.02360655737704918,
+  "epoch": 0.02622950819672131,
   "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": 26.028,
       "eval_steps_per_second": 13.095,
       "step": 9
+    },
+    {
+      "epoch": 0.02622950819672131,
+      "grad_norm": 0.03370063751935959,
+      "learning_rate": 0.0002,
+      "loss": 11.7614,
+      "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": 3666600787968.0,
+  "total_flos": 4074000875520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null