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:c61011f7e20ea7b27479b9a1adca5bee1f9763ff2a9fd6f56745900a341619b3
+oid sha256:63f56ab3e939e3a42beb50e290676e3c40ef25337f4b178b7ff660cf3566dace
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7ddff1aff5b724ee7d0e64436fa3096b9cf20860ae755394cdb41cd33356dd
+oid sha256:cdcf02bd95916403829bbe3036cd3f14668ea339562a082bd383950d15685726
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
+oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
 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": 0.0037882773860886034,
+  "epoch": 0.004209197095654004,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 23.124,
       "eval_steps_per_second": 11.574,
       "step": 9
+    },
+    {
+      "epoch": 0.004209197095654004,
+      "grad_norm": 2.989361047744751,
+      "learning_rate": 0.0002,
+      "loss": 1.9081,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 80134347423744.0,
+  "total_flos": 89038163804160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null