Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5007e1e3c5247b4a0ca8828e0c1bbdf66a0c0b6fc4d18112aad14cc058f904
+oid sha256:c330ed89d3f3399fd4872758abf30371d0c11b493c1043f2a2d042bdcb2e36d6
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d744825e71da55c638bf447d31b89fe2edab901bf6e860d48f6ed49b6fa4caba
+oid sha256:76c087e5005c3fede0bc843303817d3dfb4d3b99cfd9f28eea6b0afa7faa6cd7
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0465759d94b23e403a8125785111894d4a6dc2776a010cdcfd480fcf7cd58060
+oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
 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": 0.2155688622754491,
+  "epoch": 0.23952095808383234,
   "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": 208.205,
       "eval_steps_per_second": 104.103,
       "step": 9
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 25917.783203125,
+      "learning_rate": 0.0002,
+      "loss": 17.272,
+      "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": 1709111771136.0,
+  "total_flos": 1899013079040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null