Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0f1d90b8438b34f67d7bb6fcfb3f7221595e5eb83685defb206a8a8e0218b5
+oid sha256:69fe748606b60a80bd6564f091388348a3cbea7a353096a4b5bec9706a1c5b78
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618cf330b9bfc9f150e25ae1066c55bfb796bd8e05e89a884b0c513b013691cc
+oid sha256:b22c6432bd0006a482e451c49ab5b1280745da080edc0251588def93e92a3e55
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82d403b274d925cebcf8d248245f3cc8fc3452b5d842d4d632f41f2cd4fc6136
+oid sha256:97161de3b24be79021a60591339e6eea77728912feb63c86e098590b6c2ba6f5
 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": 0.0002405806011841912,
+  "epoch": 0.00026731177909354576,
   "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": 5.445,
       "eval_steps_per_second": 2.723,
       "step": 9
+    },
+    {
+      "epoch": 0.00026731177909354576,
+      "grad_norm": 0.8788390159606934,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "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": 5881123817127936.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null