Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591a2975d0d45fee4b6e0272453156cb0d4cc18012e3f03a4e1f850fa2788af2
+oid sha256:a338dc8207e4ae90a2b7506db3b808384565d687cacfbaff88642e4c8ee4995c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc8c34a44c8ddb1bdf26e3e71eac890162fb2260c80d2c45673ad48d47fb1ff
+oid sha256:22843b2768135d17711e83beb4d88ef630f40e3fb329a2318b006d47483f7668
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55bd3cb548c6ccabf50b457c5df01528df25277660f92993e68854b81a10359
+oid sha256:2da64af463957c9aa92f34b95febc502b2f98e3e9b4738e352cb2b7ee447c1dd
 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": 0.0002510250188268764,
+  "epoch": 0.0002789166875854182,
   "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": 17.134,
       "eval_steps_per_second": 8.567,
       "step": 9
+    },
+    {
+      "epoch": 0.0002789166875854182,
+      "grad_norm": 1.5285134315490723,
+      "learning_rate": 0.0002,
+      "loss": 4.2941,
+      "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": 2768873711468544.0,
+  "total_flos": 3053904828825600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null