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:f225ee9ed170b52276a581a078b61719c4a57e1f73f3504d661041cc716d0ad0
+oid sha256:76aed46661dff513bef7232039fe31fbf4ac0c03884eba8f2587e17c85dc4338
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834182e0e4853b884d1717563f4b44479a7cb7cf93dc6f5e97b00d7f003b2188
+oid sha256:0487f5f7638d4f74738b2504df12a8df15961199bba7a9461ae3362a633ad4e8
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
+oid sha256:922bc4b0e437c6eab2b5b79546764e47e071da6c1120c8f70c8a617934473cc2
 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": 0.012738853503184714,
+  "epoch": 0.014154281670205236,
   "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": 8.978,
       "eval_steps_per_second": 4.489,
       "step": 9
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "grad_norm": 0.6529233455657959,
+      "learning_rate": 0.0002,
+      "loss": 5.8752,
+      "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": 5699203749642240.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null