Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6e09b0cc56ae5d46b7af9912d522bde0e2725b423f1d237195c78ade513979
+oid sha256:9e79163ea0f279bf69362480da1a0cda3b53ec8bf9ccc2564e483ccbd46c15ae
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861dc8a0277dd27ce677e55506fa10f0128612adb95c159fe97f333b4c2d3300
+oid sha256:a331f76ca9cbc40f94e6a0a933d182df111f810b130a0d3cc22e05d5fa6f1727
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56713b4b79a95f0ba69a6f670426dd06a01045e2bc2332f5ab3536d682a7b5b
+oid sha256:577c1542c27140024e1cefeb7858339478d08577f0cf250c85c2ad2cfdd7426a
 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": 0.0007060623296134309,
+  "epoch": 0.0007845136995704787,
   "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": 14.76,
       "eval_steps_per_second": 7.38,
       "step": 9
+    },
+    {
+      "epoch": 0.0007845136995704787,
+      "grad_norm": 0.7166277766227722,
+      "learning_rate": 0.0002,
+      "loss": 1.9556,
+      "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": 3590710603284480.0,
+  "total_flos": 3960342577152000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null