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:b5bbe16e6dfcc4d1beaccc8733c052e51cbd7b501affc325bf0a82113f81bcff
+oid sha256:2599128468b5dceaa6056a087087eac1433d4d4ba72f0201598cb5723aefebf6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71108f33983ec8897e395094938fa7b51e50487fc5a9efc5f33b34fbf18b58ed
+oid sha256:9a694b6ff0ba48b7697e5864766bdc665d72dd8d0ec59645cf8cdcffaba4eb62
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82b9f2cb69cffb5c91e61597e033eef893451c68faed84d6275b923928391fd
+oid sha256:ffb05d0dd23412abe63381d32229c26c0a085bc225d695ef7ddf0e74e4ca3b31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2689075630252101,
+  "epoch": 0.33613445378151263,
   "eval_steps": 1,
-  "global_step": 8,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,36 @@
       "eval_samples_per_second": 11.581,
       "eval_steps_per_second": 6.236,
       "step": 8
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 1.3909317255020142,
+      "learning_rate": 9e-05,
+      "loss": 0.0562,
+      "step": 9
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "eval_loss": 0.01413269154727459,
+      "eval_runtime": 1.122,
+      "eval_samples_per_second": 11.587,
+      "eval_steps_per_second": 6.239,
+      "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.46602216362953186,
+      "learning_rate": 0.0001,
+      "loss": 0.0132,
+      "step": 10
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "eval_loss": 0.003461630782112479,
+      "eval_runtime": 1.1201,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 6.249,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -141,12 +171,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2967549134241792.0,
+  "total_flos": 3709436417802240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null