Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:669a52490d5b4732f3e0d207c0c96bfa213e7426013de97cb4ecbae0ca2a3da9
+oid sha256:bec6aadcb7ddeab2900d189d651cd1ba9d0a981823cb474077ac1681d8745a09
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4380c2cc5d91cc864e65ff66a0c787fe56370a2aeb4a6bda6b7260d490a3515
+oid sha256:81b4e32ea0b052ca815e17de7cbe78561e727b0587c701fcde4f8fa4a5f4258b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590761e6940b8a5f51a47f69d09c8ece26c1a0fc061d07ca27ebdc6e6a55b220
+oid sha256:5c15ee7e64adbbed173bd6a1ced0d959828c8fd99015a2fee41e29d011347912
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004781600401654434,
+  "epoch": 0.000717240060248165,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 3.0052,
       "step": 18
+    },
+    {
+      "epoch": 0.0005020680421737155,
+      "grad_norm": 1.4587379693984985,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.0622,
+      "step": 21
+    },
+    {
+      "epoch": 0.000573792048198532,
+      "grad_norm": 0.7186371684074402,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.4507,
+      "step": 24
+    },
+    {
+      "epoch": 0.000573792048198532,
+      "eval_loss": 2.9365055561065674,
+      "eval_runtime": 1029.7686,
+      "eval_samples_per_second": 17.103,
+      "eval_steps_per_second": 8.551,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006455160542233485,
+      "grad_norm": 1.1878702640533447,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.7715,
+      "step": 27
+    },
+    {
+      "epoch": 0.000717240060248165,
+      "grad_norm": 1.223516821861267,
+      "learning_rate": 0.0,
+      "loss": 2.7356,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7604344656494592.0,
+  "total_flos": 1.1406516984741888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null