Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aed0e645df80229a19765c009095210ee9a3585b15b77609ad81fd49b39a8f0
+oid sha256:197042b7f3a9eedbb962e28e43daa95e8d28456336c74d4079b08cf6ea810560
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8708be5d7ef4b5eaa0b63bd813221137011399b904c4b29a218a5af8b5e694b8
+oid sha256:e1913d36f51bc377d29f6775ccb3af522ce1832d6a1315d96baea55785cb667f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291e807923454e966fbad61ba440fb3d8d802be15df9a3b0b5749cb1ac1d6ffa
+oid sha256:51184bff3b5aeb206b7e81ee1f5bd11ee1519de690c0df3b7a5a1b332004b277
 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": 0.022166805209199225,
+  "epoch": 0.03325020781379884,
   "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": 0.5379,
       "step": 18
+    },
+    {
+      "epoch": 0.023275145469659187,
+      "grad_norm": 0.43810561299324036,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.496,
+      "step": 21
+    },
+    {
+      "epoch": 0.02660016625103907,
+      "grad_norm": 0.3642444908618927,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5328,
+      "step": 24
+    },
+    {
+      "epoch": 0.02660016625103907,
+      "eval_loss": 0.5327214002609253,
+      "eval_runtime": 23.4926,
+      "eval_samples_per_second": 16.175,
+      "eval_steps_per_second": 8.088,
+      "step": 24
+    },
+    {
+      "epoch": 0.029925187032418952,
+      "grad_norm": 0.30899062752723694,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5391,
+      "step": 27
+    },
+    {
+      "epoch": 0.03325020781379884,
+      "grad_norm": 0.3484113812446594,
+      "learning_rate": 0.0,
+      "loss": 0.4985,
+      "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": 7789816477384704.0,
+  "total_flos": 1.1591988805632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null