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:c9359b853e4c8f3421dc5558b34449236a40d7ab3b79c25d94f6f5de891f0aba
+oid sha256:dcee55d406616e68f0973af8bd30c3fe0f919572e4597ea27e1c3d13466ea089
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ed0780e19f5da873592c384d1423b6f7f6793cd17748ab0544db21e44ed533
+oid sha256:b28726c94655f068fef71f8f56fa7b88fe5af0ee81fee229db14d5a9952e6995
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37eb77c63e91da7bb6bbaf615748a5bfd5a6433149cdb5684759efab70c80b57
+oid sha256:e1acf987a98aac23c1f268891237a3ebef73cedd390ef4eb1565d2ae0c62c106
 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": 0.008598452278589854,
+  "epoch": 0.012897678417884782,
   "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": 6.1566,
       "step": 18
+    },
+    {
+      "epoch": 0.009028374892519347,
+      "grad_norm": 6.123845100402832,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.2371,
+      "step": 21
+    },
+    {
+      "epoch": 0.010318142734307825,
+      "grad_norm": 12.521309852600098,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.003,
+      "step": 24
+    },
+    {
+      "epoch": 0.010318142734307825,
+      "eval_loss": 0.9678913950920105,
+      "eval_runtime": 31.9725,
+      "eval_samples_per_second": 30.651,
+      "eval_steps_per_second": 15.326,
+      "step": 24
+    },
+    {
+      "epoch": 0.011607910576096303,
+      "grad_norm": 7.4081501960754395,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.2654,
+      "step": 27
+    },
+    {
+      "epoch": 0.012897678417884782,
+      "grad_norm": 16.760990142822266,
+      "learning_rate": 0.0,
+      "loss": 6.7818,
+      "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": 3032350111825920.0,
+  "total_flos": 4530687814139904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null