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:b7024ce493f10dd6c05024be5e80a613e8253aacd57472ec24e06b03d8bd7ed7
+oid sha256:7472e741eacdfc4b933f9991f76c5aac05fb2e8072a777677b080f41a2b64a3e
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511688d9d033c3b67c50390fea784ba4156d7eb9b6ff95f67e49e9bcba4305e4
+oid sha256:dfc513a8bf1fd46b95592253a5d2c2132144ad06b9d881fe7ea3e045c7495de0
 size 113416442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107a2111e838867c3feac9e98b4e198826002bd6fc18625eae8ef120b76d9b4b
+oid sha256:4b47c4edd197bc76789d6c118afa5482b2479e8ff7a1ea9e002d23eae3797360
 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": 0.21447721179624665,
+  "epoch": 0.32171581769436997,
   "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": 2.1977,
       "step": 18
+    },
+    {
+      "epoch": 0.225201072386059,
+      "grad_norm": 0.29583850502967834,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2015,
+      "step": 21
+    },
+    {
+      "epoch": 0.257372654155496,
+      "grad_norm": 0.32945993542671204,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1949,
+      "step": 24
+    },
+    {
+      "epoch": 0.257372654155496,
+      "eval_loss": 2.1296627521514893,
+      "eval_runtime": 1.8886,
+      "eval_samples_per_second": 21.18,
+      "eval_steps_per_second": 10.59,
+      "step": 24
+    },
+    {
+      "epoch": 0.289544235924933,
+      "grad_norm": 0.2930546998977661,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0839,
+      "step": 27
+    },
+    {
+      "epoch": 0.32171581769436997,
+      "grad_norm": 0.32494500279426575,
+      "learning_rate": 0.0,
+      "loss": 2.1951,
+      "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": 1305053327523840.0,
+  "total_flos": 1957579991285760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null