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:e73cbc3a46d8cd72b52e78a323a03b82dec80444b6f792cf99b78db0aff75617
+oid sha256:ab7e75feffd51dca6a8a70d7d8df19eca949eac5353d9de0ccd6cc51a6e1e921
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f27cd51db37d462301485ee1ab06a7175ea6028c25e912d08490c70aa8516c8
+oid sha256:9fba4464089a83973e2ad475cb1d1c8454b60c4f9ac24dc758141e725e436a53
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6fd42b640f00a8092cbcf8172f91307bcc479d2b1c5085a4ff026b0254ba8aa
+oid sha256:0e16a768c44c7af390fee40cf5f92af2f14032cbf59eb8cc0a45d671b0615456
 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": 0.018908059560387616,
+  "epoch": 0.028362089340581424,
   "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": 10.577,
       "step": 18
+    },
+    {
+      "epoch": 0.019853462538406995,
+      "grad_norm": 8.414092063903809,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 12.0008,
+      "step": 21
+    },
+    {
+      "epoch": 0.022689671472465138,
+      "grad_norm": 7.220608711242676,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.3984,
+      "step": 24
+    },
+    {
+      "epoch": 0.022689671472465138,
+      "eval_loss": 2.784585475921631,
+      "eval_runtime": 5.3698,
+      "eval_samples_per_second": 83.056,
+      "eval_steps_per_second": 41.528,
+      "step": 24
+    },
+    {
+      "epoch": 0.02552588040652328,
+      "grad_norm": 7.145070552825928,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.9116,
+      "step": 27
+    },
+    {
+      "epoch": 0.028362089340581424,
+      "grad_norm": 7.097597599029541,
+      "learning_rate": 0.0,
+      "loss": 10.7453,
+      "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": 86222642872320.0,
+  "total_flos": 129333964308480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null