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:cb1a1105c6d833df07b771f70ed42334ea4e13c4f6c30e5490049b757f300af0
+oid sha256:37cc445d30e1d4c88192bcfe084e0ccdd1b3896d3ef9bf1c0c6f708bdf27fbb2
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6909fe7263d2d9df6bfb88a6fef0bff02fc9d0eda63767dadf53cb814f0ad9
+oid sha256:e57e4f4073c65b596c5219c736e3fcc1521acc11e000cf8e0e20185a4c74776a
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2266acf8a27e0921094d276d2f9ac7ab363fa754423a5a22c2b9d5ce11be5972
+oid sha256:242f67602d15d37cde3c09100eb8ca58e1f8dcdd71f942618a72ad35bb058fd1
 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": 0.001970734591318914,
+  "epoch": 0.002956101886978371,
   "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": 1.7583,
       "step": 18
+    },
+    {
+      "epoch": 0.00206927132088486,
+      "grad_norm": 0.49251097440719604,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8483,
+      "step": 21
+    },
+    {
+      "epoch": 0.002364881509582697,
+      "grad_norm": 0.4831303358078003,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.8595,
+      "step": 24
+    },
+    {
+      "epoch": 0.002364881509582697,
+      "eval_loss": 1.9419726133346558,
+      "eval_runtime": 47.6991,
+      "eval_samples_per_second": 89.582,
+      "eval_steps_per_second": 44.802,
+      "step": 24
+    },
+    {
+      "epoch": 0.002660491698280534,
+      "grad_norm": 0.4990459680557251,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8028,
+      "step": 27
+    },
+    {
+      "epoch": 0.002956101886978371,
+      "grad_norm": 0.35253778100013733,
+      "learning_rate": 0.0,
+      "loss": 1.7524,
+      "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": 185695271387136.0,
+  "total_flos": 279410641993728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null