Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9c7573c2db361da068cc70a0a55466ad45e2fed141b5a25554b9c9095a4059
+oid sha256:971d99cd7de2d603549c36bbdf2124539a072a330d603b83b705f47c75decfc5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ac5b968dadc625646e22fce1bd44bfdee860b94caf8a6557bf00a48fa19e8c
+oid sha256:d1e92f43da2507aa0bf5c469b76d41fb9adbd289ebbfc1e9822201535e2f63a9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
 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": 0.0011246063877642825,
+  "epoch": 0.0016869095816464238,
   "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": 1.0761,
       "step": 18
+    },
+    {
+      "epoch": 0.0011808367071524967,
+      "grad_norm": 0.5836747288703918,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9584,
+      "step": 21
+    },
+    {
+      "epoch": 0.001349527665317139,
+      "grad_norm": 0.5562848448753357,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0451,
+      "step": 24
+    },
+    {
+      "epoch": 0.001349527665317139,
+      "eval_loss": 1.0419354438781738,
+      "eval_runtime": 985.2074,
+      "eval_samples_per_second": 7.6,
+      "eval_steps_per_second": 3.8,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015182186234817814,
+      "grad_norm": 0.6457518935203552,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9846,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016869095816464238,
+      "grad_norm": 0.6827172040939331,
+      "learning_rate": 0.0,
+      "loss": 1.0902,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null