Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a3fd444e8ba78120775dc1a1c3871e58335bfd955db243832eef4fbc8505fa
+oid sha256:cb1a1105c6d833df07b771f70ed42334ea4e13c4f6c30e5490049b757f300af0
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dc78e5d62edd5eb214df80ea9c65633ce7e8b906f802d7c19fa0825e848581
+oid sha256:9c6909fe7263d2d9df6bfb88a6fef0bff02fc9d0eda63767dadf53cb814f0ad9
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4e8bdb2926ba10b848561ef678903a7bf2e0c039054575c06a1b88c1ced787
+oid sha256:2266acf8a27e0921094d276d2f9ac7ab363fa754423a5a22c2b9d5ce11be5972
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000985367295659457,
+  "epoch": 0.001970734591318914,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 1.9808,
       "step": 9
+    },
+    {
+      "epoch": 0.0011824407547913484,
+      "grad_norm": 0.39736393094062805,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.9289,
+      "step": 12
+    },
+    {
+      "epoch": 0.0014780509434891855,
+      "grad_norm": 0.40689948201179504,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.9195,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015765876730551313,
+      "eval_loss": 2.001293659210205,
+      "eval_runtime": 47.6644,
+      "eval_samples_per_second": 89.648,
+      "eval_steps_per_second": 44.834,
+      "step": 16
+    },
+    {
+      "epoch": 0.0017736611321870228,
+      "grad_norm": 0.4287497401237488,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7583,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 91979900780544.0,
+  "total_flos": 185695271387136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null