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:bfa687d161f4a374e753fc27203d0c2e208b48d3e07cf03c5c1667395fa6d019
+oid sha256:8c19f52762fb89e249f24d1131f876b3ca0b2f2b7d030a981f6c6068fe812962
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2586ccd65c0a0d2ffad4d59c3ac40cd2be063d122d22562c1812a5cd788ebd
+oid sha256:e209bb2fb484b48d25796544c30929809e236b1f610796c58ba48eeb68a027d4
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adee774144c3525ea63cdce30a6dbeaa14cc94baae3bbeea2d2603bd5638466
+oid sha256:9bde9187c36bf5ca555d4af62901c73b296315ca3bff4e85e7b53c52c7f64dd1
 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": 0.00017722876245585895,
+  "epoch": 0.0003544575249117179,
   "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": 2.0415,
       "step": 9
+    },
+    {
+      "epoch": 0.00021267451494703075,
+      "grad_norm": 0.9889318346977234,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.9318,
+      "step": 12
+    },
+    {
+      "epoch": 0.00026584314368378843,
+      "grad_norm": 0.954679548740387,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.7932,
+      "step": 15
+    },
+    {
+      "epoch": 0.00028356601992937436,
+      "eval_loss": 1.6526117324829102,
+      "eval_runtime": 2008.4677,
+      "eval_samples_per_second": 11.829,
+      "eval_steps_per_second": 5.914,
+      "step": 16
+    },
+    {
+      "epoch": 0.00031901177242054616,
+      "grad_norm": 0.6018568277359009,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6869,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3388107349032960.0,
+  "total_flos": 6693577933455360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null