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:b180a60179b85f6b743ba9dbd74eb2feaee2da079457bbe43f9fb0e1fd9ebead
+oid sha256:70d710004dff6649495c18a033179d7f322584f9279fa0ac641251cb7d6ceda2
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b88541b054a4ad55a5255898ae6d3d1e227bd2deb7c2eb9e9a76d13d4d2a2c
+oid sha256:7cc1569ded0f43e8da58f5e396181c7c63e4cfb71ae9d5f0b3b7458f94f282f0
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171c39a51d67c5fd26a97228c49c329b7ef38a53ea4a56f315f2a2274edd0e31
+oid sha256:e843a368393e1b5efd15ce155ddf7a1314fb792347aecbb8e7a205b664e6218d
 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": 0.00135473819684346,
+  "epoch": 0.00270947639368692,
   "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": 9.0767,
       "step": 9
+    },
+    {
+      "epoch": 0.001625685836212152,
+      "grad_norm": 4.853641986846924,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.1943,
+      "step": 12
+    },
+    {
+      "epoch": 0.00203210729526519,
+      "grad_norm": 9.18185043334961,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.1932,
+      "step": 15
+    },
+    {
+      "epoch": 0.002167581114949536,
+      "eval_loss": 1.969774842262268,
+      "eval_runtime": 279.544,
+      "eval_samples_per_second": 11.118,
+      "eval_steps_per_second": 5.559,
+      "step": 16
+    },
+    {
+      "epoch": 0.002438528754318228,
+      "grad_norm": 5.340238571166992,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.2584,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.285435567374336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null