Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5fd71e0b4a95e91887356b59b5991bd67ed54198cc58bc2d764cd8b64ef678
+oid sha256:1aed0e645df80229a19765c009095210ee9a3585b15b77609ad81fd49b39a8f0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9290e821818ad98ff30de90ab55384df39a2f946031d513ec882d5a6bf344652
+oid sha256:8708be5d7ef4b5eaa0b63bd813221137011399b904c4b29a218a5af8b5e694b8
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd143af3f09eb1cb12050b53857a7a2fb5384f5cde35a4ac4066de6c24d78cea
+oid sha256:291e807923454e966fbad61ba440fb3d8d802be15df9a3b0b5749cb1ac1d6ffa
 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": 0.011083402604599613,
+  "epoch": 0.022166805209199225,
   "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": 0.6185,
       "step": 9
+    },
+    {
+      "epoch": 0.013300083125519535,
+      "grad_norm": 0.59880530834198,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.5892,
+      "step": 12
+    },
+    {
+      "epoch": 0.01662510390689942,
+      "grad_norm": 0.8566116690635681,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5471,
+      "step": 15
+    },
+    {
+      "epoch": 0.01773344416735938,
+      "eval_loss": 0.5450372099876404,
+      "eval_runtime": 23.4062,
+      "eval_samples_per_second": 16.235,
+      "eval_steps_per_second": 8.117,
+      "step": 16
+    },
+    {
+      "epoch": 0.0199501246882793,
+      "grad_norm": 0.35130101442337036,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5379,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3802172328247296.0,
+  "total_flos": 7789816477384704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null