Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00bb1e1f15bd7e0f62cd60fd2a8c2dfb89ee478a3c69a55e3f91616dafc35096
+oid sha256:b963ec04831c7765d09abfca205517a80036be002ed1009067918203644542f6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab55c925afffc39fa906f1aaf5e6ebe91e3a505c1a0b491277f78880f2afcc
+oid sha256:bbb57bfae20aab36d2e4891d1d0cc604f88cc7afbdf5cfa3f91588223e1aa5f1
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4d08a4148ca680e1acfb3044660fb81b545836e62e805b029cfbd941c9ce8a
+oid sha256:82bd5f500a8695a30b8787ca123c9046534c829bd50970d55c4b8fd686428955
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00016986364196141547,
+  "epoch": 0.00033972728392283095,
   "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": 9e-05,
       "loss": 5.5315,
       "step": 9
+    },
+    {
+      "epoch": 0.00020383637035369857,
+      "grad_norm": 47.04484176635742,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 5.9109,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002547954629421232,
+      "grad_norm": 6.6766252517700195,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.7547,
+      "step": 15
+    },
+    {
+      "epoch": 0.00027178182713826475,
+      "eval_loss": 1.2962453365325928,
+      "eval_runtime": 1823.5636,
+      "eval_samples_per_second": 13.593,
+      "eval_steps_per_second": 6.797,
+      "step": 16
+    },
+    {
+      "epoch": 0.0003057545555305479,
+      "grad_norm": 2.574517250061035,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.7193,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3349006302314496.0,
+  "total_flos": 6698012604628992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null