Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101c2329ce27e5d5c3c6f6cf03473c05de5ac57e8669dca0b5a1b06547fd626e
+oid sha256:d899bdb2486224b307036721d41ad0b636afa792ebf46dff3bf948134abbd956
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855021267904988f30b6c6a5d14ecf20a259dfe28919356bda7b6ac452b3d728
+oid sha256:3888e1b3b2b7972ec737a9fe3889d061f41cb121d19c200ace761f226f085373
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78834e7e67cff26e373758156d0de4fb81ad970930ba5af5ac26392ad240c90e
+oid sha256:f97c514d53470dc7e4ba1cf9fed99c8fdb74c2e026219c5ff950afa74acafeba
 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": 0.0012774247117810493,
+  "epoch": 0.0025548494235620987,
   "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": 11.4639,
       "step": 9
+    },
+    {
+      "epoch": 0.0015329096541372594,
+      "grad_norm": 10.815381050109863,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.6564,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019161370676715741,
+      "grad_norm": 9.865994453430176,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.6544,
+      "step": 15
+    },
+    {
+      "epoch": 0.002043879538849679,
+      "eval_loss": 1.126829743385315,
+      "eval_runtime": 369.8831,
+      "eval_samples_per_second": 8.914,
+      "eval_steps_per_second": 4.458,
+      "step": 16
+    },
+    {
+      "epoch": 0.002299364481205889,
+      "grad_norm": 7.193143367767334,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.3582,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267291009515520.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null