Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc105422a430584642eccc2cc82c05ad7352cc4aa6ab0c74751b8c7f0e21547
+oid sha256:a68903b0479938ce67f6aac0f75f1a49ee7d04b91257953b48817dee63171347
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64483a8f43dffd2c237741724ee711a6fe8da853f4a898d10cd5ec068a1516f3
+oid sha256:856a78b39b3a4c8d22049977b73ee8bebd79f4adb639638fd4d72dfc1bbc02a8
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694f3b635aadace0b66e105c4f0a42ef19cf215da35d94c165accff0c5b6ea71
+oid sha256:b9b614e76ea213bd606a3fa03078615ee2354596b18cb2b0f1976286da0079ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08780487804878048,
+  "epoch": 0.17560975609756097,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 35.515,
       "eval_steps_per_second": 4.516,
       "step": 9
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 0.17559802532196045,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 3.0003,
+      "step": 12
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.4407211244106293,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 3.3846,
+      "step": 15
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 0.24928590655326843,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 2.9842,
+      "step": 18
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "eval_loss": 3.209193229675293,
+      "eval_runtime": 4.8642,
+      "eval_samples_per_second": 35.566,
+      "eval_steps_per_second": 4.523,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3042235461402624.0,
+  "total_flos": 6004412094873600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null