Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38326b956bf807412da76b2b9c3dbfd3c8ee1dad8ef3a6709c505a2a080cbfa2
+oid sha256:3386eeaf777fa8ee04d3eb6a698d8c64d05a1a27e4b7b072d3c1e502d66f21c5
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eae6f38c1c8b8ab03c44b6895ddbb2da06f52603a3e2dcce04433d34559bf24a
+oid sha256:d91e11143c5aca4dfc98c64510c889f61e481c7b4c113e3d924b2a79f08349ba
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591a9c5e45bb1139399d3039b4c05dd34997d5462b11eb1ca1771e8044f4a6a1
+oid sha256:ab823abb115c32fa0673f758e0b0199bf6d5f3e43f5557dbadcc612729790b53
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.55287504196167,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 1.5351721048355103,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 43.61,
       "eval_steps_per_second": 5.456,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 1.525,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.5351721048355103,
+      "eval_runtime": 143.7854,
+      "eval_samples_per_second": 43.634,
+      "eval_steps_per_second": 5.46,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.347109656129536e+16,
+  "total_flos": 8.943146869488845e+16,
   "trial_name": null,
   "trial_params": null
 }