Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861e353c449af09ae282104a170ff39d0dcc164f58e7c85eb1974764df6a7ada
+oid sha256:4f094ccc5abea0d904ea580ce463412fc7284a29c39365d93b97b1e7b034443d
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169dd009594a914b28859a234e2f5ef10825ded2f196c95ae626c7b80891c18e
+oid sha256:5568c55347a90ece64e85a730462957eceb0a6739f93f320f4927b0cd736c4e2
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f72808257b7991b65ff818e20797b3f6b14292cda5605f27fdf86fe5e6da4c
+oid sha256:4bea0b80d96d23f3f961d11718afa3bd11f3aaf4fdfcb59d7ee8fe5190f75ff3
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9684687852859497,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 0.9623979330062866,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 2.638,
       "eval_steps_per_second": 0.331,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 0.7943,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.9623979330062866,
+      "eval_runtime": 731.9495,
+      "eval_samples_per_second": 2.637,
+      "eval_steps_per_second": 0.331,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.3683016270053376e+17,
+  "total_flos": 3.627481660202189e+17,
   "trial_name": null,
   "trial_params": null
 }