Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4658ca5e48d564d0874412a684d976d74cb3153cea5db2321581c7bbf2accb97
+oid sha256:7cb82b895769fac39bea732a9ba8c73d4af251575adb615b85e47f266dc077c5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4124a83b0fcd5cf2c453f9866287f4746d4d73478f2facde97eaa8c3056cad8b
+oid sha256:83ebaf6a2405689aa6334737965cba8b758affd0d4896538d79aa170dfab2538
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7aea1bef86b1056125513432a9481c64077b07ee990116c26b3bfaebd6be37
+oid sha256:64edf4072e9d9de433323939eb8f5c3fbe20486acfda2f65802e2e8a8a3efd1e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.161731481552124,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.1482728719711304,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.0666666666666667,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 10.878,
       "eval_steps_per_second": 1.364,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.1482728719711304,
+      "eval_runtime": 177.4285,
+      "eval_samples_per_second": 10.878,
+      "eval_steps_per_second": 1.364,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.2320035432448e+16,
+  "total_flos": 5.976702787313664e+16,
   "trial_name": null,
   "trial_params": null
 }