Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633ca9e2eef59d3bfec0fa314224157fc1d9be871c2307fc9065380150ade008
+oid sha256:a814f4338a852435cceba210696f153249f301a3bb02451f544a65e3359ef15c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6e6159cfe11c299979137155d520d9b6789375ed0e5ddf4bdfa678d7991cb4
+oid sha256:e05cce1829083e109319f71de7e19208706a846cb88ff70a6744eeb69bc54e3e
 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": 1.1604684591293335,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.1489245891571045,
+  "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": 10.872,
       "eval_steps_per_second": 1.363,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.9517,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.1489245891571045,
+      "eval_runtime": 180.9559,
+      "eval_samples_per_second": 10.666,
+      "eval_steps_per_second": 1.337,
+      "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
 }