Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3e1f8b0cec562fb4467971ece65fe9b94eb3ea2eab8bb408b42cc3a0990f80
+oid sha256:1c3a7ecf8548da4406e9ea55db71c4ba9d763dc65c1b0d8b020322fa1609bf5f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3af11427625f8329b704add0a16af887bc5b36ef53e0207553c8fcc14b088a3
+oid sha256:4df4e2e26529b27e7458451c84f7822f9a4040ee3e8b145e1db05264e2e8ea3b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6053380893400c5dade000ca2c1b057384a8b90a1c04643c48140a2351ddf03
+oid sha256:6c100d41f6fd4b797068cc46b1116a533d330b6f880750742ac2da0a93865598
 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": 1.9750773906707764,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9943181818181818,
+  "best_metric": 1.960465431213379,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.1363636363636362,
   "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": 27.653,
       "eval_steps_per_second": 3.466,
       "step": 700
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 2.1014,
+      "step": 800
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 1.960465431213379,
+      "eval_runtime": 54.1302,
+      "eval_samples_per_second": 27.563,
+      "eval_steps_per_second": 3.455,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.129173542494208e+16,
+  "total_flos": 2.436531182862336e+16,
   "trial_name": null,
   "trial_params": null
 }