Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a784bbc890a0661e306ced98bc39081583f2aef880cbb5c4e39ef8df30207bb
+oid sha256:c872e5083d4b5508500a3ebb619633583e1791cbd57a7599edc1fd5b44625d06
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3a5206c1d14677f1fdd4c48c80269f881f65444351667c7fce3538d0908e11
+oid sha256:37f209691fb7e29d678970f15fdc8deb69657bb928c047f5c8782645b35280e1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4590d6aae6c7c27cbcc2dfc499975411114a345041c791fe89c3cdeb8711118f
+oid sha256:fdf8a592a4e3de99a8e7bfdb0e13d9b050b0ac937f15ce1cbdb3906cf7ba692e
 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": 1.388436198234558,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.3770211935043335,
+  "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": 30.853,
       "eval_steps_per_second": 3.87,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.488,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.3770211935043335,
+      "eval_runtime": 47.1554,
+      "eval_samples_per_second": 30.771,
+      "eval_steps_per_second": 3.86,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3476240908288e+16,
+  "total_flos": 2.682370133065728e+16,
   "trial_name": null,
   "trial_params": null
 }