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:c9d4fdad1b206e05f361eb1db2f208b79a5cc1bb1c90c1d16a0409e72dfff541
+oid sha256:dc167e0a9bf6c2fe8cc265dbca7bf7cd21f97141d3e9b1fc4705c2494b9f2544
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50d7f9590b063033cebb3f7e4963693987d4f430169f04ac5a81285f67b63d3
+oid sha256:c109b013ae18bed6ce63a41dc85a2ea50d106dead973cb2e7ce43d03030b9cb2
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b708b72239765e2913894959f4b9fc75f2825e61f1491eda436ca51a25bef5f1
+oid sha256:cca3a7099dea147630d4f997ed815413f0ae73f258d866a6a2fb054f2568bdf7
 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": 1.012062430381775,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.001969337463379,
+  "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": 2.648,
       "eval_steps_per_second": 0.332,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8282,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.001969337463379,
+      "eval_runtime": 726.4944,
+      "eval_samples_per_second": 2.657,
+      "eval_steps_per_second": 0.333,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.81363638199296e+17,
+  "total_flos": 2.0717810165526528e+17,
   "trial_name": null,
   "trial_params": null
 }