Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a0789de15f8e6e34b7f851f416019c8a3eb08594f73e5d701ff41336e92493e
+oid sha256:b3e877c04611b8f75953a97cd9238d7bdfaa53f751e3d1754916023d5933db54
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb610fbe6643abf4cc34cac840cad0f272b6e4696ea96845abca7913647ff11d
+oid sha256:4b79f6b0195bac96d3f424b59f1c5bf7de3edcd06bfc93f77babdd7da8fadf3b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bea72d7bc14392060552e2632922b1efac8f9292c9a40eab92222a0ce3dae64
+oid sha256:4933eabcc84eee1438f9d6f8169b5cecd886b53e4de0afe6e5bf4f525371b890
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5523250102996826,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.5274579524993896,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 30.589,
       "eval_steps_per_second": 3.827,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.5382,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.5274579524993896,
+      "eval_runtime": 204.8352,
+      "eval_samples_per_second": 30.63,
+      "eval_steps_per_second": 3.832,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.710192402874368e+16,
+  "total_flos": 1.993348357668864e+16,
   "trial_name": null,
   "trial_params": null
 }