Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcc96e88dbbe67e2aba75e1410e8be8368740094647756f3aeda0648e40eda2
+oid sha256:0a525271f33029751bd79e6ee02b8f285c8714d8e51fbd2d01f2cbbc6f2587cf
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cc3d88eb1cd631988dadbb911dbf04d254cc8a4175f59317397b0d8cc53e57
+oid sha256:e2aa86f6d9ec2adc3adb47645de46597c94342c51105606b5b824aa6946f32b1
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1389c8fb4da5b08654d5ecff1c857ae43115866bad194f9289834fc2a0b6a9c8
+oid sha256:390f4c31f151d1b722c751920ce3c1346c4474b6f2b5548196c30af3030d0e42
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.501122236251831,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 1.4863215684890747,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3114754098360657,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,27 @@
       "eval_samples_per_second": 43.25,
       "eval_steps_per_second": 5.411,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 1.4777,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 1.4863215684890747,
+      "eval_runtime": 143.8068,
+      "eval_samples_per_second": 43.628,
+      "eval_steps_per_second": 5.459,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0135854358789325e+17,
+  "total_flos": 1.0731311264781926e+17,
   "trial_name": null,
   "trial_params": null
 }