Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e59e9d66c6abe3766a4795909850028ef3eecad1e36266bb406469eadcac77a
+oid sha256:bb225a59c974310143f5d17d604835d43b60874a8afd12b160443afb28b7a5c3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d8db54698873fb17c6207f0160eb623a648b156acdac11c8477660eccbd519
+oid sha256:3fec59b955900be9724e52e5ba1d6268f04cf008beb296419c5a2c8ae7389e45
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72d4610256ec3210e9ec5e1eee2b9b0106afc774d4eee7e345554af1a495e2b
+oid sha256:e29e66817349158337df1bd41441f26d49ce5a4752ab84d525100d2ee478d1a6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.29191255569458,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.2864296436309814,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.533333333333333,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 12.905,
       "eval_steps_per_second": 1.619,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.0486,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.2864296436309814,
+      "eval_runtime": 112.377,
+      "eval_samples_per_second": 12.912,
+      "eval_steps_per_second": 1.62,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1450811615215616e+17,
+  "total_flos": 1.2086378107969536e+17,
   "trial_name": null,
   "trial_params": null
 }