Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919801a1142c285296413ec63851c5ac2abb59224d7305e53f90c5f35b8cbc43
+oid sha256:d732ffa9a782ca178aeb71ca69c72d2c38dfdddf501d4d8ae5b2df157244e815
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b096ad9ca63f255698bd773f8a49ded4186b220623fd605a1f747c6487626ddc
+oid sha256:69a64819c9af09f81a158218e4865d0cdce42a41415dd07ea073c21b5890a8ee
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90991c2ad675e02574fbc94f99c043b9b88b65b41849dc17999930cdb657da15
+oid sha256:54d6b84dac6aaad6986d237806767d4c805191ba7fa488b63cf1a10b8e023e89
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
+oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.053786277770996,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.2586520947176685,
+  "best_metric": 2.043891668319702,
+  "best_model_checkpoint": "./outputs/checkpoint-3200",
+  "epoch": 2.3315118397085612,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -441,13 +441,27 @@
       "eval_samples_per_second": 17.755,
       "eval_steps_per_second": 2.221,
       "step": 3100
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 2.0226,
+      "step": 3200
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 2.043891668319702,
+      "eval_runtime": 414.5134,
+      "eval_samples_per_second": 15.136,
+      "eval_steps_per_second": 1.894,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.104980666392576e+16,
+  "total_flos": 9.398805406728192e+16,
   "trial_name": null,
   "trial_params": null
 }