Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d26990d34f16257fadd32045ba019dd4f3d688e7119db32f5a1391ac8ae18d3
+oid sha256:65aad62bf1aff3d91eb586ec1a6a2977aa953d7821ba35023ba8f6a89fdace45
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd892c2e43c78bce4db6c79ccf128feedd62bd74810d242084ec97410babf60
+oid sha256:c02b0e51b88ce1d2fa94c42bd4d48d731a5fc5f096e64355f55768f9925f5070
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd8bdb1856d17b194a76c19970eb51f58f0ae25d9a87ca8d59468738cbbfe5f
+oid sha256:8f7b64f3aa00f9880ea05d8fae45c424ac738ffe20f043970aba83c9f4b0840b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
+oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.145142078399658,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 2.132389545440674,
+  "best_model_checkpoint": "./outputs/checkpoint-2400",
+  "epoch": 1.748633879781421,
   "eval_steps": 100,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,13 +329,27 @@
       "eval_samples_per_second": 20.129,
       "eval_steps_per_second": 2.518,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 2.135,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.132389545440674,
+      "eval_runtime": 446.4033,
+      "eval_samples_per_second": 14.055,
+      "eval_steps_per_second": 1.758,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.762876423432192e+16,
+  "total_flos": 7.05520114725888e+16,
   "trial_name": null,
   "trial_params": null
 }