Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fa2e803c556255298a3b316715ada5e6d77b35071b1019fa180ab68c353cc7
+oid sha256:14a0b894e938b21bfa8551c8828f13e3754edf0da08fabd8e80bb80842c6006f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c4e33bb8d351e13339fbe917475eb8f0c0fff3bdba4094f3213a0642e377ba
+oid sha256:5b24df08acbdb5a8dbfad50e99ee0b32ec103f50ea81f58f73c2c0d46df24662
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14dabd6ac5b413b42d35c286b0d19e23ed4fec71087c81558b454fea8c926535
+oid sha256:524dd2e23117d8b443709151f0c30fd7b12f5af14881b8fbb512d42a7c4c2c9a
 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": 2.1652047634124756,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 2.1539299488067627,
+  "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": 30.632,
       "eval_steps_per_second": 3.833,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 2.1553,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.1539299488067627,
+      "eval_runtime": 204.9017,
+      "eval_samples_per_second": 30.62,
+      "eval_steps_per_second": 3.831,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.719177798387712e+16,
+  "total_flos": 7.009593112553472e+16,
   "trial_name": null,
   "trial_params": null
 }