Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5627d74cd6f3e21adf8f12782b492528e09abf307c18f62b12e27c630c4909
+oid sha256:eb42b3951c0196c952e2ae19e43a8d0bcc6bffd53742c673a50523c96c833432
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d77827cb1d07062bcccceca8e5c6987ec8ed81f18640659020638eb07858e5
+oid sha256:47c11bfba102f129aa6291146966a6f0fb152fb3d36d7f56bf6eddb8694d00cf
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3632eedca239f093acf9fef50ee1b2073b7130b77179cceb32827b1814399786
+oid sha256:fd1cdd076b217373af7247c4e5586438d32391ac0523ee9c4ea56789d6d16d28
 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": 2.139225959777832,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.2586520947176685,
+  "best_metric": 2.1339216232299805,
+  "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": 30.576,
       "eval_steps_per_second": 3.826,
       "step": 3100
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 2.1127,
+      "step": 3200
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 2.1339216232299805,
+      "eval_runtime": 205.3153,
+      "eval_samples_per_second": 30.558,
+      "eval_steps_per_second": 3.823,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.828952655767552e+16,
+  "total_flos": 9.113803498211328e+16,
   "trial_name": null,
   "trial_params": null
 }