Training in progress, step 3300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1150212ac716e75ebb84a850d5e56c39309dad309d1513b7ec75ed80fb0b65
+oid sha256:fe1a4cbee3e00acdb62d414df5b0f897662fd50d4108ec50fb9e60355a971244
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f103a819b5d8a2f1435f043d5b0f07be734fffc80d59276ada9775034dcf4f2c
+oid sha256:71ac08e901a9b725146df41ee1284aaef90027a5e0ce88a4a21f4b8ad637b029
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6fc0a05ece6bf6410546a20117db4d978b60197fb2c90e41d50543cdc997ec7
+oid sha256:d26adabab8044b9f565c81e512feb8a78443fda90b855252c9b6238b058d3ef7
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
+oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0629310607910156,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 2.3315118397085612,
+  "best_metric": 2.0515356063842773,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 2.4043715846994536,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,13 +455,27 @@
       "eval_samples_per_second": 30.565,
       "eval_steps_per_second": 3.824,
       "step": 3200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 2.0083,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 2.0515356063842773,
+      "eval_runtime": 205.1563,
+      "eval_samples_per_second": 30.582,
+      "eval_steps_per_second": 3.826,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.337941745606656e+16,
+  "total_flos": 9.629167658213376e+16,
   "trial_name": null,
   "trial_params": null
 }