Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf5df5f6d7116007c86a332272baa57bada46809920ed8d41b365a6337a903d
+oid sha256:1e9f8af9b1afc61ffb1b62b07b0a91b6e9c7bee01519fb1ae084500074a4f8cb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f573e1e96e5f6e7e61dbf7e18b488763536ac6c015331d6c287ce88a7ee83ed2
+oid sha256:b9364b1ad8de50779879e6434cca0ce5eb275444c21ecaa973f91700cda504e0
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3107391da0b3a22e0d165a23f3350b25d47ba522f7f12c6917275276e0455593
+oid sha256:31154012bbd8525847da1e0589dd874cfb98ce27241dc27c8e46a9cd41ffa049
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2854410409927368,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.2793278694152832,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 12.717,
       "eval_steps_per_second": 1.595,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0465,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.2793278694152832,
+      "eval_runtime": 151.7314,
+      "eval_samples_per_second": 12.72,
+      "eval_steps_per_second": 1.595,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3385286781267968e+17,
+  "total_flos": 1.4024976681848832e+17,
   "trial_name": null,
   "trial_params": null
 }