Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e827f78889e02cb290d740ca48cf0ffc7d3009e222c44bf4227c31bf24586ed
+oid sha256:948826c9dd858709de0c2c4125273aa584338fafd27c1c959a6511d3d691e523
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2dde23211f20127cc76c7d29250ba5a15939b0fdfda8347c7d090c38cdeab5
+oid sha256:0712dc73021ad81a2097d1efa5660cb999e296e42a45af3f5b76980952d3aa52
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e546ced227cdbcd028e39a6dd82c210da282c04c2410248a7e7ebf4303af3e90
+oid sha256:0a7ae3281f8a6cb460b1545701878c767c2d95ce91301108396f0564e1475c05
 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": 0.9326320290565491,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 0.9287375211715698,
+  "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": 2.446,
       "eval_steps_per_second": 0.307,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.7632,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.9287375211715698,
+      "eval_runtime": 785.4978,
+      "eval_samples_per_second": 2.457,
+      "eval_steps_per_second": 0.308,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 5.4385953933225984e+17,
+  "total_flos": 5.6983487558086656e+17,
   "trial_name": null,
   "trial_params": null
 }