Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077213219e8b8677999bcb2593f6400f44ad43e7392cc494ad1fc5c13084077e
+oid sha256:3371f13b66c969eb7ee06a87886d59c9177868b32e16052618f0ce92c817396c
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2c775ed3ea7c96df0449c20bca12ac19d6c8a9ae24fdc13c21b40f8e36a895
+oid sha256:67a38367f875f76bdb14f97bdb7183e64dc5d9b1267531c75f45bca500baca9d
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cfcaec1f5911fc7c2b7c4eeaf66555768023f53d9ed79d8ed6b38d001dcf35
+oid sha256:3438fe6cf014af3dcfd560104641977a705ec397c5ca3c2f83734a38605b07ea
 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": 1.1806031465530396,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.1772046089172363,
+  "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": 3.92,
       "eval_steps_per_second": 0.491,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9663,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.1772046089172363,
+      "eval_runtime": 491.1926,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 0.493,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.987573836110234e+16,
+  "total_flos": 7.321308131141222e+16,
   "trial_name": null,
   "trial_params": null
 }