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:bcabaed6893efa8ef18e367a7c349f30f7459129da1774cae9415a644f7bfc7b
+oid sha256:addb4eb5ef70c5d79703d08e492b212c29be0e8670b0ea7f4191ef48fd80d2de
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b650644f03d39399c2028cd9c8ada111e6d80bc59e58a3fb5366e9f4fd8ef80
+oid sha256:8bab1e9ce49bd7ee275ca2458406529b60e34c8a970a1389d813ddbe25a68d25
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8665825c42a3d9f7e4d6ea045efe267b7c691410421807dc2f776850b81af2bb
+oid sha256:0ac8a1ed22dccfd0b73fde0039db75261c479f8649c9b62376ee4e503343b09a
 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": 1.364682912826538,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.3633157014846802,
+  "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": 15.543,
       "eval_steps_per_second": 1.95,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.119,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.3633157014846802,
+      "eval_runtime": 93.3891,
+      "eval_samples_per_second": 15.537,
+      "eval_steps_per_second": 1.949,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2278575092252672e+17,
+  "total_flos": 1.2864184157454336e+17,
   "trial_name": null,
   "trial_params": null
 }