Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9168945734e861efc761211602678943bfc5e627e3517e9b3caf8d680a27a178
+oid sha256:4afbfbaa4b6c8e77f06d644ce323cc215442aa6bd161ffa25adceb8d3c16ccd9
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8071c27882b324455d8c2a198a5170e418362ab74b93b4e8dc214147065d0877
+oid sha256:bffa8f764fd1acccf478f5e0dbb3b4cec555f77224562a64b9a5a84007c2e5bd
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2cea2431b2cb13f64c00a95b19e0f4020d70871d487340ebce67c5fed0ac3a
+oid sha256:9114297f5a85998fb9b53215851ae4424aaa04406aa230e44a8963b3d87a281d
 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": 1.2773118019104004,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.2748572826385498,
+  "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": 12.883,
       "eval_steps_per_second": 1.616,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0327,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.2748572826385498,
+      "eval_runtime": 112.6112,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 1.616,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3360108283633664e+17,
+  "total_flos": 1.399789696241664e+17,
   "trial_name": null,
   "trial_params": null
 }