Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df1f960a29c44061fce66ae401b18a75ac0738ee75c302a3eebb9ed3a0c763e
+oid sha256:91297f93e21a7dd1185d2f490d7eb0bf142285f9263306b4cb0884142bd02483
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6223ebb88b8579bea4e2ca04d51e383ef3b9142dca394ff972e89f98c62bb82
+oid sha256:44e7993e5b60b547ede998a5719d38982967173c8b2465b91222b22143692301
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b6db96b2a087280e0193508072347d81e3efb5dcab769c085a2a842cb52560
+oid sha256:a027d7fcffc40b9593822e7c30c9606bda7a5ffe540e18f1c4ce8aedddf15302
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.946110725402832,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.840909090909091,
+  "best_metric": 0.9420180916786194,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.9829545454545454,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 11.976,
       "eval_steps_per_second": 1.501,
       "step": 2000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 2100
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 0.9420180916786194,
+      "eval_runtime": 124.5044,
+      "eval_samples_per_second": 11.984,
+      "eval_steps_per_second": 1.502,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1244470506924032e+17,
+  "total_flos": 1.180506237539328e+17,
   "trial_name": null,
   "trial_params": null
 }