Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681b2d24ea28ee82e6aae8302d1382a0f77801f9e454db5217e47a9a66bc37bf
+oid sha256:700b4a3aa8c84e50ce55d055ae1090e2f634ab913c412fa8ef7d05ee86aa5bed
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def6fc0dd6afafd9683b85026dd4b02c505c3ac9637eb824f80b7e3df0b7d2b7
+oid sha256:cc3e44cfc586e438cb0625f86291e9c721ce5ea12a523690602c35b5c4ff098c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8270fb5b98b86da8550d75dc7fb5d84906b144754ea3444bb49fbaae1ee321
+oid sha256:fae5c7e3e3b5b73d5c7fc005bedd764d89490ccac94349d4c0ac6f66077ac252
 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": 1.8587623834609985,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.840909090909091,
+  "best_metric": 1.8513188362121582,
+  "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": 19.012,
       "eval_steps_per_second": 2.383,
       "step": 2000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002,
+      "loss": 1.9793,
+      "step": 2100
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 1.8513188362121582,
+      "eval_runtime": 78.5905,
+      "eval_samples_per_second": 18.984,
+      "eval_steps_per_second": 2.379,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.090842007484416e+16,
+  "total_flos": 6.39302000569344e+16,
   "trial_name": null,
   "trial_params": null
 }