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:b4663053c60e5f267803a23dfc4bf6b7799e1bea84539190c45eeb0994148fd0
+oid sha256:eee718852cec003ec3db14b0f696b66edcf3f1b3c389074225a0f8b5cd2ecfc0
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2037ccc8f01df1eb9dd3cb62165d668a40294b816104d67ba12a3f0bcb38fa
+oid sha256:f3ee89b20cc4bb51d8cd942947ab05de6e2f863ef9b6d2d99c727b6a840fa09a
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f733f68e9af3a413f7f5c8bf128e0ef057938927e43869c070a32516f9bd1d62
+oid sha256:21b2b16f4c08cc27a40806f2856451e039418be2a7b192aecdaa0799e1113bb8
 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": 1.5026806592941284,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 1.4737541675567627,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6029143897996359,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,13 +301,27 @@
       "eval_samples_per_second": 11.28,
       "eval_steps_per_second": 1.411,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.4737541675567627,
+      "eval_runtime": 555.4267,
+      "eval_samples_per_second": 11.296,
+      "eval_steps_per_second": 1.413,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.47414668374655e+17,
+  "total_flos": 5.7355218612382925e+17,
   "trial_name": null,
   "trial_params": null
 }