Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8055cb4f26cf5e8d49322026dd258337b0f420901583dcee2f62d717821fc0b2
+oid sha256:557525ab6ebf99073c6638ccd8f4e685491ddbca038630e83e2ed6fb924b97a7
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f548f5b9d86727a65b850c151162aac92f6f1c6dc1c47504a26058c1c4515f79
+oid sha256:abca4028050388bba9551352fb284a9b11c16805490da76ac91ccb3ae62cf5ca
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3dfe2b0743dc299fda05b770346eca15b64e6cdb8c75ee2df253ac9b11e04c
+oid sha256:01bdbeb5937e67c48029bfb76c4643cade36da9398930f69b0a6221a6ee4eb33
 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": 1.2710933685302734,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 1.259511113166809,
+  "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": 15.025,
       "eval_steps_per_second": 1.88,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.2451,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.259511113166809,
+      "eval_runtime": 417.6409,
+      "eval_samples_per_second": 15.022,
+      "eval_steps_per_second": 1.88,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.808998544825129e+17,
+  "total_flos": 7.133138222904146e+17,
   "trial_name": null,
   "trial_params": null
 }