Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4562d5ba27bfcfe942746cdfc9c54b3815c710ad629431394f3db52d6bd80768
+oid sha256:701f13c64afee1edcc48e3f4fd6ea9864775ca8a64b2f317a6f17366dcd624bc
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a3f13f476c346b4ca6e1f06b07990dca5b54cf23815405ee57a9d264e53a88
+oid sha256:5e3e86ed23c756f0c4b1a819e3ad3ad2692bbd02554c2995e6607f5bccc85eff
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d740007b69299aafed94d2a7a15f725f57b74b4dd2ecb204659a3b705daff261
+oid sha256:ba0d2f71b3765f30a8a92ba02eaf902a1662f276a25395f9d1484f184257488f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4382610321044922,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6032786885245902,
+  "best_metric": 1.4250658750534058,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6761384335154828,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 46.956,
       "eval_steps_per_second": 5.875,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 1.4139,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 1.4250658750534058,
+      "eval_runtime": 133.6118,
+      "eval_samples_per_second": 46.957,
+      "eval_steps_per_second": 5.875,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.311400348811182e+17,
+  "total_flos": 1.3710020185554125e+17,
   "trial_name": null,
   "trial_params": null
 }