Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3aaa6d4ea3ca4713a4b145ef605575c9ba31af1f34b2cb18ff06af0badffa5a
+oid sha256:6361139705c411746a818bd6c35b582eaf11b9f0ae92ceb10ff248395f82fe96
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d8b559870cb80341e36133fe9db36c1a1210031046445d84c58f2852800436
+oid sha256:1860de668e0d0584f52b35b404d219876674af6875a22aa5ceff2e07d77bdfdb
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01457e5b90ba866937523f396ebb034542332debca0189a6a18570cda0572380
+oid sha256:58ea747baffcc60dbc2ddb0ad42496c65ba93dc6eb544acc3c718b399777b2b4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
+oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4254748821258545,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 1.4130115509033203,
+  "best_model_checkpoint": "./outputs/checkpoint-2400",
+  "epoch": 1.748633879781421,
   "eval_steps": 100,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,13 +329,27 @@
       "eval_samples_per_second": 43.679,
       "eval_steps_per_second": 5.465,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 1.4198,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 1.4130115509033203,
+      "eval_runtime": 143.5484,
+      "eval_samples_per_second": 43.707,
+      "eval_steps_per_second": 5.469,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3710280298073293e+17,
+  "total_flos": 1.4306308718896742e+17,
   "trial_name": null,
   "trial_params": null
 }