Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950e8c803fcb4a5b7e442d76459e57550da0162d8201c665b1969cd645b00901
+oid sha256:7cd4a2abb0e79d474a00b8479bcfe8e4c94b9be3184edd2cb382da313d280452
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbc58acc2834dda70661d24b6c87bbbbf67d35077648bc91f5e1770333619de
+oid sha256:42d89f03fb33f6de6c1e53f0205ed8b0f0b7472f985ef1cb2ab5f6438eb024b2
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce683b1f9b99043522516da1a6d43513b81202580862b22e361f02a471d2a8ef
+oid sha256:5535758ea04ad8843482933d69f64794466d07ff90e13c2204bdc84469ba4d4c
 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": 1.4537303447723389,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 1.431217908859253,
+  "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": 11.284,
       "eval_steps_per_second": 1.412,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 1.4171,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 1.431217908859253,
+      "eval_runtime": 557.2566,
+      "eval_samples_per_second": 11.259,
+      "eval_steps_per_second": 1.409,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.995777680716759e+17,
+  "total_flos": 6.254944630532506e+17,
   "trial_name": null,
   "trial_params": null
 }