Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c660d3de9cde476877c6bc8d9def0e0d8dd4264faa418847cd860d77ae79db
+oid sha256:3efa631529d19460ca850d512f923d0e99ff972c7aa0e6be6e5f8f92152ed1d7
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9bf3e4980e676b92220a7794352b32bff179ee2be58032db7a8ddf23d1769b
+oid sha256:641530905aae4fb6676aec0aab6bd85d867c1aa05431bf2ebab956bc1b441635
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18a675fec77c183aa0ed63668e3d676246ee7c13636976e96475dfc4e0bc176
+oid sha256:109840deab3769bfe3711ab7fc3d0717cd3af7fb8722bdab6748ba80b0be6d2f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
+oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9260075688362122,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 3.2,
+  "best_metric": 0.921540379524231,
+  "best_model_checkpoint": "./outputs/checkpoint-2500",
+  "epoch": 3.3333333333333335,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,20 @@
       "eval_samples_per_second": 2.488,
       "eval_steps_per_second": 0.312,
       "step": 2400
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0002,
+      "loss": 0.7277,
+      "step": 2500
+    },
+    {
+      "epoch": 3.33,
+      "eval_loss": 0.921540379524231,
+      "eval_runtime": 774.2681,
+      "eval_samples_per_second": 2.493,
+      "eval_steps_per_second": 0.313,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
@@ -350,7 +364,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 6.216279534801408e+17,
+  "total_flos": 6.474662583520973e+17,
   "trial_name": null,
   "trial_params": null
 }