Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129452df5b3c4db39242dc46567b4b76e0fee472c875a16d7b0a677459554e1f
+oid sha256:1377f63ed2c9dadb7c619e577650e3cc38d7909b724c9f720375231f368e5d93
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2186b4e72a0c8b9581a9f1fd64b77b87075f84d605783f258bf6ff56d2b1d5d6
+oid sha256:f860865ef7a337fe0cf9a0ab83db43be9374f836cf79de539d50c0381c00bdff
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecee011d9ea190091aa42a43d90b7c2a3d0f7b5ed88ab6e56f648d5f21aad0a
+oid sha256:2833d6a72f9c2dcc8e1caf553d9c58d438680ada5c3bfdcab9d366a01af971e9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2920022010803223,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 1.2834123373031616,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 43.64,
       "eval_steps_per_second": 5.46,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.2533,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 1.2834123373031616,
+      "eval_runtime": 143.8354,
+      "eval_samples_per_second": 43.619,
+      "eval_steps_per_second": 5.458,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.9672423394930688e+17,
+  "total_flos": 2.0268000465580032e+17,
   "trial_name": null,
   "trial_params": null
 }