Training in progress, step 2840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10f7bc2c65141fa4ebded03f209c967b4ffb87e1cc778dfc9b4a86634ba57d6
+oid sha256:10ea9419bc897f8127b2a76b23cadb89107b0764e27a08a91562681dfb2de8a6
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3615fe2b2b9addb6c497cc609999c34f4e448914d69744ff96b2430756df5daa
+oid sha256:b1dd82c95168c3e2554246bf42378f05037dfc985cac616a5e4d4886c53dc3e7
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380a1cca63ce963571458aaefc36eab189734f962738f8e4fb44ec662db4894a
+oid sha256:d8de38d9f67df6f278483c5a632a2e9d174866bbdfabf05a223a9fdb149cbf2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9945089316ed307f5a98e36c0ec8641c94a4f12f863d3c953fe640032aaa7e
+oid sha256:5c37131dd33a265ba693e5db1412fd69c16e20dba1f6320386e84def93d115d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2256,
+  "epoch": 0.2272,
   "eval_steps": 500,
-  "global_step": 2820,
+  "global_step": 2840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -994,6 +994,13 @@
       "learning_rate": 2.90410829484944e-05,
       "loss": 3.5148,
       "step": 2820
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 34.077083587646484,
+      "learning_rate": 2.902391803757764e-05,
+      "loss": 3.5561,
+      "step": 2840
     }
   ],
   "logging_steps": 20,
@@ -1001,7 +1008,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6674198884024320.0,
+  "total_flos": 6720553638494208.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null