Training in progress, step 4650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929e2242a9a0088d0fb4cc09d992569fcd02f496312666ac45152ad941d623c0
+oid sha256:be74aa09adbfb9e73506b97419af908a66b89c1b2a4ba8124bfebd46147e88a8
 size 17447528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1527a879c6977fe19797b0101cf77d86e24b5440b9a07ee810cb6a1281d301
-size 34959738
+oid sha256:f881a76326a796266f0a52903e1c1d25f422c832a117b36f746de49c5f08b8ca
+size 34959674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf8c3fc08ab547eb72202933b91049b04677fe8f9edb364f6daca74147a4218
+oid sha256:959ec0bf93f91561900c708117dbef11ece1d13f9503fe4346cd174869c09a90
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bf4acbbdf4243a5b30121f973d426853acaed3d0caa7d9deb065ee076e1e1d
+oid sha256:9612206721dab747b72325faca201c5b62b462fd9a44bcf14483ab477a2645b1
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.480732798576355,
-  "best_model_checkpoint": "./output/checkpoint-4500",
-  "epoch": 0.7087730351236415,
+  "best_metric": 1.4804431200027466,
+  "best_model_checkpoint": "./output/checkpoint-4650",
+  "epoch": 0.7323988029610963,
   "eval_steps": 150,
-  "global_step": 4500,
+  "global_step": 4650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3397,6 +3397,119 @@
       "eval_samples_per_second": 13.469,
       "eval_steps_per_second": 13.469,
       "step": 4500
+    },
+    {
+      "epoch": 0.7103480863128052,
+      "grad_norm": 0.8629345893859863,
+      "learning_rate": 3.0589677315529044e-06,
+      "loss": 1.4749,
+      "step": 4510
+    },
+    {
+      "epoch": 0.7119231375019688,
+      "grad_norm": 0.8621689677238464,
+      "learning_rate": 2.9363630392945513e-06,
+      "loss": 1.4772,
+      "step": 4520
+    },
+    {
+      "epoch": 0.7134981886911325,
+      "grad_norm": 0.873957633972168,
+      "learning_rate": 2.816206774856854e-06,
+      "loss": 1.4937,
+      "step": 4530
+    },
+    {
+      "epoch": 0.7150732398802961,
+      "grad_norm": 0.9086722135543823,
+      "learning_rate": 2.6985038773932046e-06,
+      "loss": 1.4512,
+      "step": 4540
+    },
+    {
+      "epoch": 0.7166482910694597,
+      "grad_norm": 0.8475430607795715,
+      "learning_rate": 2.583259185208714e-06,
+      "loss": 1.4621,
+      "step": 4550
+    },
+    {
+      "epoch": 0.7182233422586234,
+      "grad_norm": 0.8581358790397644,
+      "learning_rate": 2.4704774355612943e-06,
+      "loss": 1.4746,
+      "step": 4560
+    },
+    {
+      "epoch": 0.7197983934477871,
+      "grad_norm": 0.8703014254570007,
+      "learning_rate": 2.3601632644669536e-06,
+      "loss": 1.4906,
+      "step": 4570
+    },
+    {
+      "epoch": 0.7213734446369507,
+      "grad_norm": 0.9130226373672485,
+      "learning_rate": 2.2523212065091723e-06,
+      "loss": 1.4825,
+      "step": 4580
+    },
+    {
+      "epoch": 0.7229484958261143,
+      "grad_norm": 0.8566045165061951,
+      "learning_rate": 2.1469556946525706e-06,
+      "loss": 1.4732,
+      "step": 4590
+    },
+    {
+      "epoch": 0.724523547015278,
+      "grad_norm": 0.8569677472114563,
+      "learning_rate": 2.0440710600606595e-06,
+      "loss": 1.4725,
+      "step": 4600
+    },
+    {
+      "epoch": 0.7260985982044417,
+      "grad_norm": 0.9196586012840271,
+      "learning_rate": 1.9436715319177956e-06,
+      "loss": 1.4832,
+      "step": 4610
+    },
+    {
+      "epoch": 0.7276736493936052,
+      "grad_norm": 0.8641564249992371,
+      "learning_rate": 1.8457612372553348e-06,
+      "loss": 1.4994,
+      "step": 4620
+    },
+    {
+      "epoch": 0.7292487005827689,
+      "grad_norm": 0.8218653798103333,
+      "learning_rate": 1.75034420078201e-06,
+      "loss": 1.4748,
+      "step": 4630
+    },
+    {
+      "epoch": 0.7308237517719326,
+      "grad_norm": 0.8673424124717712,
+      "learning_rate": 1.6574243447184597e-06,
+      "loss": 1.4779,
+      "step": 4640
+    },
+    {
+      "epoch": 0.7323988029610963,
+      "grad_norm": 0.8800205588340759,
+      "learning_rate": 1.567005488636024e-06,
+      "loss": 1.4927,
+      "step": 4650
+    },
+    {
+      "epoch": 0.7323988029610963,
+      "eval_loss": 1.4804431200027466,
+      "eval_runtime": 37.6922,
+      "eval_samples_per_second": 13.292,
+      "eval_steps_per_second": 13.292,
+      "step": 4650
     }
   ],
   "logging_steps": 10,
@@ -3416,7 +3529,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.6814781814677504e+17,
+  "total_flos": 4.836760721871176e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null