Training in progress, step 591000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145c0a00858525cef13dcc730c322c7359bdba5e00e02a3bf89edf80af62f1d8
+oid sha256:cc9ad53a3115139f361080abe79a9737051bc035a423bc59f9cc8d229a8e895a
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
+oid sha256:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a389ff9bc9613d90441220e05bbb320a7bc427029765d050e309eaa9aac6aafa
+oid sha256:52330c0aa0d02fcb5799ed6e9cc612a980458016cf0a3f065d156f1aa64d865b
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f55b12f85aa59ff0112a71e308a0461d067a9b1044007a121298b913aae15f
+oid sha256:13ae0c12d6dffd3dc4ba83c4aefd7c6399f9d43d426c023af851822645281d9d
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba0ddaa6d2944ea53fae500fd775fdda4313267c086c538c0c4de183f8c7838
+oid sha256:ec9b92b3a1b3f86b4bf4ceafccb75f91a766a16a540352fed8d3f4b4b3e97656
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.413637269190843,
-  "global_step": 588000,
+  "epoch": 15.492277526711474,
+  "global_step": 591000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7062,11 +7062,47 @@
       "learning_rate": 6.227372205429946e-07,
       "loss": 1.0273,
       "step": 588000
+    },
+    {
+      "epoch": 15.43,
+      "learning_rate": 6.193420398182335e-07,
+      "loss": 1.0237,
+      "step": 588500
+    },
+    {
+      "epoch": 15.44,
+      "learning_rate": 6.159548307004379e-07,
+      "loss": 1.0253,
+      "step": 589000
+    },
+    {
+      "epoch": 15.45,
+      "learning_rate": 6.125756075470824e-07,
+      "loss": 1.0333,
+      "step": 589500
+    },
+    {
+      "epoch": 15.47,
+      "learning_rate": 6.092043846817916e-07,
+      "loss": 1.033,
+      "step": 590000
+    },
+    {
+      "epoch": 15.48,
+      "learning_rate": 6.058411763942787e-07,
+      "loss": 1.0371,
+      "step": 590500
+    },
+    {
+      "epoch": 15.49,
+      "learning_rate": 6.024926992769612e-07,
+      "loss": 1.0252,
+      "step": 591000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.037292973216481e+17,
+  "total_flos": 7.070228286116659e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
+oid sha256:eb3e0019bc999b90253f77b24ce40dc1e78a96ded902156b1cdea866c7ce4331
 size 1944201353

runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba38c004c778b009546003c02c04bc43ef50ddeee326ffd3e18109395d615d18
-size 11181
+oid sha256:7e58b715a66e89807c52ea029fcbe06f9781357371c2f8198cbfab569dccf0ea
+size 12141