Training in progress, step 588000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800f47d6c105599f23476b36ba02ef6cd898b37ec9f6ea6c11464b383ba2cbd7
+oid sha256:145c0a00858525cef13dcc730c322c7359bdba5e00e02a3bf89edf80af62f1d8
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade14b8fcd7033799d31d7c0b3638db665d1101ba6c901b224e22e4630967f0f
+oid sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89a086ff98497212b3403fb71dd7cca09fd28ce2e72380eabd270a7198bf63d
+oid sha256:a389ff9bc9613d90441220e05bbb320a7bc427029765d050e309eaa9aac6aafa
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a56e5f53e3690fa8d88396102c5e72891424a69c9adf23f31ba1d7ae3b5bd5e
+oid sha256:08f55b12f85aa59ff0112a71e308a0461d067a9b1044007a121298b913aae15f
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7e558efc05c7857c55680cae30ef0a4d65e8d9cbb5e001241cc014941d7312
+oid sha256:eba0ddaa6d2944ea53fae500fd775fdda4313267c086c538c0c4de183f8c7838
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.334997011670215,
-  "global_step": 585000,
+  "epoch": 15.413637269190843,
+  "global_step": 588000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7026,11 +7026,47 @@
       "learning_rate": 6.432680070962052e-07,
       "loss": 1.0271,
       "step": 585000
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 6.398253158795223e-07,
+      "loss": 1.0367,
+      "step": 585500
+    },
+    {
+      "epoch": 15.36,
+      "learning_rate": 6.363905094466666e-07,
+      "loss": 1.0408,
+      "step": 586000
+    },
+    {
+      "epoch": 15.37,
+      "learning_rate": 6.32963602356865e-07,
+      "loss": 1.0184,
+      "step": 586500
+    },
+    {
+      "epoch": 15.39,
+      "learning_rate": 6.295446091358618e-07,
+      "loss": 1.0284,
+      "step": 587000
+    },
+    {
+      "epoch": 15.4,
+      "learning_rate": 6.261335442758554e-07,
+      "loss": 1.0337,
+      "step": 587500
+    },
+    {
+      "epoch": 15.41,
+      "learning_rate": 6.227372205429946e-07,
+      "loss": 1.0273,
+      "step": 588000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.004102496447283e+17,
+  "total_flos": 7.037292973216481e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade14b8fcd7033799d31d7c0b3638db665d1101ba6c901b224e22e4630967f0f
+oid sha256:89037c61457d92a92d8a8114636f5328491a76d6f314d56f9e8167460609d7fc
 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 sha256:289f05ba23629ccf8a109c80a0479b07884acff653ab97fe91883a05fb591060
-size 10221
+oid sha256:ba38c004c778b009546003c02c04bc43ef50ddeee326ffd3e18109395d615d18
+size 11181