Training in progress, step 660000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0094043a45ee455c34cdbf7e5ed868b844e2cc109c62c31adc8eabe0945cd55
+oid sha256:facea498a3305bb3a4cf04ba493e9b7a282bf34c7699144b12c3401905a21a21
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afca04d573f1bb3162caabe1bb7b946edefb5cb8fa7beeabdf4a9618ee0ba3ea
+oid sha256:9b0253822de0f7fe54e007e60affd0913e4b68439fe1550215e7a076507078bb
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afdb75bc9c4b3b8d3f36f77e21f0d34f0633a3fe673f092dd264b1121465456
+oid sha256:46211629a4cc11950e226f7dbdda304cda1420c43879285d3e04ebb8508dc043
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334f507bebbd8e2eb32a3a52e1460054ef235aff9b388a6044a2cf6124700604
+oid sha256:05c11aa747eb56c76be6b0a8185d8eb345ab22e3a85121576df152b2d5604743
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1fe6196ed311cd8ddb4f7739bbce785a7482bd7a8a89fc83aadbb7b199e0b80
+oid sha256:87f323fe99852eb9065ab82d8c0f478aeb01397ae4967c2beb7e4de9ca3f02ec
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c16cf0e46ab235f9e251974c64ca93772ae50300b4f1505ff50d8f4e2246708
+oid sha256:8b8df123d1834d25753f8b002915374feeeb89dc9c6992036e0b849ae27e9320
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea98aa1b40d4dde89de24ce301ffc44f0dee70fb25e51e28dfe6b65e5e6240d
+oid sha256:90443240959e9f40acd615af8df90f5d9b01b4b49736141665a99e8168dc3c6a
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476caa126ce91db0ad93d8541266aa7e5c1a71c0473ab678864fc300fdd08e70
+oid sha256:1bd0fd3633719fca8fe6bbb82b9e0f5384f9458c9e7cc0938ff32b60be639fdb
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3637d3be8f9c8d6ff9f1958a71fe2d848eaecb87ddf0683d13eaae5352425491
+oid sha256:e8ca6715dedc0846ae860b91a71263b7a826d6a54596ee7919105a93c87a6496
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62727907f78fc16c3f0e4b91fbdcc94bc537750512333e674d8d2c4dcd12411
+oid sha256:555ec27b704b2cb1160b682f3e0caec8c125b854ba2add3f3b500f4ed76a0e8e
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb24dd41ced00dc957e38e97b930833d2e52e5141588b4ec2f84d6e2ee23293d
+oid sha256:2e8e59bcc271d9e83e953974cfcbd52d5f5cf63d456de8e0f805b45487976195
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2993814944086615,
-  "global_step": 650000,
+  "epoch": 1.3193719789380256,
+  "global_step": 660000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7806,11 +7806,131 @@
       "learning_rate": 5.188132027429215e-05,
       "loss": 0.2991,
       "step": 650000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.177536451140569e-05,
+      "loss": 0.3005,
+      "step": 650500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.166948591359489e-05,
+      "loss": 0.3002,
+      "step": 651000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.1563684770327804e-05,
+      "loss": 0.3003,
+      "step": 651500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.145796137086076e-05,
+      "loss": 0.3,
+      "step": 652000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.135231600423742e-05,
+      "loss": 0.2997,
+      "step": 652500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.124674895928823e-05,
+      "loss": 0.2998,
+      "step": 653000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.114126052462943e-05,
+      "loss": 0.2998,
+      "step": 653500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.103585098866237e-05,
+      "loss": 0.2995,
+      "step": 654000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.093052063957276e-05,
+      "loss": 0.2996,
+      "step": 654500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.082526976532968e-05,
+      "loss": 0.2994,
+      "step": 655000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.072009865368501e-05,
+      "loss": 0.2996,
+      "step": 655500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.061500759217261e-05,
+      "loss": 0.2999,
+      "step": 656000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.050999686810735e-05,
+      "loss": 0.2997,
+      "step": 656500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.04050667685846e-05,
+      "loss": 0.2995,
+      "step": 657000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.0300217580479244e-05,
+      "loss": 0.2997,
+      "step": 657500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.01954495904449e-05,
+      "loss": 0.2993,
+      "step": 658000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.0090763084913336e-05,
+      "loss": 0.2991,
+      "step": 658500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.998615835009339e-05,
+      "loss": 0.2995,
+      "step": 659000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.988163567197043e-05,
+      "loss": 0.2993,
+      "step": 659500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.97771953363055e-05,
+      "loss": 0.299,
+      "step": 660000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.394457756168279e+22,
+  "total_flos": 4.462065045446751e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afca04d573f1bb3162caabe1bb7b946edefb5cb8fa7beeabdf4a9618ee0ba3ea
+oid sha256:9b0253822de0f7fe54e007e60affd0913e4b68439fe1550215e7a076507078bb
 size 449450757