Training in progress, step 670000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facea498a3305bb3a4cf04ba493e9b7a282bf34c7699144b12c3401905a21a21
+oid sha256:ed5bbd83e76bfaea16133e5f4d584916d5b8420b3bb185b8e5801362569d4f69
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0253822de0f7fe54e007e60affd0913e4b68439fe1550215e7a076507078bb
+oid sha256:2d66a36b6e02c5a5390d3c9dec0faf002f0a21fa7c7b5ef13a837f052f84e013
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46211629a4cc11950e226f7dbdda304cda1420c43879285d3e04ebb8508dc043
+oid sha256:12cb7e1a11524752d8ec0a2746c2da7c87cd4d3afc083cf4a0df43b88ed43337
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c11aa747eb56c76be6b0a8185d8eb345ab22e3a85121576df152b2d5604743
+oid sha256:bd3471c82ac0fc930f64e5adbb6702a0e555d4edfcc1c2dab4ff36db308349b1
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f323fe99852eb9065ab82d8c0f478aeb01397ae4967c2beb7e4de9ca3f02ec
+oid sha256:49fa69a09ea23ef88cf7df6a3190bd2ee20d350293163871b5d1dbdf1a735794
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8df123d1834d25753f8b002915374feeeb89dc9c6992036e0b849ae27e9320
+oid sha256:0dac01a61c51f51dbd4c3cc5d50cf7d5af4a9f263667ab541575cfd5deab9645
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90443240959e9f40acd615af8df90f5d9b01b4b49736141665a99e8168dc3c6a
+oid sha256:221b7d8fdca30ab22892af203b971ac82533d02ad7492e4e8b5068d84fa6a3ca
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd0fd3633719fca8fe6bbb82b9e0f5384f9458c9e7cc0938ff32b60be639fdb
+oid sha256:548649d9f5f2f112c52d8a0f4a7c44c0a8f1f18e8bb96cd91be7066faf617949
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ca6715dedc0846ae860b91a71263b7a826d6a54596ee7919105a93c87a6496
+oid sha256:426865c62dd7c19a97ed19d06fe6fa6770f12ecb7a2997d9a0820ed2f9c93c21
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555ec27b704b2cb1160b682f3e0caec8c125b854ba2add3f3b500f4ed76a0e8e
+oid sha256:e886c38b9308720d6c044b1f01de3ee4919b1d3a6edb19ef015bd4926793ada4
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8e59bcc271d9e83e953974cfcbd52d5f5cf63d456de8e0f805b45487976195
+oid sha256:50de55c4a72c38e6722f7cb77ebe9f35ce412c17a797d93c631371b39d861204
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3193719789380256,
-  "global_step": 660000,
+  "epoch": 1.3393624634673895,
+  "global_step": 670000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7926,11 +7926,131 @@
       "learning_rate": 4.97771953363055e-05,
       "loss": 0.299,
       "step": 660000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.967283762863444e-05,
+      "loss": 0.2994,
+      "step": 660500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.956856283426728e-05,
+      "loss": 0.2994,
+      "step": 661000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.946437123828732e-05,
+      "loss": 0.2982,
+      "step": 661500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.936026312555037e-05,
+      "loss": 0.2992,
+      "step": 662000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.925623878068408e-05,
+      "loss": 0.2984,
+      "step": 662500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.915229848808698e-05,
+      "loss": 0.2994,
+      "step": 663000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.904844253192795e-05,
+      "loss": 0.2989,
+      "step": 663500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.8944671196145136e-05,
+      "loss": 0.2991,
+      "step": 664000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.884098476444539e-05,
+      "loss": 0.2984,
+      "step": 664500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.8737383520303546e-05,
+      "loss": 0.2984,
+      "step": 665000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.8633867746961356e-05,
+      "loss": 0.2988,
+      "step": 665500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.853043772742709e-05,
+      "loss": 0.2986,
+      "step": 666000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.8427093744474364e-05,
+      "loss": 0.299,
+      "step": 666500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.832383608064172e-05,
+      "loss": 0.2992,
+      "step": 667000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.822066501823172e-05,
+      "loss": 0.299,
+      "step": 667500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.811758083931005e-05,
+      "loss": 0.2984,
+      "step": 668000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.8014583825704976e-05,
+      "loss": 0.2982,
+      "step": 668500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.791167425900632e-05,
+      "loss": 0.2988,
+      "step": 669000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.780885242056493e-05,
+      "loss": 0.2983,
+      "step": 669500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.770611859149185e-05,
+      "loss": 0.2987,
+      "step": 670000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.462065045446751e+22,
+  "total_flos": 4.529677636130487e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0253822de0f7fe54e007e60affd0913e4b68439fe1550215e7a076507078bb
+oid sha256:2d66a36b6e02c5a5390d3c9dec0faf002f0a21fa7c7b5ef13a837f052f84e013
 size 449450757