Training in progress, step 830000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7fd5efb2ff87d094795926832b73ee7aa1e6614b8bfcc85208c1fac61c542d
+oid sha256:6ef1b487cabfa82f2f81ded5cef2d529a41a97f8137d750d66e05d443478e91a
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd2e6a7da537ff760743918bcaefe9c986fc2c76a2e5c7636f4801ac5b5cd7b
+oid sha256:b63e12b39341c1c8d25b10dc8ca07cde5e82303726c5b23ac1fdd24345f08c2a
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0609e713a668aa906084c6d7021e86eb2ccb60af4342d1b4397b833b19fbbc89
+oid sha256:34241c46169d6140a8feca7f2e1db99ea6d7326e000406064ac61feecf3f17b2
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3592882666e2655598af900b2cb26f9f1ba0f86a99376f61e0440aabceaa6a07
+oid sha256:9fb4767c32ae0f5cf34a94816a959b9568b2ea2174c179de2a3df992017a5f77
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca8c6c74101f99bae3f401fe7213e04d3ffd2cde1efe24238143ecf20918b53
+oid sha256:efc0c6d968c43ae24dfc91f94bcca80995b7ed16b92115235f58d28e636291a4
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a67149e6f2c803c5510419511ac904f9537eb4fbff5066e666ed08b44f9664f
+oid sha256:df72b23925eb5f82752cd028feed8cf7d2bbe1dbdf011029efc7554632b26ae2
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e59f03ce343bc2279a4caef20772b97445f7cad5f56f03c6fe562ef9297aba5
+oid sha256:bd1259a368e737ba331fab7b54a98c7cfc3dd87ed455bcbc28503bda235c71d3
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b75ef2c8e55abd504706b58ef3e0a8e29500c910d22cedece78b4bbdd0c43a
+oid sha256:5f2eac6df5cd35dc068eb0bab0d362a924c2221b17b5c9bfe0e42f4ba3c05c9c
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3e48ab19d013994e76ce74871eebcf792a7f0de0b1bc5e31a34b55c3911660
+oid sha256:4e7f8260a2f4cc917f2e6b69683488cb603bdd620504afe136b5dc796247fcec
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f313ad3307a61df4799cc55bebfd321f79a2d67e43e4af68c3ea5f2e8a2721
+oid sha256:41a93612851ee52955512369b8723183837a90f2506b353970cd64de58829b3d
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735207f6708877a90cb07d7ba5bda4e331561a0f2cd24f0dff22c21fa9a1d464
+oid sha256:5bde979dd08e67682f748b136bdd4f7c962a7cebec495023e183c816b6c75933
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1793671925447022,
-  "global_step": 820000,
+  "epoch": 1.1992968806052247,
+  "global_step": 830000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9846,11 +9846,131 @@
       "learning_rate": 2.2039381819638596e-05,
       "loss": 0.2894,
       "step": 820000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1974562300613417e-05,
+      "loss": 0.2893,
+      "step": 820500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1909901420919184e-05,
+      "loss": 0.2891,
+      "step": 821000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1845399357336326e-05,
+      "loss": 0.2891,
+      "step": 821500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1781056286210997e-05,
+      "loss": 0.2891,
+      "step": 822000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1716872383454674e-05,
+      "loss": 0.2892,
+      "step": 822500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1652847824543744e-05,
+      "loss": 0.2884,
+      "step": 823000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1588982784518853e-05,
+      "loss": 0.288,
+      "step": 823500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1525277437984636e-05,
+      "loss": 0.2889,
+      "step": 824000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1461731959109053e-05,
+      "loss": 0.2893,
+      "step": 824500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1398346521623e-05,
+      "loss": 0.2884,
+      "step": 825000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1335121298819867e-05,
+      "loss": 0.2891,
+      "step": 825500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1272056463554978e-05,
+      "loss": 0.2887,
+      "step": 826000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1209152188245214e-05,
+      "loss": 0.2887,
+      "step": 826500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.114640864486845e-05,
+      "loss": 0.2892,
+      "step": 827000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.1083826004963102e-05,
+      "loss": 0.2888,
+      "step": 827500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.1021404439627775e-05,
+      "loss": 0.2889,
+      "step": 828000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.09591441195206e-05,
+      "loss": 0.2878,
+      "step": 828500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.089704521485896e-05,
+      "loss": 0.2888,
+      "step": 829000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.083510789541883e-05,
+      "loss": 0.2879,
+      "step": 829500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.0773332330534513e-05,
+      "loss": 0.2887,
+      "step": 830000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.543772678797676e+22,
+  "total_flos": 5.6113757283593115e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd2e6a7da537ff760743918bcaefe9c986fc2c76a2e5c7636f4801ac5b5cd7b
+oid sha256:b63e12b39341c1c8d25b10dc8ca07cde5e82303726c5b23ac1fdd24345f08c2a
 size 449450757