Training in progress, step 900000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aed45f0ab31dea98b9869760d36ab73a26078c09333a23350a1212c72042c48
+oid sha256:7e68aaa7f20cf2655b5ee95587161e9676e99cc34136556add0f9965734e7755
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c213d1a42d199003850d981d6ccc1a53b07b35352b3c677b2fec2729c3a474
+oid sha256:59e51d656bcb12cf1d2e57afead6fbd882c17c7bfca89d40bc32ba44fc16d622
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77bc69e9635ccd1de21423522e341a85a08863f86590b713104bba2dbfd70bb
+oid sha256:55ad6fff41d308df46b9a1b2f331c0f91fef2419029183c0886a7d45a3462024
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1993aafd21a33893d293353cc2d3a986655d484aa3f8d8bd3ce1158082956b62
+oid sha256:a40d19463da3fc8105dffb32921ceec5ee75e4844d0eca7759a43c7f4b14bbba
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31a0dbc0a9de5b13d8d236df1a529fa25f2a462a9bcc23416d4f0397bad521d
+oid sha256:bfd73f45d2e32308ab057499cc1554bb0a6b5dce90d1016017772831b0342b94
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2118e2247b5fdbceb9d1ec4a69c6b9d09754ac3081a89daca9da9f417d9a57c
+oid sha256:90198646614d410142ba8b69e323e9efb6043fdb55e8f55a8936dc33416f4c8d
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce1b40c469ef20ff3c2e73618244894f6c048059642c597ebc6bc915a80cce6
+oid sha256:3d370228b86aa2250b5e7dcf8be134cb35dc855b6e23853f0ea74181606aa91c
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8dd4b4014883403bd302ffd7cbfd4827bc6596e89d4a566a074b59e6257940
+oid sha256:052919acbfa40e0f835c2850fde0f02534bb1eb7e31ee0f5a540aca7e0f25da3
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c955d0a8374d68c8c7fd0b4a59ac81688e461d16a4ab83367d33bbcd82c828c2
+oid sha256:e5c995fa02cdc8d504061c7c2c431119a7ac4cd2ff34fa2e7bd0545514b474d1
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d88d03c1c6897f3e815db204f99493002f497118b104ebefc70815e22888c1
+oid sha256:e9f95e8365bd03b8115e7ed1873af4534b3ec6096af843d6743d8130c920c2cc
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d5e819bb6a0b170d191713e427e3ac82a202a5b895fa2fdb4da78756f26177
+oid sha256:c027d2ad1a7ec1ccedf4c28ec4cf8e5a70643d6805bfcfeb4cb2085d818a7bdc
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3188750089683596,
-  "global_step": 890000,
+  "epoch": 1.338804697028882,
+  "global_step": 900000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10686,11 +10686,131 @@
       "learning_rate": 1.4580487478037748e-05,
       "loss": 0.2854,
       "step": 890000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4539396316922552e-05,
+      "loss": 0.2862,
+      "step": 890500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4498484122598232e-05,
+      "loss": 0.2858,
+      "step": 891000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4457751006917137e-05,
+      "loss": 0.2853,
+      "step": 891500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4417197081242083e-05,
+      "loss": 0.2856,
+      "step": 892000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4376822456445926e-05,
+      "loss": 0.2859,
+      "step": 892500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.433662724291136e-05,
+      "loss": 0.2859,
+      "step": 893000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4296611550530563e-05,
+      "loss": 0.2859,
+      "step": 893500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4256775488704904e-05,
+      "loss": 0.2859,
+      "step": 894000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4217119166344665e-05,
+      "loss": 0.2851,
+      "step": 894500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4177642691868717e-05,
+      "loss": 0.2856,
+      "step": 895000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4138346173204218e-05,
+      "loss": 0.2855,
+      "step": 895500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4099229717786368e-05,
+      "loss": 0.2857,
+      "step": 896000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.406029343255806e-05,
+      "loss": 0.2852,
+      "step": 896500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4021537423969588e-05,
+      "loss": 0.2858,
+      "step": 897000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3982961797978431e-05,
+      "loss": 0.2853,
+      "step": 897500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3944566660048863e-05,
+      "loss": 0.2851,
+      "step": 898000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3906352115151725e-05,
+      "loss": 0.285,
+      "step": 898500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3868318267764128e-05,
+      "loss": 0.2854,
+      "step": 899000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3830465221869146e-05,
+      "loss": 0.2855,
+      "step": 899500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3792793080955574e-05,
+      "loss": 0.2852,
+      "step": 900000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.017029328628566e+22,
+  "total_flos": 6.0846394803756095e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c213d1a42d199003850d981d6ccc1a53b07b35352b3c677b2fec2729c3a474
+oid sha256:59e51d656bcb12cf1d2e57afead6fbd882c17c7bfca89d40bc32ba44fc16d622
 size 449450757