Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d995b453b0a04bbd02c89c1e2a0b01d5ea8104964b6e575d18b8b2b852f0697a
-size 893440453
+oid sha256:61a48a0d3e06f6d9c4dbeec9dd5221abf842041a606411a3eb4c011b2b6ce157
+size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72110dc5fec392448defa8c45f957d936420ff0753177d0b17b355c59e5f2deb
+oid sha256:c91ea0abf3868a060d7ed4c0f943d81a8c31c59f1a4fbcac20e4c228f3d5306b
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f5f3d7fc7de25a1729f017d3d6dc7b79407bb23fd390423966864300b65a09
+oid sha256:cc4e58968df8d8de7b76afb49e34b862e7070d202e80b8a826f72b6f635c2cde
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3a210506f64342e553d4bf48e6fadb6effff0f5dbb7697fdabf52d12772ab8
+oid sha256:594120123fbd1fad56e4287c2d069c836d6ed898e13f3bf2eb5ae1995a6abf18
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e2297daa1dc20f8b8863f55ad4770a767d9eba0c8a71f314c37ad1c3871cd7
+oid sha256:7c2f001850d67d834ad6f5341284dffa53108ee6ecb8b9fb6837cfd65ff83d24
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8ca75222d5b686b4dcb8add7e5e6c8e4bb0aa54a48b6c9650ff1b0ab1d9de6
+oid sha256:e245827ca7b63a97e06cc9b0093c1d74b595472c8bc308d4290564e966646b17
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0fae1242e86663273cf365a3c63b1a3921cad2d2396be93b9c702039cd5d4a
+oid sha256:ed21c5a14597e7b8ab428400d75245e02257e563d47635efe05355069d0b1928
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f998ac055776992254d4db1276dbf13aa8f00ccf4471740b472226d6ea583d
+oid sha256:01cbc2bdac8629204109c016e1ffa5b5eef157a33d3511366f9e2f7031a7ee33
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069cccc1e69b521d4ca315007273f764ce63546923ca059673907772b710280e
+oid sha256:9b2cc8ec76a8c7fadc25b1ad07a0e21e6f5b2945d2efe03f93181052bc36951e
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d375627d89cc809d43a8a304898ce0f67be3ee70ad132436bc25574b87fe6663
+oid sha256:0b7f27abef02152cc0e2907407c48c40e2c6425985f5175919eb4dcfb4c58016
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8747acdc6c067a30e87070a5c0421cb4d690fbe00d316895f653b3a392344a3f
+oid sha256:3fe2d09bf8807c63a805e572e94358dda9d6462e44109f7e340ab10774501127
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11994290717618414,
-  "global_step": 60000,
+  "epoch": 0.13993339170554817,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -726,11 +726,131 @@
       "learning_rate": 0.00014996172801386482,
       "loss": 0.4117,
       "step": 60000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014995780552943551,
+      "loss": 0.4106,
+      "step": 60500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014995369178303722,
+      "loss": 0.4098,
+      "step": 61000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001499493867859168,
+      "loss": 0.4095,
+      "step": 61500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001499448905498439,
+      "loss": 0.4081,
+      "step": 62000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014994020308711106,
+      "loss": 0.408,
+      "step": 62500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014993532441053364,
+      "loss": 0.4074,
+      "step": 63000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001499302545334498,
+      "loss": 0.4066,
+      "step": 63500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001499249934697203,
+      "loss": 0.4055,
+      "step": 64000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014991954123372875,
+      "loss": 0.4049,
+      "step": 64500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001499138978403813,
+      "loss": 0.4038,
+      "step": 65000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014990806330510687,
+      "loss": 0.4039,
+      "step": 65500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014990203764385677,
+      "loss": 0.4029,
+      "step": 66000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014989582087310494,
+      "loss": 0.4028,
+      "step": 66500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014988941300984784,
+      "loss": 0.4022,
+      "step": 67000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00014988281407160426,
+      "loss": 0.4013,
+      "step": 67500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001498760240764155,
+      "loss": 0.4003,
+      "step": 68000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00014986904304284512,
+      "loss": 0.3996,
+      "step": 68500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000149861870989979,
+      "loss": 0.3994,
+      "step": 69000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00014985450793742527,
+      "loss": 0.399,
+      "step": 69500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001498469539053142,
+      "loss": 0.3993,
+      "step": 70000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.0564501264363663e+21,
+  "total_flos": 4.73259935611438e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72110dc5fec392448defa8c45f957d936420ff0753177d0b17b355c59e5f2deb
+oid sha256:c91ea0abf3868a060d7ed4c0f943d81a8c31c59f1a4fbcac20e4c228f3d5306b
 size 449450757