Training in progress, step 1000000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c84155e298a5a6b7ee070a8179e83bcd232eb2e5869a2fab62635fe434a15b
+oid sha256:f4ad35154e8068fb3a11d53f7dbc996f2907fbf771e6b088b60198e7662bd085
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6119a41cc84dfc82b1ad8e160d2de4f6723c4c70df2567e7b05d5135b2ad413c
+oid sha256:6aa0642d46fe211727fefc5ac6e0bc28efa8511d1f0d9e5eee1987fa821600bc
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d92331d191f9b54e8682c7179f1d46d8e4298cbee5bf860f80c01313d919cbf
+oid sha256:ffef422be2539ff2f38d9ef02e7d220a1b72474f08bb4e90499c7aaeff187041
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3f3f7f2089f141dbb6bfd17083ac633b398668fbdd29b4239ed78cd16828ef
+oid sha256:463b459e546b940eb314ddfec0443ea23a3be76cf5287309632d30e7fc449578
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1e11f0bc52abbbd19f8d4cb2af2cb9140b19cf7c5678a2b90ba0e9593a2025
+oid sha256:1dd41b22e2b316b6844ef149b2ed9245b6df6b6b1ef3eaa82e48507bd8f6361f
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffc19433b361587fa636d9fe7f366ad621d886a3e88e7b929e925c972115064
+oid sha256:6b5227791b50d3a4ce6a4303e20bb6f7a630db623b90933290f4b8be2d663b28
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf40a9092f2a61c65fa8d4b01ad107ecd14742f4e2c480971b7e313c2ab669b
+oid sha256:d8b3d25a9338c36376e5ff28e0294df3d7c9ae55a2257f11d59bab9a6b7bff56
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d8ccac7b1580c03e5bd6e78ceed5d6b1e846215ceb31ec6a8e03829af4c92e
+oid sha256:850d36f688ac21bc9b8eca3e25be925153622f77bb798cc74ba77c97e9987016
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a564015df3012aed298103a98abad0123fee1b00b18b24191670937f37a6281
+oid sha256:bae6388e81de2bc43d53517beccd69cbe0291d07b9778d77d34130d2c4dd9ade
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3839c7b56c36b9afc190821fb76a047c055639f3ce0f32d8cdce397cba6fa5f
+oid sha256:2368b26770136755d6ac3415a40478eaa9855ef850310208946463b5a771ae00
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8600853d84ba2918d905e70ba99b5bea80c1839bef1da439315875bb3ad462d
+oid sha256:d3af8ce8ebbd21d4c5d2eeb030d14d5a15759925617012e21e6e139dfa9889ef
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5181718895735843,
-  "global_step": 990000,
+  "epoch": 1.538101577634107,
+  "global_step": 1000000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11886,11 +11886,139 @@
       "learning_rate": 1.0038271986135177e-05,
       "loss": 0.2827,
       "step": 990000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.003454077439879e-05,
+      "loss": 0.2826,
+      "step": 990500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0031000845556304e-05,
+      "loss": 0.2828,
+      "step": 991000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0027652209285743e-05,
+      "loss": 0.2829,
+      "step": 991500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0024494874742152e-05,
+      "loss": 0.2832,
+      "step": 992000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0021528850557572e-05,
+      "loss": 0.283,
+      "step": 992500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0018754144840986e-05,
+      "loss": 0.2821,
+      "step": 993000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0016170765178345e-05,
+      "loss": 0.2822,
+      "step": 993500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0013778718632507e-05,
+      "loss": 0.2826,
+      "step": 994000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0011578011743233e-05,
+      "loss": 0.2828,
+      "step": 994500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.000956865052717e-05,
+      "loss": 0.2827,
+      "step": 995000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0007750640477843e-05,
+      "loss": 0.2829,
+      "step": 995500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0006123986565623e-05,
+      "loss": 0.2829,
+      "step": 996000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0004688693237708e-05,
+      "loss": 0.2832,
+      "step": 996500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0003444764418138e-05,
+      "loss": 0.2835,
+      "step": 997000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0002392203507781e-05,
+      "loss": 0.2832,
+      "step": 997500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.000153101338428e-05,
+      "loss": 0.2826,
+      "step": 998000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.00008611964021e-05,
+      "loss": 0.283,
+      "step": 998500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.00003827543925e-05,
+      "loss": 0.2832,
+      "step": 999000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0000095688663532e-05,
+      "loss": 0.2827,
+      "step": 999500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1e-05,
+      "loss": 0.2828,
+      "step": 1000000
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.3599591553211212,
+      "eval_runtime": 50.3004,
+      "eval_samples_per_second": 2519.919,
+      "eval_steps_per_second": 9.861,
+      "step": 1000000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 6.693099686599179e+22,
+  "total_flos": 6.7607019944302705e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6119a41cc84dfc82b1ad8e160d2de4f6723c4c70df2567e7b05d5135b2ad413c
+oid sha256:6aa0642d46fe211727fefc5ac6e0bc28efa8511d1f0d9e5eee1987fa821600bc
 size 449450757