Training in progress, step 680000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5bbd83e76bfaea16133e5f4d584916d5b8420b3bb185b8e5801362569d4f69
+oid sha256:55e5d00d2cd7677d6c62be4befe12ceb99e54aa60af5a94e2947d4ae516faaf9
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d66a36b6e02c5a5390d3c9dec0faf002f0a21fa7c7b5ef13a837f052f84e013
+oid sha256:fdc51c6b56a4707511277be7ae25e9ceecb4c1ce951b8055606cd763924bc386
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cb7e1a11524752d8ec0a2746c2da7c87cd4d3afc083cf4a0df43b88ed43337
+oid sha256:c5cdde6fe1592597eb282f0c1adb0c3419a3256dc73cdd2ad8141425d3367aa1
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3471c82ac0fc930f64e5adbb6702a0e555d4edfcc1c2dab4ff36db308349b1
+oid sha256:f3c1fcd1d388653574e603211bfc56c68bd7e902268c20d36edbd0c9c2c455ef
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fa69a09ea23ef88cf7df6a3190bd2ee20d350293163871b5d1dbdf1a735794
+oid sha256:7c40db2c616071d5de318f5594c12558c6be71cc3185a20daba66531013c4562
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dac01a61c51f51dbd4c3cc5d50cf7d5af4a9f263667ab541575cfd5deab9645
+oid sha256:abefb15d42bbdbc9d96701958a628e317cbc9e1c294d8e8a76d57bee1d799f4e
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221b7d8fdca30ab22892af203b971ac82533d02ad7492e4e8b5068d84fa6a3ca
+oid sha256:b5923e1314a170c5cdfcf9c517450e0d99f3907dcef2765f816ff70cb6461364
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548649d9f5f2f112c52d8a0f4a7c44c0a8f1f18e8bb96cd91be7066faf617949
+oid sha256:9887b880e911257bf7ed749ed55b173537ca64c83004df1495db6bddcf868768
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426865c62dd7c19a97ed19d06fe6fa6770f12ecb7a2997d9a0820ed2f9c93c21
+oid sha256:8f6acc5ebd016f0085aa2c2381f509e3d8d43d4652dca878fe5c1e4ef96b864c
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e886c38b9308720d6c044b1f01de3ee4919b1d3a6edb19ef015bd4926793ada4
+oid sha256:b5eeebb55361b678fa47ae3e37f81a72056ae8266b737b634b72a45e273417dd
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50de55c4a72c38e6722f7cb77ebe9f35ce412c17a797d93c631371b39d861204
+oid sha256:390e03fe3cc05eeca400d470fa9829ae91cb8c4659d5322fb96cb732dc98e5e1
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3393624634673895,
-  "global_step": 670000,
+  "epoch": 1.3593529479967534,
+  "global_step": 680000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8046,11 +8046,131 @@
       "learning_rate": 4.770611859149185e-05,
       "loss": 0.2987,
       "step": 670000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.7603473052657374e-05,
+      "loss": 0.2986,
+      "step": 670500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.7500916084690564e-05,
+      "loss": 0.298,
+      "step": 671000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.7398447967978165e-05,
+      "loss": 0.2991,
+      "step": 671500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.729606898266411e-05,
+      "loss": 0.2981,
+      "step": 672000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.71937794086487e-05,
+      "loss": 0.2989,
+      "step": 672500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.709157952558768e-05,
+      "loss": 0.2984,
+      "step": 673000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.698946961289163e-05,
+      "loss": 0.2981,
+      "step": 673500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.688744994972514e-05,
+      "loss": 0.2986,
+      "step": 674000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.6785520815006085e-05,
+      "loss": 0.2979,
+      "step": 674500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.668368248740485e-05,
+      "loss": 0.2984,
+      "step": 675000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.658193524534351e-05,
+      "loss": 0.2985,
+      "step": 675500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.6480279366995116e-05,
+      "loss": 0.2986,
+      "step": 676000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.637871513028303e-05,
+      "loss": 0.2981,
+      "step": 676500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.6277242812879914e-05,
+      "loss": 0.2978,
+      "step": 677000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.617586269220728e-05,
+      "loss": 0.2978,
+      "step": 677500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.607457504543447e-05,
+      "loss": 0.2977,
+      "step": 678000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.597338014947801e-05,
+      "loss": 0.2975,
+      "step": 678500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.5872278281000955e-05,
+      "loss": 0.2978,
+      "step": 679000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.577126971641189e-05,
+      "loss": 0.2978,
+      "step": 679500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.567035473186444e-05,
+      "loss": 0.2978,
+      "step": 680000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 4.529677636130487e+22,
+  "total_flos": 4.597284714742531e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d66a36b6e02c5a5390d3c9dec0faf002f0a21fa7c7b5ef13a837f052f84e013
+oid sha256:fdc51c6b56a4707511277be7ae25e9ceecb4c1ce951b8055606cd763924bc386
 size 449450757