Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73045cc3d0c4c73c7a304fc419b67fc70f5890b81e163e1a8a2a9bce7006b524
+oid sha256:6fafdf3dc4053a478a09fce7cd9cc15053b19a33d6b58c36ca5436ccd97913a6
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3b0e28c0382823d55f599e6bdbd134ef629f7e5342a0597c5271470ab8336f
+oid sha256:a64deb57f36a27064cc4d0b280f90a72b59990f15860b6537f49879bcfb34aa6
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b56ac7e2d49a255e26944a75af12a85964edcdc6e46d62983b15a37947b570
+oid sha256:be2d0bd68e065eb85049372f4abb8ffbf27c8d2f5fa7ea3177bedf20fcf99e26
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff90b5853455d439dc2f89f06dce4dd6575b564c20e1387efdf3e7aaf00ff95
+oid sha256:f1a5b5ce099930b883dc48f18ec0c4aafea3d1e465572f0a3a7b87ea92fa07c4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d301e6ea6f21d7b1880ccef9bfd4fbd3e69c49a007d8e22935d9fcb510c3a5
+oid sha256:93b838f5687f66973e8201c7e8dadb656fe97b315b3bbf77e5a2d000f34b91f5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c442b548bbec55775013c97b41312e4ef25472d89576d14c167f1843976d866
-size 14439
+oid sha256:e876d9529d9370e353ad6f8fd0c6b88167a47f97421642e8d8095904566a3c54
+size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3070a38ac5fbd287025149ce6d76fcde28fce103ebe6d7d53ffc82820503320f
+oid sha256:49e1f1672d845e202794ad0ccc105b119321c0e3d067197efd0a488ecef1d0bf
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a360366ed887a9dd09f52f770c090125f631416090ce14483f193c8d020d2c
+oid sha256:cb26a39e3710aced6be33af5040431a47fb2753a31b1d0a91fe360a3e160bbe4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0865afaa175e5470997944056f52744d7830792f5c6d1a926cbcaa46aeddd290
-size 14503
+oid sha256:ae3dd349d6db4f4551324cbce8200b29561e6b98026e7f91e8180d039a45cc34
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7d552313ab0fd670a96222e4be3c0d1d9dc06059697a7fd34d8ad13955978a
-size 14503
+oid sha256:57599eaa96b9ac595309802eb671733bad63e8bd6aa65ca65eb41f0a31f5c9bd
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff31836ff2c96f7fb19d95df664b507273477e3a4f87dcce611b28b7e31820b
+oid sha256:5810d5d1337eca8d561357c6c9e9920258e5fc2b2f0f70ea4b52e4984949eec8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.451055485768559,
-  "global_step": 80000,
+  "epoch": 2.757437421489629,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1606,11 +1606,211 @@
       "eval_samples_per_second": 1953.312,
       "eval_steps_per_second": 31.253,
       "step": 80000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00029034050133765947,
+      "loss": 0.3873,
+      "step": 80500
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.00029016767524635804,
+      "loss": 0.3872,
+      "step": 81000
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 0.7831702828407288,
+      "eval_runtime": 0.5564,
+      "eval_samples_per_second": 1797.202,
+      "eval_steps_per_second": 28.755,
+      "step": 81000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00028999337098301585,
+      "loss": 0.3865,
+      "step": 81500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.0002898175904537964,
+      "loss": 0.3858,
+      "step": 82000
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 0.7806258797645569,
+      "eval_runtime": 0.5186,
+      "eval_samples_per_second": 1928.174,
+      "eval_steps_per_second": 30.851,
+      "step": 82000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002896403355810075,
+      "loss": 0.3859,
+      "step": 82500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.00028946160830307997,
+      "loss": 0.3854,
+      "step": 83000
+    },
+    {
+      "epoch": 2.54,
+      "eval_loss": 0.7836428880691528,
+      "eval_runtime": 0.545,
+      "eval_samples_per_second": 1834.936,
+      "eval_steps_per_second": 29.359,
+      "step": 83000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.00028928141057454665,
+      "loss": 0.3849,
+      "step": 83500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.0002890997443660211,
+      "loss": 0.3848,
+      "step": 84000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.7852834463119507,
+      "eval_runtime": 0.5158,
+      "eval_samples_per_second": 1938.61,
+      "eval_steps_per_second": 31.018,
+      "step": 84000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.00028891661166417586,
+      "loss": 0.3844,
+      "step": 84500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00028873201447172074,
+      "loss": 0.3838,
+      "step": 85000
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.7852866053581238,
+      "eval_runtime": 0.5265,
+      "eval_samples_per_second": 1899.356,
+      "eval_steps_per_second": 30.39,
+      "step": 85000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002885459548073812,
+      "loss": 0.3837,
+      "step": 85500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.0002883584347058758,
+      "loss": 0.383,
+      "step": 86000
+    },
+    {
+      "epoch": 2.63,
+      "eval_loss": 0.7794146537780762,
+      "eval_runtime": 0.5219,
+      "eval_samples_per_second": 1916.094,
+      "eval_steps_per_second": 30.657,
+      "step": 86000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00028816945621789437,
+      "loss": 0.3831,
+      "step": 86500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002879790214100753,
+      "loss": 0.3823,
+      "step": 87000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.7845750451087952,
+      "eval_runtime": 0.5135,
+      "eval_samples_per_second": 1947.28,
+      "eval_steps_per_second": 31.156,
+      "step": 87000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.0002877871323649833,
+      "loss": 0.382,
+      "step": 87500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002875937911810861,
+      "loss": 0.3818,
+      "step": 88000
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.7793565988540649,
+      "eval_runtime": 0.5472,
+      "eval_samples_per_second": 1827.624,
+      "eval_steps_per_second": 29.242,
+      "step": 88000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.000287398999972732,
+      "loss": 0.3817,
+      "step": 88500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.00028720276087012636,
+      "loss": 0.3809,
+      "step": 89000
+    },
+    {
+      "epoch": 2.73,
+      "eval_loss": 0.786903440952301,
+      "eval_runtime": 0.522,
+      "eval_samples_per_second": 1915.886,
+      "eval_steps_per_second": 30.654,
+      "step": 89000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.0002870050760193086,
+      "loss": 0.3806,
+      "step": 89500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00028680594758212854,
+      "loss": 0.3805,
+      "step": 90000
+    },
+    {
+      "epoch": 2.76,
+      "eval_loss": 0.7848221659660339,
+      "eval_runtime": 0.5114,
+      "eval_samples_per_second": 1955.578,
+      "eval_steps_per_second": 31.289,
+      "step": 90000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 2.5558811342920483e+21,
+  "total_flos": 2.8753682730665483e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3b0e28c0382823d55f599e6bdbd134ef629f7e5342a0597c5271470ab8336f
+oid sha256:a64deb57f36a27064cc4d0b280f90a72b59990f15860b6537f49879bcfb34aa6
 size 102501541