Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c5dc947e6cf77a2f13cd5b7f75774d9ee18e8bb1706815f27839917ebc139f
+oid sha256:73045cc3d0c4c73c7a304fc419b67fc70f5890b81e163e1a8a2a9bce7006b524
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6143f947ad34a118a277142b729e7aec8108ac65db132781f90f89fd6d2d7d
+oid sha256:0b3b0e28c0382823d55f599e6bdbd134ef629f7e5342a0597c5271470ab8336f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fe73b1b40978075c02727ad4956e4d1b16707096f7223f142676127872cbe0
+oid sha256:52b56ac7e2d49a255e26944a75af12a85964edcdc6e46d62983b15a37947b570
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc72bddb53bad0049947d6480bf573724b62938239cf1810454d762aa23edd89
-size 14439
+oid sha256:eff90b5853455d439dc2f89f06dce4dd6575b564c20e1387efdf3e7aaf00ff95
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dac322e61dd5ec1258ef6267f0eb26ddd545115f42b9dd4d8d424f54644612b
+oid sha256:01d301e6ea6f21d7b1880ccef9bfd4fbd3e69c49a007d8e22935d9fcb510c3a5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f401fa11e5a9225fec902704af9ab763f5d60dd51eae4b0592a34621c9a469e2
-size 14503
+oid sha256:0c442b548bbec55775013c97b41312e4ef25472d89576d14c167f1843976d866
+size 14439

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a7924f074d2835ad5940aa65be7efd984818695ea768631ffe6ce95141de0
+oid sha256:3070a38ac5fbd287025149ce6d76fcde28fce103ebe6d7d53ffc82820503320f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a6bfbbc7a2b661e5e8652e559ad6f4c64c79db32e2bc10cca19b276788c2b6
+oid sha256:01a360366ed887a9dd09f52f770c090125f631416090ce14483f193c8d020d2c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a373660ab148daebea2355c821d057c46749d2baadf42884aac334d565f1e5ae
+oid sha256:0865afaa175e5470997944056f52744d7830792f5c6d1a926cbcaa46aeddd290
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d3442500daea86a3c50feeabd94befbadee050f02e7edb3bf2746c36f1a779
+oid sha256:bf7d552313ab0fd670a96222e4be3c0d1d9dc06059697a7fd34d8ad13955978a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
+oid sha256:8ff31836ff2c96f7fb19d95df664b507273477e3a4f87dcce611b28b7e31820b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1446735500474894,
-  "global_step": 70000,
+  "epoch": 2.451055485768559,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1406,11 +1406,211 @@
       "eval_samples_per_second": 1922.99,
       "eval_steps_per_second": 30.768,
       "step": 70000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.0002934838153624519,
+      "loss": 0.3962,
+      "step": 70500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00029334092796560427,
+      "loss": 0.3958,
+      "step": 71000
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 0.7898754477500916,
+      "eval_runtime": 0.5162,
+      "eval_samples_per_second": 1937.227,
+      "eval_steps_per_second": 30.996,
+      "step": 71000
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0002931965276945326,
+      "loss": 0.3951,
+      "step": 71500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0002930506161283751,
+      "loss": 0.3947,
+      "step": 72000
+    },
+    {
+      "epoch": 2.21,
+      "eval_loss": 0.7828860878944397,
+      "eval_runtime": 0.5502,
+      "eval_samples_per_second": 1817.401,
+      "eval_steps_per_second": 29.078,
+      "step": 72000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00029290319486279724,
+      "loss": 0.3944,
+      "step": 72500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0002927542655099744,
+      "loss": 0.3935,
+      "step": 73000
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.7836081385612488,
+      "eval_runtime": 0.518,
+      "eval_samples_per_second": 1930.433,
+      "eval_steps_per_second": 30.887,
+      "step": 73000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00029260382969857417,
+      "loss": 0.3936,
+      "step": 73500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00029245188907373845,
+      "loss": 0.393,
+      "step": 74000
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.7833809852600098,
+      "eval_runtime": 0.5265,
+      "eval_samples_per_second": 1899.502,
+      "eval_steps_per_second": 30.392,
+      "step": 74000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.0002922984452970655,
+      "loss": 0.3923,
+      "step": 74500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.000292143500046592,
+      "loss": 0.392,
+      "step": 75000
+    },
+    {
+      "epoch": 2.3,
+      "eval_loss": 0.7891106009483337,
+      "eval_runtime": 0.549,
+      "eval_samples_per_second": 1821.565,
+      "eval_steps_per_second": 29.145,
+      "step": 75000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.0002919870550167743,
+      "loss": 0.3917,
+      "step": 75500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002918291119184702,
+      "loss": 0.3913,
+      "step": 76000
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 0.7858054041862488,
+      "eval_runtime": 0.5293,
+      "eval_samples_per_second": 1889.27,
+      "eval_steps_per_second": 30.228,
+      "step": 76000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.0002916696724789201,
+      "loss": 0.3906,
+      "step": 76500
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00029150873844172823,
+      "loss": 0.3904,
+      "step": 77000
+    },
+    {
+      "epoch": 2.36,
+      "eval_loss": 0.7869090437889099,
+      "eval_runtime": 0.5095,
+      "eval_samples_per_second": 1962.553,
+      "eval_steps_per_second": 31.401,
+      "step": 77000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.00029134631156684334,
+      "loss": 0.3898,
+      "step": 77500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.0002911823936305398,
+      "loss": 0.3893,
+      "step": 78000
+    },
+    {
+      "epoch": 2.39,
+      "eval_loss": 0.7837140560150146,
+      "eval_runtime": 0.5128,
+      "eval_samples_per_second": 1950.24,
+      "eval_steps_per_second": 31.204,
+      "step": 78000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0002910169864253979,
+      "loss": 0.3892,
+      "step": 78500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0002908500917602842,
+      "loss": 0.3886,
+      "step": 79000
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 0.787075936794281,
+      "eval_runtime": 0.5289,
+      "eval_samples_per_second": 1890.813,
+      "eval_steps_per_second": 30.253,
+      "step": 79000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.00029068171146033226,
+      "loss": 0.3883,
+      "step": 79500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.0002905118473669218,
+      "loss": 0.3877,
+      "step": 80000
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.7844729423522949,
+      "eval_runtime": 0.512,
+      "eval_samples_per_second": 1953.312,
+      "eval_steps_per_second": 31.253,
+      "step": 80000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 2.2363939955175483e+21,
+  "total_flos": 2.5558811342920483e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6143f947ad34a118a277142b729e7aec8108ac65db132781f90f89fd6d2d7d
+oid sha256:0b3b0e28c0382823d55f599e6bdbd134ef629f7e5342a0597c5271470ab8336f
 size 102501541