Training in progress, step 210000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a034e9e1a9ae7c11a38b09da94316f7af857583cc75efaab5288ad761a4759
+oid sha256:cfa0ab32e38b01ddbc573768dfaf0dfddabcc8a3d70f2bee44cb82fdf48bdbfb
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe293a94506a0e024ec476b57e64723da55912f72fe82601c25ed8e88dd3d77
+oid sha256:8385ab1df2ebd2cf00e4d352e48666514cc5adaf924696c86b3104a741aaa958
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b65aef852c56a6070eb0b0c0dcb2609bdee33892af326659c5e916144ee935
+oid sha256:43a0a20032cd9b1693c0df17b5ce36ac0de1b8a71ec2dce02e457215ca17de74
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50df4816cbaa34ba1b53e6066397f6b5dfa9e0b5a42191fa041b389e35141af5
+oid sha256:8ab74f841af25583fde1ca8fdb0c1861852ed361e9321c893b9e5b237758c199
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c375b0eb05f3b84a9ffd242709f5cafdfac9ec9f6eb782f404bfa519ad8d88
-size 14439
+oid sha256:064bb77ca4a934e34a95ea9287f27a0ff8cd1d559261fa08d942aff78c8d69b3
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1225a9177adba9ce38ceb1af0c8098a1a68d43fed76f6471ce68525b7fe2bef
+oid sha256:ebe0a4f01c3d254f50684a93345a2b350eaf4ce2ffbfd3ab184e7c48ab1cbf8f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2159e22012f5706c7baac54c9475075e6a80f8026c23532336808d0140a2feea
+oid sha256:4028538ec5575e9eae4ab14227f42ba25a4d5ad871aeb0a0910dce83388d0885
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5204915df8edf520dd956c8e88b1a505319e42237567e2e0d2cc11f8993db5
-size 14503
+oid sha256:53cbe542019d2f74f171c2183d760b9998750b9b6316341cb64d43d534f9c788
+size 14439

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0083ff5459b01e74d8269a09b7fb0407b955c9098992dc865792b4c832e05385
+oid sha256:893d43631edd1f00cc9f737c881bbde999bddaa7e8c8c4da0adc745254b97b30
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9a8f48c4b1e1e02dc723041280e57b4a38fe76785f0eae322407bb67501005
+oid sha256:537d3cd36d12dd1a3735216763e1c615e8f3bdd474a41fbef3b6c5cb46612706
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e461416c63c82734faef19b4949af829ad430bff342d30400b1c1da0cafb58f
+oid sha256:de6aa60c12b8dbcda06c27a65ac30e45d66753f2960bee09a7c0ea364ae7e103
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.127638714421398,
-  "global_step": 200000,
+  "epoch": 6.434020650142467,
+  "global_step": 210000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4006,11 +4006,211 @@
       "eval_samples_per_second": 1896.43,
       "eval_steps_per_second": 30.343,
       "step": 200000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 0.000212806399860385,
+      "loss": 0.3451,
+      "step": 200500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 0.00021236633098456196,
+      "loss": 0.3455,
+      "step": 201000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.783266544342041,
+      "eval_runtime": 0.5227,
+      "eval_samples_per_second": 1913.03,
+      "eval_steps_per_second": 30.608,
+      "step": 201000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.0002119256347597342,
+      "loss": 0.3448,
+      "step": 201500
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.000211484316005285,
+      "loss": 0.3454,
+      "step": 202000
+    },
+    {
+      "epoch": 6.19,
+      "eval_loss": 0.7877166867256165,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 1922.214,
+      "eval_steps_per_second": 30.755,
+      "step": 202000
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.00021104237954740554,
+      "loss": 0.3447,
+      "step": 202500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 0.00021059983021904215,
+      "loss": 0.3444,
+      "step": 203000
+    },
+    {
+      "epoch": 6.22,
+      "eval_loss": 0.7820906043052673,
+      "eval_runtime": 0.5318,
+      "eval_samples_per_second": 1880.364,
+      "eval_steps_per_second": 30.086,
+      "step": 203000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 0.00021015667285984336,
+      "loss": 0.3444,
+      "step": 203500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.00020971291231610707,
+      "loss": 0.3445,
+      "step": 204000
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.7963393330574036,
+      "eval_runtime": 0.5097,
+      "eval_samples_per_second": 1961.765,
+      "eval_steps_per_second": 31.388,
+      "step": 204000
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 0.0002092685534407274,
+      "loss": 0.3447,
+      "step": 204500
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 0.00020882360109314197,
+      "loss": 0.3442,
+      "step": 205000
+    },
+    {
+      "epoch": 6.28,
+      "eval_loss": 0.7794355154037476,
+      "eval_runtime": 0.539,
+      "eval_samples_per_second": 1855.442,
+      "eval_steps_per_second": 29.687,
+      "step": 205000
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 0.0002083780601392783,
+      "loss": 0.3442,
+      "step": 205500
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.0002079319354515008,
+      "loss": 0.3442,
+      "step": 206000
+    },
+    {
+      "epoch": 6.31,
+      "eval_loss": 0.7892481088638306,
+      "eval_runtime": 0.5219,
+      "eval_samples_per_second": 1916.151,
+      "eval_steps_per_second": 30.658,
+      "step": 206000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00020748523190855772,
+      "loss": 0.3439,
+      "step": 206500
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 0.0002070379543955273,
+      "loss": 0.3437,
+      "step": 207000
+    },
+    {
+      "epoch": 6.34,
+      "eval_loss": 0.7817493081092834,
+      "eval_runtime": 0.5139,
+      "eval_samples_per_second": 1945.926,
+      "eval_steps_per_second": 31.135,
+      "step": 207000
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.00020659010780376487,
+      "loss": 0.3436,
+      "step": 207500
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 0.00020614169703084896,
+      "loss": 0.3436,
+      "step": 208000
+    },
+    {
+      "epoch": 6.37,
+      "eval_loss": 0.7851976156234741,
+      "eval_runtime": 0.5495,
+      "eval_samples_per_second": 1819.926,
+      "eval_steps_per_second": 29.119,
+      "step": 208000
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 0.0002056927269805279,
+      "loss": 0.3439,
+      "step": 208500
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.00020524320256266635,
+      "loss": 0.3435,
+      "step": 209000
+    },
+    {
+      "epoch": 6.4,
+      "eval_loss": 0.7840863466262817,
+      "eval_runtime": 0.5295,
+      "eval_samples_per_second": 1888.573,
+      "eval_steps_per_second": 30.217,
+      "step": 209000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 0.0002047931286931912,
+      "loss": 0.3436,
+      "step": 209500
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.00020434251029403824,
+      "loss": 0.3435,
+      "step": 210000
+    },
+    {
+      "epoch": 6.43,
+      "eval_loss": 0.7881864309310913,
+      "eval_runtime": 0.5367,
+      "eval_samples_per_second": 1863.216,
+      "eval_steps_per_second": 29.811,
+      "step": 210000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 6.389694847778145e+21,
+  "total_flos": 6.709181986552645e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe293a94506a0e024ec476b57e64723da55912f72fe82601c25ed8e88dd3d77
+oid sha256:8385ab1df2ebd2cf00e4d352e48666514cc5adaf924696c86b3104a741aaa958
 size 102501541