Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b547411c79d357104c70e5661a49a33c4c727f3979f31a84e358578efcb1bf5d
+oid sha256:5de66d4a93d929dbf59bf082b441005c55284067d059fcb692905debf93d43ec
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9908cf9403ac4306b20a0d3eb86bc03da4da8a781371917c67d6447e4350b51
+oid sha256:b866106aa5570064c241431938c823c9b3d9c0359a68aaf12dac64797d2c681f
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f347b3051d84f6b39fd81f0a25c5ca1660537f9dd78ea3f5348e6e0fe62d0
+oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60fd80961b777bf4901f5c7189278f8f31f61a50c51a19e170f6a1919a5ce33
+oid sha256:8d15e11a6de6abd55121a73bc214cc950fb971f927ae2b1d5067145da50de5d0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.260528194147037,
-  "global_step": 460000,
+  "epoch": 10.483583154889365,
+  "global_step": 470000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9206,11 +9206,211 @@
       "eval_samples_per_second": 1173.539,
       "eval_steps_per_second": 18.392,
       "step": 460000
+    },
+    {
+      "epoch": 10.27,
+      "learning_rate": 1.4920092237448903e-05,
+      "loss": 0.2554,
+      "step": 460500
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 1.4797008356541874e-05,
+      "loss": 0.2548,
+      "step": 461000
+    },
+    {
+      "epoch": 10.28,
+      "eval_loss": 0.2381051927804947,
+      "eval_runtime": 1.9705,
+      "eval_samples_per_second": 1165.71,
+      "eval_steps_per_second": 18.27,
+      "step": 461000
+    },
+    {
+      "epoch": 10.29,
+      "learning_rate": 1.4675457713088947e-05,
+      "loss": 0.2547,
+      "step": 461500
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 1.4555441636348494e-05,
+      "loss": 0.2549,
+      "step": 462000
+    },
+    {
+      "epoch": 10.31,
+      "eval_loss": 0.23718567192554474,
+      "eval_runtime": 2.0107,
+      "eval_samples_per_second": 1142.393,
+      "eval_steps_per_second": 17.904,
+      "step": 462000
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 1.4436961438797095e-05,
+      "loss": 0.2547,
+      "step": 462500
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 1.4320018416115206e-05,
+      "loss": 0.2548,
+      "step": 463000
+    },
+    {
+      "epoch": 10.33,
+      "eval_loss": 0.23715750873088837,
+      "eval_runtime": 2.0434,
+      "eval_samples_per_second": 1124.132,
+      "eval_steps_per_second": 17.618,
+      "step": 463000
+    },
+    {
+      "epoch": 10.34,
+      "learning_rate": 1.4204613847173003e-05,
+      "loss": 0.2547,
+      "step": 463500
+    },
+    {
+      "epoch": 10.35,
+      "learning_rate": 1.4090748994016354e-05,
+      "loss": 0.2547,
+      "step": 464000
+    },
+    {
+      "epoch": 10.35,
+      "eval_loss": 0.23930229246616364,
+      "eval_runtime": 2.02,
+      "eval_samples_per_second": 1137.119,
+      "eval_steps_per_second": 17.822,
+      "step": 464000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 1.3978425101853049e-05,
+      "loss": 0.2545,
+      "step": 464500
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 1.3867643399039165e-05,
+      "loss": 0.2546,
+      "step": 465000
+    },
+    {
+      "epoch": 10.37,
+      "eval_loss": 0.24023665487766266,
+      "eval_runtime": 2.0161,
+      "eval_samples_per_second": 1139.319,
+      "eval_steps_per_second": 17.856,
+      "step": 465000
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 1.3758405097065648e-05,
+      "loss": 0.2547,
+      "step": 465500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.3650711390545131e-05,
+      "loss": 0.2549,
+      "step": 466000
+    },
+    {
+      "epoch": 10.39,
+      "eval_loss": 0.2383406162261963,
+      "eval_runtime": 2.0372,
+      "eval_samples_per_second": 1127.524,
+      "eval_steps_per_second": 17.671,
+      "step": 466000
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 1.3544563457198657e-05,
+      "loss": 0.2546,
+      "step": 466500
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 1.343996245784307e-05,
+      "loss": 0.2545,
+      "step": 467000
+    },
+    {
+      "epoch": 10.42,
+      "eval_loss": 0.23841743171215057,
+      "eval_runtime": 1.9888,
+      "eval_samples_per_second": 1154.948,
+      "eval_steps_per_second": 18.101,
+      "step": 467000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 1.3336909536378107e-05,
+      "loss": 0.2549,
+      "step": 467500
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 1.3235405819774022e-05,
+      "loss": 0.2544,
+      "step": 468000
+    },
+    {
+      "epoch": 10.44,
+      "eval_loss": 0.2374790459871292,
+      "eval_runtime": 2.0476,
+      "eval_samples_per_second": 1121.805,
+      "eval_steps_per_second": 17.582,
+      "step": 468000
+    },
+    {
+      "epoch": 10.45,
+      "learning_rate": 1.3135452418059208e-05,
+      "loss": 0.2543,
+      "step": 468500
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.3037050424308027e-05,
+      "loss": 0.2544,
+      "step": 469000
+    },
+    {
+      "epoch": 10.46,
+      "eval_loss": 0.2366662174463272,
+      "eval_runtime": 2.0397,
+      "eval_samples_per_second": 1126.142,
+      "eval_steps_per_second": 17.65,
+      "step": 469000
+    },
+    {
+      "epoch": 10.47,
+      "learning_rate": 1.2940200914628945e-05,
+      "loss": 0.2547,
+      "step": 469500
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 1.2844904948152644e-05,
+      "loss": 0.255,
+      "step": 470000
+    },
+    {
+      "epoch": 10.48,
+      "eval_loss": 0.23585031926631927,
+      "eval_runtime": 1.91,
+      "eval_samples_per_second": 1202.649,
+      "eval_steps_per_second": 18.849,
+      "step": 470000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4696123841012847e+22,
+  "total_flos": 1.5015610979787347e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9908cf9403ac4306b20a0d3eb86bc03da4da8a781371917c67d6447e4350b51
+oid sha256:b866106aa5570064c241431938c823c9b3d9c0359a68aaf12dac64797d2c681f
 size 102501541