Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583b1f1834e02218d89c3b697d47dd796ee6e2f54da76dbfa4b2b4a392308637
+oid sha256:267d3df636a0162d33e130374595442a55c8d8e98b166e9f3f7d0083011ee911
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1ac07a8fd5b7f18f94228f9f3e9b88d618a44073c792161d704c98526bced7
+oid sha256:9f2373aeb4dd8a73f874cd12197ac54e4d9ac9c719856821eb66aa7befcac8c3
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
+oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
 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": 10.717863883128684,
-  "global_step": 460000,
+  "epoch": 10.950860924066264,
+  "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": 1542.873,
       "eval_steps_per_second": 24.568,
       "step": 460000
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 1.4920092237448903e-05,
+      "loss": 0.2514,
+      "step": 460500
+    },
+    {
+      "epoch": 10.74,
+      "learning_rate": 1.4797008356541874e-05,
+      "loss": 0.2513,
+      "step": 461000
+    },
+    {
+      "epoch": 10.74,
+      "eval_loss": 0.2357269674539566,
+      "eval_runtime": 1.4097,
+      "eval_samples_per_second": 1559.248,
+      "eval_steps_per_second": 24.829,
+      "step": 461000
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 1.4675457713088947e-05,
+      "loss": 0.2513,
+      "step": 461500
+    },
+    {
+      "epoch": 10.76,
+      "learning_rate": 1.4555441636348494e-05,
+      "loss": 0.2516,
+      "step": 462000
+    },
+    {
+      "epoch": 10.76,
+      "eval_loss": 0.2352001965045929,
+      "eval_runtime": 1.4391,
+      "eval_samples_per_second": 1527.384,
+      "eval_steps_per_second": 24.321,
+      "step": 462000
+    },
+    {
+      "epoch": 10.78,
+      "learning_rate": 1.4436961438797095e-05,
+      "loss": 0.2512,
+      "step": 462500
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 1.4320018416115206e-05,
+      "loss": 0.2511,
+      "step": 463000
+    },
+    {
+      "epoch": 10.79,
+      "eval_loss": 0.23254527151584625,
+      "eval_runtime": 1.4508,
+      "eval_samples_per_second": 1514.977,
+      "eval_steps_per_second": 24.124,
+      "step": 463000
+    },
+    {
+      "epoch": 10.8,
+      "learning_rate": 1.4204613847173003e-05,
+      "loss": 0.2513,
+      "step": 463500
+    },
+    {
+      "epoch": 10.81,
+      "learning_rate": 1.4090748994016354e-05,
+      "loss": 0.2515,
+      "step": 464000
+    },
+    {
+      "epoch": 10.81,
+      "eval_loss": 0.23643817007541656,
+      "eval_runtime": 1.4271,
+      "eval_samples_per_second": 1540.18,
+      "eval_steps_per_second": 24.525,
+      "step": 464000
+    },
+    {
+      "epoch": 10.82,
+      "learning_rate": 1.3978425101853049e-05,
+      "loss": 0.2513,
+      "step": 464500
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 1.3867643399039165e-05,
+      "loss": 0.2509,
+      "step": 465000
+    },
+    {
+      "epoch": 10.83,
+      "eval_loss": 0.2379205971956253,
+      "eval_runtime": 1.4615,
+      "eval_samples_per_second": 1503.93,
+      "eval_steps_per_second": 23.948,
+      "step": 465000
+    },
+    {
+      "epoch": 10.85,
+      "learning_rate": 1.3758405097065648e-05,
+      "loss": 0.2515,
+      "step": 465500
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 1.3650711390545131e-05,
+      "loss": 0.2511,
+      "step": 466000
+    },
+    {
+      "epoch": 10.86,
+      "eval_loss": 0.2360716015100479,
+      "eval_runtime": 1.4528,
+      "eval_samples_per_second": 1512.979,
+      "eval_steps_per_second": 24.092,
+      "step": 466000
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 1.3544563457198657e-05,
+      "loss": 0.2514,
+      "step": 466500
+    },
+    {
+      "epoch": 10.88,
+      "learning_rate": 1.343996245784307e-05,
+      "loss": 0.2513,
+      "step": 467000
+    },
+    {
+      "epoch": 10.88,
+      "eval_loss": 0.2349902093410492,
+      "eval_runtime": 1.4197,
+      "eval_samples_per_second": 1548.226,
+      "eval_steps_per_second": 24.653,
+      "step": 467000
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 1.3336909536378107e-05,
+      "loss": 0.2511,
+      "step": 467500
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 1.3235405819774022e-05,
+      "loss": 0.2509,
+      "step": 468000
+    },
+    {
+      "epoch": 10.9,
+      "eval_loss": 0.23496830463409424,
+      "eval_runtime": 1.4553,
+      "eval_samples_per_second": 1510.368,
+      "eval_steps_per_second": 24.05,
+      "step": 468000
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 1.3135452418059208e-05,
+      "loss": 0.2513,
+      "step": 468500
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 1.3037050424308027e-05,
+      "loss": 0.2512,
+      "step": 469000
+    },
+    {
+      "epoch": 10.93,
+      "eval_loss": 0.23394964635372162,
+      "eval_runtime": 1.4438,
+      "eval_samples_per_second": 1522.345,
+      "eval_steps_per_second": 24.241,
+      "step": 469000
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.2940200914628945e-05,
+      "loss": 0.251,
+      "step": 469500
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 1.2844904948152644e-05,
+      "loss": 0.2508,
+      "step": 470000
+    },
+    {
+      "epoch": 10.95,
+      "eval_loss": 0.23325932025909424,
+      "eval_runtime": 1.4563,
+      "eval_samples_per_second": 1509.326,
+      "eval_steps_per_second": 24.034,
+      "step": 470000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4696383413717932e+22,
+  "total_flos": 1.5015870552492432e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1ac07a8fd5b7f18f94228f9f3e9b88d618a44073c792161d704c98526bced7
+oid sha256:9f2373aeb4dd8a73f874cd12197ac54e4d9ac9c719856821eb66aa7befcac8c3
 size 102501541