Training in progress, step 590000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3c98677de897190cfb61fcdb47a41a233aacb3947cfaaf5565a6afc239a9e0
+oid sha256:ccf7cac5a21a11d7f667ccf92a06d4ca4f6e11529886f97a81cee946646a7850
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
+oid sha256:6dfc2dd7ec4e8c1ccc6143bbc6f13f079f3e7e48a8bbfe20e040b742b8d0a1df
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0acf92adb8fe29e7f8f300892a64ae6b1061f78cbc741a04875cceecbd7627bb
-size 14503
+oid sha256:2f3d7d4e29826fad65749e3d1c71437aab80b1c0083abdcf52c0c2924f0e5e69
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989d83467172119d42cc5db629615122c0d05d39b97d6151f3073b83b05e95f1
-size 14439
+oid sha256:17829d91164c4f44a41a5ead32db30cb5aee27cae3b78beefecb92d0468bafdc
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb6b551f6971cdac4e633aeb80c6604a5c29c6604766e95edb5b993ce689e66
+oid sha256:a63261dcff7584c8844400c561ac2e5b385953523dee796cb56c42af169cadd9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7228d0f23743ac31eeebdd713de3352c2963513ff68c7b3a41fefd85d589e485
-size 14439
+oid sha256:b41591d972d5c0406eef4b610a30a04b97cf79722da627acb09c85c762f5f46f
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2528712b13528834db613d1453dd7fb04ea3b7a1940fa3521b7d0be4a96c0a
+oid sha256:bf17ad9f6f8f5230f179dea9ee53bd043cf1c420455dc89092d4dbf5e8505225
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.856719654282529,
-  "global_step": 580000,
+  "epoch": 9.0094217172874,
+  "global_step": 590000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4298,11 +4298,85 @@
       "eval_samples_per_second": 932.263,
       "eval_steps_per_second": 14.916,
       "step": 580000
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 6.71107648105703e-05,
+      "loss": 0.2564,
+      "step": 581000
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 6.688330797899925e-05,
+      "loss": 0.2562,
+      "step": 582000
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 6.665599458947072e-05,
+      "loss": 0.2562,
+      "step": 583000
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 6.642882712784742e-05,
+      "loss": 0.2561,
+      "step": 584000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 6.620180807839639e-05,
+      "loss": 0.2561,
+      "step": 585000
+    },
+    {
+      "epoch": 8.93,
+      "eval_runtime": 0.9936,
+      "eval_samples_per_second": 1006.405,
+      "eval_steps_per_second": 16.102,
+      "step": 585000
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 6.597493992376152e-05,
+      "loss": 0.2557,
+      "step": 586000
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 6.574822514493664e-05,
+      "loss": 0.2554,
+      "step": 587000
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 6.552166622123824e-05,
+      "loss": 0.2554,
+      "step": 588000
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 6.52952656302784e-05,
+      "loss": 0.2556,
+      "step": 589000
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 6.506902584793773e-05,
+      "loss": 0.2553,
+      "step": 590000
+    },
+    {
+      "epoch": 9.01,
+      "eval_runtime": 0.9015,
+      "eval_samples_per_second": 1109.201,
+      "eval_steps_per_second": 17.747,
+      "step": 590000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.065809883214944e+22,
+  "total_flos": 4.135909487177143e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4bdcb08582dcc416cc4a3a9ae8bcb9040fe1e5dce27da0219c313edd1229bf9
+oid sha256:6dfc2dd7ec4e8c1ccc6143bbc6f13f079f3e7e48a8bbfe20e040b742b8d0a1df
 size 449471589