Training in progress, step 990000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6e21575dd459731b96c75fb2eff44427788a2b21e2cba9f9983669023c697a
+oid sha256:eb4cd9e789adbd1802119018bcfc4f0b6dba2541ced8918776537c19936d2aa3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081e5eabe8ef9a2817820443cfba02d1a6ecee053832fff6fbfbe29c77150986
+oid sha256:21e636c80ed6aaf4e2b5d21598685c1a08b0a8d8edf7041e56552898357162ca
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26c3fd0e63c430cd827768cc149848f896e9fbf6df9ca8358e31c62102f594
+oid sha256:4c1caabd63b797b525c8b3557d0ed6bdcb32c060e6354cffd8a2f88412a58c50
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f60f9446cba0320cf9ced93c4b14816af8d6988d011f7cc2f5b01e8ada101d
+oid sha256:b2358905887cd0ce80c53b6e8a0174e039c4c5bd62c6c91c86f0312f9b46fcf7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.929814973846515,
-  "global_step": 980000,
+  "epoch": 11.041343698069438,
+  "global_step": 990000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -19606,11 +19606,211 @@
       "eval_samples_per_second": 887.915,
       "eval_steps_per_second": 13.916,
       "step": 980000
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.0145492062574731e-05,
+      "loss": 0.1798,
+      "step": 980500
+    },
+    {
+      "epoch": 10.94,
+      "learning_rate": 1.0138129010020992e-05,
+      "loss": 0.1797,
+      "step": 981000
+    },
+    {
+      "epoch": 10.94,
+      "eval_loss": 0.17310407757759094,
+      "eval_runtime": 2.575,
+      "eval_samples_per_second": 892.044,
+      "eval_steps_per_second": 13.981,
+      "step": 981000
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 1.0130956957154867e-05,
+      "loss": 0.1796,
+      "step": 981500
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 1.0123975923584488e-05,
+      "loss": 0.1795,
+      "step": 982000
+    },
+    {
+      "epoch": 10.95,
+      "eval_loss": 0.17133940756320953,
+      "eval_runtime": 2.6289,
+      "eval_samples_per_second": 873.748,
+      "eval_steps_per_second": 13.694,
+      "step": 982000
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 1.0117185928395721e-05,
+      "loss": 0.1797,
+      "step": 982500
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 1.0110586990152152e-05,
+      "loss": 0.1796,
+      "step": 983000
+    },
+    {
+      "epoch": 10.96,
+      "eval_loss": 0.17200584709644318,
+      "eval_runtime": 2.6007,
+      "eval_samples_per_second": 883.236,
+      "eval_steps_per_second": 13.843,
+      "step": 983000
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 1.0104179126895039e-05,
+      "loss": 0.1797,
+      "step": 983500
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 1.0097962356143219e-05,
+      "loss": 0.1797,
+      "step": 984000
+    },
+    {
+      "epoch": 10.97,
+      "eval_loss": 0.17025373876094818,
+      "eval_runtime": 2.5803,
+      "eval_samples_per_second": 890.197,
+      "eval_steps_per_second": 13.952,
+      "step": 984000
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 1.009193669489312e-05,
+      "loss": 0.1797,
+      "step": 984500
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 1.0086102159618668e-05,
+      "loss": 0.1796,
+      "step": 985000
+    },
+    {
+      "epoch": 10.99,
+      "eval_loss": 0.17083962261676788,
+      "eval_runtime": 2.5712,
+      "eval_samples_per_second": 893.348,
+      "eval_steps_per_second": 14.001,
+      "step": 985000
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 1.0080458766271252e-05,
+      "loss": 0.1798,
+      "step": 985500
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.0075006530279694e-05,
+      "loss": 0.1797,
+      "step": 986000
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.1690717339515686,
+      "eval_runtime": 2.588,
+      "eval_samples_per_second": 887.569,
+      "eval_steps_per_second": 13.911,
+      "step": 986000
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.0069745466550205e-05,
+      "loss": 0.1794,
+      "step": 986500
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 1.0064675589466339e-05,
+      "loss": 0.1796,
+      "step": 987000
+    },
+    {
+      "epoch": 11.01,
+      "eval_loss": 0.16997100412845612,
+      "eval_runtime": 2.5938,
+      "eval_samples_per_second": 885.56,
+      "eval_steps_per_second": 13.879,
+      "step": 987000
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 1.005979691288893e-05,
+      "loss": 0.1795,
+      "step": 987500
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 1.0055109450156098e-05,
+      "loss": 0.1791,
+      "step": 988000
+    },
+    {
+      "epoch": 11.02,
+      "eval_loss": 0.1697554588317871,
+      "eval_runtime": 2.5898,
+      "eval_samples_per_second": 886.931,
+      "eval_steps_per_second": 13.901,
+      "step": 988000
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 1.0050613214083197e-05,
+      "loss": 0.1797,
+      "step": 988500
+    },
+    {
+      "epoch": 11.03,
+      "learning_rate": 1.0046308216962759e-05,
+      "loss": 0.1795,
+      "step": 989000
+    },
+    {
+      "epoch": 11.03,
+      "eval_loss": 0.1698392927646637,
+      "eval_runtime": 2.6586,
+      "eval_samples_per_second": 863.992,
+      "eval_steps_per_second": 13.541,
+      "step": 989000
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 1.0042194470564472e-05,
+      "loss": 0.1796,
+      "step": 989500
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 1.0038271986135177e-05,
+      "loss": 0.1799,
+      "step": 990000
+    },
+    {
+      "epoch": 11.04,
+      "eval_loss": 0.16946464776992798,
+      "eval_runtime": 2.6152,
+      "eval_samples_per_second": 878.327,
+      "eval_steps_per_second": 13.766,
+      "step": 990000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.869770816498864e+22,
+  "total_flos": 6.9398656010816955e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081e5eabe8ef9a2817820443cfba02d1a6ecee053832fff6fbfbe29c77150986
+oid sha256:21e636c80ed6aaf4e2b5d21598685c1a08b0a8d8edf7041e56552898357162ca
 size 449471589