Training in progress, step 280000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865e933af4111e3e4f4cf4bf498d36815529ed4df215ad8bdae33e309cd54198
+oid sha256:3d7d06e2c6420caccfb1dcda8898dc956eb9f8ad24fe7c47892d4aa4fe3524bf
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fbf2df0e9906787b8fc9db6246359052bee10be441671294b625a0595b9c0e2
+oid sha256:8b167d637cc3d331f7ff3b72e6e4702ade2043062cd5ae9c61947ce023c5c60e
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e5881300ba49425517624dfafb2b4b061510ced00f1f0393d364f868fb9286
+oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb61348726887e329b19406ea4e3e39ac391edeec6dfd8508b3cb524aa33e28
+oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.022483940042827,
-  "global_step": 270000,
+  "epoch": 6.245538900785154,
+  "global_step": 280000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5406,11 +5406,211 @@
       "eval_samples_per_second": 1169.619,
       "eval_steps_per_second": 18.331,
       "step": 270000
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.00014733147931802578,
+      "loss": 0.2733,
+      "step": 270500
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 0.00014685268692538238,
+      "loss": 0.273,
+      "step": 271000
+    },
+    {
+      "epoch": 6.04,
+      "eval_loss": 0.2563098967075348,
+      "eval_runtime": 1.9603,
+      "eval_samples_per_second": 1171.784,
+      "eval_steps_per_second": 18.365,
+      "step": 271000
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 0.00014637398363044946,
+      "loss": 0.2732,
+      "step": 271500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00014589537466824955,
+      "loss": 0.2732,
+      "step": 272000
+    },
+    {
+      "epoch": 6.07,
+      "eval_loss": 0.2550007402896881,
+      "eval_runtime": 1.9875,
+      "eval_samples_per_second": 1155.744,
+      "eval_steps_per_second": 18.114,
+      "step": 272000
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 0.00014541686527277356,
+      "loss": 0.2729,
+      "step": 272500
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 0.00014493846067692358,
+      "loss": 0.2759,
+      "step": 273000
+    },
+    {
+      "epoch": 6.09,
+      "eval_loss": 0.2564890682697296,
+      "eval_runtime": 1.9877,
+      "eval_samples_per_second": 1155.615,
+      "eval_steps_per_second": 18.112,
+      "step": 273000
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.00014446016611245567,
+      "loss": 0.279,
+      "step": 273500
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.00014398198680992252,
+      "loss": 0.2778,
+      "step": 274000
+    },
+    {
+      "epoch": 6.11,
+      "eval_loss": 0.25714361667633057,
+      "eval_runtime": 2.0307,
+      "eval_samples_per_second": 1131.141,
+      "eval_steps_per_second": 17.728,
+      "step": 274000
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 0.00014350392799861636,
+      "loss": 0.2758,
+      "step": 274500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 0.0001430259949065118,
+      "loss": 0.275,
+      "step": 275000
+    },
+    {
+      "epoch": 6.13,
+      "eval_loss": 0.258448988199234,
+      "eval_runtime": 1.9657,
+      "eval_samples_per_second": 1168.538,
+      "eval_steps_per_second": 18.314,
+      "step": 275000
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.0001425481927602085,
+      "loss": 0.2749,
+      "step": 275500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 0.0001420705267848743,
+      "loss": 0.2742,
+      "step": 276000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.25592052936553955,
+      "eval_runtime": 1.9618,
+      "eval_samples_per_second": 1170.879,
+      "eval_steps_per_second": 18.351,
+      "step": 276000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.00014159300220418757,
+      "loss": 0.2742,
+      "step": 276500
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.0001411156242402808,
+      "loss": 0.2741,
+      "step": 277000
+    },
+    {
+      "epoch": 6.18,
+      "eval_loss": 0.2545378506183624,
+      "eval_runtime": 1.9657,
+      "eval_samples_per_second": 1168.513,
+      "eval_steps_per_second": 18.314,
+      "step": 277000
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 0.0001406383981136829,
+      "loss": 0.2726,
+      "step": 277500
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.00014016132904326226,
+      "loss": 0.2723,
+      "step": 278000
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 0.25342997908592224,
+      "eval_runtime": 1.92,
+      "eval_samples_per_second": 1196.358,
+      "eval_steps_per_second": 18.75,
+      "step": 278000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 0.00013968442224616989,
+      "loss": 0.2721,
+      "step": 278500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 0.00013920768293778195,
+      "loss": 0.2722,
+      "step": 279000
+    },
+    {
+      "epoch": 6.22,
+      "eval_loss": 0.25338229537010193,
+      "eval_runtime": 1.9729,
+      "eval_samples_per_second": 1164.267,
+      "eval_steps_per_second": 18.247,
+      "step": 279000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 0.00013873111633164336,
+      "loss": 0.2722,
+      "step": 279500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.00013825472763941,
+      "loss": 0.2722,
+      "step": 280000
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.25419288873672485,
+      "eval_runtime": 1.9659,
+      "eval_samples_per_second": 1168.404,
+      "eval_steps_per_second": 18.312,
+      "step": 280000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 8.625982021343008e+21,
+  "total_flos": 8.945469160117508e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fbf2df0e9906787b8fc9db6246359052bee10be441671294b625a0595b9c0e2
+oid sha256:8b167d637cc3d331f7ff3b72e6e4702ade2043062cd5ae9c61947ce023c5c60e
 size 102501541