Training in progress, step 350000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc8c307e09c2ee7140e86493006e9375ce3828ae419bfd73dd8e77040dc9432
+oid sha256:836759fedb3c04c1e36e698a6cd3899f162ede3f32c56386ef24d49bc2163cbb
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db82336fde2ca798cca2552947b8f10e1dae6da490a1f40a713b479f4e821a2d
+oid sha256:998435b0f9ce53e66113d7bec14d46ccd8a7918639830988194463c1e5db1349
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c78bed16f0847936846c879bca5d8a536a9a3a59d08245d05fbfcc52edb347e
+oid sha256:4c8523a23b2126f1e0b2250304237778c9e938ca58ea61d2aaa56f9cdd412f84
 size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8b7b2390f7d5ddc6390197696d6aa0925d05d2ef38d7290149a060e461ae44
-size 14439
+oid sha256:e1c4bd77bedf03001af3b9ef889b6dfe87e92115f91a7e639d6fdb4f2831fa70
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9313e219a1869a99c69734744312a0517c71c6052de358efa7a1080ce122046c
+oid sha256:ec34896b527ce9812ef17fb169750711c41b89b6349b3cbcdfa7be94e1a6baf1
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416722c1edd0afe1ceb2e8573cb1ac6a96bfc6996efd996f3b5e077d838af66f
+oid sha256:8d73239bf94e1fdf6dfa1faf7bc1d6eac9849348001cddeb5d7b0b44851b2a55
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09f85aaae937e7534df6bd43ac24aa3578e31af78965f5ed61081b83c1046da
+oid sha256:d82a5834c903434e02d3959ef5a762fdae6236f6271145404caf4e2755eebe70
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4e2a6a930e95dd4bd770a07c72d2fac11a8c63fc0f19ad213c91a2d9c6320b
-size 14439
+oid sha256:1f0e5e58f841742c4dc32af4083c8e6dd9bd1edca9f29e95f20db66083298fd7
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c68c66e599d0d64dd47fb2d9ad7cf41ba596f6439d733b5b753368eb3156e13
-size 14503
+oid sha256:c5cc705bc82ed7c42464d2fba05f65cc617ebee401f1689c9b01b9b6c7d23636
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12b1e861045ff9922be9ad05050d7efb0f92e7378cdd8573f5012b3fb1b1b30
+oid sha256:280859229d77bcf03b4604363e8dcb5eb462972def25bd8dc14847679a550bcd
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0f100ea6da4a9ff03fc2cc9b0cbbba13b42ccc41293a1d6143e5a081a97f70
+oid sha256:3aecc6465a886ff601ea303358a61f89a30e07c965e206675258095a3d963058
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.416985814516377,
-  "global_step": 340000,
+  "epoch": 10.723367750237447,
+  "global_step": 350000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6806,11 +6806,211 @@
       "eval_samples_per_second": 1984.543,
       "eval_steps_per_second": 31.753,
       "step": 340000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 8.347109939861605e-05,
+      "loss": 0.3251,
+      "step": 340500
+    },
+    {
+      "epoch": 10.45,
+      "learning_rate": 8.305438908125285e-05,
+      "loss": 0.3249,
+      "step": 341000
+    },
+    {
+      "epoch": 10.45,
+      "eval_loss": 0.7789011001586914,
+      "eval_runtime": 0.52,
+      "eval_samples_per_second": 1923.154,
+      "eval_steps_per_second": 30.77,
+      "step": 341000
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 8.263846554956402e-05,
+      "loss": 0.3247,
+      "step": 341500
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 8.222333335202254e-05,
+      "loss": 0.3248,
+      "step": 342000
+    },
+    {
+      "epoch": 10.48,
+      "eval_loss": 0.7844606041908264,
+      "eval_runtime": 0.4974,
+      "eval_samples_per_second": 2010.3,
+      "eval_steps_per_second": 32.165,
+      "step": 342000
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 8.18089970284477e-05,
+      "loss": 0.3247,
+      "step": 342500
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 8.1395461109955e-05,
+      "loss": 0.3244,
+      "step": 343000
+    },
+    {
+      "epoch": 10.51,
+      "eval_loss": 0.7819501161575317,
+      "eval_runtime": 0.518,
+      "eval_samples_per_second": 1930.544,
+      "eval_steps_per_second": 30.889,
+      "step": 343000
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 8.098273011890726e-05,
+      "loss": 0.3248,
+      "step": 343500
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 8.057080856886426e-05,
+      "loss": 0.3242,
+      "step": 344000
+    },
+    {
+      "epoch": 10.54,
+      "eval_loss": 0.7827469110488892,
+      "eval_runtime": 0.5044,
+      "eval_samples_per_second": 1982.423,
+      "eval_steps_per_second": 31.719,
+      "step": 344000
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 8.015970096453414e-05,
+      "loss": 0.3245,
+      "step": 344500
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 7.974941180172382e-05,
+      "loss": 0.3245,
+      "step": 345000
+    },
+    {
+      "epoch": 10.57,
+      "eval_loss": 0.7778306007385254,
+      "eval_runtime": 0.5124,
+      "eval_samples_per_second": 1951.443,
+      "eval_steps_per_second": 31.223,
+      "step": 345000
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 7.933994556728976e-05,
+      "loss": 0.3245,
+      "step": 345500
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 7.893130673908927e-05,
+      "loss": 0.3241,
+      "step": 346000
+    },
+    {
+      "epoch": 10.6,
+      "eval_loss": 0.7757638096809387,
+      "eval_runtime": 0.5021,
+      "eval_samples_per_second": 1991.816,
+      "eval_steps_per_second": 31.869,
+      "step": 346000
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 7.852349978593091e-05,
+      "loss": 0.3243,
+      "step": 346500
+    },
+    {
+      "epoch": 10.63,
+      "learning_rate": 7.811652916752633e-05,
+      "loss": 0.3243,
+      "step": 347000
+    },
+    {
+      "epoch": 10.63,
+      "eval_loss": 0.7844104766845703,
+      "eval_runtime": 0.4987,
+      "eval_samples_per_second": 2005.114,
+      "eval_steps_per_second": 32.082,
+      "step": 347000
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 7.771039933444092e-05,
+      "loss": 0.3243,
+      "step": 347500
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 7.730511472804544e-05,
+      "loss": 0.324,
+      "step": 348000
+    },
+    {
+      "epoch": 10.66,
+      "eval_loss": 0.7820024490356445,
+      "eval_runtime": 0.5033,
+      "eval_samples_per_second": 1986.81,
+      "eval_steps_per_second": 31.789,
+      "step": 348000
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 7.690067978046758e-05,
+      "loss": 0.3237,
+      "step": 348500
+    },
+    {
+      "epoch": 10.69,
+      "learning_rate": 7.649709891454298e-05,
+      "loss": 0.3237,
+      "step": 349000
+    },
+    {
+      "epoch": 10.69,
+      "eval_loss": 0.7792369723320007,
+      "eval_runtime": 0.5182,
+      "eval_samples_per_second": 1929.628,
+      "eval_steps_per_second": 30.874,
+      "step": 349000
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 7.609437654376742e-05,
+      "loss": 0.3236,
+      "step": 349500
+    },
+    {
+      "epoch": 10.72,
+      "learning_rate": 7.569251707224812e-05,
+      "loss": 0.3235,
+      "step": 350000
+    },
+    {
+      "epoch": 10.72,
+      "eval_loss": 0.7803741693496704,
+      "eval_runtime": 0.5045,
+      "eval_samples_per_second": 1982.304,
+      "eval_steps_per_second": 31.717,
+      "step": 350000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.0862482838813242e+22,
+  "total_flos": 1.1181969977587741e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db82336fde2ca798cca2552947b8f10e1dae6da490a1f40a713b479f4e821a2d
+oid sha256:998435b0f9ce53e66113d7bec14d46ccd8a7918639830988194463c1e5db1349
 size 102501541