Training in progress, step 350000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9697a4208e91543945338a4f4e4b0865355f4f56763ee61fbd92200c086baa3e
+oid sha256:85908e2b98581215a0ac8cbf941b1d1e0a4b20f9b117671316dac735f1680a0a
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724b6d72f0d9d61428cae11f63e8d73911644650c2b3a36828f03dde6fa5b8fd
+oid sha256:b4b9d197cab81c7a1095d7eb78f234bda3652ddb59d597c931a0dd43203299b1
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9af55dec33596d4e4eab80f0d6e856e790d4e6b88e6dd783d976e786aca8d
+oid sha256:34df7360092c998e783422dc04d58c14439cc8c291ce068c1e5ac0a940265f80
 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": 7.921899391877723,
-  "global_step": 340000,
+  "epoch": 8.154896432815303,
+  "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": 1583.125,
       "eval_steps_per_second": 25.209,
       "step": 340000
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 8.347109939861605e-05,
+      "loss": 0.2623,
+      "step": 340500
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 8.305438908125285e-05,
+      "loss": 0.2624,
+      "step": 341000
+    },
+    {
+      "epoch": 7.95,
+      "eval_loss": 0.24358774721622467,
+      "eval_runtime": 1.4516,
+      "eval_samples_per_second": 1514.19,
+      "eval_steps_per_second": 24.111,
+      "step": 341000
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 8.263846554956402e-05,
+      "loss": 0.2621,
+      "step": 341500
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 8.222333335202254e-05,
+      "loss": 0.2618,
+      "step": 342000
+    },
+    {
+      "epoch": 7.97,
+      "eval_loss": 0.24512818455696106,
+      "eval_runtime": 1.4448,
+      "eval_samples_per_second": 1521.327,
+      "eval_steps_per_second": 24.225,
+      "step": 342000
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 8.18089970284477e-05,
+      "loss": 0.2616,
+      "step": 342500
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 8.1395461109955e-05,
+      "loss": 0.2617,
+      "step": 343000
+    },
+    {
+      "epoch": 7.99,
+      "eval_loss": 0.24306875467300415,
+      "eval_runtime": 1.4195,
+      "eval_samples_per_second": 1548.387,
+      "eval_steps_per_second": 24.656,
+      "step": 343000
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 8.098273011890726e-05,
+      "loss": 0.2614,
+      "step": 343500
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 8.057080856886426e-05,
+      "loss": 0.2614,
+      "step": 344000
+    },
+    {
+      "epoch": 8.02,
+      "eval_loss": 0.24457786977291107,
+      "eval_runtime": 1.4376,
+      "eval_samples_per_second": 1528.919,
+      "eval_steps_per_second": 24.346,
+      "step": 344000
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 8.015970096453414e-05,
+      "loss": 0.2616,
+      "step": 344500
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 7.974941180172382e-05,
+      "loss": 0.2617,
+      "step": 345000
+    },
+    {
+      "epoch": 8.04,
+      "eval_loss": 0.24457286298274994,
+      "eval_runtime": 1.4399,
+      "eval_samples_per_second": 1526.508,
+      "eval_steps_per_second": 24.307,
+      "step": 345000
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 7.933994556728976e-05,
+      "loss": 0.2614,
+      "step": 345500
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 7.893130673908927e-05,
+      "loss": 0.2612,
+      "step": 346000
+    },
+    {
+      "epoch": 8.06,
+      "eval_loss": 0.24429433047771454,
+      "eval_runtime": 1.4483,
+      "eval_samples_per_second": 1517.626,
+      "eval_steps_per_second": 24.166,
+      "step": 346000
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 7.852349978593091e-05,
+      "loss": 0.2616,
+      "step": 346500
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 7.811652916752633e-05,
+      "loss": 0.261,
+      "step": 347000
+    },
+    {
+      "epoch": 8.08,
+      "eval_loss": 0.24454987049102783,
+      "eval_runtime": 1.4519,
+      "eval_samples_per_second": 1513.913,
+      "eval_steps_per_second": 24.107,
+      "step": 347000
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 7.771039933444092e-05,
+      "loss": 0.261,
+      "step": 347500
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 7.730511472804544e-05,
+      "loss": 0.261,
+      "step": 348000
+    },
+    {
+      "epoch": 8.11,
+      "eval_loss": 0.24601994454860687,
+      "eval_runtime": 1.4399,
+      "eval_samples_per_second": 1526.461,
+      "eval_steps_per_second": 24.307,
+      "step": 348000
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 7.690067978046758e-05,
+      "loss": 0.2611,
+      "step": 348500
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 7.649709891454298e-05,
+      "loss": 0.261,
+      "step": 349000
+    },
+    {
+      "epoch": 8.13,
+      "eval_loss": 0.24198506772518158,
+      "eval_runtime": 1.4613,
+      "eval_samples_per_second": 1504.096,
+      "eval_steps_per_second": 23.951,
+      "step": 349000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 7.609437654376742e-05,
+      "loss": 0.2606,
+      "step": 349500
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 7.569251707224812e-05,
+      "loss": 0.2608,
+      "step": 350000
+    },
+    {
+      "epoch": 8.15,
+      "eval_loss": 0.24344965815544128,
+      "eval_runtime": 1.444,
+      "eval_samples_per_second": 1522.152,
+      "eval_steps_per_second": 24.238,
+      "step": 350000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.0862545239396653e+22,
+  "total_flos": 1.1182029881180246e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724b6d72f0d9d61428cae11f63e8d73911644650c2b3a36828f03dde6fa5b8fd
+oid sha256:b4b9d197cab81c7a1095d7eb78f234bda3652ddb59d597c931a0dd43203299b1
 size 102501541