Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e2116038f17a755ee0cd7f714c11f53fb07e5f62178c545ddce403c568ffbe
+oid sha256:dfd6bf6424245454271decd3b53eca84bb0231c75269a1abfef86fc10e306e13
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6673bee6889f96f4d0585736b0bbd0104ce06075881649e694ae573ad1d2887a
+oid sha256:05568a72287e960fd9739070140c44a287f370c2fcded0e2c9e42000a5ecda50
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644e2fc163f368345d150d3fc83a57447c36fc56a8c5b1ac9505e0d54bf78bd0
+oid sha256:6ba591c6f74b15a56dee3a71187bae3451fe611d14ab4c6b5094ba97f5b2e1bd
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9725305d551fdabba33dd56f81db3b2c581f84aafc700effd4e6475b7ec812
-size 14439
+oid sha256:9b3b1d8b9ec088f9488e7777a87dcba6709bc61a5820efc403674b616e4790ed
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe151312b54baa9a4e64116f572138b7b71dec85430cd296cb3640e4c2da8a4
+oid sha256:38db8a281134056cc67716d0423f4a90c16aea7e8a53b20d38460d854f2fb474
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368b6ac98a14548e894c6dec52e2926741be3331b9c05acbb8210a7533733def
+oid sha256:3b3991a2efc9d121e256fe106ba687ac6c896be2424603b102f4091356c237e3
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb22d9d447646758c04766cf11ca8c2e8fc19a36cd697a9779fc029a142baac3
+oid sha256:cfe479370cc5e540b724877394cc13eb749f3953b33b916c9a22b3165f5dbb7e
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978268c9f7cbaa0bf6afcfb4a36b2945ad3b7df5c70456c1598647d77f700d81
-size 14503
+oid sha256:6080f58c6154f51a2b844dd6ced9f6d46e00dd93181694ec96024dbb4b15f736
+size 14439

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea73efb8fdbffbda3c38be20fe382b5f7cbbd8a80c55ee21bf5ba148273fa6a6
-size 14503
+oid sha256:c4291e6d684d83f32e6a530eca103a0c81e9858aece41197b882687fab12530d
+size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363c6a12aae6b2a1c1924495d50178e5b2b9c07c6657605723562b286ea4de81
-size 14503
+oid sha256:b8638e3fa087e0a193aeb627c3597747b6e37bf1ecc2043b8e409a9b8a85efb9
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d798ff13d72fe751bc0ea721c37eb1e98064dde5819b90f3504db53fdceee97
+oid sha256:53a074c65f43dfe683b5f0e988de79e3365c939ebb4b13c8f9ce84b59bdb64a7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.012714850332424,
-  "global_step": 490000,
+  "epoch": 15.319096786053494,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9806,11 +9806,211 @@
       "eval_samples_per_second": 2008.198,
       "eval_steps_per_second": 32.131,
       "step": 490000
+    },
+    {
+      "epoch": 15.03,
+      "learning_rate": 1.0286124377900624e-05,
+      "loss": 0.3123,
+      "step": 490500
+    },
+    {
+      "epoch": 15.04,
+      "learning_rate": 1.0256807270282153e-05,
+      "loss": 0.3122,
+      "step": 491000
+    },
+    {
+      "epoch": 15.04,
+      "eval_loss": 0.7738854885101318,
+      "eval_runtime": 0.4992,
+      "eval_samples_per_second": 2003.188,
+      "eval_steps_per_second": 32.051,
+      "step": 491000
+    },
+    {
+      "epoch": 15.06,
+      "learning_rate": 1.0229073051029455e-05,
+      "loss": 0.3124,
+      "step": 491500
+    },
+    {
+      "epoch": 15.07,
+      "learning_rate": 1.020292202343952e-05,
+      "loss": 0.3125,
+      "step": 492000
+    },
+    {
+      "epoch": 15.07,
+      "eval_loss": 0.7788605690002441,
+      "eval_runtime": 0.5071,
+      "eval_samples_per_second": 1971.996,
+      "eval_steps_per_second": 31.552,
+      "step": 492000
+    },
+    {
+      "epoch": 15.09,
+      "learning_rate": 1.0178354473495813e-05,
+      "loss": 0.3126,
+      "step": 492500
+    },
+    {
+      "epoch": 15.1,
+      "learning_rate": 1.0155370669865077e-05,
+      "loss": 0.3121,
+      "step": 493000
+    },
+    {
+      "epoch": 15.1,
+      "eval_loss": 0.7763463854789734,
+      "eval_runtime": 0.4971,
+      "eval_samples_per_second": 2011.654,
+      "eval_steps_per_second": 32.186,
+      "step": 493000
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 1.0133970863894557e-05,
+      "loss": 0.3121,
+      "step": 493500
+    },
+    {
+      "epoch": 15.14,
+      "learning_rate": 1.0114155289609061e-05,
+      "loss": 0.3121,
+      "step": 494000
+    },
+    {
+      "epoch": 15.14,
+      "eval_loss": 0.7747126221656799,
+      "eval_runtime": 0.5031,
+      "eval_samples_per_second": 1987.677,
+      "eval_steps_per_second": 31.803,
+      "step": 494000
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.0095924163708572e-05,
+      "loss": 0.3124,
+      "step": 494500
+    },
+    {
+      "epoch": 15.17,
+      "learning_rate": 1.0079277685565724e-05,
+      "loss": 0.3124,
+      "step": 495000
+    },
+    {
+      "epoch": 15.17,
+      "eval_loss": 0.7728501558303833,
+      "eval_runtime": 0.5097,
+      "eval_samples_per_second": 1962.024,
+      "eval_steps_per_second": 31.392,
+      "step": 495000
+    },
+    {
+      "epoch": 15.18,
+      "learning_rate": 1.0064216037223772e-05,
+      "loss": 0.3126,
+      "step": 495500
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 1.0050739383394454e-05,
+      "loss": 0.3124,
+      "step": 496000
+    },
+    {
+      "epoch": 15.2,
+      "eval_loss": 0.7736043930053711,
+      "eval_runtime": 0.504,
+      "eval_samples_per_second": 1984.023,
+      "eval_steps_per_second": 31.744,
+      "step": 496000
+    },
+    {
+      "epoch": 15.21,
+      "learning_rate": 1.003884787145633e-05,
+      "loss": 0.3123,
+      "step": 496500
+    },
+    {
+      "epoch": 15.23,
+      "learning_rate": 1.002854163145305e-05,
+      "loss": 0.3125,
+      "step": 497000
+    },
+    {
+      "epoch": 15.23,
+      "eval_loss": 0.7738491892814636,
+      "eval_runtime": 0.5171,
+      "eval_samples_per_second": 1933.887,
+      "eval_steps_per_second": 30.942,
+      "step": 497000
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 1.0019820776091995e-05,
+      "loss": 0.3123,
+      "step": 497500
+    },
+    {
+      "epoch": 15.26,
+      "learning_rate": 1.0012685400743077e-05,
+      "loss": 0.3123,
+      "step": 498000
+    },
+    {
+      "epoch": 15.26,
+      "eval_loss": 0.7730560898780823,
+      "eval_runtime": 0.5124,
+      "eval_samples_per_second": 1951.657,
+      "eval_steps_per_second": 31.227,
+      "step": 498000
+    },
+    {
+      "epoch": 15.27,
+      "learning_rate": 1.0007135583437572e-05,
+      "loss": 0.3126,
+      "step": 498500
+    },
+    {
+      "epoch": 15.29,
+      "learning_rate": 1.0003171384867436e-05,
+      "loss": 0.3123,
+      "step": 499000
+    },
+    {
+      "epoch": 15.29,
+      "eval_loss": 0.7752643823623657,
+      "eval_runtime": 0.5071,
+      "eval_samples_per_second": 1972.007,
+      "eval_steps_per_second": 31.552,
+      "step": 499000
+    },
+    {
+      "epoch": 15.3,
+      "learning_rate": 1.0000792848384467e-05,
+      "loss": 0.3121,
+      "step": 499500
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 1e-05,
+      "loss": 0.3122,
+      "step": 500000
+    },
+    {
+      "epoch": 15.32,
+      "eval_loss": 0.7746031284332275,
+      "eval_runtime": 0.5134,
+      "eval_samples_per_second": 1947.857,
+      "eval_steps_per_second": 31.166,
+      "step": 500000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.5654749980670862e+22,
+  "total_flos": 1.5974237119445362e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6673bee6889f96f4d0585736b0bbd0104ce06075881649e694ae573ad1d2887a
+oid sha256:05568a72287e960fd9739070140c44a287f370c2fcded0e2c9e42000a5ecda50
 size 102501541