Training in progress, step 490000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915c0a3320162732d7d0277198910bd1c5fe36e91a2494488dcd5fe9ecfa67b3
+oid sha256:c2e2116038f17a755ee0cd7f714c11f53fb07e5f62178c545ddce403c568ffbe
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8136bbdd727fc3ba0cd916f87b90e8d7992cbeeded2bac704ee561d225bd54ff
+oid sha256:6673bee6889f96f4d0585736b0bbd0104ce06075881649e694ae573ad1d2887a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dd7aa49620cc3a97afcabbb7850c385a241b9dcc8d07d333d6f65040a60603
+oid sha256:644e2fc163f368345d150d3fc83a57447c36fc56a8c5b1ac9505e0d54bf78bd0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e70e32ef25d8d010a4b8053a0291d1477416df257354e41c4a63cf4dc2e643
-size 14503
+oid sha256:4a9725305d551fdabba33dd56f81db3b2c581f84aafc700effd4e6475b7ec812
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e68cc11f4318aee75c400e1894d33192a70b9883c303c9fa9cedc5946464e08
-size 14439
+oid sha256:cbe151312b54baa9a4e64116f572138b7b71dec85430cd296cb3640e4c2da8a4
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a46f3a13aa9f98adfc5de8699e24132915127b3a6b2cea5827a2046f9700ac
-size 14439
+oid sha256:368b6ac98a14548e894c6dec52e2926741be3331b9c05acbb8210a7533733def
+size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb51fb524aa906bf1e2b1400af5152fa96888bd9aa6527a094a0343f901ed25d
-size 14439
+oid sha256:cb22d9d447646758c04766cf11ca8c2e8fc19a36cd697a9779fc029a142baac3
+size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c12f52a705d4e5218bd23d5bd9019926a903ddc54e4326eae90cf72f0b4f8f
-size 14439
+oid sha256:978268c9f7cbaa0bf6afcfb4a36b2945ad3b7df5c70456c1598647d77f700d81
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e0d82ec0129c8f13f015b8a1236f72049a8e4b658d7d70897f776f9bde416e
-size 14439
+oid sha256:ea73efb8fdbffbda3c38be20fe382b5f7cbbd8a80c55ee21bf5ba148273fa6a6
+size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58c7e90cbf160b31d955598aee9f14bbda5806f105e3c62619fe3545749dd33
-size 14567
+oid sha256:363c6a12aae6b2a1c1924495d50178e5b2b9c07c6657605723562b286ea4de81
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
+oid sha256:7d798ff13d72fe751bc0ea721c37eb1e98064dde5819b90f3504db53fdceee97
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.706332914611355,
-  "global_step": 480000,
+  "epoch": 15.012714850332424,
+  "global_step": 490000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9606,11 +9606,211 @@
       "eval_samples_per_second": 1946.296,
       "eval_steps_per_second": 31.141,
       "step": 480000
+    },
+    {
+      "epoch": 14.72,
+      "learning_rate": 1.1204252864868377e-05,
+      "loss": 0.3127,
+      "step": 480500
+    },
+    {
+      "epoch": 14.74,
+      "learning_rate": 1.1143368309400725e-05,
+      "loss": 0.3125,
+      "step": 481000
+    },
+    {
+      "epoch": 14.74,
+      "eval_loss": 0.7771226763725281,
+      "eval_runtime": 0.5065,
+      "eval_samples_per_second": 1974.24,
+      "eval_steps_per_second": 31.588,
+      "step": 481000
+    },
+    {
+      "epoch": 14.75,
+      "learning_rate": 1.1084056947009348e-05,
+      "loss": 0.3125,
+      "step": 481500
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 1.1026319426313837e-05,
+      "loss": 0.3124,
+      "step": 482000
+    },
+    {
+      "epoch": 14.77,
+      "eval_loss": 0.7745999693870544,
+      "eval_runtime": 0.4972,
+      "eval_samples_per_second": 2011.082,
+      "eval_steps_per_second": 32.177,
+      "step": 482000
+    },
+    {
+      "epoch": 14.78,
+      "learning_rate": 1.097015637872247e-05,
+      "loss": 0.3126,
+      "step": 482500
+    },
+    {
+      "epoch": 14.8,
+      "learning_rate": 1.0915568418425301e-05,
+      "loss": 0.3125,
+      "step": 483000
+    },
+    {
+      "epoch": 14.8,
+      "eval_loss": 0.7761328220367432,
+      "eval_runtime": 0.5155,
+      "eval_samples_per_second": 1939.967,
+      "eval_steps_per_second": 31.039,
+      "step": 483000
+    },
+    {
+      "epoch": 14.81,
+      "learning_rate": 1.0862556142387571e-05,
+      "loss": 0.3126,
+      "step": 483500
+    },
+    {
+      "epoch": 14.83,
+      "learning_rate": 1.081112013034298e-05,
+      "loss": 0.3127,
+      "step": 484000
+    },
+    {
+      "epoch": 14.83,
+      "eval_loss": 0.7775337100028992,
+      "eval_runtime": 0.5093,
+      "eval_samples_per_second": 1963.507,
+      "eval_steps_per_second": 31.416,
+      "step": 484000
+    },
+    {
+      "epoch": 14.84,
+      "learning_rate": 1.0761260944787561e-05,
+      "loss": 0.313,
+      "step": 484500
+    },
+    {
+      "epoch": 14.86,
+      "learning_rate": 1.0712979130973347e-05,
+      "loss": 0.3126,
+      "step": 485000
+    },
+    {
+      "epoch": 14.86,
+      "eval_loss": 0.7740907073020935,
+      "eval_runtime": 0.5188,
+      "eval_samples_per_second": 1927.581,
+      "eval_steps_per_second": 30.841,
+      "step": 485000
+    },
+    {
+      "epoch": 14.87,
+      "learning_rate": 1.0666275216902535e-05,
+      "loss": 0.3125,
+      "step": 485500
+    },
+    {
+      "epoch": 14.89,
+      "learning_rate": 1.0621149713321656e-05,
+      "loss": 0.3128,
+      "step": 486000
+    },
+    {
+      "epoch": 14.89,
+      "eval_loss": 0.7765258550643921,
+      "eval_runtime": 0.52,
+      "eval_samples_per_second": 1923.021,
+      "eval_steps_per_second": 30.768,
+      "step": 486000
+    },
+    {
+      "epoch": 14.91,
+      "learning_rate": 1.0577603113715964e-05,
+      "loss": 0.3125,
+      "step": 486500
+    },
+    {
+      "epoch": 14.92,
+      "learning_rate": 1.0535635894304106e-05,
+      "loss": 0.3126,
+      "step": 487000
+    },
+    {
+      "epoch": 14.92,
+      "eval_loss": 0.7741805911064148,
+      "eval_runtime": 0.5052,
+      "eval_samples_per_second": 1979.424,
+      "eval_steps_per_second": 31.671,
+      "step": 487000
+    },
+    {
+      "epoch": 14.94,
+      "learning_rate": 1.0495248514032875e-05,
+      "loss": 0.3123,
+      "step": 487500
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 1.045644141457218e-05,
+      "loss": 0.3126,
+      "step": 488000
+    },
+    {
+      "epoch": 14.95,
+      "eval_loss": 0.7744404077529907,
+      "eval_runtime": 0.5273,
+      "eval_samples_per_second": 1896.451,
+      "eval_steps_per_second": 30.343,
+      "step": 488000
+    },
+    {
+      "epoch": 14.97,
+      "learning_rate": 1.0419215020310254e-05,
+      "loss": 0.3123,
+      "step": 488500
+    },
+    {
+      "epoch": 14.98,
+      "learning_rate": 1.0383569738348988e-05,
+      "loss": 0.3125,
+      "step": 489000
+    },
+    {
+      "epoch": 14.98,
+      "eval_loss": 0.7724484205245972,
+      "eval_runtime": 0.5078,
+      "eval_samples_per_second": 1969.112,
+      "eval_steps_per_second": 31.506,
+      "step": 489000
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 1.0349505958499436e-05,
+      "loss": 0.3126,
+      "step": 489500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 1.0317024053277693e-05,
+      "loss": 0.3124,
+      "step": 490000
+    },
+    {
+      "epoch": 15.01,
+      "eval_loss": 0.7753793001174927,
+      "eval_runtime": 0.498,
+      "eval_samples_per_second": 2008.198,
+      "eval_steps_per_second": 32.131,
+      "step": 490000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.5335270829848338e+22,
+  "total_flos": 1.5654749980670862e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8136bbdd727fc3ba0cd916f87b90e8d7992cbeeded2bac704ee561d225bd54ff
+oid sha256:6673bee6889f96f4d0585736b0bbd0104ce06075881649e694ae573ad1d2887a
 size 102501541