Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42990d05abd03b227efee730c20308633082f939be092f71cc5b9076c4f1f00f
+oid sha256:8c9d46c0928f6304f48bd62fa6e71bd8d578d23bad4ca4e988379cbeabeca88e
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e1731fe3a6eb4e4ccd7a3149a9f80511c7c48771332f37b10e3da39628567e
+oid sha256:236aaee0ef2e2b221aabbd9376533af723e290eee22b162dcb3dc545c9bc0456
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68af5319effdf337d3ee874ac36fe8afc374d22904eb956e7c540c9458fb59
+oid sha256:7e47c014bce57a678aa8e29889fa3baa2aec11726dcca68d912de21df35c6be0
 size 14503

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": 11.416855005941425,
-  "global_step": 490000,
+  "epoch": 11.649852046879005,
+  "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": 1543.227,
       "eval_steps_per_second": 24.574,
       "step": 490000
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 1.0286124377900624e-05,
+      "loss": 0.2504,
+      "step": 490500
+    },
+    {
+      "epoch": 11.44,
+      "learning_rate": 1.0256807270282153e-05,
+      "loss": 0.2503,
+      "step": 491000
+    },
+    {
+      "epoch": 11.44,
+      "eval_loss": 0.2337212711572647,
+      "eval_runtime": 1.4623,
+      "eval_samples_per_second": 1503.072,
+      "eval_steps_per_second": 23.934,
+      "step": 491000
+    },
+    {
+      "epoch": 11.45,
+      "learning_rate": 1.0229073051029455e-05,
+      "loss": 0.25,
+      "step": 491500
+    },
+    {
+      "epoch": 11.46,
+      "learning_rate": 1.020292202343952e-05,
+      "loss": 0.2501,
+      "step": 492000
+    },
+    {
+      "epoch": 11.46,
+      "eval_loss": 0.23177069425582886,
+      "eval_runtime": 1.4821,
+      "eval_samples_per_second": 1482.991,
+      "eval_steps_per_second": 23.615,
+      "step": 492000
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 1.0178354473495813e-05,
+      "loss": 0.2503,
+      "step": 492500
+    },
+    {
+      "epoch": 11.49,
+      "learning_rate": 1.0155370669865077e-05,
+      "loss": 0.2505,
+      "step": 493000
+    },
+    {
+      "epoch": 11.49,
+      "eval_loss": 0.23253387212753296,
+      "eval_runtime": 1.4831,
+      "eval_samples_per_second": 1482.001,
+      "eval_steps_per_second": 23.599,
+      "step": 493000
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 1.0133970863894557e-05,
+      "loss": 0.2502,
+      "step": 493500
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 1.0114155289609061e-05,
+      "loss": 0.2504,
+      "step": 494000
+    },
+    {
+      "epoch": 11.51,
+      "eval_loss": 0.23376800119876862,
+      "eval_runtime": 1.4253,
+      "eval_samples_per_second": 1542.116,
+      "eval_steps_per_second": 24.556,
+      "step": 494000
+    },
+    {
+      "epoch": 11.52,
+      "learning_rate": 1.0095924163708572e-05,
+      "loss": 0.2503,
+      "step": 494500
+    },
+    {
+      "epoch": 11.53,
+      "learning_rate": 1.0079277685565724e-05,
+      "loss": 0.2503,
+      "step": 495000
+    },
+    {
+      "epoch": 11.53,
+      "eval_loss": 0.23174437880516052,
+      "eval_runtime": 1.4318,
+      "eval_samples_per_second": 1535.107,
+      "eval_steps_per_second": 24.444,
+      "step": 495000
+    },
+    {
+      "epoch": 11.55,
+      "learning_rate": 1.0064216037223772e-05,
+      "loss": 0.2501,
+      "step": 495500
+    },
+    {
+      "epoch": 11.56,
+      "learning_rate": 1.0050739383394454e-05,
+      "loss": 0.2502,
+      "step": 496000
+    },
+    {
+      "epoch": 11.56,
+      "eval_loss": 0.23404622077941895,
+      "eval_runtime": 1.4342,
+      "eval_samples_per_second": 1532.524,
+      "eval_steps_per_second": 24.403,
+      "step": 496000
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 1.003884787145633e-05,
+      "loss": 0.2505,
+      "step": 496500
+    },
+    {
+      "epoch": 11.58,
+      "learning_rate": 1.002854163145305e-05,
+      "loss": 0.25,
+      "step": 497000
+    },
+    {
+      "epoch": 11.58,
+      "eval_loss": 0.2340567409992218,
+      "eval_runtime": 1.4613,
+      "eval_samples_per_second": 1504.132,
+      "eval_steps_per_second": 23.951,
+      "step": 497000
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 1.0019820776091995e-05,
+      "loss": 0.2503,
+      "step": 497500
+    },
+    {
+      "epoch": 11.6,
+      "learning_rate": 1.0012685400743077e-05,
+      "loss": 0.2502,
+      "step": 498000
+    },
+    {
+      "epoch": 11.6,
+      "eval_loss": 0.2324497401714325,
+      "eval_runtime": 1.4433,
+      "eval_samples_per_second": 1522.91,
+      "eval_steps_per_second": 24.25,
+      "step": 498000
+    },
+    {
+      "epoch": 11.61,
+      "learning_rate": 1.0007135583437572e-05,
+      "loss": 0.25,
+      "step": 498500
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 1.0003171384867436e-05,
+      "loss": 0.2504,
+      "step": 499000
+    },
+    {
+      "epoch": 11.63,
+      "eval_loss": 0.2359778881072998,
+      "eval_runtime": 1.4253,
+      "eval_samples_per_second": 1542.145,
+      "eval_steps_per_second": 24.556,
+      "step": 499000
+    },
+    {
+      "epoch": 11.64,
+      "learning_rate": 1.0000792848384467e-05,
+      "loss": 0.2501,
+      "step": 499500
+    },
+    {
+      "epoch": 11.65,
+      "learning_rate": 1e-05,
+      "loss": 0.2501,
+      "step": 500000
+    },
+    {
+      "epoch": 11.65,
+      "eval_loss": 0.23462386429309845,
+      "eval_runtime": 1.444,
+      "eval_samples_per_second": 1522.115,
+      "eval_steps_per_second": 24.238,
+      "step": 500000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5654842333050526e+22,
+  "total_flos": 1.5974329471825026e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e1731fe3a6eb4e4ccd7a3149a9f80511c7c48771332f37b10e3da39628567e
+oid sha256:236aaee0ef2e2b221aabbd9376533af723e290eee22b162dcb3dc545c9bc0456
 size 102501541