Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3851379e290e595ff406c21b8b10ddb1e73359dd0f6752ee66fd50b92159710
+oid sha256:2bc4138b4d57f8e4a675a838e7f7c445fa2f2850d452063b02b0b163a34a7798
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cc55a03d0db3d8e5de6630971dddba20e9587291496d77623230dc60cf541c
+oid sha256:399d2fd5053b20d89296de77093797a9b20b303b26b5c54e0ac988e918c3a2b8
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca511f19607ffe13077a404fa6aa93a3f99da5d803f11fc8cc4ffd982f7eaa96
-size 14439
+oid sha256:39649affd710e5288e8103a7ce71440cea00f53d7c4b1b77287e55e4fba903c9
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c5e63367d8a48da7291ac4cad9dbf22e45f23c04ad6dc36fb819eee5567b30
+oid sha256:24fdf31146f9e2573e4fd97d3ef660e7e36be173064143bba073688856627f33
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ef310867dca4f3b22b044f838f0a52fca0a2ae9be44b0e97a33f54ca14b37c
+oid sha256:5340a3b2a3128c15a2e26d8d92bda85367d97c29b7ab61268eaf585f02d028cc
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07690c863ee7f95b67ca0330c6c558692a4c5296256a3c0c1e6edf6ee11f4a99
+oid sha256:ac2d9083cc062d05a152912781673b09c3efbb96bd37d28e564815b34b3ab7b4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd623ae3bafd7bee294fb51f9ab76259bcc1a1e3cb80be656ec13fa7aea6663f
-size 14503
+oid sha256:a59c37be606f12c13a42a1df1734ee1dfacdb5c6d84f45ffa367935178d29c37
+size 14439

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f7a345bdac720f75c3e4ebf8a9d6d8895e230a0405992893aeb1c567a9dd75
+oid sha256:8b5928441e789260c503b832ccd0e73fec0b6dedeb24fbfc4a89078adb4680e9
 size 14439

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099663ce4dbefceb2b014dd475ab003207ed8b9ddbfafed2491187b9c10f927a
+oid sha256:1cfa650386285df001bb485d9e06712c20b2d44c391fb3f87f5e92d68fae75c4
 size 14439

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4435aedaa43e7ef631652a5bc79634e81959ca100d2c5dc8b85db021834925b4
-size 14439
+oid sha256:3e02ab0e747b127b3be6acd4dea7efa17b59fc5315b526da3be35482035d021d
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60fd80961b777bf4901f5c7189278f8f31f61a50c51a19e170f6a1919a5ce33
+oid sha256:8d15e11a6de6abd55121a73bc214cc950fb971f927ae2b1d5067145da50de5d0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.093569043169214,
-  "global_step": 460000,
+  "epoch": 14.399950978890285,
+  "global_step": 470000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9206,11 +9206,211 @@
       "eval_samples_per_second": 1998.696,
       "eval_steps_per_second": 31.979,
       "step": 460000
+    },
+    {
+      "epoch": 14.11,
+      "learning_rate": 1.4920092237448903e-05,
+      "loss": 0.3138,
+      "step": 460500
+    },
+    {
+      "epoch": 14.12,
+      "learning_rate": 1.4797008356541874e-05,
+      "loss": 0.3134,
+      "step": 461000
+    },
+    {
+      "epoch": 14.12,
+      "eval_loss": 0.7742542028427124,
+      "eval_runtime": 0.4997,
+      "eval_samples_per_second": 2001.196,
+      "eval_steps_per_second": 32.019,
+      "step": 461000
+    },
+    {
+      "epoch": 14.14,
+      "learning_rate": 1.4675457713088947e-05,
+      "loss": 0.3134,
+      "step": 461500
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 1.4555441636348494e-05,
+      "loss": 0.3136,
+      "step": 462000
+    },
+    {
+      "epoch": 14.15,
+      "eval_loss": 0.7772946357727051,
+      "eval_runtime": 0.5121,
+      "eval_samples_per_second": 1952.647,
+      "eval_steps_per_second": 31.242,
+      "step": 462000
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 1.4436961438797095e-05,
+      "loss": 0.3136,
+      "step": 462500
+    },
+    {
+      "epoch": 14.19,
+      "learning_rate": 1.4320018416115206e-05,
+      "loss": 0.3132,
+      "step": 463000
+    },
+    {
+      "epoch": 14.19,
+      "eval_loss": 0.7742455005645752,
+      "eval_runtime": 0.5004,
+      "eval_samples_per_second": 1998.244,
+      "eval_steps_per_second": 31.972,
+      "step": 463000
+    },
+    {
+      "epoch": 14.2,
+      "learning_rate": 1.4204613847173003e-05,
+      "loss": 0.3134,
+      "step": 463500
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 1.4090748994016354e-05,
+      "loss": 0.3135,
+      "step": 464000
+    },
+    {
+      "epoch": 14.22,
+      "eval_loss": 0.7742483019828796,
+      "eval_runtime": 0.5003,
+      "eval_samples_per_second": 1998.899,
+      "eval_steps_per_second": 31.982,
+      "step": 464000
+    },
+    {
+      "epoch": 14.23,
+      "learning_rate": 1.3978425101853049e-05,
+      "loss": 0.3132,
+      "step": 464500
+    },
+    {
+      "epoch": 14.25,
+      "learning_rate": 1.3867643399039165e-05,
+      "loss": 0.3134,
+      "step": 465000
+    },
+    {
+      "epoch": 14.25,
+      "eval_loss": 0.7741165161132812,
+      "eval_runtime": 0.5054,
+      "eval_samples_per_second": 1978.738,
+      "eval_steps_per_second": 31.66,
+      "step": 465000
+    },
+    {
+      "epoch": 14.26,
+      "learning_rate": 1.3758405097065648e-05,
+      "loss": 0.3128,
+      "step": 465500
+    },
+    {
+      "epoch": 14.28,
+      "learning_rate": 1.3650711390545131e-05,
+      "loss": 0.313,
+      "step": 466000
+    },
+    {
+      "epoch": 14.28,
+      "eval_loss": 0.7737331986427307,
+      "eval_runtime": 0.505,
+      "eval_samples_per_second": 1980.27,
+      "eval_steps_per_second": 31.684,
+      "step": 466000
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 1.3544563457198657e-05,
+      "loss": 0.3132,
+      "step": 466500
+    },
+    {
+      "epoch": 14.31,
+      "learning_rate": 1.343996245784307e-05,
+      "loss": 0.3131,
+      "step": 467000
+    },
+    {
+      "epoch": 14.31,
+      "eval_loss": 0.7716790437698364,
+      "eval_runtime": 0.504,
+      "eval_samples_per_second": 1983.936,
+      "eval_steps_per_second": 31.743,
+      "step": 467000
+    },
+    {
+      "epoch": 14.32,
+      "learning_rate": 1.3336909536378107e-05,
+      "loss": 0.313,
+      "step": 467500
+    },
+    {
+      "epoch": 14.34,
+      "learning_rate": 1.3235405819774022e-05,
+      "loss": 0.3131,
+      "step": 468000
+    },
+    {
+      "epoch": 14.34,
+      "eval_loss": 0.7737191319465637,
+      "eval_runtime": 0.5136,
+      "eval_samples_per_second": 1947.194,
+      "eval_steps_per_second": 31.155,
+      "step": 468000
+    },
+    {
+      "epoch": 14.35,
+      "learning_rate": 1.3135452418059208e-05,
+      "loss": 0.3132,
+      "step": 468500
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 1.3037050424308027e-05,
+      "loss": 0.3126,
+      "step": 469000
+    },
+    {
+      "epoch": 14.37,
+      "eval_loss": 0.7744223475456238,
+      "eval_runtime": 0.5036,
+      "eval_samples_per_second": 1985.727,
+      "eval_steps_per_second": 31.772,
+      "step": 469000
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 1.2940200914628945e-05,
+      "loss": 0.3132,
+      "step": 469500
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 1.2844904948152644e-05,
+      "loss": 0.3132,
+      "step": 470000
+    },
+    {
+      "epoch": 14.4,
+      "eval_loss": 0.7742005586624146,
+      "eval_runtime": 0.5167,
+      "eval_samples_per_second": 1935.302,
+      "eval_steps_per_second": 30.965,
+      "step": 470000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 1.4696296552299338e+22,
+  "total_flos": 1.5015783691073838e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cc55a03d0db3d8e5de6630971dddba20e9587291496d77623230dc60cf541c
+oid sha256:399d2fd5053b20d89296de77093797a9b20b303b26b5c54e0ac988e918c3a2b8
 size 102501541