Training in progress, step 280000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db59304ac09b28bcb3c65afafd5ee1982c926ae9e5b3be0a3041e16925dc09d
+oid sha256:a559b0eb78c919f7317440c34ff9418c01d3807356031c4529bd37c83a4e55b0
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
+oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
+oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb61348726887e329b19406ea4e3e39ac391edeec6dfd8508b3cb524aa33e28
+oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.290920105314663,
-  "global_step": 270000,
+  "epoch": 6.523917146252242,
+  "global_step": 280000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5406,11 +5406,211 @@
       "eval_samples_per_second": 1513.389,
       "eval_steps_per_second": 24.099,
       "step": 270000
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 0.00014733147931802578,
+      "loss": 0.27,
+      "step": 270500
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.00014685268692538238,
+      "loss": 0.2698,
+      "step": 271000
+    },
+    {
+      "epoch": 6.31,
+      "eval_loss": 0.2508079409599304,
+      "eval_runtime": 1.42,
+      "eval_samples_per_second": 1547.911,
+      "eval_steps_per_second": 24.648,
+      "step": 271000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00014637398363044946,
+      "loss": 0.2699,
+      "step": 271500
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 0.00014589537466824955,
+      "loss": 0.2703,
+      "step": 272000
+    },
+    {
+      "epoch": 6.34,
+      "eval_loss": 0.2517754137516022,
+      "eval_runtime": 1.4219,
+      "eval_samples_per_second": 1545.829,
+      "eval_steps_per_second": 24.615,
+      "step": 272000
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 0.00014541686527277356,
+      "loss": 0.27,
+      "step": 272500
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.00014493846067692358,
+      "loss": 0.2693,
+      "step": 273000
+    },
+    {
+      "epoch": 6.36,
+      "eval_loss": 0.25326284766197205,
+      "eval_runtime": 1.4476,
+      "eval_samples_per_second": 1518.396,
+      "eval_steps_per_second": 24.178,
+      "step": 273000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 0.00014446016611245567,
+      "loss": 0.2694,
+      "step": 273500
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 0.00014398198680992252,
+      "loss": 0.2698,
+      "step": 274000
+    },
+    {
+      "epoch": 6.38,
+      "eval_loss": 0.25300565361976624,
+      "eval_runtime": 1.4333,
+      "eval_samples_per_second": 1533.534,
+      "eval_steps_per_second": 24.419,
+      "step": 274000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.00014350392799861636,
+      "loss": 0.2699,
+      "step": 274500
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 0.0001430259949065118,
+      "loss": 0.2697,
+      "step": 275000
+    },
+    {
+      "epoch": 6.41,
+      "eval_loss": 0.2506762742996216,
+      "eval_runtime": 1.4367,
+      "eval_samples_per_second": 1529.926,
+      "eval_steps_per_second": 24.362,
+      "step": 275000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 0.0001425481927602085,
+      "loss": 0.2694,
+      "step": 275500
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.0001420705267848743,
+      "loss": 0.2691,
+      "step": 276000
+    },
+    {
+      "epoch": 6.43,
+      "eval_loss": 0.25103089213371277,
+      "eval_runtime": 1.4586,
+      "eval_samples_per_second": 1506.907,
+      "eval_steps_per_second": 23.995,
+      "step": 276000
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 0.00014159300220418757,
+      "loss": 0.2692,
+      "step": 276500
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 0.0001411156242402808,
+      "loss": 0.2691,
+      "step": 277000
+    },
+    {
+      "epoch": 6.45,
+      "eval_loss": 0.2522771656513214,
+      "eval_runtime": 1.4334,
+      "eval_samples_per_second": 1533.4,
+      "eval_steps_per_second": 24.417,
+      "step": 277000
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 0.0001406383981136829,
+      "loss": 0.269,
+      "step": 277500
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 0.00014016132904326226,
+      "loss": 0.2689,
+      "step": 278000
+    },
+    {
+      "epoch": 6.48,
+      "eval_loss": 0.2521708011627197,
+      "eval_runtime": 1.4301,
+      "eval_samples_per_second": 1536.934,
+      "eval_steps_per_second": 24.473,
+      "step": 278000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 0.00013968442224616989,
+      "loss": 0.269,
+      "step": 278500
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00013920768293778195,
+      "loss": 0.2688,
+      "step": 279000
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.25149086117744446,
+      "eval_runtime": 1.4307,
+      "eval_samples_per_second": 1536.357,
+      "eval_steps_per_second": 24.464,
+      "step": 279000
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 0.00013873111633164336,
+      "loss": 0.2686,
+      "step": 279500
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 0.00013825472763941,
+      "loss": 0.2686,
+      "step": 280000
+    },
+    {
+      "epoch": 6.52,
+      "eval_loss": 0.25161558389663696,
+      "eval_runtime": 1.4115,
+      "eval_samples_per_second": 1557.23,
+      "eval_steps_per_second": 24.797,
+      "step": 280000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 8.626137764966059e+21,
+  "total_flos": 8.945624903740559e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
+oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
 size 102501541