Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00828d7c5b2ee9d934868fffc62db5886616a7f03a8761ef8254b89f6589bb74
+oid sha256:31f8b72df9e81d9020de8c0d757b3e594d6732915b9d9225bd73528701124126
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cedfbffe43fc18644cc6de989fcca94f4a26075ab174ed0f9cb823c12e426d
+oid sha256:683da2699cf4f6f0cc7ad0bd863d30bc6b3ce3591f2b81f581d00b7a55c36f19
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
+oid sha256:a4c841acb13540ac94fe640beda68267e633bf6f66d1bd05ecc4a8b2a3acbdc1
 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": 11.723329425556859,
-  "global_step": 460000,
+  "epoch": 11.978184413068965,
+  "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": 768.777,
       "eval_steps_per_second": 12.3,
       "step": 460000
+    },
+    {
+      "epoch": 11.74,
+      "learning_rate": 1.4920092237448903e-05,
+      "loss": 0.2677,
+      "step": 460500
+    },
+    {
+      "epoch": 11.75,
+      "learning_rate": 1.4797008356541874e-05,
+      "loss": 0.2677,
+      "step": 461000
+    },
+    {
+      "epoch": 11.75,
+      "eval_loss": 0.8057255744934082,
+      "eval_runtime": 1.2455,
+      "eval_samples_per_second": 802.869,
+      "eval_steps_per_second": 12.846,
+      "step": 461000
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 1.4675457713088947e-05,
+      "loss": 0.2676,
+      "step": 461500
+    },
+    {
+      "epoch": 11.77,
+      "learning_rate": 1.4555441636348494e-05,
+      "loss": 0.2676,
+      "step": 462000
+    },
+    {
+      "epoch": 11.77,
+      "eval_loss": 0.8142445087432861,
+      "eval_runtime": 1.2424,
+      "eval_samples_per_second": 804.89,
+      "eval_steps_per_second": 12.878,
+      "step": 462000
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 1.4436961438797095e-05,
+      "loss": 0.2679,
+      "step": 462500
+    },
+    {
+      "epoch": 11.8,
+      "learning_rate": 1.4320018416115206e-05,
+      "loss": 0.2679,
+      "step": 463000
+    },
+    {
+      "epoch": 11.8,
+      "eval_loss": 0.8076353073120117,
+      "eval_runtime": 1.3419,
+      "eval_samples_per_second": 745.235,
+      "eval_steps_per_second": 11.924,
+      "step": 463000
+    },
+    {
+      "epoch": 11.81,
+      "learning_rate": 1.4204613847173003e-05,
+      "loss": 0.2674,
+      "step": 463500
+    },
+    {
+      "epoch": 11.83,
+      "learning_rate": 1.4090748994016354e-05,
+      "loss": 0.2676,
+      "step": 464000
+    },
+    {
+      "epoch": 11.83,
+      "eval_loss": 0.8087449669837952,
+      "eval_runtime": 1.2685,
+      "eval_samples_per_second": 788.361,
+      "eval_steps_per_second": 12.614,
+      "step": 464000
+    },
+    {
+      "epoch": 11.84,
+      "learning_rate": 1.3978425101853049e-05,
+      "loss": 0.2681,
+      "step": 464500
+    },
+    {
+      "epoch": 11.85,
+      "learning_rate": 1.3867643399039165e-05,
+      "loss": 0.2677,
+      "step": 465000
+    },
+    {
+      "epoch": 11.85,
+      "eval_loss": 0.8065741062164307,
+      "eval_runtime": 1.2179,
+      "eval_samples_per_second": 821.068,
+      "eval_steps_per_second": 13.137,
+      "step": 465000
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 1.3758405097065648e-05,
+      "loss": 0.2676,
+      "step": 465500
+    },
+    {
+      "epoch": 11.88,
+      "learning_rate": 1.3650711390545131e-05,
+      "loss": 0.2673,
+      "step": 466000
+    },
+    {
+      "epoch": 11.88,
+      "eval_loss": 0.8059167861938477,
+      "eval_runtime": 1.3496,
+      "eval_samples_per_second": 740.983,
+      "eval_steps_per_second": 11.856,
+      "step": 466000
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 1.3544563457198657e-05,
+      "loss": 0.2673,
+      "step": 466500
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 1.343996245784307e-05,
+      "loss": 0.2676,
+      "step": 467000
+    },
+    {
+      "epoch": 11.9,
+      "eval_loss": 0.8066999316215515,
+      "eval_runtime": 1.2927,
+      "eval_samples_per_second": 773.582,
+      "eval_steps_per_second": 12.377,
+      "step": 467000
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 1.3336909536378107e-05,
+      "loss": 0.2678,
+      "step": 467500
+    },
+    {
+      "epoch": 11.93,
+      "learning_rate": 1.3235405819774022e-05,
+      "loss": 0.2675,
+      "step": 468000
+    },
+    {
+      "epoch": 11.93,
+      "eval_loss": 0.8042522072792053,
+      "eval_runtime": 1.2835,
+      "eval_samples_per_second": 779.135,
+      "eval_steps_per_second": 12.466,
+      "step": 468000
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 1.3135452418059208e-05,
+      "loss": 0.2675,
+      "step": 468500
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 1.3037050424308027e-05,
+      "loss": 0.2675,
+      "step": 469000
+    },
+    {
+      "epoch": 11.95,
+      "eval_loss": 0.8102657198905945,
+      "eval_runtime": 1.2622,
+      "eval_samples_per_second": 792.261,
+      "eval_steps_per_second": 12.676,
+      "step": 469000
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 1.2940200914628945e-05,
+      "loss": 0.2676,
+      "step": 469500
+    },
+    {
+      "epoch": 11.98,
+      "learning_rate": 1.2844904948152644e-05,
+      "loss": 0.2673,
+      "step": 470000
+    },
+    {
+      "epoch": 11.98,
+      "eval_loss": 0.8092105984687805,
+      "eval_runtime": 1.2931,
+      "eval_samples_per_second": 773.322,
+      "eval_steps_per_second": 12.373,
+      "step": 470000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.4696260115583505e+22,
+  "total_flos": 1.5015747254358005e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cedfbffe43fc18644cc6de989fcca94f4a26075ab174ed0f9cb823c12e426d
+oid sha256:683da2699cf4f6f0cc7ad0bd863d30bc6b3ce3591f2b81f581d00b7a55c36f19
 size 102501541