Training in progress, step 340000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d2a5e73283aa1880b29f29feb6316701d271842328e195271c3e399e6c920a
+oid sha256:f848b004ca69d971cd5024827329eb728808850f3ba285aae6ae2d66c5e9a1ea
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb067e8d99d964806b68ae99e0f39bdecb3dd4f00cbe7958a115e1392dffcc7
+oid sha256:5bfba4eea74dece360d73bbeb68171b0f24c78184fc1168b69bc18ed84fe5243
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623a6385c6947219614a206f325f0d5bbe602621d1fd3e48972b7fdd72be25d2
+oid sha256:20c5b304cccca8b5844ddfec128e44995bacab68346ff44d01e8476a83259d32
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ac5973a9776fb5558d0d5471ce91f9f5f08200895aa832ab0411732da0bb62
+oid sha256:3a6026e8cbd4826fee12ad344c0bb2e47d863082fccddfed4801c66cbc3305df
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe8a6d91f7528a2132dc105f5a011209849ce078b5ae84cd752340614efc89b
-size 14439
+oid sha256:276a39a4e5fc9bbf2fc7156d49a68ce7b2b8c02aa8d52e98747eb94a987f3191
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57da30fd98664b01593e067ac432f0638ebe9389fdcddf47146e4e5d78f9b45b
-size 14439
+oid sha256:e64783857a8ded45f594a9d4d98ef3bd8c1d156f9923bb0bef61858daa470a8e
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ab9ece5cf2fe3d99e3bf57fddd4aebe29db0bd41b88067fc2fa8ae9ef5bedb
+oid sha256:e61c24f771644e6cd7fccf329b7b1a8621bd89eecc91f4043864ce60f81c96b6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.039168079160749,
-  "global_step": 330000,
+  "epoch": 5.19187014216562,
+  "global_step": 340000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2448,11 +2448,85 @@
       "eval_samples_per_second": 883.862,
       "eval_steps_per_second": 14.142,
       "step": 330000
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 0.00012189044992813972,
+      "loss": 0.2858,
+      "step": 331000
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 0.0001217047614392187,
+      "loss": 0.2857,
+      "step": 332000
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 0.00012151861687370828,
+      "loss": 0.2857,
+      "step": 333000
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 0.00012133201826725558,
+      "loss": 0.2852,
+      "step": 334000
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.0001211449676604731,
+      "loss": 0.2853,
+      "step": 335000
+    },
+    {
+      "epoch": 5.12,
+      "eval_runtime": 1.3419,
+      "eval_samples_per_second": 745.216,
+      "eval_steps_per_second": 11.923,
+      "step": 335000
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 0.00012095746709891632,
+      "loss": 0.2852,
+      "step": 336000
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.00012076951863306127,
+      "loss": 0.285,
+      "step": 337000
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 0.0001205811243182823,
+      "loss": 0.2848,
+      "step": 338000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 0.00012039228621482949,
+      "loss": 0.2858,
+      "step": 339000
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 0.00012020300638780604,
+      "loss": 0.2845,
+      "step": 340000
+    },
+    {
+      "epoch": 5.19,
+      "eval_runtime": 1.2559,
+      "eval_samples_per_second": 796.26,
+      "eval_steps_per_second": 12.74,
+      "step": 340000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.313305328660712e+22,
+  "total_flos": 2.383405589691059e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb067e8d99d964806b68ae99e0f39bdecb3dd4f00cbe7958a115e1392dffcc7
+oid sha256:5bfba4eea74dece360d73bbeb68171b0f24c78184fc1168b69bc18ed84fe5243
 size 449471589