Training in progress, step 600000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba1a60953f474b23784dd49858737503638550c3096a7f534e92e574e05a543
+oid sha256:671e662c6c0e9e72ffdf63ae76361931e62dda8934e73fb45c3bdfafe9299996
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8bbf9aa941f450bae2344c4f3ace716b8d409472808a8af9bbe468eecca5b1
+oid sha256:da8af5408d1b5fb7d927d259061d24f1b2ad7a5b6145f36a7ec1c919a2b9edd8
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e0931a17310d4650ee3518b83c618a6ffd8c6840ad8bd778d326fb339eb375
+oid sha256:c0be7c4ced12e0858928365082a1279c3330778ef5c90870360fd46cc963be5c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf17ad9f6f8f5230f179dea9ee53bd043cf1c420455dc89092d4dbf5e8505225
+oid sha256:34904d09dca1d79fb910d11916faed0bf8107fa6c955fc65b114b5f30425510a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.223057448445847,
-  "global_step": 590000,
+  "epoch": 6.334586172668771,
+  "global_step": 600000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11806,11 +11806,211 @@
       "eval_samples_per_second": 916.62,
       "eval_steps_per_second": 14.366,
       "step": 590000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 6.495596703323214e-05,
+      "loss": 0.203,
+      "step": 590500
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 6.484294934833822e-05,
+      "loss": 0.203,
+      "step": 591000
+    },
+    {
+      "epoch": 6.23,
+      "eval_loss": 0.19498485326766968,
+      "eval_runtime": 2.4612,
+      "eval_samples_per_second": 933.27,
+      "eval_steps_per_second": 14.627,
+      "step": 591000
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 6.472997310224204e-05,
+      "loss": 0.2028,
+      "step": 591500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 6.461703860381628e-05,
+      "loss": 0.2029,
+      "step": 592000
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.19485318660736084,
+      "eval_runtime": 2.5316,
+      "eval_samples_per_second": 907.333,
+      "eval_steps_per_second": 14.22,
+      "step": 592000
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 6.450414616181959e-05,
+      "loss": 0.2027,
+      "step": 592500
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 6.439129608489559e-05,
+      "loss": 0.2023,
+      "step": 593000
+    },
+    {
+      "epoch": 6.26,
+      "eval_loss": 0.19170017540454865,
+      "eval_runtime": 2.5465,
+      "eval_samples_per_second": 902.036,
+      "eval_steps_per_second": 14.137,
+      "step": 593000
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 6.427848868157208e-05,
+      "loss": 0.2021,
+      "step": 593500
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 6.41657242602602e-05,
+      "loss": 0.2024,
+      "step": 594000
+    },
+    {
+      "epoch": 6.27,
+      "eval_loss": 0.19145548343658447,
+      "eval_runtime": 2.5956,
+      "eval_samples_per_second": 884.955,
+      "eval_steps_per_second": 13.87,
+      "step": 594000
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 6.405300312925353e-05,
+      "loss": 0.2026,
+      "step": 594500
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 6.39403255967274e-05,
+      "loss": 0.2021,
+      "step": 595000
+    },
+    {
+      "epoch": 6.28,
+      "eval_loss": 0.19004245102405548,
+      "eval_runtime": 2.516,
+      "eval_samples_per_second": 912.956,
+      "eval_steps_per_second": 14.308,
+      "step": 595000
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 6.382769197073783e-05,
+      "loss": 0.2023,
+      "step": 595500
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 6.371510255922088e-05,
+      "loss": 0.2024,
+      "step": 596000
+    },
+    {
+      "epoch": 6.29,
+      "eval_loss": 0.19270072877407074,
+      "eval_runtime": 2.4967,
+      "eval_samples_per_second": 920.021,
+      "eval_steps_per_second": 14.419,
+      "step": 596000
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 6.360255766999172e-05,
+      "loss": 0.2025,
+      "step": 596500
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 6.349005761074372e-05,
+      "loss": 0.2027,
+      "step": 597000
+    },
+    {
+      "epoch": 6.3,
+      "eval_loss": 0.18951117992401123,
+      "eval_runtime": 2.5319,
+      "eval_samples_per_second": 907.212,
+      "eval_steps_per_second": 14.218,
+      "step": 597000
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 6.33776026890478e-05,
+      "loss": 0.2019,
+      "step": 597500
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 6.326519321235139e-05,
+      "loss": 0.2025,
+      "step": 598000
+    },
+    {
+      "epoch": 6.31,
+      "eval_loss": 0.19144007563591003,
+      "eval_runtime": 2.4829,
+      "eval_samples_per_second": 925.137,
+      "eval_steps_per_second": 14.499,
+      "step": 598000
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 6.315282948797776e-05,
+      "loss": 0.2022,
+      "step": 598500
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 6.304051182312496e-05,
+      "loss": 0.2021,
+      "step": 599000
+    },
+    {
+      "epoch": 6.32,
+      "eval_loss": 0.18959102034568787,
+      "eval_runtime": 2.5681,
+      "eval_samples_per_second": 894.45,
+      "eval_steps_per_second": 14.018,
+      "step": 599000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 6.292824052486525e-05,
+      "loss": 0.2023,
+      "step": 599500
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 6.281601590014407e-05,
+      "loss": 0.2018,
+      "step": 600000
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 0.1930903047323227,
+      "eval_runtime": 2.4861,
+      "eval_samples_per_second": 923.926,
+      "eval_steps_per_second": 14.48,
+      "step": 600000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.135882542105388e+22,
+  "total_flos": 4.205982803135735e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8bbf9aa941f450bae2344c4f3ace716b8d409472808a8af9bbe468eecca5b1
+oid sha256:da8af5408d1b5fb7d927d259061d24f1b2ad7a5b6145f36a7ec1c919a2b9edd8
 size 449471589