Training in progress, step 800000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6d0b8731469184859b6e2af2323dc331e9f7e709ceb8418eca6fab2f75e9cb
+oid sha256:05cce4c1769cad62058c494e3844f2366f5491f558c117a5601783f8f4aca538
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c99a6d8856f7a728dbbbf96bf0c858122cdeb2ae96a80fcc6876c29d8e2666
+oid sha256:1f6d411bd0a38f2cff0679d6b8d24e5bbf393f3e64bddfcb6100439be517e6e9
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
+oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d1297302d20060e31d476195b98906c23904815e65152eb2d3ffb7dd074183
+oid sha256:57cc3662a36c24e948440a9c5383a944373362c15a98a0fb5317ec1e024dd4c4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.453631932904319,
-  "global_step": 790000,
+  "epoch": 8.565160657127244,
+  "global_step": 800000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15806,11 +15806,211 @@
       "eval_samples_per_second": 887.972,
       "eval_steps_per_second": 13.917,
       "step": 790000
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 2.6137923994427768e-05,
+      "loss": 0.1881,
+      "step": 790500
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 2.6064073005694758e-05,
+      "loss": 0.1876,
+      "step": 791000
+    },
+    {
+      "epoch": 8.46,
+      "eval_loss": 0.17775288224220276,
+      "eval_runtime": 2.6373,
+      "eval_samples_per_second": 870.95,
+      "eval_steps_per_second": 13.65,
+      "step": 791000
+    },
+    {
+      "epoch": 8.47,
+      "learning_rate": 2.5990369475726598e-05,
+      "loss": 0.1878,
+      "step": 791500
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 2.591681360602595e-05,
+      "loss": 0.1876,
+      "step": 792000
+    },
+    {
+      "epoch": 8.48,
+      "eval_loss": 0.1769527643918991,
+      "eval_runtime": 2.7236,
+      "eval_samples_per_second": 843.383,
+      "eval_steps_per_second": 13.218,
+      "step": 792000
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 2.5843405597691748e-05,
+      "loss": 0.188,
+      "step": 792500
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 2.577014565141866e-05,
+      "loss": 0.1872,
+      "step": 793000
+    },
+    {
+      "epoch": 8.49,
+      "eval_loss": 0.1795121282339096,
+      "eval_runtime": 2.6103,
+      "eval_samples_per_second": 879.963,
+      "eval_steps_per_second": 13.791,
+      "step": 793000
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 2.569703396749661e-05,
+      "loss": 0.1875,
+      "step": 793500
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.562407074581014e-05,
+      "loss": 0.188,
+      "step": 794000
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 0.17704832553863525,
+      "eval_runtime": 2.6547,
+      "eval_samples_per_second": 865.258,
+      "eval_steps_per_second": 13.561,
+      "step": 794000
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.5551256185837897e-05,
+      "loss": 0.1878,
+      "step": 794500
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 2.5478590486652137e-05,
+      "loss": 0.1879,
+      "step": 795000
+    },
+    {
+      "epoch": 8.51,
+      "eval_loss": 0.1775512397289276,
+      "eval_runtime": 2.704,
+      "eval_samples_per_second": 849.487,
+      "eval_steps_per_second": 13.314,
+      "step": 795000
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 2.5406073846918076e-05,
+      "loss": 0.1873,
+      "step": 795500
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 2.533370646489347e-05,
+      "loss": 0.1872,
+      "step": 796000
+    },
+    {
+      "epoch": 8.52,
+      "eval_loss": 0.17661112546920776,
+      "eval_runtime": 2.6375,
+      "eval_samples_per_second": 870.909,
+      "eval_steps_per_second": 13.649,
+      "step": 796000
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 2.526148853842796e-05,
+      "loss": 0.1874,
+      "step": 796500
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 2.5189420264962586e-05,
+      "loss": 0.1875,
+      "step": 797000
+    },
+    {
+      "epoch": 8.53,
+      "eval_loss": 0.17768479883670807,
+      "eval_runtime": 2.6644,
+      "eval_samples_per_second": 862.092,
+      "eval_steps_per_second": 13.511,
+      "step": 797000
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 2.5117501841529297e-05,
+      "loss": 0.1871,
+      "step": 797500
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 2.504573346475026e-05,
+      "loss": 0.1874,
+      "step": 798000
+    },
+    {
+      "epoch": 8.54,
+      "eval_loss": 0.17816244065761566,
+      "eval_runtime": 2.6304,
+      "eval_samples_per_second": 873.254,
+      "eval_steps_per_second": 13.686,
+      "step": 798000
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.497411533083753e-05,
+      "loss": 0.1874,
+      "step": 798500
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.4902647635592324e-05,
+      "loss": 0.187,
+      "step": 799000
+    },
+    {
+      "epoch": 8.55,
+      "eval_loss": 0.17790637910366058,
+      "eval_runtime": 2.6765,
+      "eval_samples_per_second": 858.201,
+      "eval_steps_per_second": 13.45,
+      "step": 799000
+    },
+    {
+      "epoch": 8.56,
+      "learning_rate": 2.483133057440458e-05,
+      "loss": 0.1871,
+      "step": 799500
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 2.476016434225246e-05,
+      "loss": 0.1872,
+      "step": 800000
+    },
+    {
+      "epoch": 8.57,
+      "eval_loss": 0.17626047134399414,
+      "eval_runtime": 2.6916,
+      "eval_samples_per_second": 853.408,
+      "eval_steps_per_second": 13.375,
+      "step": 800000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.5378768098172995e+22,
+  "total_flos": 5.607977070847647e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c99a6d8856f7a728dbbbf96bf0c858122cdeb2ae96a80fcc6876c29d8e2666
+oid sha256:1f6d411bd0a38f2cff0679d6b8d24e5bbf393f3e64bddfcb6100439be517e6e9
 size 449471589