Training in progress, step 820000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20271fe04ea74ef6c1f5d2a4d1320cc4e3cdd71160c77649afb9825f61cfb447
+oid sha256:f6d93c3e982e0579f40b8abbb458ec9e37e56aeab75677fc246cecb087804c2e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd0bb237b46c76aefe15f9280bc4734a0b83f8b031790d8bd933f10088a4b40
+oid sha256:41345120e0d1385984c4967bb7df3bbe42ffb08d61340ff50f089fccaf2a5880
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
+oid sha256:d63a66ccb6dc97ab9b83be4c1a0e1c26e5449019e9e3ce121febf772eda3a493
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ff99717fc66d7e2670093ac4b787c0d4e68c8bb6b50d5d8a0a59479daaf2a3
+oid sha256:c63a65d51252613e1cd5f3ab255f2a8e56d55631776ee22be37789c5802ebbf2
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.676689381350167,
-  "global_step": 810000,
+  "epoch": 8.78821810557309,
+  "global_step": 820000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16206,11 +16206,211 @@
       "eval_samples_per_second": 876.614,
       "eval_steps_per_second": 13.739,
       "step": 810000
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 2.3300855876332162e-05,
+      "loss": 0.1868,
+      "step": 810500
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 2.32330563722056e-05,
+      "loss": 0.1864,
+      "step": 811000
+    },
+    {
+      "epoch": 8.69,
+      "eval_loss": 0.1779273897409439,
+      "eval_runtime": 2.7339,
+      "eval_samples_per_second": 840.196,
+      "eval_steps_per_second": 13.168,
+      "step": 811000
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 2.316541206673529e-05,
+      "loss": 0.1865,
+      "step": 811500
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 2.309792314485815e-05,
+      "loss": 0.1866,
+      "step": 812000
+    },
+    {
+      "epoch": 8.7,
+      "eval_loss": 0.17686782777309418,
+      "eval_runtime": 2.8998,
+      "eval_samples_per_second": 792.124,
+      "eval_steps_per_second": 12.415,
+      "step": 812000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 2.3030589791086353e-05,
+      "loss": 0.1865,
+      "step": 812500
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 2.2963412189506695e-05,
+      "loss": 0.1869,
+      "step": 813000
+    },
+    {
+      "epoch": 8.71,
+      "eval_loss": 0.1769571304321289,
+      "eval_runtime": 2.6694,
+      "eval_samples_per_second": 860.483,
+      "eval_steps_per_second": 13.486,
+      "step": 813000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 2.2896390523780156e-05,
+      "loss": 0.1865,
+      "step": 813500
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 2.282952497714145e-05,
+      "loss": 0.186,
+      "step": 814000
+    },
+    {
+      "epoch": 8.72,
+      "eval_loss": 0.17855176329612732,
+      "eval_runtime": 2.6874,
+      "eval_samples_per_second": 854.735,
+      "eval_steps_per_second": 13.396,
+      "step": 814000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 2.2762815732398387e-05,
+      "loss": 0.1862,
+      "step": 814500
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 2.2696262971931538e-05,
+      "loss": 0.1863,
+      "step": 815000
+    },
+    {
+      "epoch": 8.73,
+      "eval_loss": 0.17720898985862732,
+      "eval_runtime": 2.6031,
+      "eval_samples_per_second": 882.4,
+      "eval_steps_per_second": 13.83,
+      "step": 815000
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 2.2629866877693577e-05,
+      "loss": 0.1865,
+      "step": 815500
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 2.2563627631208887e-05,
+      "loss": 0.1869,
+      "step": 816000
+    },
+    {
+      "epoch": 8.74,
+      "eval_loss": 0.17861302196979523,
+      "eval_runtime": 2.6611,
+      "eval_samples_per_second": 863.188,
+      "eval_steps_per_second": 13.528,
+      "step": 816000
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.2497545413573065e-05,
+      "loss": 0.1863,
+      "step": 816500
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.2431620405452336e-05,
+      "loss": 0.1859,
+      "step": 817000
+    },
+    {
+      "epoch": 8.75,
+      "eval_loss": 0.17606213688850403,
+      "eval_runtime": 2.6726,
+      "eval_samples_per_second": 859.474,
+      "eval_steps_per_second": 13.47,
+      "step": 817000
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 2.23658527870832e-05,
+      "loss": 0.1863,
+      "step": 817500
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 2.230024273827179e-05,
+      "loss": 0.1862,
+      "step": 818000
+    },
+    {
+      "epoch": 8.77,
+      "eval_loss": 0.17465642094612122,
+      "eval_runtime": 2.6831,
+      "eval_samples_per_second": 856.102,
+      "eval_steps_per_second": 13.417,
+      "step": 818000
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 2.223479043839345e-05,
+      "loss": 0.1867,
+      "step": 818500
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 2.216949606639231e-05,
+      "loss": 0.1863,
+      "step": 819000
+    },
+    {
+      "epoch": 8.78,
+      "eval_loss": 0.17773117125034332,
+      "eval_runtime": 2.6871,
+      "eval_samples_per_second": 854.84,
+      "eval_steps_per_second": 13.398,
+      "step": 819000
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 2.2104359800780665e-05,
+      "loss": 0.1859,
+      "step": 819500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 2.2039381819638596e-05,
+      "loss": 0.186,
+      "step": 820000
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.1770503968000412,
+      "eval_runtime": 2.6357,
+      "eval_samples_per_second": 871.505,
+      "eval_steps_per_second": 13.659,
+      "step": 820000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.678077331877994e+22,
+  "total_flos": 5.748177592908341e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd0bb237b46c76aefe15f9280bc4734a0b83f8b031790d8bd933f10088a4b40
+oid sha256:41345120e0d1385984c4967bb7df3bbe42ffb08d61340ff50f089fccaf2a5880
 size 449471589