Training in progress, step 770000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744468515cac0c3240d5c1cd517f8b57698c194dc97662786f3cf3dc69ab9490
+oid sha256:b5105a858ffab625db37b27758634fe5b8c1b35907833c43fc65bb602a31b990
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:072104784f649f9e9dd18a714fb4b5fb2fe7b25afb0493e74c9a0d1196d29cde
+oid sha256:c648013f5ed7befcc6d0574bd56efee82e2bbfbe3a861e2cb87c9284829b027c
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56c75b12f46e7f7cf7eed48370bee49af2c2cec1c8baea805cd0e9dfeb5cc0f
+oid sha256:9a30f32fec6ec5c21d68cc3a1d22e4da7da026f7616b5ae278ca7ceb322b0d09
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e175165a3eac134d38f788fbf76210f5cf20ad100371de72779cc7de9da4b86f
+oid sha256:c87245ad3a3a643f81f3f2450a9b83d6c09d17eda4b9f8dcf29bf1d0ea618777
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.119045760235549,
-  "global_step": 760000,
+  "epoch": 8.230574484458472,
+  "global_step": 770000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15206,11 +15206,211 @@
       "eval_samples_per_second": 845.029,
       "eval_steps_per_second": 13.244,
       "step": 760000
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 3.083097584193693e-05,
+      "loss": 0.1896,
+      "step": 760500
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 3.0748661009182616e-05,
+      "loss": 0.1898,
+      "step": 761000
+    },
+    {
+      "epoch": 8.13,
+      "eval_loss": 0.17937108874320984,
+      "eval_runtime": 2.6571,
+      "eval_samples_per_second": 864.488,
+      "eval_steps_per_second": 13.549,
+      "step": 761000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 3.066648082770845e-05,
+      "loss": 0.19,
+      "step": 761500
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 3.0584435522191896e-05,
+      "loss": 0.1893,
+      "step": 762000
+    },
+    {
+      "epoch": 8.14,
+      "eval_loss": 0.18026237189769745,
+      "eval_runtime": 2.6859,
+      "eval_samples_per_second": 855.204,
+      "eval_steps_per_second": 13.403,
+      "step": 762000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 3.0502525316941673e-05,
+      "loss": 0.1896,
+      "step": 762500
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 3.0420750435897183e-05,
+      "loss": 0.1895,
+      "step": 763000
+    },
+    {
+      "epoch": 8.15,
+      "eval_loss": 0.18032604455947876,
+      "eval_runtime": 2.6799,
+      "eval_samples_per_second": 857.123,
+      "eval_steps_per_second": 13.433,
+      "step": 763000
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 3.0339111102627846e-05,
+      "loss": 0.1897,
+      "step": 763500
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 3.025760754033246e-05,
+      "loss": 0.1892,
+      "step": 764000
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.18092449009418488,
+      "eval_runtime": 2.6398,
+      "eval_samples_per_second": 870.157,
+      "eval_steps_per_second": 13.638,
+      "step": 764000
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 3.017623997183864e-05,
+      "loss": 0.1897,
+      "step": 764500
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 3.0095008619602206e-05,
+      "loss": 0.1894,
+      "step": 765000
+    },
+    {
+      "epoch": 8.17,
+      "eval_loss": 0.17851532995700836,
+      "eval_runtime": 2.6678,
+      "eval_samples_per_second": 861.0,
+      "eval_steps_per_second": 13.494,
+      "step": 765000
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 3.0013913705706587e-05,
+      "loss": 0.1892,
+      "step": 765500
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 2.993295545186223e-05,
+      "loss": 0.19,
+      "step": 766000
+    },
+    {
+      "epoch": 8.19,
+      "eval_loss": 0.18047097325325012,
+      "eval_runtime": 2.6997,
+      "eval_samples_per_second": 850.838,
+      "eval_steps_per_second": 13.335,
+      "step": 766000
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 2.9852134079405817e-05,
+      "loss": 0.1897,
+      "step": 766500
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 2.977144980929996e-05,
+      "loss": 0.1895,
+      "step": 767000
+    },
+    {
+      "epoch": 8.2,
+      "eval_loss": 0.1800650954246521,
+      "eval_runtime": 2.6124,
+      "eval_samples_per_second": 879.254,
+      "eval_steps_per_second": 13.78,
+      "step": 767000
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 2.969090286213233e-05,
+      "loss": 0.1896,
+      "step": 767500
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 2.961049345811523e-05,
+      "loss": 0.1891,
+      "step": 768000
+    },
+    {
+      "epoch": 8.21,
+      "eval_loss": 0.18048371374607086,
+      "eval_runtime": 2.7369,
+      "eval_samples_per_second": 839.265,
+      "eval_steps_per_second": 13.153,
+      "step": 768000
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 2.9530221817084937e-05,
+      "loss": 0.1894,
+      "step": 768500
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 2.945008815850097e-05,
+      "loss": 0.1895,
+      "step": 769000
+    },
+    {
+      "epoch": 8.22,
+      "eval_loss": 0.17877112329006195,
+      "eval_runtime": 2.6697,
+      "eval_samples_per_second": 860.384,
+      "eval_steps_per_second": 13.484,
+      "step": 769000
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 2.9370092701445748e-05,
+      "loss": 0.1891,
+      "step": 769500
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 2.929023566462377e-05,
+      "loss": 0.1894,
+      "step": 770000
+    },
+    {
+      "epoch": 8.23,
+      "eval_loss": 0.1808948516845703,
+      "eval_runtime": 2.6258,
+      "eval_samples_per_second": 874.77,
+      "eval_steps_per_second": 13.71,
+      "step": 770000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.327576026726258e+22,
+  "total_flos": 5.397676287756605e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:072104784f649f9e9dd18a714fb4b5fb2fe7b25afb0493e74c9a0d1196d29cde
+oid sha256:c648013f5ed7befcc6d0574bd56efee82e2bbfbe3a861e2cb87c9284829b027c
 size 449471589