Training in progress, step 810000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05cce4c1769cad62058c494e3844f2366f5491f558c117a5601783f8f4aca538
+oid sha256:20271fe04ea74ef6c1f5d2a4d1320cc4e3cdd71160c77649afb9825f61cfb447
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6d411bd0a38f2cff0679d6b8d24e5bbf393f3e64bddfcb6100439be517e6e9
+oid sha256:5cd0bb237b46c76aefe15f9280bc4734a0b83f8b031790d8bd933f10088a4b40
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4556b030f4b10d8ec54832aab87f365d5f534e5c8f2aba138109a6119b60109f
+oid sha256:5c229483d7671f93f7f6ccbe0ea6c92e0f0e6de8b45b16f50c28569110970a54
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cc3662a36c24e948440a9c5383a944373362c15a98a0fb5317ec1e024dd4c4
+oid sha256:80ff99717fc66d7e2670093ac4b787c0d4e68c8bb6b50d5d8a0a59479daaf2a3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.565160657127244,
-  "global_step": 800000,
+  "epoch": 8.676689381350167,
+  "global_step": 810000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16006,11 +16006,211 @@
       "eval_samples_per_second": 853.408,
       "eval_steps_per_second": 13.375,
       "step": 800000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 2.4689149133701672e-05,
+      "loss": 0.1867,
+      "step": 800500
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 2.461828514290513e-05,
+      "loss": 0.1869,
+      "step": 801000
+    },
+    {
+      "epoch": 8.58,
+      "eval_loss": 0.17704518139362335,
+      "eval_runtime": 2.7376,
+      "eval_samples_per_second": 839.048,
+      "eval_steps_per_second": 13.15,
+      "step": 801000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 2.4547572563602267e-05,
+      "loss": 0.1872,
+      "step": 801500
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 2.447701158911855e-05,
+      "loss": 0.1868,
+      "step": 802000
+    },
+    {
+      "epoch": 8.59,
+      "eval_loss": 0.17794357240200043,
+      "eval_runtime": 2.6487,
+      "eval_samples_per_second": 867.219,
+      "eval_steps_per_second": 13.592,
+      "step": 802000
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 2.4406602412365027e-05,
+      "loss": 0.187,
+      "step": 802500
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 2.4336345225837658e-05,
+      "loss": 0.1872,
+      "step": 803000
+    },
+    {
+      "epoch": 8.6,
+      "eval_loss": 0.1776154637336731,
+      "eval_runtime": 2.7206,
+      "eval_samples_per_second": 844.313,
+      "eval_steps_per_second": 13.233,
+      "step": 803000
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 2.4266240221616956e-05,
+      "loss": 0.1873,
+      "step": 803500
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 2.4196287591367296e-05,
+      "loss": 0.1868,
+      "step": 804000
+    },
+    {
+      "epoch": 8.61,
+      "eval_loss": 0.176628977060318,
+      "eval_runtime": 2.6337,
+      "eval_samples_per_second": 872.144,
+      "eval_steps_per_second": 13.669,
+      "step": 804000
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 2.412648752633649e-05,
+      "loss": 0.1869,
+      "step": 804500
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 2.405684021735527e-05,
+      "loss": 0.1866,
+      "step": 805000
+    },
+    {
+      "epoch": 8.62,
+      "eval_loss": 0.1774420291185379,
+      "eval_runtime": 2.6036,
+      "eval_samples_per_second": 882.223,
+      "eval_steps_per_second": 13.827,
+      "step": 805000
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 2.39873458548367e-05,
+      "loss": 0.1871,
+      "step": 805500
+    },
+    {
+      "epoch": 8.63,
+      "learning_rate": 2.3918004628775736e-05,
+      "loss": 0.1871,
+      "step": 806000
+    },
+    {
+      "epoch": 8.63,
+      "eval_loss": 0.1766408383846283,
+      "eval_runtime": 2.6553,
+      "eval_samples_per_second": 865.055,
+      "eval_steps_per_second": 13.558,
+      "step": 806000
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 2.3848816728748643e-05,
+      "loss": 0.187,
+      "step": 806500
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 2.3779782343912463e-05,
+      "loss": 0.1871,
+      "step": 807000
+    },
+    {
+      "epoch": 8.64,
+      "eval_loss": 0.17578239738941193,
+      "eval_runtime": 2.6261,
+      "eval_samples_per_second": 874.674,
+      "eval_steps_per_second": 13.708,
+      "step": 807000
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 2.3710901663004604e-05,
+      "loss": 0.1867,
+      "step": 807500
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 2.364217487434221e-05,
+      "loss": 0.1867,
+      "step": 808000
+    },
+    {
+      "epoch": 8.65,
+      "eval_loss": 0.17686133086681366,
+      "eval_runtime": 2.5799,
+      "eval_samples_per_second": 890.356,
+      "eval_steps_per_second": 13.954,
+      "step": 808000
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 2.3573602165821668e-05,
+      "loss": 0.187,
+      "step": 808500
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 2.3505183724918196e-05,
+      "loss": 0.1867,
+      "step": 809000
+    },
+    {
+      "epoch": 8.67,
+      "eval_loss": 0.1787070780992508,
+      "eval_runtime": 2.6677,
+      "eval_samples_per_second": 861.032,
+      "eval_steps_per_second": 13.495,
+      "step": 809000
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 2.3436919738685132e-05,
+      "loss": 0.1864,
+      "step": 809500
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 2.3368810393753687e-05,
+      "loss": 0.1866,
+      "step": 810000
+    },
+    {
+      "epoch": 8.68,
+      "eval_loss": 0.17782823741436005,
+      "eval_runtime": 2.6203,
+      "eval_samples_per_second": 876.614,
+      "eval_steps_per_second": 13.739,
+      "step": 810000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.607977070847647e+22,
+  "total_flos": 5.678077331877994e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6d411bd0a38f2cff0679d6b8d24e5bbf393f3e64bddfcb6100439be517e6e9
+oid sha256:5cd0bb237b46c76aefe15f9280bc4734a0b83f8b031790d8bd933f10088a4b40
 size 449471589