Training in progress, step 720000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b4f5708667fda381a1ab66f80f980e40daa1a707f100921fdae99c2db5e334
+oid sha256:a026519ac0ff0c3f1289d77d525568015b7857390a799b13b0638f4259cfacf4
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7dafd574b6c18c8b0838dfe7c6fd825d5c841584d2d916d404b3af2a78c999
+oid sha256:1129389ce9bcf343c0f3cd3aed67df3cad67444a99046ba4741058e82d747211
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7fee820bb752afb8f603542eaf0336c5e7c41a61ac1c1147dd536354714a47
+oid sha256:aae7d49de4956e7c91d479fafd3b4d2ed56ba19e47ab8cacf05f2f824d1b2a28
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2561ae8bb02e359a9713b9977fa63ca1b6854d76fd4510a159042ccdda7aff7
+oid sha256:cebea51ed6ff0008f8a6cacb32ade3887e6067fbd934b29f2ec5132ff8c8883a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330a4501421948528f860e170d41c93583e955ea4b60c53d7ee73adbfd6aa9e2
+oid sha256:b973a3a6eadc1982d4cc67d2b41bd0f42e96e285ea7f0a54482ed3274795569d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014d339be1f5943d92bce27af7e1e9d7ced53c7dfd7c34412b3de983c10ddb04
+oid sha256:41cae4c446a75e16a0da874d105e34b48768289141d592a014669a4b78d9fe62
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099db39f4d942e6817b283451a401c36d6ba4059eea01842b742770347fceca3
+oid sha256:ed967cda4343e3de3b9b5189aaee239028fc09bd89309a5564f84c1374d13bfc
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.841846473345855,
-  "global_step": 710000,
+  "epoch": 10.994548536350726,
+  "global_step": 720000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5260,11 +5260,85 @@
       "eval_samples_per_second": 1338.326,
       "eval_steps_per_second": 21.413,
       "step": 710000
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 3.960771378517049e-05,
+      "loss": 0.2438,
+      "step": 711000
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 3.941887568171766e-05,
+      "loss": 0.2464,
+      "step": 712000
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 3.923048136693873e-05,
+      "loss": 0.2445,
+      "step": 713000
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 3.904253290108369e-05,
+      "loss": 0.2435,
+      "step": 714000
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 3.885503233952689e-05,
+      "loss": 0.2446,
+      "step": 715000
+    },
+    {
+      "epoch": 10.92,
+      "eval_runtime": 0.8432,
+      "eval_samples_per_second": 1186.017,
+      "eval_steps_per_second": 18.976,
+      "step": 715000
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 3.86679817327444e-05,
+      "loss": 0.2432,
+      "step": 716000
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 3.848138312629171e-05,
+      "loss": 0.2433,
+      "step": 717000
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 3.8295238560781317e-05,
+      "loss": 0.2436,
+      "step": 718000
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 3.810955007186029e-05,
+      "loss": 0.2433,
+      "step": 719000
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 3.792431969018824e-05,
+      "loss": 0.243,
+      "step": 720000
+    },
+    {
+      "epoch": 10.99,
+      "eval_runtime": 0.7755,
+      "eval_samples_per_second": 1289.466,
+      "eval_steps_per_second": 20.631,
+      "step": 720000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.97711196247316e+22,
+  "total_flos": 5.047212223503507e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7dafd574b6c18c8b0838dfe7c6fd825d5c841584d2d916d404b3af2a78c999
+oid sha256:1129389ce9bcf343c0f3cd3aed67df3cad67444a99046ba4741058e82d747211
 size 449471589