Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0245292760b62513586c26ecff5192e7b5ad83e4daf7f643ddd61d6aad92d500
-size 893438545
+oid sha256:99c98283f4eee4bb758c71ec62014a67a4552b0758eea313df980226947b2ade
+size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a835f354ab09525c33e280985ebd252ba93511526376509b024f45deb2f1ce
+oid sha256:bd35fbb667c7c8278fafcb67c5061ab4d6f220dcd06ca61480a2cb447bf773e4
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b21161fe5b062917103c130cb71a421351140e37488dc23aeb32719319cb94c
+oid sha256:8876c50e1ce3fb4970a80eb0614074ef9eef11af29d4d4a411c34a56cba5b25f
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3871d161af5dbcdf99fa548f2814e73dcf94f0ccbb13b2f6c2217e93008fee6
+oid sha256:128b78bf39c57c4ee291c8fde7c2cc6eead3eaf12fff730867105475c3c602a9
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d89e9311da168e5510e65cc996f92e058a83847391982c385da0d08e788c7ea
+oid sha256:1cdae046482883391f6321c0f8158f1008a657f80a5068452ca97c45f0f69142
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.917812989726624,
-  "global_step": 65000,
+  "epoch": 5.353125544140693,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -890,11 +890,79 @@
       "eval_samples_per_second": 64.0,
       "eval_steps_per_second": 1.011,
       "step": 65000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 3.4181250060824136e-05,
+      "loss": 0.4105,
+      "step": 65500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.355352132804756e-05,
+      "loss": 0.4104,
+      "step": 66000
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 3.293118057384647e-05,
+      "loss": 0.4109,
+      "step": 66500
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 3.231438135148965e-05,
+      "loss": 0.41,
+      "step": 67000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 3.17044922751775e-05,
+      "loss": 0.4098,
+      "step": 67500
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 3.109921943108062e-05,
+      "loss": 0.4084,
+      "step": 68000
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 3.0499940127827767e-05,
+      "loss": 0.4083,
+      "step": 68500
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 2.990680222861982e-05,
+      "loss": 0.4088,
+      "step": 69000
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 2.9319952081358052e-05,
+      "loss": 0.408,
+      "step": 69500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 2.8739534482535135e-05,
+      "loss": 0.4077,
+      "step": 70000
+    },
+    {
+      "epoch": 5.35,
+      "eval_loss": 0.38781091570854187,
+      "eval_runtime": 90.5362,
+      "eval_samples_per_second": 55.227,
+      "eval_steps_per_second": 0.873,
+      "step": 70000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.061349633329319e+21,
+  "total_flos": 3.29682408031201e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a835f354ab09525c33e280985ebd252ba93511526376509b024f45deb2f1ce
+oid sha256:bd35fbb667c7c8278fafcb67c5061ab4d6f220dcd06ca61480a2cb447bf773e4
 size 449471589