Training in progress, step 75000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c98283f4eee4bb758c71ec62014a67a4552b0758eea313df980226947b2ade
+oid sha256:76c4615a4cfb3d6284272ff52bb78802562addac25bc47aecac63ac87926f3e1
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd35fbb667c7c8278fafcb67c5061ab4d6f220dcd06ca61480a2cb447bf773e4
+oid sha256:7146f8d52213faf72703e230b94defd59fa1f96a4226817fcd5fb6b8b82642d0
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8876c50e1ce3fb4970a80eb0614074ef9eef11af29d4d4a411c34a56cba5b25f
+oid sha256:9592ccee7cd881c490789d0c081e96e3bd0737279468e6c4dda1fabb2546355a
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128b78bf39c57c4ee291c8fde7c2cc6eead3eaf12fff730867105475c3c602a9
+oid sha256:2bcd13dbe306fa5a2ee25614c30d95796b3d386c2395432ebb37f537a50477e0
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cdae046482883391f6321c0f8158f1008a657f80a5068452ca97c45f0f69142
+oid sha256:91b1cc3df0b7ebdcaaea83c1d1aa72c613ada98ab7f2fb32d66ee37180c5fcdf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.353125544140693,
-  "global_step": 70000,
+  "epoch": 5.788438098554762,
+  "global_step": 75000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -958,11 +958,79 @@
       "eval_samples_per_second": 55.227,
       "eval_steps_per_second": 0.873,
       "step": 70000
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 2.8166833668202425e-05,
+      "loss": 0.4087,
+      "step": 70500
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 2.759969559696268e-05,
+      "loss": 0.4088,
+      "step": 71000
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 2.703941452170851e-05,
+      "loss": 0.4073,
+      "step": 71500
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 2.648612868341161e-05,
+      "loss": 0.4084,
+      "step": 72000
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 2.5939974597073566e-05,
+      "loss": 0.4077,
+      "step": 72500
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 2.5402157452548983e-05,
+      "loss": 0.4072,
+      "step": 73000
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 2.487065441284431e-05,
+      "loss": 0.4079,
+      "step": 73500
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 2.4346681719201903e-05,
+      "loss": 0.4076,
+      "step": 74000
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 2.383036865404354e-05,
+      "loss": 0.4069,
+      "step": 74500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 2.332184260989229e-05,
+      "loss": 0.4078,
+      "step": 75000
+    },
+    {
+      "epoch": 5.79,
+      "eval_loss": 0.3861904740333557,
+      "eval_runtime": 75.9418,
+      "eval_samples_per_second": 65.84,
+      "eval_steps_per_second": 1.04,
+      "step": 75000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.29682408031201e+21,
+  "total_flos": 3.5323171476767716e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd35fbb667c7c8278fafcb67c5061ab4d6f220dcd06ca61480a2cb447bf773e4
+oid sha256:7146f8d52213faf72703e230b94defd59fa1f96a4226817fcd5fb6b8b82642d0
 size 449471589