Training in progress, step 110000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2e288361a09b4b7188ac62d2aadda977c3d294af8ad3f73e2b72bd0663ea87
+oid sha256:6c948eebbc33dfa7163a265ead1f1a9361b0c30c12a12de00dcf340d40d2658b
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfd008c5411020d58a84a813d4db30ca837b9cce0a2b859586eb276a2928563
+oid sha256:3496297d45c4ecf853137342e06ee76ffd7a454b5f8f23c88381de10d12213d2
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f9af544e31603097b82ac1d9757b18d1e77cd9d3f5e0d82ff6f70151a0ec04
-size 14503
+oid sha256:adcae24276cfe7a6f029d01f999621482dc39224a9126d96b9666e8134968416
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e543431b9b9286d502e9e435479120e37dfd67af853c03aa4e1515f6425d35
+oid sha256:50b86582c3ae12c705a7005fed2da8884791451301066581e22169aa8046a6bd
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d6b11ee335cf1f946095db74d4fad452219b5271b7968de8a4d7e06234c4ee
+oid sha256:9ea4115312e60b99085371b9865a77942fe890528298791f0e387803437d5ebb
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b705ae3e4d654b3daa3e7cb177baf9ea0f4c55d7b0f6bedb7d163c3dc6d902c
-size 14503
+oid sha256:9811453ee080e5df1835ce925467584d500ae5c97c544e104ff63747920507e0
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0b752b3079dc9be868ddd61d4a48c6f227ceaa95b4267c4d5e0911b7baba7b
+oid sha256:4aabac21e516317a7b98a87a94ce8a8b7afae82a6e696839a4840e30fc5507ba
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.527020630048712,
-  "global_step": 100000,
+  "epoch": 1.6797226930535831,
+  "global_step": 110000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -746,11 +746,85 @@
       "eval_samples_per_second": 995.424,
       "eval_steps_per_second": 15.927,
       "step": 100000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00014900681246730852,
+      "loss": 0.3643,
+      "step": 101000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00014896757904898125,
+      "loss": 0.3646,
+      "step": 102000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00014892759141225904,
+      "loss": 0.3628,
+      "step": 103000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00014888684999444035,
+      "loss": 0.3616,
+      "step": 104000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00014884535524106675,
+      "loss": 0.3604,
+      "step": 105000
+    },
+    {
+      "epoch": 1.6,
+      "eval_runtime": 1.0499,
+      "eval_samples_per_second": 952.499,
+      "eval_steps_per_second": 15.24,
+      "step": 105000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00014880310760591824,
+      "loss": 0.3594,
+      "step": 106000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0001487601075510082,
+      "loss": 0.3597,
+      "step": 107000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001487163555465783,
+      "loss": 0.3583,
+      "step": 108000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001486718520710935,
+      "loss": 0.3583,
+      "step": 109000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00014862659761123663,
+      "loss": 0.3558,
+      "step": 110000
+    },
+    {
+      "epoch": 1.68,
+      "eval_runtime": 1.0153,
+      "eval_samples_per_second": 984.91,
+      "eval_steps_per_second": 15.759,
+      "step": 110000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 7.010019532353227e+21,
+  "total_flos": 7.711022142656698e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfd008c5411020d58a84a813d4db30ca837b9cce0a2b859586eb276a2928563
+oid sha256:3496297d45c4ecf853137342e06ee76ffd7a454b5f8f23c88381de10d12213d2
 size 449471589