Training in progress, step 930000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37962abda8557285d298a4265c60f4356df61e7cc10bd44c3063d910102d66d3
+oid sha256:91affa27b1d7efbf8500bedc38da98f478db48755c9fd801061dc5b4d75ce322
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f1c4302a150ebf621ef207481964f3a7603e3f271a1522dc7c4f830b5f8ea8
+oid sha256:87aca36ccecce90e6bf8bad654e975fd48ce737fd544cee69dc518d7e58bab00
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f7de72f01c7df685d896df6cd18118f7cd962784b86c13c1ec4716f711fe5e
-size 14439
+oid sha256:e3d510ecd6732523942dd3424a57ac538e5be0c4138342f6ae56c3919c1d5b02
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce3ab5e3a6adf4b5050188a365eda6e65d45b5f880ed022a630511122a962d8
+oid sha256:574b715a429374590efb47af45146a59e5fe229195a8d8f19378988db5b1824a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac1435372cea6f546c378b27a4b5fc759dcb93ae36e129dcb0cfa5374977cc3
-size 14503
+oid sha256:cd2a278c4b4e6f37059e27f47d47f9a954e78837662918db9679befac603ce60
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7314965ea42ee1f19abe451e572b5d6938b7b63a561ae48af7903b9728329e39
+oid sha256:5bdc5281c9ba61c674d20be79979807c56cc05caf6ef31ad1992614f01419db4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df508c344c1f04d3b388cef9605593fbfd129cd18e2830701d3110873541479
+oid sha256:3b0e1b3397ffbcdba72f77e0e72529212805b3efe290aff36c3ecd969d87bca4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.04858979644815,
-  "global_step": 920000,
+  "epoch": 14.201291859453022,
+  "global_step": 930000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6814,11 +6814,85 @@
       "eval_samples_per_second": 1300.053,
       "eval_steps_per_second": 20.801,
       "step": 920000
+    },
+    {
+      "epoch": 14.06,
+      "learning_rate": 1.2375216942216713e-05,
+      "loss": 0.2306,
+      "step": 921000
+    },
+    {
+      "epoch": 14.08,
+      "learning_rate": 1.2315797137640906e-05,
+      "loss": 0.2298,
+      "step": 922000
+    },
+    {
+      "epoch": 14.09,
+      "learning_rate": 1.225711751666363e-05,
+      "loss": 0.2295,
+      "step": 923000
+    },
+    {
+      "epoch": 14.11,
+      "learning_rate": 1.2199178720995825e-05,
+      "loss": 0.2299,
+      "step": 924000
+    },
+    {
+      "epoch": 14.12,
+      "learning_rate": 1.2141981384246874e-05,
+      "loss": 0.23,
+      "step": 925000
+    },
+    {
+      "epoch": 14.12,
+      "eval_runtime": 0.827,
+      "eval_samples_per_second": 1209.23,
+      "eval_steps_per_second": 19.348,
+      "step": 925000
+    },
+    {
+      "epoch": 14.14,
+      "learning_rate": 1.2085526131917685e-05,
+      "loss": 0.2294,
+      "step": 926000
+    },
+    {
+      "epoch": 14.16,
+      "learning_rate": 1.2029813581393866e-05,
+      "loss": 0.2289,
+      "step": 927000
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 1.197484434193893e-05,
+      "loss": 0.2295,
+      "step": 928000
+    },
+    {
+      "epoch": 14.19,
+      "learning_rate": 1.192061901468768e-05,
+      "loss": 0.2293,
+      "step": 929000
+    },
+    {
+      "epoch": 14.2,
+      "learning_rate": 1.1867138192639601e-05,
+      "loss": 0.2293,
+      "step": 930000
+    },
+    {
+      "epoch": 14.2,
+      "eval_runtime": 0.9644,
+      "eval_samples_per_second": 1036.936,
+      "eval_steps_per_second": 16.591,
+      "step": 930000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.449214815837855e+22,
+  "total_flos": 6.519315076868202e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f1c4302a150ebf621ef207481964f3a7603e3f271a1522dc7c4f830b5f8ea8
+oid sha256:87aca36ccecce90e6bf8bad654e975fd48ce737fd544cee69dc518d7e58bab00
 size 449471589