Training in progress, step 940000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91affa27b1d7efbf8500bedc38da98f478db48755c9fd801061dc5b4d75ce322
+oid sha256:a56a8f0ae8b5b9f2aec995742da47ff25dfe07ebb15ec7ee61db4a763d8289c8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87aca36ccecce90e6bf8bad654e975fd48ce737fd544cee69dc518d7e58bab00
+oid sha256:c00c6557048c11e66b95589de29730bca35a40598e37017f064297cb592c4f93
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d510ecd6732523942dd3424a57ac538e5be0c4138342f6ae56c3919c1d5b02
+oid sha256:8e8be78115c1d7a8b7fd3ba012ea9e0890f7c8e7c74970d79909bd336b578ec4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574b715a429374590efb47af45146a59e5fe229195a8d8f19378988db5b1824a
+oid sha256:a534ad0e2fa8f314cc3ae9bccc570e59499e6b5c546b12853d32ae75d416e0e6
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2a278c4b4e6f37059e27f47d47f9a954e78837662918db9679befac603ce60
-size 14439
+oid sha256:a2825291049da8c0b63497c412e6d53ce0d529ebee7d30f4f47c2a1d271fc14d
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdc5281c9ba61c674d20be79979807c56cc05caf6ef31ad1992614f01419db4
+oid sha256:087eacd702285507c39ac952397dc9f6dae700c001504f218d7b716e9f249005
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0e1b3397ffbcdba72f77e0e72529212805b3efe290aff36c3ecd969d87bca4
+oid sha256:3dab84d4b75593cd9349f424c4371ea8ac2493751bc544a294c8ef74a18b08e9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.201291859453022,
-  "global_step": 930000,
+  "epoch": 14.353993922457892,
+  "global_step": 940000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6888,11 +6888,85 @@
       "eval_samples_per_second": 1036.936,
       "eval_steps_per_second": 16.591,
       "step": 930000
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 1.1814402460652382e-05,
+      "loss": 0.2291,
+      "step": 931000
+    },
+    {
+      "epoch": 14.23,
+      "learning_rate": 1.176241239543558e-05,
+      "loss": 0.229,
+      "step": 932000
+    },
+    {
+      "epoch": 14.25,
+      "learning_rate": 1.171116856554418e-05,
+      "loss": 0.2291,
+      "step": 933000
+    },
+    {
+      "epoch": 14.26,
+      "learning_rate": 1.1660671531372517e-05,
+      "loss": 0.2301,
+      "step": 934000
+    },
+    {
+      "epoch": 14.28,
+      "learning_rate": 1.1610921845148052e-05,
+      "loss": 0.2295,
+      "step": 935000
+    },
+    {
+      "epoch": 14.28,
+      "eval_runtime": 0.8534,
+      "eval_samples_per_second": 1171.832,
+      "eval_steps_per_second": 18.749,
+      "step": 935000
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 1.156192005092539e-05,
+      "loss": 0.2301,
+      "step": 936000
+    },
+    {
+      "epoch": 14.31,
+      "learning_rate": 1.1513666684580308e-05,
+      "loss": 0.2291,
+      "step": 937000
+    },
+    {
+      "epoch": 14.32,
+      "learning_rate": 1.1466162273803876e-05,
+      "loss": 0.2292,
+      "step": 938000
+    },
+    {
+      "epoch": 14.34,
+      "learning_rate": 1.1419407338096732e-05,
+      "loss": 0.2287,
+      "step": 939000
+    },
+    {
+      "epoch": 14.35,
+      "learning_rate": 1.1373402388763346e-05,
+      "loss": 0.2286,
+      "step": 940000
+    },
+    {
+      "epoch": 14.35,
+      "eval_runtime": 0.7875,
+      "eval_samples_per_second": 1269.803,
+      "eval_steps_per_second": 20.317,
+      "step": 940000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.519315076868202e+22,
+  "total_flos": 6.589415337898549e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87aca36ccecce90e6bf8bad654e975fd48ce737fd544cee69dc518d7e58bab00
+oid sha256:c00c6557048c11e66b95589de29730bca35a40598e37017f064297cb592c4f93
 size 449471589