Training in progress, step 870000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5c106db74e42dc51679adae4b838c3fc769d432ccf7ad2ad85b3ca08257bba7
+oid sha256:6e93b07dd856f0dcb5f8d337f717d57dfe290919f17cc810a0ab94d8971b7b8e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b3810346b06651e6d4da88b6c7ab5a4c39c9ed73386ee5a2037c7eee7d792a
+oid sha256:10f95eaff5ba49e944cce01defd24612a1c006bd8b68e7d8b6c201dec46570c0
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91922deb8d5a3dcc119e5076f52f06901e3c1963deb40c98ef6a2a56110eecfe
+oid sha256:be9a5b19b5e6086c1b46537730410e6434224c5e3b8a150ae1f6ffa0b0403da5
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda717afacbcc37a057674c94e7755da0f047a833361ec1cbdae8c11451a0ab4
+oid sha256:d406f3a150dc327386b1fe7c40ac833ace65767a7a63b870db21104ccf5eb518
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5b4e2d79497f15fdd0b8e63be121802d33321a338ff2ad99cc0c2d94fed90e9
+oid sha256:0e79e63475cece03ae5d2720177141fff64fcde5033ba647f27c46dc1cce1e92
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6dd21c66e6f1818612e884579b2f3fe6cd6395a735470cd934326c7e7a0170
+oid sha256:64496346cbbe377de7eb74096cb4a928e4b77370483c82ca56a5a6927676dd2a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af16532ed7776301ec2b0d23baf8c67ba74ec07e3f7e0782860705643ea3c80
+oid sha256:d368f4f79d735aeb82977d11fd8d84913a3919ff8ecbae0982e3d606c331447e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.132377418418923,
-  "global_step": 860000,
+  "epoch": 13.285079481423795,
+  "global_step": 870000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6370,11 +6370,85 @@
       "eval_samples_per_second": 1321.327,
       "eval_steps_per_second": 21.141,
       "step": 860000
+    },
+    {
+      "epoch": 13.15,
+      "learning_rate": 1.726590597701708e-05,
+      "loss": 0.2322,
+      "step": 861000
+    },
+    {
+      "epoch": 13.16,
+      "learning_rate": 1.7163551091488952e-05,
+      "loss": 0.2375,
+      "step": 862000
+    },
+    {
+      "epoch": 13.18,
+      "learning_rate": 1.7061883375298788e-05,
+      "loss": 0.2328,
+      "step": 863000
+    },
+    {
+      "epoch": 13.19,
+      "learning_rate": 1.6960903940268456e-05,
+      "loss": 0.2323,
+      "step": 864000
+    },
+    {
+      "epoch": 13.21,
+      "learning_rate": 1.6860613890692876e-05,
+      "loss": 0.2334,
+      "step": 865000
+    },
+    {
+      "epoch": 13.21,
+      "eval_runtime": 0.7389,
+      "eval_samples_per_second": 1353.416,
+      "eval_steps_per_second": 21.655,
+      "step": 865000
+    },
+    {
+      "epoch": 13.22,
+      "learning_rate": 1.6761014323327962e-05,
+      "loss": 0.233,
+      "step": 866000
+    },
+    {
+      "epoch": 13.24,
+      "learning_rate": 1.6662106327378645e-05,
+      "loss": 0.2334,
+      "step": 867000
+    },
+    {
+      "epoch": 13.25,
+      "learning_rate": 1.6563890984486884e-05,
+      "loss": 0.2333,
+      "step": 868000
+    },
+    {
+      "epoch": 13.27,
+      "learning_rate": 1.6466369368719955e-05,
+      "loss": 0.2324,
+      "step": 869000
+    },
+    {
+      "epoch": 13.29,
+      "learning_rate": 1.6369542546558626e-05,
+      "loss": 0.2324,
+      "step": 870000
+    },
+    {
+      "epoch": 13.29,
+      "eval_runtime": 0.8823,
+      "eval_samples_per_second": 1133.455,
+      "eval_steps_per_second": 18.135,
+      "step": 870000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.028613906723921e+22,
+  "total_flos": 6.098714167754268e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b3810346b06651e6d4da88b6c7ab5a4c39c9ed73386ee5a2037c7eee7d792a
+oid sha256:10f95eaff5ba49e944cce01defd24612a1c006bd8b68e7d8b6c201dec46570c0
 size 449471589