Training in progress, step 320000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b00071efc84beb2feace3b5a3f0a50851e6aef7cfc9f54978cffaf5df2df0e7
+oid sha256:e953bb14c52ac73828ddbb8d0fdec2f5d345e3cbc51fce0abb2a9e0782d8fb45
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e2ee92a6eaf05a81d8cc01dee92eda2af9b205d2ac738942206a8dc6fa3a0e
+oid sha256:ebbb0a403c4c85850b5f1bad1d089cdec8ce35c071f9b4d707f0145c3de24b2e
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0bf92a765d09c7474a24e0b91454931a94402222241ea8b1d6ef7d1cfb2a2f
+oid sha256:15759c491e0cbc3c20a789defaa3eb9b1ba5f51f160318f99e2a7896f2394a59
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f1efcee6a815bf5e7abad62d9857979801ac6926e6361e60063a1830c0e0cf
-size 14567
+oid sha256:7549533ede2b1dd6fe53e5571a6126478875eb81cddb6c662ba0261be0e9f079
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56ee00cae3dff0125b532f391da7e095ad5ffe308a7da8b824c5f69e3852d28
+oid sha256:17b33604be61df5ac96216c3e2908cb72d7bc7445f1fbb6123710e746f63011f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063d140296abe43f5c05bc7e1492ad16b8cd4d6e4e44bfa11ee5374ad0035817
+oid sha256:3ecf67d692ebf3eeab712f96e8bcf2b206bea3bf44b342d23dd61fb929784bb0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510bbb6396dcecf907e43c584a6f575f85c197777553938b74c3d9882298be6b
+oid sha256:6e51637100435f199d054651c862159e9a427229daea6570b6d23739f5a17de3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.733763953151007,
-  "global_step": 310000,
+  "epoch": 4.886466016155878,
+  "global_step": 320000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2300,11 +2300,85 @@
       "eval_samples_per_second": 954.11,
       "eval_steps_per_second": 15.266,
       "step": 310000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 0.0001255053536328589,
+      "loss": 0.2887,
+      "step": 311000
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.0001253292063197693,
+      "loss": 0.2887,
+      "step": 312000
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 0.0001251525632937418,
+      "loss": 0.2886,
+      "step": 313000
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 0.00012497542648651615,
+      "loss": 0.2887,
+      "step": 314000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 0.00012479779783523216,
+      "loss": 0.2883,
+      "step": 315000
+    },
+    {
+      "epoch": 4.81,
+      "eval_runtime": 1.0333,
+      "eval_samples_per_second": 967.804,
+      "eval_steps_per_second": 15.485,
+      "step": 315000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.00012461967928240828,
+      "loss": 0.2883,
+      "step": 316000
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 0.00012444107277592047,
+      "loss": 0.2877,
+      "step": 317000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 0.0001242619802689809,
+      "loss": 0.2879,
+      "step": 318000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.00012408240372011647,
+      "loss": 0.2876,
+      "step": 319000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0001239023450931476,
+      "loss": 0.2874,
+      "step": 320000
+    },
+    {
+      "epoch": 4.89,
+      "eval_runtime": 1.04,
+      "eval_samples_per_second": 961.537,
+      "eval_steps_per_second": 15.385,
+      "step": 320000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.1731054636681665e+22,
+  "total_flos": 2.2432057246985136e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e2ee92a6eaf05a81d8cc01dee92eda2af9b205d2ac738942206a8dc6fa3a0e
+oid sha256:ebbb0a403c4c85850b5f1bad1d089cdec8ce35c071f9b4d707f0145c3de24b2e
 size 449471589