Training in progress, step 310000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce18f0748d256d97c3ffa8fd0dca4af493eeb80a1e3c680178d29c9ddddf382
+oid sha256:0b00071efc84beb2feace3b5a3f0a50851e6aef7cfc9f54978cffaf5df2df0e7
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674942f3a22b761c6237130c7c1c65ef4ae9c18ea51c2e94629488e89aee1787
+oid sha256:e7e2ee92a6eaf05a81d8cc01dee92eda2af9b205d2ac738942206a8dc6fa3a0e
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79632fe258ae9bf0159b29eb8f75054c68c6d067b87a65bb1e5ce3d8111e8b99
-size 14439
+oid sha256:aa0bf92a765d09c7474a24e0b91454931a94402222241ea8b1d6ef7d1cfb2a2f
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30038ba0292443919b51298718047b6773e6d7e41921e311f8e57713dd04b046
-size 14503
+oid sha256:b7f1efcee6a815bf5e7abad62d9857979801ac6926e6361e60063a1830c0e0cf
+size 14567

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c3448ae7122fabd57f3afe7b464dea056b6f69fb30306ac34573daa9a6e577
+oid sha256:e56ee00cae3dff0125b532f391da7e095ad5ffe308a7da8b824c5f69e3852d28
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2edb4ed6c12c84109dcab5c035479f8f5be0a6003c13da100daa3666a0ffbb98
-size 14439
+oid sha256:063d140296abe43f5c05bc7e1492ad16b8cd4d6e4e44bfa11ee5374ad0035817
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09aaf2baea19ad11e593b229d87541fdc460178a4ce9400acb0896ac15b65425
+oid sha256:510bbb6396dcecf907e43c584a6f575f85c197777553938b74c3d9882298be6b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.5810618901461355,
-  "global_step": 300000,
+  "epoch": 4.733763953151007,
+  "global_step": 310000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2226,11 +2226,85 @@
       "eval_samples_per_second": 994.612,
       "eval_steps_per_second": 15.914,
       "step": 300000
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 0.00012723914147245663,
+      "loss": 0.2906,
+      "step": 301000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.00012706805633142863,
+      "loss": 0.2906,
+      "step": 302000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 0.00012689645646167755,
+      "loss": 0.2902,
+      "step": 303000
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.00012672434373979207,
+      "loss": 0.291,
+      "step": 304000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.00012655172004796936,
+      "loss": 0.2899,
+      "step": 305000
+    },
+    {
+      "epoch": 4.66,
+      "eval_runtime": 1.0975,
+      "eval_samples_per_second": 911.158,
+      "eval_steps_per_second": 14.579,
+      "step": 305000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.00012637858727399448,
+      "loss": 0.2898,
+      "step": 306000
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.00012620494731121966,
+      "loss": 0.2896,
+      "step": 307000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 0.00012603080205854372,
+      "loss": 0.2894,
+      "step": 308000
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 0.00012585615342039126,
+      "loss": 0.2894,
+      "step": 309000
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 0.0001256810033066918,
+      "loss": 0.2894,
+      "step": 310000
+    },
+    {
+      "epoch": 4.73,
+      "eval_runtime": 1.0481,
+      "eval_samples_per_second": 954.11,
+      "eval_steps_per_second": 15.266,
+      "step": 310000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.1030052026378193e+22,
+  "total_flos": 2.1731054636681665e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674942f3a22b761c6237130c7c1c65ef4ae9c18ea51c2e94629488e89aee1787
+oid sha256:e7e2ee92a6eaf05a81d8cc01dee92eda2af9b205d2ac738942206a8dc6fa3a0e
 size 449471589