Training in progress, step 350000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f848b004ca69d971cd5024827329eb728808850f3ba285aae6ae2d66c5e9a1ea
+oid sha256:2412ccb8485cd06f014a9d3ba5fd1d0975b7e018d8cff9900e50d917bc1fdf5d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfba4eea74dece360d73bbeb68171b0f24c78184fc1168b69bc18ed84fe5243
+oid sha256:ce357ce3d6b529f718a69a4a019a30353262fc7b3a74b394a29c905d74c6bace
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c5b304cccca8b5844ddfec128e44995bacab68346ff44d01e8476a83259d32
+oid sha256:0cf77bfa9438d97e6b94c6d8adb49ea05fe2793189bc403350f9c99c3df0b70f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6026e8cbd4826fee12ad344c0bb2e47d863082fccddfed4801c66cbc3305df
+oid sha256:4364109b281ee76bcd1190601f937d3035fb627994056b37c2278ac5b210512f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276a39a4e5fc9bbf2fc7156d49a68ce7b2b8c02aa8d52e98747eb94a987f3191
+oid sha256:76fee5dcfb398dec8998f78597ffb2351be755c012a3c680797e842622a89e1a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64783857a8ded45f594a9d4d98ef3bd8c1d156f9923bb0bef61858daa470a8e
+oid sha256:4fe21a6975cd1ab6dcf33bd2f5c91b79d5cc1adb46d481b8d3e4e4d4a9034b6a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61c24f771644e6cd7fccf329b7b1a8621bd89eecc91f4043864ce60f81c96b6
+oid sha256:ef93f126c2f64dc8d66788d8ad781c47bda9696dee0f2e314ba09dc6f0be1c9e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.19187014216562,
-  "global_step": 340000,
+  "epoch": 5.344572205170492,
+  "global_step": 350000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2522,11 +2522,85 @@
       "eval_samples_per_second": 796.26,
       "eval_steps_per_second": 12.74,
       "step": 340000
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.00012001328690714582,
+      "loss": 0.284,
+      "step": 341000
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.00011982312984759068,
+      "loss": 0.2845,
+      "step": 342000
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.00011963253728866778,
+      "loss": 0.2841,
+      "step": 343000
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.00011944151131466675,
+      "loss": 0.284,
+      "step": 344000
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 0.00011925005401461709,
+      "loss": 0.2836,
+      "step": 345000
+    },
+    {
+      "epoch": 5.27,
+      "eval_runtime": 1.1037,
+      "eval_samples_per_second": 906.031,
+      "eval_steps_per_second": 14.496,
+      "step": 345000
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 0.00011905816748226513,
+      "loss": 0.2834,
+      "step": 346000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.00011886585381605125,
+      "loss": 0.2835,
+      "step": 347000
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 0.00011867311511908693,
+      "loss": 0.2832,
+      "step": 348000
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.00011847995349913162,
+      "loss": 0.2828,
+      "step": 349000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 0.00011828637106856989,
+      "loss": 0.2828,
+      "step": 350000
+    },
+    {
+      "epoch": 5.34,
+      "eval_runtime": 1.0295,
+      "eval_samples_per_second": 971.32,
+      "eval_steps_per_second": 15.541,
+      "step": 350000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.383405589691059e+22,
+  "total_flos": 2.4535058507214063e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfba4eea74dece360d73bbeb68171b0f24c78184fc1168b69bc18ed84fe5243
+oid sha256:ce357ce3d6b529f718a69a4a019a30353262fc7b3a74b394a29c905d74c6bace
 size 449471589