Training in progress, step 790000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f7748e8c1a812c7750cfe501e1201374a5c3fe0aa18d46f95d5f2b333fc8c81
+oid sha256:ee6d0b8731469184859b6e2af2323dc331e9f7e709ceb8418eca6fab2f75e9cb
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c535b39652a41a9bd80472f25014719ca46117003764349c033c0d865a69629
+oid sha256:b3c99a6d8856f7a728dbbbf96bf0c858122cdeb2ae96a80fcc6876c29d8e2666
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4647c95708e00e5dd99d1b79f20ca15f89d2d2a7bd2cde7a42a8d199abac73fd
+oid sha256:c08292d027d8ba65de9023aba96bca0e44920026e543fcb86c6e89c28847c9ce
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c067c2b3d8b4465df473fc8f38cbbeff61d1e95141d65c9e7d5985b861950165
+oid sha256:83d1297302d20060e31d476195b98906c23904815e65152eb2d3ffb7dd074183
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.342103208681396,
-  "global_step": 780000,
+  "epoch": 8.453631932904319,
+  "global_step": 790000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15606,11 +15606,211 @@
       "eval_samples_per_second": 840.721,
       "eval_steps_per_second": 13.176,
       "step": 780000
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 2.7645596244470935e-05,
+      "loss": 0.1885,
+      "step": 780500
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 2.7568839012773365e-05,
+      "loss": 0.1884,
+      "step": 781000
+    },
+    {
+      "epoch": 8.35,
+      "eval_loss": 0.1805545538663864,
+      "eval_runtime": 2.6452,
+      "eval_samples_per_second": 868.354,
+      "eval_steps_per_second": 13.609,
+      "step": 781000
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 2.7492225125867825e-05,
+      "loss": 0.1889,
+      "step": 781500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 2.7415754793213826e-05,
+      "loss": 0.1886,
+      "step": 782000
+    },
+    {
+      "epoch": 8.36,
+      "eval_loss": 0.1767302304506302,
+      "eval_runtime": 2.6579,
+      "eval_samples_per_second": 864.226,
+      "eval_steps_per_second": 13.545,
+      "step": 782000
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 2.7339428223878283e-05,
+      "loss": 0.1883,
+      "step": 782500
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 2.7263245626535116e-05,
+      "loss": 0.1884,
+      "step": 783000
+    },
+    {
+      "epoch": 8.38,
+      "eval_loss": 0.1802656203508377,
+      "eval_runtime": 2.7131,
+      "eval_samples_per_second": 846.621,
+      "eval_steps_per_second": 13.269,
+      "step": 783000
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 2.7187207209464687e-05,
+      "loss": 0.1883,
+      "step": 783500
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 2.7111313180553077e-05,
+      "loss": 0.1882,
+      "step": 784000
+    },
+    {
+      "epoch": 8.39,
+      "eval_loss": 0.17976997792720795,
+      "eval_runtime": 2.668,
+      "eval_samples_per_second": 860.932,
+      "eval_steps_per_second": 13.493,
+      "step": 784000
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 2.703556374729169e-05,
+      "loss": 0.1885,
+      "step": 784500
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 2.6959959116776587e-05,
+      "loss": 0.188,
+      "step": 785000
+    },
+    {
+      "epoch": 8.4,
+      "eval_loss": 0.1783231794834137,
+      "eval_runtime": 2.6459,
+      "eval_samples_per_second": 868.123,
+      "eval_steps_per_second": 13.606,
+      "step": 785000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 2.68844994957079e-05,
+      "loss": 0.1881,
+      "step": 785500
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 2.6809185090389406e-05,
+      "loss": 0.1884,
+      "step": 786000
+    },
+    {
+      "epoch": 8.41,
+      "eval_loss": 0.18017184734344482,
+      "eval_runtime": 2.6671,
+      "eval_samples_per_second": 861.233,
+      "eval_steps_per_second": 13.498,
+      "step": 786000
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 2.6734016106727777e-05,
+      "loss": 0.1881,
+      "step": 786500
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 2.6658992750232167e-05,
+      "loss": 0.188,
+      "step": 787000
+    },
+    {
+      "epoch": 8.42,
+      "eval_loss": 0.17710144817829132,
+      "eval_runtime": 2.6667,
+      "eval_samples_per_second": 861.367,
+      "eval_steps_per_second": 13.5,
+      "step": 787000
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 2.6584115226013553e-05,
+      "loss": 0.1883,
+      "step": 787500
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 2.6509383738784218e-05,
+      "loss": 0.188,
+      "step": 788000
+    },
+    {
+      "epoch": 8.43,
+      "eval_loss": 0.1786525398492813,
+      "eval_runtime": 2.6579,
+      "eval_samples_per_second": 864.232,
+      "eval_steps_per_second": 13.545,
+      "step": 788000
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 2.6434798492857228e-05,
+      "loss": 0.1881,
+      "step": 788500
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 2.6360359692145757e-05,
+      "loss": 0.1882,
+      "step": 789000
+    },
+    {
+      "epoch": 8.44,
+      "eval_loss": 0.17897970974445343,
+      "eval_runtime": 2.6253,
+      "eval_samples_per_second": 874.933,
+      "eval_steps_per_second": 13.712,
+      "step": 789000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 2.6286067540162677e-05,
+      "loss": 0.1882,
+      "step": 789500
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 2.6211922240019883e-05,
+      "loss": 0.1883,
+      "step": 790000
+    },
+    {
+      "epoch": 8.45,
+      "eval_loss": 0.17872017621994019,
+      "eval_runtime": 2.5868,
+      "eval_samples_per_second": 887.972,
+      "eval_steps_per_second": 13.917,
+      "step": 790000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.467776548786952e+22,
+  "total_flos": 5.5378768098172995e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c535b39652a41a9bd80472f25014719ca46117003764349c033c0d865a69629
+oid sha256:b3c99a6d8856f7a728dbbbf96bf0c858122cdeb2ae96a80fcc6876c29d8e2666
 size 449471589