Training in progress, step 460000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75b6a012ab82fb16d27738e0a95c3b1b8ef7e5d1f6ee0116a8c50549bb847f8
+oid sha256:583b1f1834e02218d89c3b697d47dd796ee6e2f54da76dbfa4b2b4a392308637
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b24f59351cac08b9824b3f79acd0f1dc0a89b48a8f25dc820166f982b53fa7
+oid sha256:1b1ac07a8fd5b7f18f94228f9f3e9b88d618a44073c792161d704c98526bced7
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4f1f1c1cb0bb3ff6487630da96ece6a563c0a58db594f3dd7e10d4cd4b3713
+oid sha256:8cc778d00dc1434fe3ece5ed1e4f0a69b755dfb4b5125022a7e4273f579b7722
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc29c434fb0390a8f4f90d65ac745a0b4f381dbd06e857762d450d4a464c7045
+oid sha256:d60fd80961b777bf4901f5c7189278f8f31f61a50c51a19e170f6a1919a5ce33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.484866842191105,
-  "global_step": 450000,
+  "epoch": 10.717863883128684,
+  "global_step": 460000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9006,11 +9006,211 @@
       "eval_samples_per_second": 1528.604,
       "eval_steps_per_second": 24.341,
       "step": 450000
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 1.770155470293445e-05,
+      "loss": 0.2519,
+      "step": 450500
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 1.7548110926261522e-05,
+      "loss": 0.2518,
+      "step": 451000
+    },
+    {
+      "epoch": 10.51,
+      "eval_loss": 0.23447871208190918,
+      "eval_runtime": 1.4307,
+      "eval_samples_per_second": 1536.276,
+      "eval_steps_per_second": 24.463,
+      "step": 451000
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 1.7396170301425777e-05,
+      "loss": 0.2518,
+      "step": 451500
+    },
+    {
+      "epoch": 10.53,
+      "learning_rate": 1.7245734490025544e-05,
+      "loss": 0.252,
+      "step": 452000
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 0.23647595942020416,
+      "eval_runtime": 1.4161,
+      "eval_samples_per_second": 1552.16,
+      "eval_steps_per_second": 24.716,
+      "step": 452000
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 1.7096805137202738e-05,
+      "loss": 0.2518,
+      "step": 452500
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 1.6949383871624917e-05,
+      "loss": 0.2517,
+      "step": 453000
+    },
+    {
+      "epoch": 10.55,
+      "eval_loss": 0.23766835033893585,
+      "eval_runtime": 1.4533,
+      "eval_samples_per_second": 1512.402,
+      "eval_steps_per_second": 24.083,
+      "step": 453000
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 1.6803472305467368e-05,
+      "loss": 0.2515,
+      "step": 453500
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 1.665907203439568e-05,
+      "loss": 0.2516,
+      "step": 454000
+    },
+    {
+      "epoch": 10.58,
+      "eval_loss": 0.23621916770935059,
+      "eval_runtime": 1.476,
+      "eval_samples_per_second": 1489.127,
+      "eval_steps_per_second": 23.712,
+      "step": 454000
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 1.6516184637548058e-05,
+      "loss": 0.2515,
+      "step": 454500
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 1.6374811677518142e-05,
+      "loss": 0.2517,
+      "step": 455000
+    },
+    {
+      "epoch": 10.6,
+      "eval_loss": 0.23542185127735138,
+      "eval_runtime": 1.4176,
+      "eval_samples_per_second": 1550.543,
+      "eval_steps_per_second": 24.69,
+      "step": 455000
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 1.6234954700338025e-05,
+      "loss": 0.2516,
+      "step": 455500
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 1.6096615235461148e-05,
+      "loss": 0.2515,
+      "step": 456000
+    },
+    {
+      "epoch": 10.62,
+      "eval_loss": 0.2339724451303482,
+      "eval_runtime": 1.3908,
+      "eval_samples_per_second": 1580.393,
+      "eval_steps_per_second": 25.165,
+      "step": 456000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 1.59597947957458e-05,
+      "loss": 0.2519,
+      "step": 456500
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 1.5824494877438344e-05,
+      "loss": 0.2515,
+      "step": 457000
+    },
+    {
+      "epoch": 10.65,
+      "eval_loss": 0.23481862246990204,
+      "eval_runtime": 1.4326,
+      "eval_samples_per_second": 1534.248,
+      "eval_steps_per_second": 24.431,
+      "step": 457000
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 1.569071696015702e-05,
+      "loss": 0.2513,
+      "step": 457500
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 1.555846250687569e-05,
+      "loss": 0.2517,
+      "step": 458000
+    },
+    {
+      "epoch": 10.67,
+      "eval_loss": 0.23701262474060059,
+      "eval_runtime": 1.4718,
+      "eval_samples_per_second": 1493.443,
+      "eval_steps_per_second": 23.781,
+      "step": 458000
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 1.542773296390789e-05,
+      "loss": 0.2518,
+      "step": 458500
+    },
+    {
+      "epoch": 10.69,
+      "learning_rate": 1.5298529760890945e-05,
+      "loss": 0.2514,
+      "step": 459000
+    },
+    {
+      "epoch": 10.69,
+      "eval_loss": 0.23413069546222687,
+      "eval_runtime": 1.4496,
+      "eval_samples_per_second": 1516.277,
+      "eval_steps_per_second": 24.145,
+      "step": 459000
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 1.5170854310770376e-05,
+      "loss": 0.251,
+      "step": 459500
+    },
+    {
+      "epoch": 10.72,
+      "learning_rate": 1.5044708009784457e-05,
+      "loss": 0.2514,
+      "step": 460000
+    },
+    {
+      "epoch": 10.72,
+      "eval_loss": 0.2361001968383789,
+      "eval_runtime": 1.4246,
+      "eval_samples_per_second": 1542.873,
+      "eval_steps_per_second": 24.568,
+      "step": 460000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.4376896274943432e+22,
+  "total_flos": 1.4696383413717932e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b24f59351cac08b9824b3f79acd0f1dc0a89b48a8f25dc820166f982b53fa7
+oid sha256:1b1ac07a8fd5b7f18f94228f9f3e9b88d618a44073c792161d704c98526bced7
 size 102501541