Training in progress, step 900000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683c63bc197cf3bb64f6c2ce95a62fc4f0bf6028b19e6d2e5831707a2f06c758
+oid sha256:15d8bbdd8e9ea2eabe38aad0708eba010797097fc97de2bc108dfae7de70eae1
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f6901c05f87feaf8e889e20cabff1c85d845893260d2343fe525c0b122a6e9
+oid sha256:083d2e25ea0ac8e88690f7365c08a3344ba965c5f4549f033918008711bc1651
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
+oid sha256:20800e78ca6d34f9d5b11fa5e4b130d78895eafe993ba74e5838487393b5953b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afa6aa14483adb7c817c2439178a198c4680dbfe427eab82def33bea1566914
+oid sha256:aa624c96f92eaad028a188cf78acc34c38cdc88db165dfecd04176965e65555e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.568919175133555,
-  "global_step": 890000,
+  "epoch": 9.68044789935648,
+  "global_step": 900000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17806,11 +17806,211 @@
       "eval_samples_per_second": 855.002,
       "eval_steps_per_second": 13.4,
       "step": 890000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 1.4539396316922552e-05,
+      "loss": 0.1822,
+      "step": 890500
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 1.4498484122598232e-05,
+      "loss": 0.1824,
+      "step": 891000
+    },
+    {
+      "epoch": 9.58,
+      "eval_loss": 0.17072877287864685,
+      "eval_runtime": 2.7539,
+      "eval_samples_per_second": 834.091,
+      "eval_steps_per_second": 13.072,
+      "step": 891000
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 1.4457751006917137e-05,
+      "loss": 0.1822,
+      "step": 891500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 1.4417197081242083e-05,
+      "loss": 0.1829,
+      "step": 892000
+    },
+    {
+      "epoch": 9.59,
+      "eval_loss": 0.17135965824127197,
+      "eval_runtime": 2.7156,
+      "eval_samples_per_second": 845.864,
+      "eval_steps_per_second": 13.257,
+      "step": 892000
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 1.4376822456445926e-05,
+      "loss": 0.1825,
+      "step": 892500
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 1.433662724291136e-05,
+      "loss": 0.1828,
+      "step": 893000
+    },
+    {
+      "epoch": 9.6,
+      "eval_loss": 0.17201776802539825,
+      "eval_runtime": 2.6531,
+      "eval_samples_per_second": 865.779,
+      "eval_steps_per_second": 13.569,
+      "step": 893000
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 1.4296611550530563e-05,
+      "loss": 0.1823,
+      "step": 893500
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 1.4256775488704904e-05,
+      "loss": 0.1825,
+      "step": 894000
+    },
+    {
+      "epoch": 9.61,
+      "eval_loss": 0.17262525856494904,
+      "eval_runtime": 2.6435,
+      "eval_samples_per_second": 868.939,
+      "eval_steps_per_second": 13.619,
+      "step": 894000
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 1.4217119166344665e-05,
+      "loss": 0.1822,
+      "step": 894500
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 1.4177642691868717e-05,
+      "loss": 0.1819,
+      "step": 895000
+    },
+    {
+      "epoch": 9.62,
+      "eval_loss": 0.1716921329498291,
+      "eval_runtime": 2.6607,
+      "eval_samples_per_second": 863.304,
+      "eval_steps_per_second": 13.53,
+      "step": 895000
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 1.4138346173204218e-05,
+      "loss": 0.1823,
+      "step": 895500
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 1.4099229717786368e-05,
+      "loss": 0.1825,
+      "step": 896000
+    },
+    {
+      "epoch": 9.64,
+      "eval_loss": 0.1738402545452118,
+      "eval_runtime": 2.7328,
+      "eval_samples_per_second": 840.538,
+      "eval_steps_per_second": 13.173,
+      "step": 896000
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 1.406029343255806e-05,
+      "loss": 0.1823,
+      "step": 896500
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 1.4021537423969588e-05,
+      "loss": 0.1823,
+      "step": 897000
+    },
+    {
+      "epoch": 9.65,
+      "eval_loss": 0.1751101166009903,
+      "eval_runtime": 2.7169,
+      "eval_samples_per_second": 845.459,
+      "eval_steps_per_second": 13.251,
+      "step": 897000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 1.3982961797978431e-05,
+      "loss": 0.1819,
+      "step": 897500
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 1.3944566660048863e-05,
+      "loss": 0.1823,
+      "step": 898000
+    },
+    {
+      "epoch": 9.66,
+      "eval_loss": 0.1745595484972,
+      "eval_runtime": 2.78,
+      "eval_samples_per_second": 826.25,
+      "eval_steps_per_second": 12.95,
+      "step": 898000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 1.3906352115151725e-05,
+      "loss": 0.1821,
+      "step": 898500
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.3868318267764128e-05,
+      "loss": 0.1821,
+      "step": 899000
+    },
+    {
+      "epoch": 9.67,
+      "eval_loss": 0.17514048516750336,
+      "eval_runtime": 2.6917,
+      "eval_samples_per_second": 853.365,
+      "eval_steps_per_second": 13.374,
+      "step": 899000
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.3830465221869146e-05,
+      "loss": 0.1821,
+      "step": 899500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 1.3792793080955574e-05,
+      "loss": 0.1819,
+      "step": 900000
+    },
+    {
+      "epoch": 9.68,
+      "eval_loss": 0.17348013818264008,
+      "eval_runtime": 2.6872,
+      "eval_samples_per_second": 854.803,
+      "eval_steps_per_second": 13.397,
+      "step": 900000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.238873943673255e+22,
+  "total_flos": 6.3089742047036024e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f6901c05f87feaf8e889e20cabff1c85d845893260d2343fe525c0b122a6e9
+oid sha256:083d2e25ea0ac8e88690f7365c08a3344ba965c5f4549f033918008711bc1651
 size 449471589