Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d053774b6389f97348f5fa02f2789d9380cd22ec9c56252d6cb43ae07a9c71
+oid sha256:9b25ce26c4c4eb983ffdc2bc9c7b644b728aef230ff82ddd8a2030da415dbb2b
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41ef1449515965c8c4ad61e0e0ab0776df2e27d22ece58583e00038b5639984
+oid sha256:421173a6d0b779538ba1088b472ee8a48ec34ebc9c6001dc0452a17c3f898cd8
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
+oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec5c60f6b831a1ad5ababd554115ca1132f641d196d63d42183ef95c8827963
+oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1649852046879006,
-  "global_step": 50000,
+  "epoch": 1.3979822456254807,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 1558.283,
       "eval_steps_per_second": 24.813,
       "step": 50000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002979426829679962,
+      "loss": 0.3334,
+      "step": 50500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002978614137443183,
+      "loss": 0.3325,
+      "step": 51000
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.31682637333869934,
+      "eval_runtime": 1.4213,
+      "eval_samples_per_second": 1546.472,
+      "eval_steps_per_second": 24.625,
+      "step": 51000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.000297778582211108,
+      "loss": 0.3322,
+      "step": 51500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00029769418927419786,
+      "loss": 0.3316,
+      "step": 52000
+    },
+    {
+      "epoch": 1.21,
+      "eval_loss": 0.31410133838653564,
+      "eval_runtime": 1.4261,
+      "eval_samples_per_second": 1541.269,
+      "eval_steps_per_second": 24.542,
+      "step": 52000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002976082358564954,
+      "loss": 0.331,
+      "step": 52500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00029752072289797353,
+      "loss": 0.3305,
+      "step": 53000
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 0.3114263713359833,
+      "eval_runtime": 1.4182,
+      "eval_samples_per_second": 1549.888,
+      "eval_steps_per_second": 24.68,
+      "step": 53000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00029743165135565986,
+      "loss": 0.3301,
+      "step": 53500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00029734102220362654,
+      "loss": 0.3303,
+      "step": 54000
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.3110273778438568,
+      "eval_runtime": 1.3899,
+      "eval_samples_per_second": 1581.462,
+      "eval_steps_per_second": 25.183,
+      "step": 54000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00029724883643297937,
+      "loss": 0.3289,
+      "step": 54500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002971550950518473,
+      "loss": 0.3284,
+      "step": 55000
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.3112471401691437,
+      "eval_runtime": 1.3713,
+      "eval_samples_per_second": 1602.906,
+      "eval_steps_per_second": 25.524,
+      "step": 55000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.000297059799085371,
+      "loss": 0.3284,
+      "step": 55500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00029696294957569196,
+      "loss": 0.3276,
+      "step": 56000
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 0.30989283323287964,
+      "eval_runtime": 1.4309,
+      "eval_samples_per_second": 1536.096,
+      "eval_steps_per_second": 24.46,
+      "step": 56000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00029686454758194076,
+      "loss": 0.3269,
+      "step": 56500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00029676459418022594,
+      "loss": 0.3264,
+      "step": 57000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.3089369833469391,
+      "eval_runtime": 1.4226,
+      "eval_samples_per_second": 1545.068,
+      "eval_steps_per_second": 24.603,
+      "step": 57000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0002966630904636219,
+      "loss": 0.3261,
+      "step": 57500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0002965600375421569,
+      "loss": 0.3256,
+      "step": 58000
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 0.31043851375579834,
+      "eval_runtime": 1.4043,
+      "eval_samples_per_second": 1565.245,
+      "eval_steps_per_second": 24.924,
+      "step": 58000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002964554365428013,
+      "loss": 0.3251,
+      "step": 58500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00029634928860945486,
+      "loss": 0.3247,
+      "step": 59000
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 0.3088381588459015,
+      "eval_runtime": 1.4281,
+      "eval_samples_per_second": 1539.081,
+      "eval_steps_per_second": 24.508,
+      "step": 59000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002962415949029343,
+      "loss": 0.3243,
+      "step": 59500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00029613235660096084,
+      "loss": 0.3241,
+      "step": 60000
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.3055568337440491,
+      "eval_runtime": 1.4302,
+      "eval_samples_per_second": 1536.88,
+      "eval_steps_per_second": 24.473,
+      "step": 60000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5974331968815932e+21,
+  "total_flos": 1.9169203356560932e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41ef1449515965c8c4ad61e0e0ab0776df2e27d22ece58583e00038b5639984
+oid sha256:421173a6d0b779538ba1088b472ee8a48ec34ebc9c6001dc0452a17c3f898cd8
 size 102501541