Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ecaa40659da5359d9e6f7d069ca323ca4c45fa18fcb4784f875bec7976d461
+oid sha256:2bfe26318a498d7159440a97f6aa88e178fd8cfca07f0e3c0f2baa3c80edd1cc
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94d64a0ae504309548136437084f536028b5f9b3d523c385c79db34cb72c3bb
+oid sha256:30edd70a79d1324bf23d2b4cd2aadc6dcc51387b691e7868236c4f9d83750ba9
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01b23c0fe6122788b87f39f9d97726d4354152bd24d5ac8cf11369955b4ef3
+oid sha256:c0233886821304635fe3bf8eadf86594512eb946966fdd9dd2d08d378904b503
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09454c2cc8aac6faf99c7970cf8bec57b59b683887c6bb291c3a0936d0e7d0d
+oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.4949556140637013,
-  "global_step": 150000,
+  "epoch": 3.7279526550012814,
+  "global_step": 160000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3006,11 +3006,211 @@
       "eval_samples_per_second": 1560.897,
       "eval_steps_per_second": 24.855,
       "step": 150000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 0.000252852507335803,
+      "loss": 0.2894,
+      "step": 150500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.0002524981166865307,
+      "loss": 0.2889,
+      "step": 151000
+    },
+    {
+      "epoch": 3.52,
+      "eval_loss": 0.2722132205963135,
+      "eval_runtime": 1.426,
+      "eval_samples_per_second": 1541.329,
+      "eval_steps_per_second": 24.543,
+      "step": 151000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 0.00025214265981347487,
+      "loss": 0.2889,
+      "step": 151500
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.000251786140603855,
+      "loss": 0.289,
+      "step": 152000
+    },
+    {
+      "epoch": 3.54,
+      "eval_loss": 0.27176567912101746,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 1548.585,
+      "eval_steps_per_second": 24.659,
+      "step": 152000
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.00025142856295650795,
+      "loss": 0.2898,
+      "step": 152500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.0002510699307818457,
+      "loss": 0.2888,
+      "step": 153000
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 0.2718333601951599,
+      "eval_runtime": 1.4384,
+      "eval_samples_per_second": 1528.088,
+      "eval_steps_per_second": 24.333,
+      "step": 153000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.00025071024800181214,
+      "loss": 0.2889,
+      "step": 153500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.0002503495185498405,
+      "loss": 0.2887,
+      "step": 154000
+    },
+    {
+      "epoch": 3.59,
+      "eval_loss": 0.2725473940372467,
+      "eval_runtime": 1.4286,
+      "eval_samples_per_second": 1538.528,
+      "eval_steps_per_second": 24.499,
+      "step": 154000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00024998774637081044,
+      "loss": 0.2896,
+      "step": 154500
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.00024962493542100443,
+      "loss": 0.2888,
+      "step": 155000
+    },
+    {
+      "epoch": 3.61,
+      "eval_loss": 0.27104923129081726,
+      "eval_runtime": 1.4479,
+      "eval_samples_per_second": 1518.017,
+      "eval_steps_per_second": 24.172,
+      "step": 155000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0002492610896680649,
+      "loss": 0.2879,
+      "step": 155500
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 0.00024889621309095067,
+      "loss": 0.289,
+      "step": 156000
+    },
+    {
+      "epoch": 3.63,
+      "eval_loss": 0.2686387598514557,
+      "eval_runtime": 1.428,
+      "eval_samples_per_second": 1539.209,
+      "eval_steps_per_second": 24.51,
+      "step": 156000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.00024853030967989366,
+      "loss": 0.288,
+      "step": 156500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.00024816338343635485,
+      "loss": 0.2873,
+      "step": 157000
+    },
+    {
+      "epoch": 3.66,
+      "eval_loss": 0.2692621946334839,
+      "eval_runtime": 1.4361,
+      "eval_samples_per_second": 1530.504,
+      "eval_steps_per_second": 24.371,
+      "step": 157000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.0002477954383729809,
+      "loss": 0.288,
+      "step": 157500
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.00024742647851355997,
+      "loss": 0.2876,
+      "step": 158000
+    },
+    {
+      "epoch": 3.68,
+      "eval_loss": 0.2716818153858185,
+      "eval_runtime": 1.4202,
+      "eval_samples_per_second": 1547.632,
+      "eval_steps_per_second": 24.644,
+      "step": 158000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.0002470565078929781,
+      "loss": 0.2872,
+      "step": 158500
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.00024668553055717465,
+      "loss": 0.2873,
+      "step": 159000
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 0.2711220681667328,
+      "eval_runtime": 1.4791,
+      "eval_samples_per_second": 1486.051,
+      "eval_steps_per_second": 23.663,
+      "step": 159000
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.0002463135505630984,
+      "loss": 0.2892,
+      "step": 159500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.00024594057197866283,
+      "loss": 0.2883,
+      "step": 160000
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 0.2702338993549347,
+      "eval_runtime": 1.4449,
+      "eval_samples_per_second": 1521.168,
+      "eval_steps_per_second": 24.222,
+      "step": 160000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 4.79229959064478e+21,
+  "total_flos": 5.11178672941928e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94d64a0ae504309548136437084f536028b5f9b3d523c385c79db34cb72c3bb
+oid sha256:30edd70a79d1324bf23d2b4cd2aadc6dcc51387b691e7868236c4f9d83750ba9
 size 102501541