Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c71503ee1be825f92e3abeedc33b7a6047ab3271078c12e7596499868d30e2
+oid sha256:ce756be38c7d806962a75c4ecd24790cdff6367292efa2cdf7ed0fff4145bbe4
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024301d8ba60de43a5f5ed99419c50422c1c826da65f5623681ea6f121160a82
+oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19060d643fcaa3a7b8933dd35852a490bf0b6b6b34dc4dd07e146c20f2bf45ce
+oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
 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": 3.822824812681584,
-  "global_step": 150000,
+  "epoch": 4.07767980019369,
+  "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": 725.588,
       "eval_steps_per_second": 11.609,
       "step": 150000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.000252852507335803,
+      "loss": 0.3008,
+      "step": 150500
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.0002524981166865307,
+      "loss": 0.3014,
+      "step": 151000
+    },
+    {
+      "epoch": 3.85,
+      "eval_loss": 0.8369771242141724,
+      "eval_runtime": 1.2701,
+      "eval_samples_per_second": 787.344,
+      "eval_steps_per_second": 12.598,
+      "step": 151000
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.00025214265981347487,
+      "loss": 0.3007,
+      "step": 151500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.000251786140603855,
+      "loss": 0.3012,
+      "step": 152000
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 0.8284549117088318,
+      "eval_runtime": 1.3354,
+      "eval_samples_per_second": 748.855,
+      "eval_steps_per_second": 11.982,
+      "step": 152000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.00025142856295650795,
+      "loss": 0.3026,
+      "step": 152500
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.0002510699307818457,
+      "loss": 0.3012,
+      "step": 153000
+    },
+    {
+      "epoch": 3.9,
+      "eval_loss": 0.8453160524368286,
+      "eval_runtime": 1.3185,
+      "eval_samples_per_second": 758.466,
+      "eval_steps_per_second": 12.135,
+      "step": 153000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.00025071024800181214,
+      "loss": 0.3009,
+      "step": 153500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.0002503495185498405,
+      "loss": 0.3007,
+      "step": 154000
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 0.8194591999053955,
+      "eval_runtime": 1.3313,
+      "eval_samples_per_second": 751.123,
+      "eval_steps_per_second": 12.018,
+      "step": 154000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.00024998774637081044,
+      "loss": 0.3008,
+      "step": 154500
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.00024962493542100443,
+      "loss": 0.3009,
+      "step": 155000
+    },
+    {
+      "epoch": 3.95,
+      "eval_loss": 0.8309118747711182,
+      "eval_runtime": 1.304,
+      "eval_samples_per_second": 766.849,
+      "eval_steps_per_second": 12.27,
+      "step": 155000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.0002492610896680649,
+      "loss": 0.3001,
+      "step": 155500
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.00024889621309095067,
+      "loss": 0.3007,
+      "step": 156000
+    },
+    {
+      "epoch": 3.98,
+      "eval_loss": 0.8357002139091492,
+      "eval_runtime": 1.337,
+      "eval_samples_per_second": 747.964,
+      "eval_steps_per_second": 11.967,
+      "step": 156000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.00024853030967989366,
+      "loss": 0.3005,
+      "step": 156500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00024816338343635485,
+      "loss": 0.3003,
+      "step": 157000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8225012421607971,
+      "eval_runtime": 1.2983,
+      "eval_samples_per_second": 770.222,
+      "eval_steps_per_second": 12.324,
+      "step": 157000
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.0002477954383729809,
+      "loss": 0.2997,
+      "step": 157500
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.00024742647851355997,
+      "loss": 0.3014,
+      "step": 158000
+    },
+    {
+      "epoch": 4.03,
+      "eval_loss": 0.8343092203140259,
+      "eval_runtime": 1.2683,
+      "eval_samples_per_second": 788.447,
+      "eval_steps_per_second": 12.615,
+      "step": 158000
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.0002470565078929781,
+      "loss": 0.3001,
+      "step": 158500
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00024668553055717465,
+      "loss": 0.3005,
+      "step": 159000
+    },
+    {
+      "epoch": 4.05,
+      "eval_loss": 0.8266953229904175,
+      "eval_runtime": 1.3214,
+      "eval_samples_per_second": 756.765,
+      "eval_steps_per_second": 12.108,
+      "step": 159000
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.0002463135505630984,
+      "loss": 0.299,
+      "step": 159500
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00024594057197866283,
+      "loss": 0.2994,
+      "step": 160000
+    },
+    {
+      "epoch": 4.08,
+      "eval_loss": 0.8257858157157898,
+      "eval_runtime": 1.2672,
+      "eval_samples_per_second": 789.172,
+      "eval_steps_per_second": 12.627,
+      "step": 160000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 4.792266644878365e+21,
+  "total_flos": 5.11174030473982e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024301d8ba60de43a5f5ed99419c50422c1c826da65f5623681ea6f121160a82
+oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
 size 102501541