Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115ffe163e25d965deaf1e95234c158ffd00fbc71531098c0b9ab43a32b44422
+oid sha256:68579b000c67ae02c93fef507e910ee24187e399ca1591a2c497efffe8459dac
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5f5ae4e2c1f14e613311f65c9deaf0995f26ac33b108067f68da4920fbd182
+oid sha256:bce1b6fb3fb5d372a1bae3a15433a06de19284c7aa2bc4d3c1962d8f51884be2
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970f5edc45b72267b07b2b29a2f000865ed4d4ecdc6c514dcf59f57e03814ca9
+oid sha256:6516d5b46fda40bf4c056933976209142d5376bc9d4025a968296f31b52bf24b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684030441e546f328363202be7e7a1e6d60b5494506eab9e81487ca712343e2e
+oid sha256:dc071f88617eb6afe60581ffbadbc2441a73aeec527e5556ce742e0646660ab9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.191176470588236,
-  "global_step": 150000,
+  "epoch": 9.803921568627452,
+  "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": 750.39,
       "eval_steps_per_second": 12.006,
       "step": 150000
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 0.00023069198757093631,
+      "loss": 0.4555,
+      "step": 150500
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 0.00022880544432159663,
+      "loss": 0.4551,
+      "step": 151000
+    },
+    {
+      "epoch": 9.25,
+      "eval_loss": 0.8021363615989685,
+      "eval_runtime": 1.3155,
+      "eval_samples_per_second": 760.176,
+      "eval_steps_per_second": 12.163,
+      "step": 151000
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 0.00022692223406895848,
+      "loss": 0.4554,
+      "step": 151500
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 0.000225042439190739,
+      "loss": 0.4549,
+      "step": 152000
+    },
+    {
+      "epoch": 9.31,
+      "eval_loss": 0.7971563339233398,
+      "eval_runtime": 1.2684,
+      "eval_samples_per_second": 788.389,
+      "eval_steps_per_second": 12.614,
+      "step": 152000
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 0.00022316614191525587,
+      "loss": 0.4546,
+      "step": 152500
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 0.00022129342431783026,
+      "loss": 0.4545,
+      "step": 153000
+    },
+    {
+      "epoch": 9.38,
+      "eval_loss": 0.8002565503120422,
+      "eval_runtime": 1.2924,
+      "eval_samples_per_second": 773.739,
+      "eval_steps_per_second": 12.38,
+      "step": 153000
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 0.00021942436831719677,
+      "loss": 0.4542,
+      "step": 153500
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 0.00021755905567191967,
+      "loss": 0.4542,
+      "step": 154000
+    },
+    {
+      "epoch": 9.44,
+      "eval_loss": 0.7999687790870667,
+      "eval_runtime": 1.2876,
+      "eval_samples_per_second": 776.658,
+      "eval_steps_per_second": 12.427,
+      "step": 154000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 0.00021569756797681686,
+      "loss": 0.4538,
+      "step": 154500
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.00021383998665939054,
+      "loss": 0.4539,
+      "step": 155000
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.7960466146469116,
+      "eval_runtime": 1.3325,
+      "eval_samples_per_second": 750.454,
+      "eval_steps_per_second": 12.007,
+      "step": 155000
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 0.00021198639297626516,
+      "loss": 0.4537,
+      "step": 155500
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 0.0002101368680096334,
+      "loss": 0.4533,
+      "step": 156000
+    },
+    {
+      "epoch": 9.56,
+      "eval_loss": 0.8035251498222351,
+      "eval_runtime": 1.3033,
+      "eval_samples_per_second": 767.279,
+      "eval_steps_per_second": 12.276,
+      "step": 156000
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 0.00020829149266370862,
+      "loss": 0.4532,
+      "step": 156500
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 0.00020645034766118703,
+      "loss": 0.453,
+      "step": 157000
+    },
+    {
+      "epoch": 9.62,
+      "eval_loss": 0.7953096628189087,
+      "eval_runtime": 1.3024,
+      "eval_samples_per_second": 767.789,
+      "eval_steps_per_second": 12.285,
+      "step": 157000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 0.00020461351353971526,
+      "loss": 0.4527,
+      "step": 157500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 0.00020278107064836847,
+      "loss": 0.4527,
+      "step": 158000
+    },
+    {
+      "epoch": 9.68,
+      "eval_loss": 0.7937498688697815,
+      "eval_runtime": 1.2999,
+      "eval_samples_per_second": 769.267,
+      "eval_steps_per_second": 12.308,
+      "step": 158000
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 0.00020095309914413485,
+      "loss": 0.4526,
+      "step": 158500
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 0.00019912967898840997,
+      "loss": 0.4524,
+      "step": 159000
+    },
+    {
+      "epoch": 9.74,
+      "eval_loss": 0.8021422624588013,
+      "eval_runtime": 1.3181,
+      "eval_samples_per_second": 758.64,
+      "eval_steps_per_second": 12.138,
+      "step": 159000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 0.00019731088994349834,
+      "loss": 0.4524,
+      "step": 159500
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.0001954968115691248,
+      "loss": 0.4519,
+      "step": 160000
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 0.8028143644332886,
+      "eval_runtime": 1.282,
+      "eval_samples_per_second": 780.028,
+      "eval_steps_per_second": 12.48,
+      "step": 160000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 2.4024299484545255e+21,
+  "total_flos": 2.5625979513203296e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5f5ae4e2c1f14e613311f65c9deaf0995f26ac33b108067f68da4920fbd182
+oid sha256:bce1b6fb3fb5d372a1bae3a15433a06de19284c7aa2bc4d3c1962d8f51884be2
 size 25761253