Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760d623b03dfc06d080b7126a9d45c8cd1c2d423be145e736a8133be816236da
+oid sha256:a9396b036e3d42153258868d83ab6272bb561cb514c6bd86d35ed30e8bbbd239
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab7f775c70cb8c6d0bea61e693eaab2cd63a4819bde10b49c6f776391ada7c1
+oid sha256:14e2ac0bd2e3b89b8235e3e0a65f4c992d830147db31a60541e63658d5546aed
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a86e01f43ddb1fd5a08f6c753d52a2302c58b2849cdd39b3a7c7782ea76f07e
+oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
 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": 3.345824411134904,
-  "global_step": 150000,
+  "epoch": 3.5688793718772307,
+  "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": 1155.618,
       "eval_steps_per_second": 18.112,
       "step": 150000
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.000252852507335803,
+      "loss": 0.2923,
+      "step": 150500
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 0.0002524981166865307,
+      "loss": 0.2924,
+      "step": 151000
+    },
+    {
+      "epoch": 3.37,
+      "eval_loss": 0.2738962769508362,
+      "eval_runtime": 1.9816,
+      "eval_samples_per_second": 1159.146,
+      "eval_steps_per_second": 18.167,
+      "step": 151000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 0.00025214265981347487,
+      "loss": 0.2921,
+      "step": 151500
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.000251786140603855,
+      "loss": 0.292,
+      "step": 152000
+    },
+    {
+      "epoch": 3.39,
+      "eval_loss": 0.27476462721824646,
+      "eval_runtime": 1.9539,
+      "eval_samples_per_second": 1175.601,
+      "eval_steps_per_second": 18.425,
+      "step": 152000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.00025142856295650795,
+      "loss": 0.2919,
+      "step": 152500
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.0002510699307818457,
+      "loss": 0.2917,
+      "step": 153000
+    },
+    {
+      "epoch": 3.41,
+      "eval_loss": 0.2740522623062134,
+      "eval_runtime": 1.9887,
+      "eval_samples_per_second": 1155.036,
+      "eval_steps_per_second": 18.102,
+      "step": 153000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.00025071024800181214,
+      "loss": 0.2913,
+      "step": 153500
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.0002503495185498405,
+      "loss": 0.2913,
+      "step": 154000
+    },
+    {
+      "epoch": 3.44,
+      "eval_loss": 0.27570095658302307,
+      "eval_runtime": 1.9561,
+      "eval_samples_per_second": 1174.293,
+      "eval_steps_per_second": 18.404,
+      "step": 154000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.00024998774637081044,
+      "loss": 0.2914,
+      "step": 154500
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.00024962493542100443,
+      "loss": 0.2911,
+      "step": 155000
+    },
+    {
+      "epoch": 3.46,
+      "eval_loss": 0.27467048168182373,
+      "eval_runtime": 1.9751,
+      "eval_samples_per_second": 1163.003,
+      "eval_steps_per_second": 18.227,
+      "step": 155000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.0002492610896680649,
+      "loss": 0.2911,
+      "step": 155500
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.00024889621309095067,
+      "loss": 0.2911,
+      "step": 156000
+    },
+    {
+      "epoch": 3.48,
+      "eval_loss": 0.27558836340904236,
+      "eval_runtime": 1.9879,
+      "eval_samples_per_second": 1155.504,
+      "eval_steps_per_second": 18.11,
+      "step": 156000
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.00024853030967989366,
+      "loss": 0.2913,
+      "step": 156500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.00024816338343635485,
+      "loss": 0.2909,
+      "step": 157000
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.27131345868110657,
+      "eval_runtime": 1.9424,
+      "eval_samples_per_second": 1182.575,
+      "eval_steps_per_second": 18.534,
+      "step": 157000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 0.0002477954383729809,
+      "loss": 0.2908,
+      "step": 157500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.00024742647851355997,
+      "loss": 0.2908,
+      "step": 158000
+    },
+    {
+      "epoch": 3.52,
+      "eval_loss": 0.2729162871837616,
+      "eval_runtime": 2.0222,
+      "eval_samples_per_second": 1135.884,
+      "eval_steps_per_second": 17.802,
+      "step": 158000
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.0002470565078929781,
+      "loss": 0.2909,
+      "step": 158500
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.00024668553055717465,
+      "loss": 0.2905,
+      "step": 159000
+    },
+    {
+      "epoch": 3.55,
+      "eval_loss": 0.2731362581253052,
+      "eval_runtime": 1.928,
+      "eval_samples_per_second": 1191.362,
+      "eval_steps_per_second": 18.672,
+      "step": 159000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.0002463135505630984,
+      "loss": 0.2905,
+      "step": 159500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.00024594057197866283,
+      "loss": 0.2902,
+      "step": 160000
+    },
+    {
+      "epoch": 3.57,
+      "eval_loss": 0.27327215671539307,
+      "eval_runtime": 1.9424,
+      "eval_samples_per_second": 1182.586,
+      "eval_steps_per_second": 18.534,
+      "step": 160000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 4.792221718833254e+21,
+  "total_flos": 5.111708857607754e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab7f775c70cb8c6d0bea61e693eaab2cd63a4819bde10b49c6f776391ada7c1
+oid sha256:14e2ac0bd2e3b89b8235e3e0a65f4c992d830147db31a60541e63658d5546aed
 size 102501541