Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0bfce1b1773be96f0d3fe813d2ed231bcc619aa9d86090dabfebda938938679
+oid sha256:016da91c7614d6a57ffcc5938a0b68675bc967aee110a7fe186334a10cf0dffd
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd79899bdba4b0a42b6695b21b791ea0a1c2b1e7f7e8aeb0419ab9a5bb16c136
+oid sha256:da03f29f9d43fcaa0d12888b54defcd8a6a1be294c2c1e7d74429358a9688082
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
+oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2047b5f47fc3de929bb0738f7fbdd248300ab063f6fd4eddcabc29f5482852
+oid sha256:864647684ab3694f7aa2a258c1806e10c4abf99f67ed5e54443050e485ac9436
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.684489525460013,
-  "global_step": 380000,
+  "epoch": 9.939344512972118,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7606,11 +7606,211 @@
       "eval_samples_per_second": 758.149,
       "eval_steps_per_second": 12.13,
       "step": 380000
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 5.2979369233306834e-05,
+      "loss": 0.2732,
+      "step": 380500
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 5.26391878673975e-05,
+      "loss": 0.2736,
+      "step": 381000
+    },
+    {
+      "epoch": 9.71,
+      "eval_loss": 0.8043585419654846,
+      "eval_runtime": 1.3216,
+      "eval_samples_per_second": 756.661,
+      "eval_steps_per_second": 12.107,
+      "step": 381000
+    },
+    {
+      "epoch": 9.72,
+      "learning_rate": 5.230012590292987e-05,
+      "loss": 0.2736,
+      "step": 381500
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 5.1962187047831517e-05,
+      "loss": 0.2739,
+      "step": 382000
+    },
+    {
+      "epoch": 9.74,
+      "eval_loss": 0.8078375458717346,
+      "eval_runtime": 1.2548,
+      "eval_samples_per_second": 796.917,
+      "eval_steps_per_second": 12.751,
+      "step": 382000
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 5.162537499774743e-05,
+      "loss": 0.2736,
+      "step": 382500
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 5.128969343600032e-05,
+      "loss": 0.2729,
+      "step": 383000
+    },
+    {
+      "epoch": 9.76,
+      "eval_loss": 0.8074722290039062,
+      "eval_runtime": 1.3011,
+      "eval_samples_per_second": 768.601,
+      "eval_steps_per_second": 12.298,
+      "step": 383000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 5.09551460335499e-05,
+      "loss": 0.2732,
+      "step": 383500
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 5.062173644895296e-05,
+      "loss": 0.2735,
+      "step": 384000
+    },
+    {
+      "epoch": 9.79,
+      "eval_loss": 0.8107377290725708,
+      "eval_runtime": 1.3439,
+      "eval_samples_per_second": 744.113,
+      "eval_steps_per_second": 11.906,
+      "step": 384000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 5.0289468328323434e-05,
+      "loss": 0.2728,
+      "step": 384500
+    },
+    {
+      "epoch": 9.81,
+      "learning_rate": 4.995834530529208e-05,
+      "loss": 0.2729,
+      "step": 385000
+    },
+    {
+      "epoch": 9.81,
+      "eval_loss": 0.8120101690292358,
+      "eval_runtime": 1.2896,
+      "eval_samples_per_second": 775.434,
+      "eval_steps_per_second": 12.407,
+      "step": 385000
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 4.9628371000967394e-05,
+      "loss": 0.2731,
+      "step": 385500
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 4.929954902389534e-05,
+      "loss": 0.2731,
+      "step": 386000
+    },
+    {
+      "epoch": 9.84,
+      "eval_loss": 0.8058800101280212,
+      "eval_runtime": 1.3835,
+      "eval_samples_per_second": 722.807,
+      "eval_steps_per_second": 11.565,
+      "step": 386000
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 4.897188297002046e-05,
+      "loss": 0.2732,
+      "step": 386500
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 4.8645376422646226e-05,
+      "loss": 0.2727,
+      "step": 387000
+    },
+    {
+      "epoch": 9.86,
+      "eval_loss": 0.8082349896430969,
+      "eval_runtime": 1.3707,
+      "eval_samples_per_second": 729.563,
+      "eval_steps_per_second": 11.673,
+      "step": 387000
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 4.832003295239591e-05,
+      "loss": 0.2728,
+      "step": 387500
+    },
+    {
+      "epoch": 9.89,
+      "learning_rate": 4.7995856117173624e-05,
+      "loss": 0.2726,
+      "step": 388000
+    },
+    {
+      "epoch": 9.89,
+      "eval_loss": 0.8089985847473145,
+      "eval_runtime": 1.3037,
+      "eval_samples_per_second": 767.033,
+      "eval_steps_per_second": 12.273,
+      "step": 388000
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 4.767284946212521e-05,
+      "loss": 0.2727,
+      "step": 388500
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 4.735101651959977e-05,
+      "loss": 0.2727,
+      "step": 389000
+    },
+    {
+      "epoch": 9.91,
+      "eval_loss": 0.8019598126411438,
+      "eval_runtime": 1.3529,
+      "eval_samples_per_second": 739.159,
+      "eval_steps_per_second": 11.827,
+      "step": 389000
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 4.7030360809110754e-05,
+      "loss": 0.2726,
+      "step": 389500
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 4.6710885837297726e-05,
+      "loss": 0.273,
+      "step": 390000
+    },
+    {
+      "epoch": 9.94,
+      "eval_loss": 0.8114839792251587,
+      "eval_runtime": 1.3138,
+      "eval_samples_per_second": 761.14,
+      "eval_steps_per_second": 12.178,
+      "step": 390000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.2140389963213595e+22,
+  "total_flos": 1.2459877101988095e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd79899bdba4b0a42b6695b21b791ea0a1c2b1e7f7e8aeb0419ab9a5bb16c136
+oid sha256:da03f29f9d43fcaa0d12888b54defcd8a6a1be294c2c1e7d74429358a9688082
 size 102501541