Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed32c01ba5914256ee8f4a1db952372628199494048f85def9b6bea2d03f63e
+oid sha256:8be6802b9d992ac2c3994565edfc5567d3f523032a5e6e5411ff08074758c58f
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa4e826f8cd2d5cd8fce3cffdce3fc09b41b0fb0a4b74491ee02350a70950a4
+oid sha256:a0ed0a890cada09375208ef03bdfdd6d63ca0c33270b092aa04ab6ca525c88e1
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164dbb3fe005b62eb1c3ed6eb3ead419d710b64e59abcb8b03a20d4e00ab7cc9
+oid sha256:6c6f8570c2dac95236cdc5d351a3c8ca55f21ec8e5bc0a65475a416cca474cb1
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3f000e1c939912bb1fea4c3fda9ca6e80fe563342ccf4a59cb3d0b46d78187
+oid sha256:36f11c380127c9b2248f3452b83eb7e7a6efc224b0b84b63651e3db0e819c91c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.901960784313726,
-  "global_step": 80000,
+  "epoch": 5.514705882352941,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1606,11 +1606,211 @@
       "eval_samples_per_second": 769.194,
       "eval_steps_per_second": 12.307,
       "step": 80000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0004884933271217461,
+      "loss": 0.501,
+      "step": 80500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.0004869616019012347,
+      "loss": 0.5008,
+      "step": 81000
+    },
+    {
+      "epoch": 4.96,
+      "eval_loss": 0.8512425422668457,
+      "eval_runtime": 1.2521,
+      "eval_samples_per_second": 798.677,
+      "eval_steps_per_second": 12.779,
+      "step": 81000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.00048542191709078226,
+      "loss": 0.5004,
+      "step": 81500
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.00048387434004119027,
+      "loss": 0.5002,
+      "step": 82000
+    },
+    {
+      "epoch": 5.02,
+      "eval_loss": 0.8470181822776794,
+      "eval_runtime": 1.2894,
+      "eval_samples_per_second": 775.545,
+      "eval_steps_per_second": 12.409,
+      "step": 82000
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.0004823189384484924,
+      "loss": 0.5007,
+      "step": 82500
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 0.000480755780350993,
+      "loss": 0.4995,
+      "step": 83000
+    },
+    {
+      "epoch": 5.09,
+      "eval_loss": 0.846192479133606,
+      "eval_runtime": 1.2808,
+      "eval_samples_per_second": 780.79,
+      "eval_steps_per_second": 12.493,
+      "step": 83000
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 0.0004791849341262914,
+      "loss": 0.4993,
+      "step": 83500
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 0.0004776064684882901,
+      "loss": 0.4991,
+      "step": 84000
+    },
+    {
+      "epoch": 5.15,
+      "eval_loss": 0.8454980254173279,
+      "eval_runtime": 1.3356,
+      "eval_samples_per_second": 748.729,
+      "eval_steps_per_second": 11.98,
+      "step": 84000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 0.0004760204524841897,
+      "loss": 0.4985,
+      "step": 84500
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.0004744269554914683,
+      "loss": 0.4982,
+      "step": 85000
+    },
+    {
+      "epoch": 5.21,
+      "eval_loss": 0.8464594483375549,
+      "eval_runtime": 1.368,
+      "eval_samples_per_second": 730.977,
+      "eval_steps_per_second": 11.696,
+      "step": 85000
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 0.00047282604721484643,
+      "loss": 0.4979,
+      "step": 85500
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 0.0004712177976832385,
+      "loss": 0.4978,
+      "step": 86000
+    },
+    {
+      "epoch": 5.27,
+      "eval_loss": 0.8433752655982971,
+      "eval_runtime": 1.3279,
+      "eval_samples_per_second": 753.055,
+      "eval_steps_per_second": 12.049,
+      "step": 86000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.0004696022772466888,
+      "loss": 0.4974,
+      "step": 86500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.00046797955657329487,
+      "loss": 0.4969,
+      "step": 87000
+    },
+    {
+      "epoch": 5.33,
+      "eval_loss": 0.843237042427063,
+      "eval_runtime": 1.3349,
+      "eval_samples_per_second": 749.108,
+      "eval_steps_per_second": 11.986,
+      "step": 87000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.000466349706646116,
+      "loss": 0.4967,
+      "step": 87500
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.00046471279876006763,
+      "loss": 0.4964,
+      "step": 88000
+    },
+    {
+      "epoch": 5.39,
+      "eval_loss": 0.8417282104492188,
+      "eval_runtime": 1.3291,
+      "eval_samples_per_second": 752.394,
+      "eval_steps_per_second": 12.038,
+      "step": 88000
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 0.00046306890451880395,
+      "loss": 0.4964,
+      "step": 88500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 0.0004614180958315844,
+      "loss": 0.4957,
+      "step": 89000
+    },
+    {
+      "epoch": 5.45,
+      "eval_loss": 0.8362923860549927,
+      "eval_runtime": 1.2708,
+      "eval_samples_per_second": 786.921,
+      "eval_steps_per_second": 12.591,
+      "step": 89000
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.00045976044491012884,
+      "loss": 0.4954,
+      "step": 89500
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 0.00045809602426545847,
+      "loss": 0.495,
+      "step": 90000
+    },
+    {
+      "epoch": 5.51,
+      "eval_loss": 0.8392152190208435,
+      "eval_runtime": 1.26,
+      "eval_samples_per_second": 793.671,
+      "eval_steps_per_second": 12.699,
+      "step": 90000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 1.2813039809119723e+21,
+  "total_flos": 1.4414619732741613e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa4e826f8cd2d5cd8fce3cffdce3fc09b41b0fb0a4b74491ee02350a70950a4
+oid sha256:a0ed0a890cada09375208ef03bdfdd6d63ca0c33270b092aa04ab6ca525c88e1
 size 25761253