Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd90268a183d4a4023e5612c8fb0216ae28336b775995df418dab01a0f952f3
+oid sha256:78d053774b6389f97348f5fa02f2789d9380cd22ec9c56252d6cb43ae07a9c71
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfa522f93b8ede7d3066bcbe6d05c94f3a226c317ea2a1bebd0b5057965b5b7
+oid sha256:d41ef1449515965c8c4ad61e0e0ab0776df2e27d22ece58583e00038b5639984
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c299ab3f67efb821bf899b5b131b39e16d8d0f58bf6054bb217d5f7cebfe56
+oid sha256:88586047bcfe6a4bb7d99cf7e4e2674bac6309979a3ebf2050de05d1a7cb7cfb
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74054da3729955ad5eacae83f875e2df84ec7d4ca3ed3437d6f2cf84557171f
+oid sha256:8ec5c60f6b831a1ad5ababd554115ca1132f641d196d63d42183ef95c8827963
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9319881637503203,
-  "global_step": 40000,
+  "epoch": 1.1649852046879006,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -806,11 +806,211 @@
       "eval_samples_per_second": 1667.699,
       "eval_steps_per_second": 26.556,
       "step": 40000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00029923873905521244,
+      "loss": 0.3483,
+      "step": 40500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.000299188879869657,
+      "loss": 0.3477,
+      "step": 41000
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.33138296008110046,
+      "eval_runtime": 1.2875,
+      "eval_samples_per_second": 1707.216,
+      "eval_steps_per_second": 27.185,
+      "step": 41000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00029913744385761244,
+      "loss": 0.3466,
+      "step": 41500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00029908443158157465,
+      "loss": 0.3459,
+      "step": 42000
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.32563212513923645,
+      "eval_runtime": 1.2983,
+      "eval_samples_per_second": 1692.964,
+      "eval_steps_per_second": 26.958,
+      "step": 42000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002990298436212775,
+      "loss": 0.3448,
+      "step": 42500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002989736805736861,
+      "loss": 0.3441,
+      "step": 43000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.32700827717781067,
+      "eval_runtime": 1.3967,
+      "eval_samples_per_second": 1573.716,
+      "eval_steps_per_second": 25.059,
+      "step": 43000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00029891594305299065,
+      "loss": 0.3432,
+      "step": 43500
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00029885663169059926,
+      "loss": 0.3424,
+      "step": 44000
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.3216361701488495,
+      "eval_runtime": 1.4298,
+      "eval_samples_per_second": 1537.25,
+      "eval_steps_per_second": 24.479,
+      "step": 44000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002987957471351316,
+      "loss": 0.3415,
+      "step": 44500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00029873329005241137,
+      "loss": 0.3408,
+      "step": 45000
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.324531614780426,
+      "eval_runtime": 1.3974,
+      "eval_samples_per_second": 1572.95,
+      "eval_steps_per_second": 25.047,
+      "step": 45000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00029866926112545925,
+      "loss": 0.3399,
+      "step": 45500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00029860366105448534,
+      "loss": 0.3394,
+      "step": 46000
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.3231622278690338,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 1578.889,
+      "eval_steps_per_second": 25.142,
+      "step": 46000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00029853649055688143,
+      "loss": 0.3387,
+      "step": 46500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00029846775036721337,
+      "loss": 0.338,
+      "step": 47000
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.32254886627197266,
+      "eval_runtime": 1.4182,
+      "eval_samples_per_second": 1549.86,
+      "eval_steps_per_second": 24.679,
+      "step": 47000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002983974412372129,
+      "loss": 0.337,
+      "step": 47500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00029832556393576934,
+      "loss": 0.3363,
+      "step": 48000
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.3195147216320038,
+      "eval_runtime": 1.408,
+      "eval_samples_per_second": 1561.07,
+      "eval_steps_per_second": 24.858,
+      "step": 48000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002982521192489214,
+      "loss": 0.3357,
+      "step": 48500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002981771079798483,
+      "loss": 0.3353,
+      "step": 49000
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.3167419731616974,
+      "eval_runtime": 1.4463,
+      "eval_samples_per_second": 1519.733,
+      "eval_steps_per_second": 24.2,
+      "step": 49000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029810053094886136,
+      "loss": 0.3345,
+      "step": 49500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029802238899339473,
+      "loss": 0.3338,
+      "step": 50000
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.3171909749507904,
+      "eval_runtime": 1.4105,
+      "eval_samples_per_second": 1558.283,
+      "eval_steps_per_second": 24.813,
+      "step": 50000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.277948555098e+21,
+  "total_flos": 1.5974331968815932e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfa522f93b8ede7d3066bcbe6d05c94f3a226c317ea2a1bebd0b5057965b5b7
+oid sha256:d41ef1449515965c8c4ad61e0e0ab0776df2e27d22ece58583e00038b5639984
 size 102501541