Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a5b6e2d3a240e31f2407589b74bf56102df3cd6db72efc78606028852235e7
-size 893438545
+oid sha256:3ed924fbf244552502b394f746883a6e11b9da238444af325c3d3fb38fa9fed4
+size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9d1af9969e324f9fedc078ab1e1ab334bc4c8eeeb0d4b38445a40029af3cf3
+oid sha256:5a2c2b1f31e602dcbc6fa8e9cd193a75249372c2a301104271bb1cb69568ffa1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
+oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ff94ce099b109f6c343c1450c170171a247badda4343ab1850180869cf03e2
+oid sha256:f7c802ff93fc9d67d63f3e03f7bd5fd1c7e4a71a3faef71bb4d686a1c5885c38
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6691723453375417,
-  "global_step": 60000,
+  "epoch": 0.7807010695604653,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1206,11 +1206,211 @@
       "eval_samples_per_second": 942.115,
       "eval_steps_per_second": 14.765,
       "step": 60000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00014995780552943551,
+      "loss": 0.3321,
+      "step": 60500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00014995369178303722,
+      "loss": 0.3311,
+      "step": 61000
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3181557357311249,
+      "eval_runtime": 2.3632,
+      "eval_samples_per_second": 971.967,
+      "eval_steps_per_second": 15.233,
+      "step": 61000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001499493867859168,
+      "loss": 0.3298,
+      "step": 61500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001499448905498439,
+      "loss": 0.3289,
+      "step": 62000
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.31774210929870605,
+      "eval_runtime": 2.4377,
+      "eval_samples_per_second": 942.269,
+      "eval_steps_per_second": 14.768,
+      "step": 62000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00014994020308711106,
+      "loss": 0.3281,
+      "step": 62500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00014993532441053364,
+      "loss": 0.3272,
+      "step": 63000
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 0.31380537152290344,
+      "eval_runtime": 2.4068,
+      "eval_samples_per_second": 954.378,
+      "eval_steps_per_second": 14.958,
+      "step": 63000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001499302545334498,
+      "loss": 0.3262,
+      "step": 63500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001499249934697203,
+      "loss": 0.3253,
+      "step": 64000
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.3134210705757141,
+      "eval_runtime": 2.4456,
+      "eval_samples_per_second": 939.234,
+      "eval_steps_per_second": 14.72,
+      "step": 64000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00014991954123372875,
+      "loss": 0.3246,
+      "step": 64500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001499138978403813,
+      "loss": 0.3242,
+      "step": 65000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.3107437193393707,
+      "eval_runtime": 2.3823,
+      "eval_samples_per_second": 964.183,
+      "eval_steps_per_second": 15.111,
+      "step": 65000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00014990806330510687,
+      "loss": 0.3231,
+      "step": 65500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00014990203764385677,
+      "loss": 0.3221,
+      "step": 66000
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.308339387178421,
+      "eval_runtime": 2.4467,
+      "eval_samples_per_second": 938.797,
+      "eval_steps_per_second": 14.713,
+      "step": 66000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00014989582087310494,
+      "loss": 0.3211,
+      "step": 66500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00014988941300984784,
+      "loss": 0.3203,
+      "step": 67000
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.3079957365989685,
+      "eval_runtime": 2.3779,
+      "eval_samples_per_second": 965.976,
+      "eval_steps_per_second": 15.139,
+      "step": 67000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00014988281407160426,
+      "loss": 0.3194,
+      "step": 67500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001498760240764155,
+      "loss": 0.3188,
+      "step": 68000
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.30548328161239624,
+      "eval_runtime": 2.3902,
+      "eval_samples_per_second": 961.017,
+      "eval_steps_per_second": 15.062,
+      "step": 68000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00014986904304284512,
+      "loss": 0.3181,
+      "step": 68500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000149861870989979,
+      "loss": 0.3169,
+      "step": 69000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.3034500181674957,
+      "eval_runtime": 2.3995,
+      "eval_samples_per_second": 957.293,
+      "eval_steps_per_second": 15.003,
+      "step": 69000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014985450793742527,
+      "loss": 0.3164,
+      "step": 69500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001498469539053142,
+      "loss": 0.3157,
+      "step": 70000
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.3020155429840088,
+      "eval_runtime": 2.3865,
+      "eval_samples_per_second": 962.488,
+      "eval_steps_per_second": 15.085,
+      "step": 70000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.2060156618208287e+21,
+  "total_flos": 4.9070182721243e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9d1af9969e324f9fedc078ab1e1ab334bc4c8eeeb0d4b38445a40029af3cf3
+oid sha256:5a2c2b1f31e602dcbc6fa8e9cd193a75249372c2a301104271bb1cb69568ffa1
 size 449471589