Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61231d17702dfc54da0df39c22bae2d1eeca50c901ef6c70c2d09f7f924d00c7
+oid sha256:6640249a1c6041c32dfd1464a658338887363ff5085678afe917eb168bf7a616
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6491475de43c8b876f271481f40ac671b352de875d87744fae94f453e73e7076
+oid sha256:5b9279029389011e28791bcbea261efc23528afcc9ebee41b4e9cca6964cc5f3
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
+oid sha256:4bfa0b7d5c3d248e8db4db63af9bfcb5ccbe3aa3f4c28b0b4e1a7ce6f0017bb0
 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": 1.0194199500484225,
-  "global_step": 40000,
+  "epoch": 1.274274937560528,
+  "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": 711.674,
       "eval_steps_per_second": 11.387,
       "step": 40000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00029923873905521244,
+      "loss": 0.3545,
+      "step": 40500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000299188879869657,
+      "loss": 0.3535,
+      "step": 41000
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 0.8638287782669067,
+      "eval_runtime": 1.2182,
+      "eval_samples_per_second": 820.876,
+      "eval_steps_per_second": 13.134,
+      "step": 41000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00029913744385761244,
+      "loss": 0.3524,
+      "step": 41500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00029908443158157465,
+      "loss": 0.3518,
+      "step": 42000
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.8664878606796265,
+      "eval_runtime": 1.2547,
+      "eval_samples_per_second": 796.987,
+      "eval_steps_per_second": 12.752,
+      "step": 42000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002990298436212775,
+      "loss": 0.3511,
+      "step": 42500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002989736805736861,
+      "loss": 0.3502,
+      "step": 43000
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.8559480905532837,
+      "eval_runtime": 1.2272,
+      "eval_samples_per_second": 814.861,
+      "eval_steps_per_second": 13.038,
+      "step": 43000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00029891594305299065,
+      "loss": 0.3494,
+      "step": 43500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00029885663169059926,
+      "loss": 0.3488,
+      "step": 44000
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.859957754611969,
+      "eval_runtime": 1.2944,
+      "eval_samples_per_second": 772.587,
+      "eval_steps_per_second": 12.361,
+      "step": 44000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002987957471351316,
+      "loss": 0.3478,
+      "step": 44500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00029873329005241137,
+      "loss": 0.3469,
+      "step": 45000
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.852756917476654,
+      "eval_runtime": 1.2478,
+      "eval_samples_per_second": 801.439,
+      "eval_steps_per_second": 12.823,
+      "step": 45000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00029866926112545925,
+      "loss": 0.3464,
+      "step": 45500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00029860366105448534,
+      "loss": 0.3459,
+      "step": 46000
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 0.8597527146339417,
+      "eval_runtime": 1.1814,
+      "eval_samples_per_second": 846.435,
+      "eval_steps_per_second": 13.543,
+      "step": 46000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00029853649055688143,
+      "loss": 0.3451,
+      "step": 46500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00029846775036721337,
+      "loss": 0.3444,
+      "step": 47000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.860701322555542,
+      "eval_runtime": 1.2083,
+      "eval_samples_per_second": 827.633,
+      "eval_steps_per_second": 13.242,
+      "step": 47000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002983974412372129,
+      "loss": 0.3438,
+      "step": 47500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00029832556393576934,
+      "loss": 0.3428,
+      "step": 48000
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.865045964717865,
+      "eval_runtime": 1.2493,
+      "eval_samples_per_second": 800.445,
+      "eval_steps_per_second": 12.807,
+      "step": 48000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002982521192489214,
+      "loss": 0.3425,
+      "step": 48500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002981771079798483,
+      "loss": 0.342,
+      "step": 49000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.8640099167823792,
+      "eval_runtime": 1.2369,
+      "eval_samples_per_second": 808.489,
+      "eval_steps_per_second": 12.936,
+      "step": 49000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00029810053094886136,
+      "loss": 0.3417,
+      "step": 49500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00029802238899339473,
+      "loss": 0.3408,
+      "step": 50000
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 0.8549481630325317,
+      "eval_runtime": 1.3108,
+      "eval_samples_per_second": 762.871,
+      "eval_steps_per_second": 12.206,
+      "step": 50000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.277935076184955e+21,
+  "total_flos": 1.597422214959455e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6491475de43c8b876f271481f40ac671b352de875d87744fae94f453e73e7076
+oid sha256:5b9279029389011e28791bcbea261efc23528afcc9ebee41b4e9cca6964cc5f3
 size 102501541