Training in progress, step 40000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621885238091f20d2a0d641b95a90fdb9bc3444198b5397e5acf7ccaf99d5986
+oid sha256:61231d17702dfc54da0df39c22bae2d1eeca50c901ef6c70c2d09f7f924d00c7
 size 202193937

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa203d33d859117c15113363e612cb47f6ca37647ffc177ded20da5dfb658c7d
+oid sha256:6491475de43c8b876f271481f40ac671b352de875d87744fae94f453e73e7076
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134018a77d9bfe9ebc485a3aeba679430c44f1cee525ba448c6f914dc323fe07
+oid sha256:040772ef0e121e2fe79b90f7b74d0118c9dffb2edec04e04df9f9cfb55a592d2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9b79eba2b3c3487d57b5f9509b60a9305753a31bdaa8757ad442412114850e
+oid sha256:a74054da3729955ad5eacae83f875e2df84ec7d4ca3ed3437d6f2cf84557171f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7645649625363168,
-  "global_step": 30000,
+  "epoch": 1.0194199500484225,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -606,11 +606,211 @@
       "eval_samples_per_second": 830.296,
       "eval_steps_per_second": 13.285,
       "step": 30000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002999040758362914,
+      "loss": 0.3804,
+      "step": 30500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00029988584471039094,
+      "loss": 0.378,
+      "step": 31000
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.8780514001846313,
+      "eval_runtime": 1.1913,
+      "eval_samples_per_second": 839.425,
+      "eval_steps_per_second": 13.431,
+      "step": 31000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002998660291361054,
+      "loss": 0.3763,
+      "step": 31500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002998446293301349,
+      "loss": 0.3748,
+      "step": 32000
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.8814873099327087,
+      "eval_runtime": 1.3032,
+      "eval_samples_per_second": 767.316,
+      "eval_steps_per_second": 12.277,
+      "step": 32000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002998216455265042,
+      "loss": 0.3735,
+      "step": 32500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00029979707797656046,
+      "loss": 0.3716,
+      "step": 33000
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.868879497051239,
+      "eval_runtime": 1.2062,
+      "eval_samples_per_second": 829.022,
+      "eval_steps_per_second": 13.264,
+      "step": 33000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00029977092694897053,
+      "loss": 0.3702,
+      "step": 33500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002997431927297178,
+      "loss": 0.3689,
+      "step": 34000
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.8758594989776611,
+      "eval_runtime": 1.2131,
+      "eval_samples_per_second": 824.364,
+      "eval_steps_per_second": 13.19,
+      "step": 34000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00029971387562209936,
+      "loss": 0.3677,
+      "step": 34500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00029968297594672226,
+      "loss": 0.3665,
+      "step": 35000
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.8690294623374939,
+      "eval_runtime": 1.1601,
+      "eval_samples_per_second": 861.986,
+      "eval_steps_per_second": 13.792,
+      "step": 35000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002996504940415005,
+      "loss": 0.365,
+      "step": 35500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00029961643026165096,
+      "loss": 0.364,
+      "step": 36000
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.8695961236953735,
+      "eval_runtime": 1.2184,
+      "eval_samples_per_second": 820.732,
+      "eval_steps_per_second": 13.132,
+      "step": 36000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00029958078497968973,
+      "loss": 0.3627,
+      "step": 36500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0002995435585854278,
+      "loss": 0.3614,
+      "step": 37000
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.8684411644935608,
+      "eval_runtime": 1.2551,
+      "eval_samples_per_second": 796.719,
+      "eval_steps_per_second": 12.747,
+      "step": 37000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002995047514859671,
+      "loss": 0.3603,
+      "step": 37500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002994643641056959,
+      "loss": 0.3592,
+      "step": 38000
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.8597822189331055,
+      "eval_runtime": 1.198,
+      "eval_samples_per_second": 834.721,
+      "eval_steps_per_second": 13.356,
+      "step": 38000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.000299422396886284,
+      "loss": 0.358,
+      "step": 38500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002993788502866783,
+      "loss": 0.3571,
+      "step": 39000
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.8572097420692444,
+      "eval_runtime": 1.21,
+      "eval_samples_per_second": 826.463,
+      "eval_steps_per_second": 13.223,
+      "step": 39000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00029933372478309746,
+      "loss": 0.3562,
+      "step": 39500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00029928702086902664,
+      "loss": 0.3555,
+      "step": 40000
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.8637193441390991,
+      "eval_runtime": 1.4051,
+      "eval_samples_per_second": 711.674,
+      "eval_steps_per_second": 11.387,
+      "step": 40000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 9.584614163235e+20,
+  "total_flos": 1.277935076184955e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa203d33d859117c15113363e612cb47f6ca37647ffc177ded20da5dfb658c7d
+oid sha256:6491475de43c8b876f271481f40ac671b352de875d87744fae94f453e73e7076
 size 102501541