Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a806770a6d25518cb1674ae526f6d236de399a295d5a453821ffdc0e6a41627
+oid sha256:11a5b6e2d3a240e31f2407589b74bf56102df3cd6db72efc78606028852235e7
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175c9af2cd55b51e9df8d727ba8d18aab140807b11f81fcd4adde2c5741e4d30
+oid sha256:5a9d1af9969e324f9fedc078ab1e1ab334bc4c8eeeb0d4b38445a40029af3cf3
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
+oid sha256:d33ce3108e385660090a22247b2e131088c6273bea93f4243061660df0632b29
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8d45ebb28c7b9f23a6abeafd90122c1ed22446a846f1cf2ac94e95c51e1adb
+oid sha256:90ff94ce099b109f6c343c1450c170171a247badda4343ab1850180869cf03e2
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5576436211146181,
-  "global_step": 50000,
+  "epoch": 0.6691723453375417,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1006,11 +1006,211 @@
       "eval_samples_per_second": 950.212,
       "eval_steps_per_second": 14.892,
       "step": 50000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00014999990431133645,
+      "loss": 0.3579,
+      "step": 50500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001499996172456075,
+      "loss": 0.3563,
+      "step": 51000
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.3443795442581177,
+      "eval_runtime": 2.3466,
+      "eval_samples_per_second": 978.854,
+      "eval_steps_per_second": 15.341,
+      "step": 51000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00014999913880359787,
+      "loss": 0.3547,
+      "step": 51500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00014999846898661572,
+      "loss": 0.353,
+      "step": 52000
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 0.34043800830841064,
+      "eval_runtime": 2.4046,
+      "eval_samples_per_second": 955.259,
+      "eval_steps_per_second": 14.971,
+      "step": 52000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00014999760779649222,
+      "loss": 0.3516,
+      "step": 52500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00014999655523558183,
+      "loss": 0.3502,
+      "step": 53000
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.3358021378517151,
+      "eval_runtime": 2.3861,
+      "eval_samples_per_second": 962.643,
+      "eval_steps_per_second": 15.087,
+      "step": 53000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00014999531130676229,
+      "loss": 0.3491,
+      "step": 53500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00014999387601343436,
+      "loss": 0.3473,
+      "step": 54000
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.3330630362033844,
+      "eval_runtime": 2.3348,
+      "eval_samples_per_second": 983.811,
+      "eval_steps_per_second": 15.419,
+      "step": 54000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00014999224935952215,
+      "loss": 0.3463,
+      "step": 54500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00014999043134947282,
+      "loss": 0.3445,
+      "step": 55000
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 0.33030495047569275,
+      "eval_runtime": 2.318,
+      "eval_samples_per_second": 990.921,
+      "eval_steps_per_second": 15.53,
+      "step": 55000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00014998842198825674,
+      "loss": 0.3434,
+      "step": 55500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00014998622128136748,
+      "loss": 0.342,
+      "step": 56000
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.3295433819293976,
+      "eval_runtime": 2.3042,
+      "eval_samples_per_second": 996.891,
+      "eval_steps_per_second": 15.624,
+      "step": 56000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014998382923482164,
+      "loss": 0.3411,
+      "step": 56500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000149981245855159,
+      "loss": 0.3396,
+      "step": 57000
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.32805606722831726,
+      "eval_runtime": 2.4137,
+      "eval_samples_per_second": 951.659,
+      "eval_steps_per_second": 14.915,
+      "step": 57000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00014997847114944242,
+      "loss": 0.3383,
+      "step": 57500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00014997550512525784,
+      "loss": 0.3374,
+      "step": 58000
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.3256905674934387,
+      "eval_runtime": 2.4211,
+      "eval_samples_per_second": 948.748,
+      "eval_steps_per_second": 14.869,
+      "step": 58000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00014997234779071426,
+      "loss": 0.3365,
+      "step": 58500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001499689991544437,
+      "loss": 0.3353,
+      "step": 59000
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.32548126578330994,
+      "eval_runtime": 2.4309,
+      "eval_samples_per_second": 944.932,
+      "eval_steps_per_second": 14.81,
+      "step": 59000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001499654592256012,
+      "loss": 0.3342,
+      "step": 59500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00014996172801386482,
+      "loss": 0.3333,
+      "step": 60000
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.3190021514892578,
+      "eval_runtime": 2.4381,
+      "eval_samples_per_second": 942.115,
+      "eval_steps_per_second": 14.765,
+      "step": 60000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.505013051517357e+21,
+  "total_flos": 4.2060156618208287e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175c9af2cd55b51e9df8d727ba8d18aab140807b11f81fcd4adde2c5741e4d30
+oid sha256:5a9d1af9969e324f9fedc078ab1e1ab334bc4c8eeeb0d4b38445a40029af3cf3
 size 449471589