Training in progress, step 40000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a92335164a57171365050fd07a22cee199d87b5d4f31f9f266d934997806ef1
+oid sha256:1b2aa3ac438aafc200ae70f8085f90242dc992cf907ac3f0294370fe40a0df68
 size 50044241

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17ced65414e5fa0fdf019e711ae42967ebbbc1772201d6c2fa0f444b22af2ac
+oid sha256:3d18c8e7e9886f3271a24bd5849f3f89c80dbc60739565e2d86ced010c5eeb20
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1c87c4f861c3b9c96d42cb3e1fac9d804a68e14a3351872cbc3092e0046c79
+oid sha256:2ede58e3004a4327d493f9d870219b307a5ef56e0c4fc6821301c4f24058b122
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285c70cc0b99f831fd558ed5749dae6f2d660f449e704cb70ab7d67faaef2748
+oid sha256:c7750ccd53e61fd7fcec6ad8e54086c4abb8aa56c6a0781b4ecadd56cbb87c42
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3383297644539613,
-  "global_step": 30000,
+  "epoch": 1.7844396859386151,
+  "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": 1022.498,
       "eval_steps_per_second": 16.025,
       "step": 30000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0005916774417018287,
+      "loss": 0.6772,
+      "step": 30500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0005912109970154897,
+      "loss": 0.6772,
+      "step": 31000
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 0.6777171492576599,
+      "eval_runtime": 2.1569,
+      "eval_samples_per_second": 1064.935,
+      "eval_steps_per_second": 16.69,
+      "step": 31000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0005907320325329461,
+      "loss": 0.6772,
+      "step": 31500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0005902405692056561,
+      "loss": 0.6772,
+      "step": 32000
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.676947832107544,
+      "eval_runtime": 2.3119,
+      "eval_samples_per_second": 993.573,
+      "eval_steps_per_second": 15.572,
+      "step": 32000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0005897366285318178,
+      "loss": 0.6772,
+      "step": 32500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0005892202325554288,
+      "loss": 0.6773,
+      "step": 33000
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.6766595840454102,
+      "eval_runtime": 2.1462,
+      "eval_samples_per_second": 1070.248,
+      "eval_steps_per_second": 16.774,
+      "step": 33000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0005886914038653217,
+      "loss": 0.6772,
+      "step": 33500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0005881501655941771,
+      "loss": 0.677,
+      "step": 34000
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 0.6765649914741516,
+      "eval_runtime": 2.1369,
+      "eval_samples_per_second": 1074.929,
+      "eval_steps_per_second": 16.847,
+      "step": 34000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00058759654141751,
+      "loss": 0.6768,
+      "step": 34500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0005870305555526355,
+      "loss": 0.6765,
+      "step": 35000
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.676632821559906,
+      "eval_runtime": 2.2745,
+      "eval_samples_per_second": 1009.888,
+      "eval_steps_per_second": 15.828,
+      "step": 35000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0005864522327576088,
+      "loss": 0.6764,
+      "step": 35500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0005858615983301424,
+      "loss": 0.6763,
+      "step": 36000
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.6765820980072021,
+      "eval_runtime": 2.1766,
+      "eval_samples_per_second": 1055.304,
+      "eval_steps_per_second": 16.539,
+      "step": 36000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0005852586781064997,
+      "loss": 0.6763,
+      "step": 36500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0005846434984603645,
+      "loss": 0.6764,
+      "step": 37000
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 0.6758345365524292,
+      "eval_runtime": 2.237,
+      "eval_samples_per_second": 1026.821,
+      "eval_steps_per_second": 16.093,
+      "step": 37000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0005840160863016872,
+      "loss": 0.6763,
+      "step": 37500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0005833764690755083,
+      "loss": 0.6764,
+      "step": 38000
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.6762025952339172,
+      "eval_runtime": 2.1722,
+      "eval_samples_per_second": 1057.45,
+      "eval_steps_per_second": 16.573,
+      "step": 38000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0005827246747607574,
+      "loss": 0.6765,
+      "step": 38500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0005820607318690293,
+      "loss": 0.6758,
+      "step": 39000
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.6771443486213684,
+      "eval_runtime": 2.2147,
+      "eval_samples_per_second": 1037.153,
+      "eval_steps_per_second": 16.255,
+      "step": 39000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0005813846694433368,
+      "loss": 0.6773,
+      "step": 39500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0005806965170568409,
+      "loss": 0.6772,
+      "step": 40000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.6770426630973816,
+      "eval_runtime": 2.1711,
+      "eval_samples_per_second": 1057.979,
+      "eval_steps_per_second": 16.581,
+      "step": 40000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 12,
-  "total_flos": 4.804968766152387e+20,
+  "total_flos": 6.406648794810428e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17ced65414e5fa0fdf019e711ae42967ebbbc1772201d6c2fa0f444b22af2ac
+oid sha256:3d18c8e7e9886f3271a24bd5849f3f89c80dbc60739565e2d86ced010c5eeb20
 size 25761253