Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9396b036e3d42153258868d83ab6272bb561cb514c6bd86d35ed30e8bbbd239
+oid sha256:5626330790b12ee2d7ce7d4dcbd8b273b3b64a7b65064555fe8d9c06a390f401
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e2ac0bd2e3b89b8235e3e0a65f4c992d830147db31a60541e63658d5546aed
+oid sha256:d8969f99bc4b2bf9a49ddcf8f8089d61d1b6aab08eeb71271b1d9cf0901fd3e5
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca47bf9995f2597fd7f061968e53085c146d732c2288e465bcef41a8e15455cc
+oid sha256:cfecb5780a8de35fb1e4440365e206fa247793c1e0d3163d77035dd10be829b7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
+oid sha256:fd2861f0d820018c213fdc57cc6eebc5c8df9d5485c4072b9ac9a4ac6f902e69
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5688793718772307,
-  "global_step": 160000,
+  "epoch": 3.7919343326195576,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3206,11 +3206,211 @@
       "eval_samples_per_second": 1182.586,
       "eval_steps_per_second": 18.534,
       "step": 160000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.0002455665988827021,
+      "loss": 0.2899,
+      "step": 160500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.0002451916353649261,
+      "loss": 0.2903,
+      "step": 161000
+    },
+    {
+      "epoch": 3.59,
+      "eval_loss": 0.2730531692504883,
+      "eval_runtime": 1.9636,
+      "eval_samples_per_second": 1169.786,
+      "eval_steps_per_second": 18.334,
+      "step": 161000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00024481568552587566,
+      "loss": 0.2901,
+      "step": 161500
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0002444387534768781,
+      "loss": 0.2895,
+      "step": 162000
+    },
+    {
+      "epoch": 3.61,
+      "eval_loss": 0.2728096544742584,
+      "eval_runtime": 1.9828,
+      "eval_samples_per_second": 1158.488,
+      "eval_steps_per_second": 18.157,
+      "step": 162000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0002440608433400018,
+      "loss": 0.2938,
+      "step": 162500
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 0.00024368195924801158,
+      "loss": 0.2904,
+      "step": 163000
+    },
+    {
+      "epoch": 3.64,
+      "eval_loss": 0.27427318692207336,
+      "eval_runtime": 1.9845,
+      "eval_samples_per_second": 1157.485,
+      "eval_steps_per_second": 18.141,
+      "step": 163000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.00024330210534432314,
+      "loss": 0.29,
+      "step": 163500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0002429212857829579,
+      "loss": 0.2891,
+      "step": 164000
+    },
+    {
+      "epoch": 3.66,
+      "eval_loss": 0.2683263421058655,
+      "eval_runtime": 1.9558,
+      "eval_samples_per_second": 1174.46,
+      "eval_steps_per_second": 18.407,
+      "step": 164000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00024253950472849758,
+      "loss": 0.2893,
+      "step": 164500
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0002421567663560386,
+      "loss": 0.2888,
+      "step": 165000
+    },
+    {
+      "epoch": 3.68,
+      "eval_loss": 0.27206218242645264,
+      "eval_runtime": 1.9344,
+      "eval_samples_per_second": 1187.465,
+      "eval_steps_per_second": 18.611,
+      "step": 165000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.00024177307485114653,
+      "loss": 0.2891,
+      "step": 165500
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.0002413884344098101,
+      "loss": 0.2889,
+      "step": 166000
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 0.2694759666919708,
+      "eval_runtime": 1.9374,
+      "eval_samples_per_second": 1185.599,
+      "eval_steps_per_second": 18.581,
+      "step": 166000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.00024100284923839568,
+      "loss": 0.2892,
+      "step": 166500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.0002406163235536008,
+      "loss": 0.289,
+      "step": 167000
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 0.27140599489212036,
+      "eval_runtime": 2.0107,
+      "eval_samples_per_second": 1142.373,
+      "eval_steps_per_second": 17.904,
+      "step": 167000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.00024022886158240857,
+      "loss": 0.2887,
+      "step": 167500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0002398404675620409,
+      "loss": 0.6252,
+      "step": 168000
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.6785263419151306,
+      "eval_runtime": 1.9867,
+      "eval_samples_per_second": 1156.175,
+      "eval_steps_per_second": 18.12,
+      "step": 168000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.0002394511457399126,
+      "loss": 0.6774,
+      "step": 168500
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.00023906090037358478,
+      "loss": 0.6773,
+      "step": 169000
+    },
+    {
+      "epoch": 3.77,
+      "eval_loss": 0.6770340800285339,
+      "eval_runtime": 1.9319,
+      "eval_samples_per_second": 1188.977,
+      "eval_steps_per_second": 18.634,
+      "step": 169000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.0002386697357307182,
+      "loss": 0.6769,
+      "step": 169500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.00023827765608902676,
+      "loss": 0.6547,
+      "step": 170000
+    },
+    {
+      "epoch": 3.79,
+      "eval_loss": 0.6202901601791382,
+      "eval_runtime": 1.9551,
+      "eval_samples_per_second": 1174.884,
+      "eval_steps_per_second": 18.414,
+      "step": 170000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 5.111708857607754e+21,
+  "total_flos": 5.431195996382254e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e2ac0bd2e3b89b8235e3e0a65f4c992d830147db31a60541e63658d5546aed
+oid sha256:d8969f99bc4b2bf9a49ddcf8f8089d61d1b6aab08eeb71271b1d9cf0901fd3e5
 size 102501541