Training in progress, step 430000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac94a60c95ba2596b6d1d05315af6a3ea5bad0a2404c9fbebd7db8a3b7f370f8
+oid sha256:485576f1d48c6a4e3bf5c2faeabd28b10bf14e54c686faf5ee4b916aae291248
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cf499ab54bc6b5b46a8f12dd922823d0795f7339d994c55bfa6c710a91461c
+oid sha256:402c24544f87635066120a062e0f54ba50aad454021fed3207324dcff5633224
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
+oid sha256:0132b64d8716021d47991e50e22003dfc788052c2c88a7966cf5395f369a4260
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fa0c13fc0e3348f6228394f5e318945295debe26ba21ec91b2c06a47593869
+oid sha256:f427c751ea4b109969727e0c5f2ef9ef6fd7587de8192ab50fc2201ab4ba3ed9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.703909475508436,
-  "global_step": 420000,
+  "epoch": 10.958764463020541,
+  "global_step": 430000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8406,11 +8406,211 @@
       "eval_samples_per_second": 753.638,
       "eval_steps_per_second": 12.058,
       "step": 420000
+    },
+    {
+      "epoch": 10.72,
+      "learning_rate": 2.9586456905128618e-05,
+      "loss": 0.27,
+      "step": 420500
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 2.9346475051519687e-05,
+      "loss": 0.2699,
+      "step": 421000
+    },
+    {
+      "epoch": 10.73,
+      "eval_loss": 0.8154944777488708,
+      "eval_runtime": 1.3065,
+      "eval_samples_per_second": 765.411,
+      "eval_steps_per_second": 12.247,
+      "step": 421000
+    },
+    {
+      "epoch": 10.74,
+      "learning_rate": 2.910786732472815e-05,
+      "loss": 0.27,
+      "step": 421500
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 2.887063633412981e-05,
+      "loss": 0.2701,
+      "step": 422000
+    },
+    {
+      "epoch": 10.75,
+      "eval_loss": 0.8139403462409973,
+      "eval_runtime": 1.2861,
+      "eval_samples_per_second": 777.555,
+      "eval_steps_per_second": 12.441,
+      "step": 422000
+    },
+    {
+      "epoch": 10.77,
+      "learning_rate": 2.863478467404478e-05,
+      "loss": 0.2699,
+      "step": 422500
+    },
+    {
+      "epoch": 10.78,
+      "learning_rate": 2.8400314923709112e-05,
+      "loss": 0.2701,
+      "step": 423000
+    },
+    {
+      "epoch": 10.78,
+      "eval_loss": 0.8132787942886353,
+      "eval_runtime": 1.3439,
+      "eval_samples_per_second": 744.104,
+      "eval_steps_per_second": 11.906,
+      "step": 423000
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 2.816722964724636e-05,
+      "loss": 0.2697,
+      "step": 423500
+    },
+    {
+      "epoch": 10.81,
+      "learning_rate": 2.793553139363981e-05,
+      "loss": 0.2701,
+      "step": 424000
+    },
+    {
+      "epoch": 10.81,
+      "eval_loss": 0.8099727034568787,
+      "eval_runtime": 1.3264,
+      "eval_samples_per_second": 753.909,
+      "eval_steps_per_second": 12.063,
+      "step": 424000
+    },
+    {
+      "epoch": 10.82,
+      "learning_rate": 2.7705222696704366e-05,
+      "loss": 0.27,
+      "step": 424500
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 2.7476306075059096e-05,
+      "loss": 0.2696,
+      "step": 425000
+    },
+    {
+      "epoch": 10.83,
+      "eval_loss": 0.8077329993247986,
+      "eval_runtime": 1.3315,
+      "eval_samples_per_second": 751.038,
+      "eval_steps_per_second": 12.017,
+      "step": 425000
+    },
+    {
+      "epoch": 10.84,
+      "learning_rate": 2.7248784032099478e-05,
+      "loss": 0.2696,
+      "step": 425500
+    },
+    {
+      "epoch": 10.86,
+      "learning_rate": 2.7022659055970144e-05,
+      "loss": 0.2696,
+      "step": 426000
+    },
+    {
+      "epoch": 10.86,
+      "eval_loss": 0.8097303509712219,
+      "eval_runtime": 1.3191,
+      "eval_samples_per_second": 758.11,
+      "eval_steps_per_second": 12.13,
+      "step": 426000
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 2.6797933619537604e-05,
+      "loss": 0.2694,
+      "step": 426500
+    },
+    {
+      "epoch": 10.88,
+      "learning_rate": 2.6574610180363166e-05,
+      "loss": 0.2698,
+      "step": 427000
+    },
+    {
+      "epoch": 10.88,
+      "eval_loss": 0.8035640120506287,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 718.328,
+      "eval_steps_per_second": 11.493,
+      "step": 427000
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 2.6352691180676286e-05,
+      "loss": 0.2696,
+      "step": 427500
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 2.6132179047347505e-05,
+      "loss": 0.2698,
+      "step": 428000
+    },
+    {
+      "epoch": 10.91,
+      "eval_loss": 0.8066699504852295,
+      "eval_runtime": 1.5174,
+      "eval_samples_per_second": 659.02,
+      "eval_steps_per_second": 10.544,
+      "step": 428000
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 2.5913076191862238e-05,
+      "loss": 0.2696,
+      "step": 428500
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 2.5695385010294165e-05,
+      "loss": 0.2699,
+      "step": 429000
+    },
+    {
+      "epoch": 10.93,
+      "eval_loss": 0.813107430934906,
+      "eval_runtime": 1.3419,
+      "eval_samples_per_second": 745.228,
+      "eval_steps_per_second": 11.924,
+      "step": 429000
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 2.5479107883279144e-05,
+      "loss": 0.2692,
+      "step": 429500
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 2.5264247175989292e-05,
+      "loss": 0.2695,
+      "step": 430000
+    },
+    {
+      "epoch": 10.96,
+      "eval_loss": 0.8058525323867798,
+      "eval_runtime": 1.3197,
+      "eval_samples_per_second": 757.744,
+      "eval_steps_per_second": 12.124,
+      "step": 430000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.341832503939855e+22,
+  "total_flos": 1.373781217817305e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cf499ab54bc6b5b46a8f12dd922823d0795f7339d994c55bfa6c710a91461c
+oid sha256:402c24544f87635066120a062e0f54ba50aad454021fed3207324dcff5633224
 size 102501541