Training in progress, step 420000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23757c0288979d27bb8e7d987ca91414953ed2fb98096163be33a545f5af5ab4
+oid sha256:ac94a60c95ba2596b6d1d05315af6a3ea5bad0a2404c9fbebd7db8a3b7f370f8
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
+oid sha256:09cf499ab54bc6b5b46a8f12dd922823d0795f7339d994c55bfa6c710a91461c
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
+oid sha256:9a10c6d1216669debf3750d55e62e1d7be5eb19a554ae8b1f1f2b6955d97a50b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498c95fdcab578849c69bf4a10f0532f5bf3ba8048fa37c1b416b3afd0ea5f33
+oid sha256:21fa0c13fc0e3348f6228394f5e318945295debe26ba21ec91b2c06a47593869
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.44905448799633,
-  "global_step": 410000,
+  "epoch": 10.703909475508436,
+  "global_step": 420000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8206,11 +8206,211 @@
       "eval_samples_per_second": 742.097,
       "eval_steps_per_second": 11.874,
       "step": 410000
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 3.4670510086189736e-05,
+      "loss": 0.271,
+      "step": 410500
+    },
+    {
+      "epoch": 10.47,
+      "learning_rate": 3.440361659286563e-05,
+      "loss": 0.2712,
+      "step": 411000
+    },
+    {
+      "epoch": 10.47,
+      "eval_loss": 0.8162291049957275,
+      "eval_runtime": 1.3642,
+      "eval_samples_per_second": 733.056,
+      "eval_steps_per_second": 11.729,
+      "step": 411000
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 3.413804192226918e-05,
+      "loss": 0.271,
+      "step": 411500
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 3.387378897868246e-05,
+      "loss": 0.2709,
+      "step": 412000
+    },
+    {
+      "epoch": 10.5,
+      "eval_loss": 0.8157584071159363,
+      "eval_runtime": 1.3922,
+      "eval_samples_per_second": 718.295,
+      "eval_steps_per_second": 11.493,
+      "step": 412000
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 3.361086065193336e-05,
+      "loss": 0.2705,
+      "step": 412500
+    },
+    {
+      "epoch": 10.53,
+      "learning_rate": 3.334925981736389e-05,
+      "loss": 0.2706,
+      "step": 413000
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 0.8102970123291016,
+      "eval_runtime": 1.343,
+      "eval_samples_per_second": 744.614,
+      "eval_steps_per_second": 11.914,
+      "step": 413000
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 3.3088989335798925e-05,
+      "loss": 0.2707,
+      "step": 413500
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 3.283005205351467e-05,
+      "loss": 0.2709,
+      "step": 414000
+    },
+    {
+      "epoch": 10.55,
+      "eval_loss": 0.8069249987602234,
+      "eval_runtime": 1.3236,
+      "eval_samples_per_second": 755.504,
+      "eval_steps_per_second": 12.088,
+      "step": 414000
+    },
+    {
+      "epoch": 10.56,
+      "learning_rate": 3.2572450802207845e-05,
+      "loss": 0.2705,
+      "step": 414500
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 3.2316188398964344e-05,
+      "loss": 0.2706,
+      "step": 415000
+    },
+    {
+      "epoch": 10.58,
+      "eval_loss": 0.812959611415863,
+      "eval_runtime": 1.3895,
+      "eval_samples_per_second": 719.683,
+      "eval_steps_per_second": 11.515,
+      "step": 415000
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 3.206126764622888e-05,
+      "loss": 0.2708,
+      "step": 415500
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 3.180769133177392e-05,
+      "loss": 0.2706,
+      "step": 416000
+    },
+    {
+      "epoch": 10.6,
+      "eval_loss": 0.8125792145729065,
+      "eval_runtime": 1.3667,
+      "eval_samples_per_second": 731.714,
+      "eval_steps_per_second": 11.707,
+      "step": 416000
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 3.155546222866939e-05,
+      "loss": 0.2704,
+      "step": 416500
+    },
+    {
+      "epoch": 10.63,
+      "learning_rate": 3.130458309525239e-05,
+      "loss": 0.2704,
+      "step": 417000
+    },
+    {
+      "epoch": 10.63,
+      "eval_loss": 0.8181024193763733,
+      "eval_runtime": 1.3224,
+      "eval_samples_per_second": 756.173,
+      "eval_steps_per_second": 12.099,
+      "step": 417000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 3.1055056675096826e-05,
+      "loss": 0.2702,
+      "step": 417500
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 3.0806885696983816e-05,
+      "loss": 0.2704,
+      "step": 418000
+    },
+    {
+      "epoch": 10.65,
+      "eval_loss": 0.8099979162216187,
+      "eval_runtime": 1.388,
+      "eval_samples_per_second": 720.469,
+      "eval_steps_per_second": 11.528,
+      "step": 418000
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 3.056007287487128e-05,
+      "loss": 0.2705,
+      "step": 418500
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 3.0314620907864744e-05,
+      "loss": 0.2702,
+      "step": 419000
+    },
+    {
+      "epoch": 10.68,
+      "eval_loss": 0.8089344501495361,
+      "eval_runtime": 1.3483,
+      "eval_samples_per_second": 741.661,
+      "eval_steps_per_second": 11.867,
+      "step": 419000
+    },
+    {
+      "epoch": 10.69,
+      "learning_rate": 3.0070532480187637e-05,
+      "loss": 0.2701,
+      "step": 419500
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 2.9827810261151784e-05,
+      "loss": 0.2702,
+      "step": 420000
+    },
+    {
+      "epoch": 10.7,
+      "eval_loss": 0.8132815957069397,
+      "eval_runtime": 1.3269,
+      "eval_samples_per_second": 753.638,
+      "eval_steps_per_second": 12.058,
+      "step": 420000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.309883790062405e+22,
+  "total_flos": 1.341832503939855e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
+oid sha256:09cf499ab54bc6b5b46a8f12dd922823d0795f7339d994c55bfa6c710a91461c
 size 102501541