Training in progress, step 410000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07b83dacbaddaed6e5cad0c80115438e4840da7d3099679de039cec028aef36
+oid sha256:23757c0288979d27bb8e7d987ca91414953ed2fb98096163be33a545f5af5ab4
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebaf503b44bc5d1dd314e475075123bf9e2c562de76e39616ae5b46cfba21a4
+oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
+oid sha256:359855992dc1f001a1fd11d5cfc159df4486cdababa23a98e30e2a0152bffc69
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba83cbca80cb672828600b248dd69c4c050beb355cdcf7faf0b56212421edca
+oid sha256:498c95fdcab578849c69bf4a10f0532f5bf3ba8048fa37c1b416b3afd0ea5f33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.194199500484224,
-  "global_step": 400000,
+  "epoch": 10.44905448799633,
+  "global_step": 410000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8006,11 +8006,211 @@
       "eval_samples_per_second": 742.696,
       "eval_steps_per_second": 11.883,
       "step": 400000
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 4.0280733510303475e-05,
+      "loss": 0.2717,
+      "step": 400500
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 3.9988095434602716e-05,
+      "loss": 0.2715,
+      "step": 401000
+    },
+    {
+      "epoch": 10.22,
+      "eval_loss": 0.8082920908927917,
+      "eval_runtime": 1.4032,
+      "eval_samples_per_second": 712.676,
+      "eval_steps_per_second": 11.403,
+      "step": 401000
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 3.9696715110663726e-05,
+      "loss": 0.2715,
+      "step": 401500
+    },
+    {
+      "epoch": 10.25,
+      "learning_rate": 3.9406595724975116e-05,
+      "loss": 0.2717,
+      "step": 402000
+    },
+    {
+      "epoch": 10.25,
+      "eval_loss": 0.8099567890167236,
+      "eval_runtime": 1.3773,
+      "eval_samples_per_second": 726.038,
+      "eval_steps_per_second": 11.617,
+      "step": 402000
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 3.9117740450235914e-05,
+      "loss": 0.2714,
+      "step": 402500
+    },
+    {
+      "epoch": 10.27,
+      "learning_rate": 3.8830152445321163e-05,
+      "loss": 0.2715,
+      "step": 403000
+    },
+    {
+      "epoch": 10.27,
+      "eval_loss": 0.8108043670654297,
+      "eval_runtime": 1.3727,
+      "eval_samples_per_second": 728.507,
+      "eval_steps_per_second": 11.656,
+      "step": 403000
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 3.854383485524724e-05,
+      "loss": 0.2714,
+      "step": 403500
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 3.8258790811137425e-05,
+      "loss": 0.2715,
+      "step": 404000
+    },
+    {
+      "epoch": 10.3,
+      "eval_loss": 0.8089959621429443,
+      "eval_runtime": 1.3482,
+      "eval_samples_per_second": 741.756,
+      "eval_steps_per_second": 11.868,
+      "step": 404000
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 3.7975023430187676e-05,
+      "loss": 0.2715,
+      "step": 404500
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 3.7692535815632624e-05,
+      "loss": 0.2716,
+      "step": 405000
+    },
+    {
+      "epoch": 10.32,
+      "eval_loss": 0.8159785270690918,
+      "eval_runtime": 1.3646,
+      "eval_samples_per_second": 732.809,
+      "eval_steps_per_second": 11.725,
+      "step": 405000
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 3.741133105671159e-05,
+      "loss": 0.2713,
+      "step": 405500
+    },
+    {
+      "epoch": 10.35,
+      "learning_rate": 3.713141222863474e-05,
+      "loss": 0.2712,
+      "step": 406000
+    },
+    {
+      "epoch": 10.35,
+      "eval_loss": 0.8142402172088623,
+      "eval_runtime": 1.3812,
+      "eval_samples_per_second": 724.033,
+      "eval_steps_per_second": 11.585,
+      "step": 406000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 3.6852782392549584e-05,
+      "loss": 0.2713,
+      "step": 406500
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 3.657544459550729e-05,
+      "loss": 0.2712,
+      "step": 407000
+    },
+    {
+      "epoch": 10.37,
+      "eval_loss": 0.8070803284645081,
+      "eval_runtime": 1.5878,
+      "eval_samples_per_second": 629.794,
+      "eval_steps_per_second": 10.077,
+      "step": 407000
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 3.6299401870429606e-05,
+      "loss": 0.2712,
+      "step": 407500
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 3.6024657236075546e-05,
+      "loss": 0.2712,
+      "step": 408000
+    },
+    {
+      "epoch": 10.4,
+      "eval_loss": 0.8115477561950684,
+      "eval_runtime": 1.3152,
+      "eval_samples_per_second": 760.367,
+      "eval_steps_per_second": 12.166,
+      "step": 408000
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 3.575121369700841e-05,
+      "loss": 0.2714,
+      "step": 408500
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 3.5479074243562995e-05,
+      "loss": 0.2709,
+      "step": 409000
+    },
+    {
+      "epoch": 10.42,
+      "eval_loss": 0.80928635597229,
+      "eval_runtime": 1.3461,
+      "eval_samples_per_second": 742.862,
+      "eval_steps_per_second": 11.886,
+      "step": 409000
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 3.5208241851812644e-05,
+      "loss": 0.2711,
+      "step": 409500
+    },
+    {
+      "epoch": 10.45,
+      "learning_rate": 3.493871948353709e-05,
+      "loss": 0.271,
+      "step": 410000
+    },
+    {
+      "epoch": 10.45,
+      "eval_loss": 0.8108725547790527,
+      "eval_runtime": 1.3475,
+      "eval_samples_per_second": 742.097,
+      "eval_steps_per_second": 11.874,
+      "step": 410000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.277935076184955e+22,
+  "total_flos": 1.309883790062405e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebaf503b44bc5d1dd314e475075123bf9e2c562de76e39616ae5b46cfba21a4
+oid sha256:7c16dce11ea3eb455970382761036fdc46346bc29673783c86afe6088466197d
 size 102501541