Training in progress, step 460000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48da217ea188770413b01ab5847a04b2b361555bd731533e7a2791bedfd928dd
+oid sha256:00828d7c5b2ee9d934868fffc62db5886616a7f03a8761ef8254b89f6589bb74
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2291b66065799571b4264696030000d7ec1a0e86601a7f2aefc345f1b8fac97d
+oid sha256:96cedfbffe43fc18644cc6de989fcca94f4a26075ab174ed0f9cb823c12e426d
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5ef0740ac3df960078bba8a97e2da86f6b2673b0404aac1c245b336272b522
+oid sha256:5faebccac6dae6326e45bd9ddb3db4ec532e2978e697cb2496075e507408e404
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc29c434fb0390a8f4f90d65ac745a0b4f381dbd06e857762d450d4a464c7045
+oid sha256:d60fd80961b777bf4901f5c7189278f8f31f61a50c51a19e170f6a1919a5ce33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.468474438044753,
-  "global_step": 450000,
+  "epoch": 11.723329425556859,
+  "global_step": 460000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9006,11 +9006,211 @@
       "eval_samples_per_second": 787.258,
       "eval_steps_per_second": 12.596,
       "step": 450000
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 1.770155470293445e-05,
+      "loss": 0.2684,
+      "step": 450500
+    },
+    {
+      "epoch": 11.49,
+      "learning_rate": 1.7548110926261522e-05,
+      "loss": 0.2682,
+      "step": 451000
+    },
+    {
+      "epoch": 11.49,
+      "eval_loss": 0.8042126297950745,
+      "eval_runtime": 1.3486,
+      "eval_samples_per_second": 741.514,
+      "eval_steps_per_second": 11.864,
+      "step": 451000
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 1.7396170301425777e-05,
+      "loss": 0.2683,
+      "step": 451500
+    },
+    {
+      "epoch": 11.52,
+      "learning_rate": 1.7245734490025544e-05,
+      "loss": 0.2683,
+      "step": 452000
+    },
+    {
+      "epoch": 11.52,
+      "eval_loss": 0.8097262382507324,
+      "eval_runtime": 1.2797,
+      "eval_samples_per_second": 781.424,
+      "eval_steps_per_second": 12.503,
+      "step": 452000
+    },
+    {
+      "epoch": 11.53,
+      "learning_rate": 1.7096805137202738e-05,
+      "loss": 0.2682,
+      "step": 452500
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 1.6949383871624917e-05,
+      "loss": 0.2678,
+      "step": 453000
+    },
+    {
+      "epoch": 11.54,
+      "eval_loss": 0.8061630725860596,
+      "eval_runtime": 1.2741,
+      "eval_samples_per_second": 784.845,
+      "eval_steps_per_second": 12.558,
+      "step": 453000
+    },
+    {
+      "epoch": 11.56,
+      "learning_rate": 1.6803472305467368e-05,
+      "loss": 0.2683,
+      "step": 453500
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 1.665907203439568e-05,
+      "loss": 0.2678,
+      "step": 454000
+    },
+    {
+      "epoch": 11.57,
+      "eval_loss": 0.808397114276886,
+      "eval_runtime": 1.2841,
+      "eval_samples_per_second": 778.785,
+      "eval_steps_per_second": 12.461,
+      "step": 454000
+    },
+    {
+      "epoch": 11.58,
+      "learning_rate": 1.6516184637548058e-05,
+      "loss": 0.2681,
+      "step": 454500
+    },
+    {
+      "epoch": 11.6,
+      "learning_rate": 1.6374811677518142e-05,
+      "loss": 0.2681,
+      "step": 455000
+    },
+    {
+      "epoch": 11.6,
+      "eval_loss": 0.8134533762931824,
+      "eval_runtime": 1.2711,
+      "eval_samples_per_second": 786.7,
+      "eval_steps_per_second": 12.587,
+      "step": 455000
+    },
+    {
+      "epoch": 11.61,
+      "learning_rate": 1.6234954700338025e-05,
+      "loss": 0.2679,
+      "step": 455500
+    },
+    {
+      "epoch": 11.62,
+      "learning_rate": 1.6096615235461148e-05,
+      "loss": 0.2678,
+      "step": 456000
+    },
+    {
+      "epoch": 11.62,
+      "eval_loss": 0.8097538948059082,
+      "eval_runtime": 1.2712,
+      "eval_samples_per_second": 786.682,
+      "eval_steps_per_second": 12.587,
+      "step": 456000
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 1.59597947957458e-05,
+      "loss": 0.2678,
+      "step": 456500
+    },
+    {
+      "epoch": 11.65,
+      "learning_rate": 1.5824494877438344e-05,
+      "loss": 0.2681,
+      "step": 457000
+    },
+    {
+      "epoch": 11.65,
+      "eval_loss": 0.8078885674476624,
+      "eval_runtime": 1.2534,
+      "eval_samples_per_second": 797.802,
+      "eval_steps_per_second": 12.765,
+      "step": 457000
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 1.569071696015702e-05,
+      "loss": 0.2679,
+      "step": 457500
+    },
+    {
+      "epoch": 11.67,
+      "learning_rate": 1.555846250687569e-05,
+      "loss": 0.2679,
+      "step": 458000
+    },
+    {
+      "epoch": 11.67,
+      "eval_loss": 0.8051915764808655,
+      "eval_runtime": 1.2442,
+      "eval_samples_per_second": 803.754,
+      "eval_steps_per_second": 12.86,
+      "step": 458000
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 1.542773296390789e-05,
+      "loss": 0.2679,
+      "step": 458500
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 1.5298529760890945e-05,
+      "loss": 0.268,
+      "step": 459000
+    },
+    {
+      "epoch": 11.7,
+      "eval_loss": 0.8038084506988525,
+      "eval_runtime": 1.3255,
+      "eval_samples_per_second": 754.438,
+      "eval_steps_per_second": 12.071,
+      "step": 459000
+    },
+    {
+      "epoch": 11.71,
+      "learning_rate": 1.5170854310770376e-05,
+      "loss": 0.2678,
+      "step": 459500
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 1.5044708009784457e-05,
+      "loss": 0.268,
+      "step": 460000
+    },
+    {
+      "epoch": 11.72,
+      "eval_loss": 0.8099783062934875,
+      "eval_runtime": 1.3008,
+      "eval_samples_per_second": 768.777,
+      "eval_steps_per_second": 12.3,
+      "step": 460000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.4376772976809005e+22,
+  "total_flos": 1.4696260115583505e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2291b66065799571b4264696030000d7ec1a0e86601a7f2aefc345f1b8fac97d
+oid sha256:96cedfbffe43fc18644cc6de989fcca94f4a26075ab174ed0f9cb823c12e426d
 size 102501541