Training in progress, step 400000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016da91c7614d6a57ffcc5938a0b68675bc967aee110a7fe186334a10cf0dffd
+oid sha256:a07b83dacbaddaed6e5cad0c80115438e4840da7d3099679de039cec028aef36
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03f29f9d43fcaa0d12888b54defcd8a6a1be294c2c1e7d74429358a9688082
+oid sha256:aebaf503b44bc5d1dd314e475075123bf9e2c562de76e39616ae5b46cfba21a4
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4ee1f5ea05fd5b5af4e685b13d34537bf6d8bfafcf82bbf12ab3c078f9c700
+oid sha256:ae0c5aa717c3a9161f73c918d736998d943d82bab8038706d83985bab7118cb4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864647684ab3694f7aa2a258c1806e10c4abf99f67ed5e54443050e485ac9436
+oid sha256:7ba83cbca80cb672828600b248dd69c4c050beb355cdcf7faf0b56212421edca
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.939344512972118,
-  "global_step": 390000,
+  "epoch": 10.194199500484224,
+  "global_step": 400000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7806,11 +7806,211 @@
       "eval_samples_per_second": 761.14,
       "eval_steps_per_second": 12.178,
       "step": 390000
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 4.639259509788768e-05,
+      "loss": 0.2727,
+      "step": 390500
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 4.60754920716572e-05,
+      "loss": 0.2727,
+      "step": 391000
+    },
+    {
+      "epoch": 9.96,
+      "eval_loss": 0.8076984882354736,
+      "eval_runtime": 1.3566,
+      "eval_samples_per_second": 737.152,
+      "eval_steps_per_second": 11.794,
+      "step": 391000
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 4.5759580226394167e-05,
+      "loss": 0.2727,
+      "step": 391500
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 4.544486301685993e-05,
+      "loss": 0.2726,
+      "step": 392000
+    },
+    {
+      "epoch": 9.99,
+      "eval_loss": 0.8174979090690613,
+      "eval_runtime": 1.2981,
+      "eval_samples_per_second": 770.339,
+      "eval_steps_per_second": 12.325,
+      "step": 392000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.5131343884751484e-05,
+      "loss": 0.2723,
+      "step": 392500
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 4.4819026258663774e-05,
+      "loss": 0.2722,
+      "step": 393000
+    },
+    {
+      "epoch": 10.02,
+      "eval_loss": 0.8073344826698303,
+      "eval_runtime": 1.3446,
+      "eval_samples_per_second": 743.69,
+      "eval_steps_per_second": 11.899,
+      "step": 393000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 4.450791355405234e-05,
+      "loss": 0.2722,
+      "step": 393500
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 4.419800917319588e-05,
+      "loss": 0.2725,
+      "step": 394000
+    },
+    {
+      "epoch": 10.04,
+      "eval_loss": 0.8089223504066467,
+      "eval_runtime": 1.4579,
+      "eval_samples_per_second": 685.895,
+      "eval_steps_per_second": 10.974,
+      "step": 394000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 4.3889316505159056e-05,
+      "loss": 0.2723,
+      "step": 394500
+    },
+    {
+      "epoch": 10.07,
+      "learning_rate": 4.3581838925755465e-05,
+      "loss": 0.2721,
+      "step": 395000
+    },
+    {
+      "epoch": 10.07,
+      "eval_loss": 0.8180590867996216,
+      "eval_runtime": 1.4056,
+      "eval_samples_per_second": 711.416,
+      "eval_steps_per_second": 11.383,
+      "step": 395000
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 4.327557979751057e-05,
+      "loss": 0.2722,
+      "step": 395500
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 4.297054246962517e-05,
+      "loss": 0.2722,
+      "step": 396000
+    },
+    {
+      "epoch": 10.09,
+      "eval_loss": 0.8067134022712708,
+      "eval_runtime": 1.3816,
+      "eval_samples_per_second": 723.788,
+      "eval_steps_per_second": 11.581,
+      "step": 396000
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 4.266673027793864e-05,
+      "loss": 0.2717,
+      "step": 396500
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 4.236414654489242e-05,
+      "loss": 0.2721,
+      "step": 397000
+    },
+    {
+      "epoch": 10.12,
+      "eval_loss": 0.8154900074005127,
+      "eval_runtime": 1.3572,
+      "eval_samples_per_second": 736.809,
+      "eval_steps_per_second": 11.789,
+      "step": 397000
+    },
+    {
+      "epoch": 10.13,
+      "learning_rate": 4.206279457949371e-05,
+      "loss": 0.272,
+      "step": 397500
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 4.1762677677279335e-05,
+      "loss": 0.2718,
+      "step": 398000
+    },
+    {
+      "epoch": 10.14,
+      "eval_loss": 0.814974844455719,
+      "eval_runtime": 1.3197,
+      "eval_samples_per_second": 757.75,
+      "eval_steps_per_second": 12.124,
+      "step": 398000
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 4.146379912027964e-05,
+      "loss": 0.2715,
+      "step": 398500
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 4.1166162176982664e-05,
+      "loss": 0.272,
+      "step": 399000
+    },
+    {
+      "epoch": 10.17,
+      "eval_loss": 0.8131051063537598,
+      "eval_runtime": 1.3374,
+      "eval_samples_per_second": 747.697,
+      "eval_steps_per_second": 11.963,
+      "step": 399000
+    },
+    {
+      "epoch": 10.18,
+      "learning_rate": 4.086977010229838e-05,
+      "loss": 0.2717,
+      "step": 399500
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 4.057462613752294e-05,
+      "loss": 0.2721,
+      "step": 400000
+    },
+    {
+      "epoch": 10.19,
+      "eval_loss": 0.8092121481895447,
+      "eval_runtime": 1.3464,
+      "eval_samples_per_second": 742.696,
+      "eval_steps_per_second": 11.883,
+      "step": 400000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.2459877101988095e+22,
+  "total_flos": 1.277935076184955e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03f29f9d43fcaa0d12888b54defcd8a6a1be294c2c1e7d74429358a9688082
+oid sha256:aebaf503b44bc5d1dd314e475075123bf9e2c562de76e39616ae5b46cfba21a4
 size 102501541