Training in progress, step 680000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890198f678ba65d216debb2bc86f4ae914eacfa0277bfe9ecb7d160986d858d3
+oid sha256:71ace107cb3306bf38f89c2c358d90d9f9b920dec40fa540483fcf810c61573d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3bbdcfad15508d1c6487b56498c528da76f45271d070de2c2ce847ed3bd008
+oid sha256:860f45e45a38c8c4831e62f235226a2c06ad959b94f5078bae9f558e28ff6cd1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
+oid sha256:f9bd922b27e3778fc7c4d666e951bbe41a5e77971bd723f807b0e20131d7a108
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651f855ada6fd7cfa09b534ad266032caacaa52b90009ef1696c08e67fbed919
+oid sha256:d737cb5c8a42fd478f2f6309865787d8315dbe8632150ec0b5dc4840a67a78da
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.115287242229236,
-  "global_step": 670000,
+  "epoch": 7.226815966452159,
+  "global_step": 680000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13406,11 +13406,211 @@
       "eval_samples_per_second": 860.127,
       "eval_steps_per_second": 13.48,
       "step": 670000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 4.7603473052657374e-05,
+      "loss": 0.1966,
+      "step": 670500
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 4.7500916084690564e-05,
+      "loss": 0.1967,
+      "step": 671000
+    },
+    {
+      "epoch": 7.13,
+      "eval_loss": 0.186045840382576,
+      "eval_runtime": 2.6321,
+      "eval_samples_per_second": 872.688,
+      "eval_steps_per_second": 13.677,
+      "step": 671000
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 4.7398447967978165e-05,
+      "loss": 0.1963,
+      "step": 671500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 4.729606898266411e-05,
+      "loss": 0.1969,
+      "step": 672000
+    },
+    {
+      "epoch": 7.14,
+      "eval_loss": 0.1882571130990982,
+      "eval_runtime": 2.6187,
+      "eval_samples_per_second": 877.14,
+      "eval_steps_per_second": 13.747,
+      "step": 672000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 4.71937794086487e-05,
+      "loss": 0.1963,
+      "step": 672500
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 4.709157952558768e-05,
+      "loss": 0.1963,
+      "step": 673000
+    },
+    {
+      "epoch": 7.15,
+      "eval_loss": 0.18748030066490173,
+      "eval_runtime": 2.6428,
+      "eval_samples_per_second": 869.147,
+      "eval_steps_per_second": 13.622,
+      "step": 673000
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 4.698946961289163e-05,
+      "loss": 0.1962,
+      "step": 673500
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 4.688744994972514e-05,
+      "loss": 0.1962,
+      "step": 674000
+    },
+    {
+      "epoch": 7.16,
+      "eval_loss": 0.18707983195781708,
+      "eval_runtime": 2.661,
+      "eval_samples_per_second": 863.195,
+      "eval_steps_per_second": 13.529,
+      "step": 674000
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 4.6785520815006085e-05,
+      "loss": 0.1965,
+      "step": 674500
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 4.668368248740485e-05,
+      "loss": 0.196,
+      "step": 675000
+    },
+    {
+      "epoch": 7.17,
+      "eval_loss": 0.18474501371383667,
+      "eval_runtime": 2.6847,
+      "eval_samples_per_second": 855.597,
+      "eval_steps_per_second": 13.409,
+      "step": 675000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 4.658193524534351e-05,
+      "loss": 0.1959,
+      "step": 675500
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 4.6480279366995116e-05,
+      "loss": 0.1959,
+      "step": 676000
+    },
+    {
+      "epoch": 7.18,
+      "eval_loss": 0.1878414750099182,
+      "eval_runtime": 2.6912,
+      "eval_samples_per_second": 853.536,
+      "eval_steps_per_second": 13.377,
+      "step": 676000
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 4.637871513028303e-05,
+      "loss": 0.196,
+      "step": 676500
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 4.6277242812879914e-05,
+      "loss": 0.1959,
+      "step": 677000
+    },
+    {
+      "epoch": 7.19,
+      "eval_loss": 0.18550430238246918,
+      "eval_runtime": 2.7131,
+      "eval_samples_per_second": 846.623,
+      "eval_steps_per_second": 13.269,
+      "step": 677000
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 4.617586269220728e-05,
+      "loss": 0.1959,
+      "step": 677500
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 4.607457504543447e-05,
+      "loss": 0.1962,
+      "step": 678000
+    },
+    {
+      "epoch": 7.2,
+      "eval_loss": 0.1865391880273819,
+      "eval_runtime": 2.6562,
+      "eval_samples_per_second": 864.771,
+      "eval_steps_per_second": 13.553,
+      "step": 678000
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 4.597338014947801e-05,
+      "loss": 0.1956,
+      "step": 678500
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 4.5872278281000955e-05,
+      "loss": 0.1954,
+      "step": 679000
+    },
+    {
+      "epoch": 7.22,
+      "eval_loss": 0.18739037215709686,
+      "eval_runtime": 2.5862,
+      "eval_samples_per_second": 888.174,
+      "eval_steps_per_second": 13.92,
+      "step": 679000
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 4.577126971641189e-05,
+      "loss": 0.1959,
+      "step": 679500
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 4.567035473186444e-05,
+      "loss": 0.1955,
+      "step": 680000
+    },
+    {
+      "epoch": 7.23,
+      "eval_loss": 0.18440315127372742,
+      "eval_runtime": 2.6652,
+      "eval_samples_per_second": 861.845,
+      "eval_steps_per_second": 13.507,
+      "step": 680000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.696679153900649e+22,
+  "total_flos": 4.7667794149309965e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3bbdcfad15508d1c6487b56498c528da76f45271d070de2c2ce847ed3bd008
+oid sha256:860f45e45a38c8c4831e62f235226a2c06ad959b94f5078bae9f558e28ff6cd1
 size 449471589