Training in progress, step 520000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c7cde519c11bec5ed8e21c1c5f7e7a48e4331db9100e67e0f7768dfb456674
+oid sha256:dff40157bf3742c8b21f53f2322e73342fc065e8772423f3999033957d5a66bd
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6d7bd0a49b23290ba71dd1b9be309e7cb7e756973affa570765d9e0327dcf1
+oid sha256:91e0e94c5a6037200ef903f8fe73caf33854246cdca4d17f5dd1d03ffcdcb4f5
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b70dfee257c642602f7c3f1ed43cef4aa5ccfe8fedec32ff54410f192e88eb6
+oid sha256:384aea0e5f6d022d8f660cfde96c61a9f493d19909a7af22387885e66de278b6
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc166cba1eb0e6e74e3f3bd2046727896088467fe3b854b45c839137552ff680
+oid sha256:dcc0739a046c0e6446f60e8683c8b90305e2fea169b76b64f56106f66b6420d0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523dad95eba9c45397e0fcdf0c46383b4719d62bdd88758deb0f327662ac86d0
+oid sha256:9e44d4ec16875ec90faf97785738c3779aee1f020966316b5892073b0622b56d
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1cff2e14d92828be5901277d3f564e9608bb294b5c00feb6b3bc8739ef4af7
+oid sha256:09aadf2a5ab4eb2176572147df0f7002cbd6c8df6b1aea2c4ed7fd23277b83ba
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6a9467a251e9cbea13fa7869db249fdcb8d7f75671c56b9051c9e63a855aaa
+oid sha256:fd06a603e7f0cb9a198767e099f70695383faf72e0162b6befb3712823cfe27e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.787805213248431,
-  "global_step": 510000,
+  "epoch": 7.940507276253302,
+  "global_step": 520000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3780,11 +3780,85 @@
       "eval_samples_per_second": 903.278,
       "eval_steps_per_second": 14.452,
       "step": 510000
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 8.323964323029136e-05,
+      "loss": 0.2633,
+      "step": 511000
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 8.300838820523784e-05,
+      "loss": 0.2634,
+      "step": 512000
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 8.277710028093289e-05,
+      "loss": 0.263,
+      "step": 513000
+    },
+    {
+      "epoch": 7.85,
+      "learning_rate": 8.254578198670421e-05,
+      "loss": 0.2632,
+      "step": 514000
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 8.231443585221157e-05,
+      "loss": 0.2629,
+      "step": 515000
+    },
+    {
+      "epoch": 7.86,
+      "eval_runtime": 1.0457,
+      "eval_samples_per_second": 956.256,
+      "eval_steps_per_second": 15.3,
+      "step": 515000
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 8.208306440741926e-05,
+      "loss": 0.2626,
+      "step": 516000
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 8.185167018256834e-05,
+      "loss": 0.2629,
+      "step": 517000
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 8.162025570814896e-05,
+      "loss": 0.2625,
+      "step": 518000
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 8.138882351487275e-05,
+      "loss": 0.2623,
+      "step": 519000
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 8.115737613364511e-05,
+      "loss": 0.2626,
+      "step": 520000
+    },
+    {
+      "epoch": 7.94,
+      "eval_runtime": 1.0504,
+      "eval_samples_per_second": 952.036,
+      "eval_steps_per_second": 15.233,
+      "step": 520000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.575108713070663e+22,
+  "total_flos": 3.6452089741010102e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6d7bd0a49b23290ba71dd1b9be309e7cb7e756973affa570765d9e0327dcf1
+oid sha256:91e0e94c5a6037200ef903f8fe73caf33854246cdca4d17f5dd1d03ffcdcb4f5
 size 449471589