Training in progress, step 510000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a329db70ea5526ba5e4b910d073864205b498f32a4378b384003610aada51d6
+oid sha256:f9c7cde519c11bec5ed8e21c1c5f7e7a48e4331db9100e67e0f7768dfb456674
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a4d73b67517b389449be9b81a6d62f88071ffeb1fb6ad679e4c42b56b14bda
+oid sha256:cd6d7bd0a49b23290ba71dd1b9be309e7cb7e756973affa570765d9e0327dcf1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d512ffa1b18c6ccc8dac4806c6008b76bb8f78c31b60a4336ad6a2a9fa9bb7a3
-size 14439
+oid sha256:6b70dfee257c642602f7c3f1ed43cef4aa5ccfe8fedec32ff54410f192e88eb6
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66cebabe552d21647073ceeabf71a9c5fddbc9e0c70066a6914d3a038a79677
+oid sha256:cc166cba1eb0e6e74e3f3bd2046727896088467fe3b854b45c839137552ff680
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572120ff5e1d57786cb947f3c52e750254c5a4ff2a5c06ef2608f45e6a4e60de
+oid sha256:523dad95eba9c45397e0fcdf0c46383b4719d62bdd88758deb0f327662ac86d0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3efb56468deb71f34f2a6667b3f91c0deb4e0556b62db345c7c959c339450d
-size 14439
+oid sha256:de1cff2e14d92828be5901277d3f564e9608bb294b5c00feb6b3bc8739ef4af7
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61639df917cea6bc1eea9e7a1f48d3f6c9acb9557d8752aa9847613f1b857ad8
+oid sha256:ce6a9467a251e9cbea13fa7869db249fdcb8d7f75671c56b9051c9e63a855aaa
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.63510315024356,
-  "global_step": 500000,
+  "epoch": 7.787805213248431,
+  "global_step": 510000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3706,11 +3706,85 @@
       "eval_samples_per_second": 907.298,
       "eval_steps_per_second": 14.517,
       "step": 500000
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 8.55498278627369e-05,
+      "loss": 0.2646,
+      "step": 501000
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 8.531904085038221e-05,
+      "loss": 0.2646,
+      "step": 502000
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 8.508819566984897e-05,
+      "loss": 0.2641,
+      "step": 503000
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 8.485729484562307e-05,
+      "loss": 0.2641,
+      "step": 504000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 8.462634090279895e-05,
+      "loss": 0.264,
+      "step": 505000
+    },
+    {
+      "epoch": 7.71,
+      "eval_runtime": 1.0129,
+      "eval_samples_per_second": 987.309,
+      "eval_steps_per_second": 15.797,
+      "step": 505000
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 8.439533636705194e-05,
+      "loss": 0.2635,
+      "step": 506000
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 8.416428376461061e-05,
+      "loss": 0.2644,
+      "step": 507000
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 8.393318562222916e-05,
+      "loss": 0.2642,
+      "step": 508000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 8.370204446715997e-05,
+      "loss": 0.2638,
+      "step": 509000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 8.347086282712556e-05,
+      "loss": 0.2637,
+      "step": 510000
+    },
+    {
+      "epoch": 7.79,
+      "eval_runtime": 1.1071,
+      "eval_samples_per_second": 903.278,
+      "eval_steps_per_second": 14.452,
+      "step": 510000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.505008452040316e+22,
+  "total_flos": 3.575108713070663e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a4d73b67517b389449be9b81a6d62f88071ffeb1fb6ad679e4c42b56b14bda
+oid sha256:cd6d7bd0a49b23290ba71dd1b9be309e7cb7e756973affa570765d9e0327dcf1
 size 449471589