Training in progress, step 640000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d82e2070f1b6c3e7ba3ac4e05d24d0c3c44e21fea62b60f30dbcd4b8aea7947
+oid sha256:6c444c75d0337de46e35f539ad919e0e13abb76dfe8d15c375255f6a83fa8fd2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
+oid sha256:f5808a95cf4864d9e7dd396fa3d5d75f6fe69b93fbc2376d586a3a7fc3b0fe04
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4acbb51e13aa598f4ce3e939d773ff547815a4a8c85e2bd41643e066b97a863b
+oid sha256:7aaf518826c7b02349e0c4043ecb7a38ebc1a14f60809955f00a7944ae21e6fc
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798c603bd32aeea05803afc8a5c1b8f53a6193b4dd4a2b5a26aa63e0065ce70e
+oid sha256:bcb6ee46cb325ce6d5d0f15d240a67578f4710009ebcab3be0d17117038d01fa
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0fb0d506dd83556c6bb13f32358c5188773f715722e0fae2529869d20b06680
+oid sha256:7121d5ba757842882faa79dcd7ac54d5b1c2ec66868fe528ff6cebaa506df816
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6390e57fdd76fefb80f0c1ccc262a99cb2e588a24afb098b63de6015cd6400
-size 14503
+oid sha256:6083d2cad6c63a2b0e7d04c706615465f15ee7e67189e761029a05d0b2f204c9
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445023bf71af0013aa9e5796238ea2c1da2dcfc1e0064784bf2e5fc75bdc80c6
+oid sha256:4ba925316c6e59686c34db192a6703d2b94be7f6c9b908cf313be2f93b23828d
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.620229969306886,
-  "global_step": 630000,
+  "epoch": 9.772932032311756,
+  "global_step": 640000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4668,11 +4668,85 @@
       "eval_samples_per_second": 836.899,
       "eval_steps_per_second": 13.39,
       "step": 630000
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 5.596193787225254e-05,
+      "loss": 0.2514,
+      "step": 631000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 5.574466083181624e-05,
+      "loss": 0.2512,
+      "step": 632000
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 5.552764904388305e-05,
+      "loss": 0.2511,
+      "step": 633000
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 5.5310904881659116e-05,
+      "loss": 0.2511,
+      "step": 634000
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 5.5094430715423835e-05,
+      "loss": 0.2509,
+      "step": 635000
+    },
+    {
+      "epoch": 9.7,
+      "eval_runtime": 1.0102,
+      "eval_samples_per_second": 989.889,
+      "eval_steps_per_second": 15.838,
+      "step": 635000
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 5.487822891250406e-05,
+      "loss": 0.2511,
+      "step": 636000
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 5.4662301837247985e-05,
+      "loss": 0.2508,
+      "step": 637000
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 5.4446651850999604e-05,
+      "loss": 0.2506,
+      "step": 638000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 5.4231281312072544e-05,
+      "loss": 0.2505,
+      "step": 639000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 5.401619257572453e-05,
+      "loss": 0.2502,
+      "step": 640000
+    },
+    {
+      "epoch": 9.77,
+      "eval_runtime": 1.0069,
+      "eval_samples_per_second": 993.184,
+      "eval_steps_per_second": 15.891,
+      "step": 640000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.416310531298531e+22,
+  "total_flos": 4.4864107923288785e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
+oid sha256:f5808a95cf4864d9e7dd396fa3d5d75f6fe69b93fbc2376d586a3a7fc3b0fe04
 size 449471589