Training in progress, step 630000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b35f979d5fe4527b6f42c2add375e7239aec55be0317190f1a665e6ab5f35c
+oid sha256:8d82e2070f1b6c3e7ba3ac4e05d24d0c3c44e21fea62b60f30dbcd4b8aea7947
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
+oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb920f1348e13fdd02418f5a8bdde3a29115945de004c35412bd2480fdb9afa
+oid sha256:4acbb51e13aa598f4ce3e939d773ff547815a4a8c85e2bd41643e066b97a863b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154b8f14236fa636789c866c5bab186dc1c4e26fc03e987f1aabe66a3981e8a2
+oid sha256:798c603bd32aeea05803afc8a5c1b8f53a6193b4dd4a2b5a26aa63e0065ce70e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a933eb9e98ce78bdca0e9e206bab865aad1983b58e12a370b79e23c847c34cac
+oid sha256:b0fb0d506dd83556c6bb13f32358c5188773f715722e0fae2529869d20b06680
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502983b98bc6a8911d0348894791667ff6481b824870d33d6fccaa23995ed7f4
-size 14439
+oid sha256:aa6390e57fdd76fefb80f0c1ccc262a99cb2e588a24afb098b63de6015cd6400
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87df12c543e6333a1257623848db6de543e5639171e7cc03225528d064da559b
+oid sha256:445023bf71af0013aa9e5796238ea2c1da2dcfc1e0064784bf2e5fc75bdc80c6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.467527906302013,
-  "global_step": 620000,
+  "epoch": 9.620229969306886,
+  "global_step": 630000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4594,11 +4594,85 @@
       "eval_samples_per_second": 944.48,
       "eval_steps_per_second": 15.112,
       "step": 620000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 5.814877301838688e-05,
+      "loss": 0.2523,
+      "step": 621000
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 5.7928974604537494e-05,
+      "loss": 0.2522,
+      "step": 622000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 5.770941755588573e-05,
+      "loss": 0.2537,
+      "step": 623000
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 5.749010427347233e-05,
+      "loss": 0.254,
+      "step": 624000
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 5.7271037155672156e-05,
+      "loss": 0.2522,
+      "step": 625000
+    },
+    {
+      "epoch": 9.54,
+      "eval_runtime": 1.0707,
+      "eval_samples_per_second": 934.001,
+      "eval_steps_per_second": 14.944,
+      "step": 625000
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 5.7052218598168154e-05,
+      "loss": 0.2524,
+      "step": 626000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 5.6833650993925016e-05,
+      "loss": 0.2522,
+      "step": 627000
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 5.661533673316303e-05,
+      "loss": 0.2522,
+      "step": 628000
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 5.639727820333198e-05,
+      "loss": 0.2518,
+      "step": 629000
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 5.617947778908498e-05,
+      "loss": 0.2517,
+      "step": 630000
+    },
+    {
+      "epoch": 9.62,
+      "eval_runtime": 1.1949,
+      "eval_samples_per_second": 836.899,
+      "eval_steps_per_second": 13.39,
+      "step": 630000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.346210270268184e+22,
+  "total_flos": 4.416310531298531e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03035ba4bf151910d41d4c213cf2390c9903cf8cb85be4525c8f2b5574fe579
+oid sha256:2aa845416abb07e55de755c0df750468c782329996a5b84f0336b895c9a2baa1
 size 449471589