Training in progress, step 1000000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbfc1ed883942984be588c84681fbb0b292e529986dcbab5a1fecaa3f6ad447
+oid sha256:a58a32262e0ffbdac27815bc97d0e11c733c93ea33c2ca18dc9c3802edf93ed0
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc73418bd52c0694a19af6083331d7a4a133f36616e77cb56fc9fc0bb18ad264
+oid sha256:95c385e8e74e4a9e4e29d16e7bcc51330a32ca96f31f3958d42f7f6d81cb5517
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cbe84c4b275ece4dfc8b045971a9447b9468599c6de1ac7856d818ab7fcce6
-size 14503
+oid sha256:bc3d5753924cf4929822397824e69f8755eca737deedad3eadd6591cc8055f63
+size 14567

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca4b049386ceb25b5284b9754462b13ddabb069762bc1b4ce1a9e94d95e348c
+oid sha256:1dcf0c5d64fc7f0b4d4af0e5dd48c408044c47545a256fa9ec3bd6934aa5b874
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733172b1d4a99d1dcac219cdba47537d2e3c42c728e60a468833c7a7eb409d93
+oid sha256:ce03c924c5530c6249464a77507fae462c6707b0b26098ea916b622fcbba7a6a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a20d0d880982442a49c1adeca0b36b7c4aa9ce9768b58e40b03f2358d78bf3
+oid sha256:ac733fdea8118ca8aaba1980be73398e21c242cc2758b7dfd3a00de2a13d686a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2358905887cd0ce80c53b6e8a0174e039c4c5bd62c6c91c86f0312f9b46fcf7
+oid sha256:d806e9f9f09813043b95cbeda18b18cdfb60c100fbde3239bf79ee81c659dc36
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.11750423748225,
-  "global_step": 990000,
+  "epoch": 15.27020630048712,
+  "global_step": 1000000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7332,11 +7332,85 @@
       "eval_samples_per_second": 1296.438,
       "eval_steps_per_second": 20.743,
       "step": 990000
+    },
+    {
+      "epoch": 15.13,
+      "learning_rate": 1.0031000845556304e-05,
+      "loss": 0.2272,
+      "step": 991000
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.0024494874742152e-05,
+      "loss": 0.2272,
+      "step": 992000
+    },
+    {
+      "epoch": 15.16,
+      "learning_rate": 1.0018754144840986e-05,
+      "loss": 0.2272,
+      "step": 993000
+    },
+    {
+      "epoch": 15.18,
+      "learning_rate": 1.0013778718632507e-05,
+      "loss": 0.227,
+      "step": 994000
+    },
+    {
+      "epoch": 15.19,
+      "learning_rate": 1.000956865052717e-05,
+      "loss": 0.2269,
+      "step": 995000
+    },
+    {
+      "epoch": 15.19,
+      "eval_runtime": 0.7194,
+      "eval_samples_per_second": 1390.055,
+      "eval_steps_per_second": 22.241,
+      "step": 995000
+    },
+    {
+      "epoch": 15.21,
+      "learning_rate": 1.0006123986565623e-05,
+      "loss": 0.2267,
+      "step": 996000
+    },
+    {
+      "epoch": 15.22,
+      "learning_rate": 1.0003444764418138e-05,
+      "loss": 0.2265,
+      "step": 997000
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 1.000153101338428e-05,
+      "loss": 0.2268,
+      "step": 998000
+    },
+    {
+      "epoch": 15.25,
+      "learning_rate": 1.00003827543925e-05,
+      "loss": 0.2269,
+      "step": 999000
+    },
+    {
+      "epoch": 15.27,
+      "learning_rate": 1e-05,
+      "loss": 0.2268,
+      "step": 1000000
+    },
+    {
+      "epoch": 15.27,
+      "eval_runtime": 0.8245,
+      "eval_samples_per_second": 1212.903,
+      "eval_steps_per_second": 19.406,
+      "step": 1000000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.939915985982136e+22,
+  "total_flos": 7.010016247012483e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc73418bd52c0694a19af6083331d7a4a133f36616e77cb56fc9fc0bb18ad264
+oid sha256:95c385e8e74e4a9e4e29d16e7bcc51330a32ca96f31f3958d42f7f6d81cb5517
 size 449471589