Training in progress, step 460000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30290edc8628fd3c3ef18b3c5aeed7f069b37f58cee15ba21ffc0026c01c3730
+oid sha256:e074c33dcba955530635f7c301cc0616d35e94c4d9e25f501a0d9edd512370f3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9bd4abec55ec3aff5c6a63e004f193b84327f4dea19bd4c7a418c248e58ed7
+oid sha256:8e2e3c76b0bd22486ffeb7f1582064821337785eddce5493639f753ea7af7c21
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d4cd7454368d736d737996ed03879986986a143829539c951d1987c1b5985b
+oid sha256:f07bf259da4db58c67f5752e41be50bd05dbfaf1912a8b5878788f3ede910eb7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7336b286bfd4476ee4aa817ed5f237f90f8c52aba8afeb7d24431d41ce3a20dc
+oid sha256:1e069aee1aca48a60052a1c66c7d1551fec7d9dcab99912ac030e1863b14f6a1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3e44169554700b12ce1323e27998dd02eb610802144e6e40dc2e6668fa701b
-size 14503
+oid sha256:642ba2efc3dad359eda3b33bb6c5d67fffdc0e921c5ed6b47ef80068231cbd4a
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37e67e1cf58930910192e85abdd9cbaabe8e6e23dc6148e7d6f7fcf570a387a
+oid sha256:5475a56a8e58f3a6d30456ecb3d60c907f9c5dd05e43f39a9dbfefa6d303c24c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca5b8ec583e6ebb62b2f3066d6bca2c46b8614e9cfbd4e5e7bfdb3a9d7a2d86
+oid sha256:d470fe106a7d346e8d83a1e5754bc519572ca0d497bb4adce56ffd8f58de945f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.871592835219204,
-  "global_step": 450000,
+  "epoch": 7.024294898224075,
+  "global_step": 460000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3336,11 +3336,85 @@
       "eval_samples_per_second": 1006.215,
       "eval_steps_per_second": 16.099,
       "step": 450000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 9.695948817687504e-05,
+      "loss": 0.2699,
+      "step": 451000
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 9.673480678764858e-05,
+      "loss": 0.2698,
+      "step": 452000
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 9.650994238925626e-05,
+      "loss": 0.2699,
+      "step": 453000
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 9.628489744077911e-05,
+      "loss": 0.2696,
+      "step": 454000
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 9.60596744032726e-05,
+      "loss": 0.2699,
+      "step": 455000
+    },
+    {
+      "epoch": 6.95,
+      "eval_runtime": 1.0008,
+      "eval_samples_per_second": 999.165,
+      "eval_steps_per_second": 15.987,
+      "step": 455000
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 9.583427573973982e-05,
+      "loss": 0.2696,
+      "step": 456000
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 9.560870391510441e-05,
+      "loss": 0.2695,
+      "step": 457000
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 9.538296139618371e-05,
+      "loss": 0.2691,
+      "step": 458000
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 9.515705065166178e-05,
+      "loss": 0.2693,
+      "step": 459000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 9.493097415206228e-05,
+      "loss": 0.2688,
+      "step": 460000
+    },
+    {
+      "epoch": 7.02,
+      "eval_runtime": 1.0225,
+      "eval_samples_per_second": 978.034,
+      "eval_steps_per_second": 15.649,
+      "step": 460000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.154507803956729e+22,
+  "total_flos": 3.2246074079189274e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9bd4abec55ec3aff5c6a63e004f193b84327f4dea19bd4c7a418c248e58ed7
+oid sha256:8e2e3c76b0bd22486ffeb7f1582064821337785eddce5493639f753ea7af7c21
 size 449471589