Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a827260146648964e1c0473647fdd276801d3a7209c7df3eb87d73e4518f74c
-size 893438545
+oid sha256:e0d611070fc96c13fe2a726a75aa89fbb18b267a55a563cdceaf1c3fbade3f8c
+size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
+oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad14af5dd7abce3c61cc5e578461c309f69e60de21b0c054a8f3f4c7bba9e4e6
-size 14503
+oid sha256:ff190ea62daf1e533d229f2cbdc2bf1b0b91f1b54ad94055b49d136687089c2b
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8388ca66f8f9c6c8c8157a81f6bde550f1b25a31aa2aa22e4704b5ef4e971ee
+oid sha256:40b1051d2935e5a6ad2bc776aeb5c7effef95653590b063d7af64113e86e7198
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782279cba623055efc3193875769c57ec4b067421ccba6e615fbf1b5214e724b
-size 14439
+oid sha256:ca733adc62d3884a07b0f3bff0700e4d418d28a780a35e3db8b9f7f1147beb15
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749c503bc6cade081df3a923d8ae2be2ccf707f9f3b893640379c785aa6facd4
+oid sha256:9f9ae59fc5fa85627e7d16c864bbec928ea1cdb8c2fa89705bb65d8bdd8ab7fb
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ff94ce099b109f6c343c1450c170171a247badda4343ab1850180869cf03e2
+oid sha256:f7c802ff93fc9d67d63f3e03f7bd5fd1c7e4a71a3faef71bb4d686a1c5885c38
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9162123780292272,
-  "global_step": 60000,
+  "epoch": 1.0689144410340983,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -450,11 +450,85 @@
       "eval_samples_per_second": 813.826,
       "eval_steps_per_second": 13.021,
       "step": 60000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00014995369178303722,
+      "loss": 0.4408,
+      "step": 61000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001499448905498439,
+      "loss": 0.4381,
+      "step": 62000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00014993532441053364,
+      "loss": 0.434,
+      "step": 63000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001499249934697203,
+      "loss": 0.4316,
+      "step": 64000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001499138978403813,
+      "loss": 0.4275,
+      "step": 65000
+    },
+    {
+      "epoch": 0.99,
+      "eval_runtime": 1.0345,
+      "eval_samples_per_second": 966.655,
+      "eval_steps_per_second": 15.466,
+      "step": 65000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014990203764385677,
+      "loss": 0.425,
+      "step": 66000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014988941300984784,
+      "loss": 0.422,
+      "step": 67000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001498760240764155,
+      "loss": 0.4191,
+      "step": 68000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.000149861870989979,
+      "loss": 0.4164,
+      "step": 69000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001498469539053142,
+      "loss": 0.4138,
+      "step": 70000
+    },
+    {
+      "epoch": 1.07,
+      "eval_runtime": 1.1341,
+      "eval_samples_per_second": 881.784,
+      "eval_steps_per_second": 14.109,
+      "step": 70000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.2060156618208287e+21,
+  "total_flos": 4.907011701442813e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5671fc2a233d9d155c62d2c9fb67023f69b7d1fe8428c704d638f8bca4866498
+oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
 size 449471589