Training in progress, step 970000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42f08cee5e5899e421c92c3ab8339aaf83a7d5a71e0f986946de70dd25827b8
+oid sha256:f6337e42221c0412df86c7992210272b9971c9d1fc461208785aaf4d8ac59d2f
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d19d365ff7d0b903b4bd79b61ced5f6aeb7b3ebb2cae5d9721a7be356fbe96
+oid sha256:02e43adcfc82aa259193d845850177a25c81c1a4194053ab16836d335061826a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1eb140f3b501b632da9f0e177d93dfa92f96327fc83b8ab3f8543beea312596
+oid sha256:896791a7c2af828c5892ebdd0c2594828d16ab816d74f045b54f109ae6d9494f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae02e1b16438a09fd7c39d026b7058dcba2dd8135cc32faa7d3ef32101cb552c
-size 14439
+oid sha256:d2b1d003a5601ab66979661e59677be128945b2fa99167367a5f20eee9647c21
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f7bfdfb2e7526898925192623454d203e22c96e04a99fdbcc255d8c59ba2ffd
-size 14503
+oid sha256:881d6829cb0acc89bbda293c5817890086c3d5c60b0bada5736d21401b19e6e3
+size 14567

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19bc56ae136ac8d5c6f4be4ce221d0a363428f1eb15ee73fbd5e9c04b3ecc844
-size 14439
+oid sha256:df3df06c4c66eb76fd186c61e084b6f3a769bb5d036f690f217d70cc8d7d4fc4
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351338e637aa543d98ac6400f2e05e86270a6a5900e20a3e790dbfa3cb26dbef
+oid sha256:9af3eb0d3db8162f6de4427ee5f19b1787f4bdb865e0ebda13f4fed6034a8890
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.659398048467635,
-  "global_step": 960000,
+  "epoch": 14.812100111472507,
+  "global_step": 970000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7110,11 +7110,85 @@
       "eval_samples_per_second": 1227.238,
       "eval_steps_per_second": 19.636,
       "step": 960000
+    },
+    {
+      "epoch": 14.67,
+      "learning_rate": 1.0581363452005424e-05,
+      "loss": 0.2279,
+      "step": 961000
+    },
+    {
+      "epoch": 14.69,
+      "learning_rate": 1.0551970907986557e-05,
+      "loss": 0.2277,
+      "step": 962000
+    },
+    {
+      "epoch": 14.71,
+      "learning_rate": 1.0523337836487271e-05,
+      "loss": 0.2276,
+      "step": 963000
+    },
+    {
+      "epoch": 14.72,
+      "learning_rate": 1.0495464550634267e-05,
+      "loss": 0.2278,
+      "step": 964000
+    },
+    {
+      "epoch": 14.74,
+      "learning_rate": 1.046835135524533e-05,
+      "loss": 0.2277,
+      "step": 965000
+    },
+    {
+      "epoch": 14.74,
+      "eval_runtime": 0.7884,
+      "eval_samples_per_second": 1268.404,
+      "eval_steps_per_second": 20.294,
+      "step": 965000
+    },
+    {
+      "epoch": 14.75,
+      "learning_rate": 1.044199854682601e-05,
+      "loss": 0.2278,
+      "step": 966000
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 1.0416406413566414e-05,
+      "loss": 0.2279,
+      "step": 967000
+    },
+    {
+      "epoch": 14.78,
+      "learning_rate": 1.0391575235337991e-05,
+      "loss": 0.2278,
+      "step": 968000
+    },
+    {
+      "epoch": 14.8,
+      "learning_rate": 1.0367505283690547e-05,
+      "loss": 0.2276,
+      "step": 969000
+    },
+    {
+      "epoch": 14.81,
+      "learning_rate": 1.0344196821849202e-05,
+      "loss": 0.2279,
+      "step": 970000
+    },
+    {
+      "epoch": 14.81,
+      "eval_runtime": 0.7534,
+      "eval_samples_per_second": 1327.252,
+      "eval_steps_per_second": 21.236,
+      "step": 970000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.729615859959243e+22,
+  "total_flos": 6.7997161209895905e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d19d365ff7d0b903b4bd79b61ced5f6aeb7b3ebb2cae5d9721a7be356fbe96
+oid sha256:02e43adcfc82aa259193d845850177a25c81c1a4194053ab16836d335061826a
 size 449471589