Training in progress, step 960000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e10dc58492fed71483adf6f5b8363903e23bef03e170ace087681ebc08713a
+oid sha256:d42f08cee5e5899e421c92c3ab8339aaf83a7d5a71e0f986946de70dd25827b8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b779e5dbc65f9055978747a6483cc3aacc9d67baf238821e25b63cb286556c36
+oid sha256:b4d19d365ff7d0b903b4bd79b61ced5f6aeb7b3ebb2cae5d9721a7be356fbe96
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c593a167703dbaf9947d32973b51a125779553f32e153671a91b63abf7f7876
+oid sha256:c1eb140f3b501b632da9f0e177d93dfa92f96327fc83b8ab3f8543beea312596
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c374b98251ab1768e65aa1b6a7f148a712a2ce1b1f2f903e4af64c54752379
-size 14503
+oid sha256:ae02e1b16438a09fd7c39d026b7058dcba2dd8135cc32faa7d3ef32101cb552c
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891f782320602223f61f367a6458f228c51432918fe313542e407d34511dfc6d
-size 14567
+oid sha256:0f7bfdfb2e7526898925192623454d203e22c96e04a99fdbcc255d8c59ba2ffd
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9286b15801381b7a96fc2895ff30b4645bc69f0722e3eeae374fcb4eb7890f47
-size 14503
+oid sha256:19bc56ae136ac8d5c6f4be4ce221d0a363428f1eb15ee73fbd5e9c04b3ecc844
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d771b6aa86b6db5c1d3a18a5ba01d5f7ff8a339c98c29586734738700dc44c
+oid sha256:351338e637aa543d98ac6400f2e05e86270a6a5900e20a3e790dbfa3cb26dbef
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.506695985462764,
-  "global_step": 950000,
+  "epoch": 14.659398048467635,
+  "global_step": 960000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7036,11 +7036,85 @@
       "eval_samples_per_second": 1300.007,
       "eval_steps_per_second": 20.8,
       "step": 950000
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 1.091698505917036e-05,
+      "loss": 0.2281,
+      "step": 951000
+    },
+    {
+      "epoch": 14.54,
+      "learning_rate": 1.0880016837314599e-05,
+      "loss": 0.2283,
+      "step": 952000
+    },
+    {
+      "epoch": 14.55,
+      "learning_rate": 1.084380450052071e-05,
+      "loss": 0.2281,
+      "step": 953000
+    },
+    {
+      "epoch": 14.57,
+      "learning_rate": 1.0808348444801e-05,
+      "loss": 0.2278,
+      "step": 954000
+    },
+    {
+      "epoch": 14.58,
+      "learning_rate": 1.0773649057897206e-05,
+      "loss": 0.2283,
+      "step": 955000
+    },
+    {
+      "epoch": 14.58,
+      "eval_runtime": 0.7689,
+      "eval_samples_per_second": 1300.511,
+      "eval_steps_per_second": 20.808,
+      "step": 955000
+    },
+    {
+      "epoch": 14.6,
+      "learning_rate": 1.073970671927628e-05,
+      "loss": 0.2277,
+      "step": 956000
+    },
+    {
+      "epoch": 14.61,
+      "learning_rate": 1.0706521800126198e-05,
+      "loss": 0.2279,
+      "step": 957000
+    },
+    {
+      "epoch": 14.63,
+      "learning_rate": 1.0674094663351906e-05,
+      "loss": 0.2278,
+      "step": 958000
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 1.0642425663571383e-05,
+      "loss": 0.2279,
+      "step": 959000
+    },
+    {
+      "epoch": 14.66,
+      "learning_rate": 1.0611515147111736e-05,
+      "loss": 0.2279,
+      "step": 960000
+    },
+    {
+      "epoch": 14.66,
+      "eval_runtime": 0.8148,
+      "eval_samples_per_second": 1227.238,
+      "eval_steps_per_second": 19.636,
+      "step": 960000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.659515598928896e+22,
+  "total_flos": 6.729615859959243e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b779e5dbc65f9055978747a6483cc3aacc9d67baf238821e25b63cb286556c36
+oid sha256:b4d19d365ff7d0b903b4bd79b61ced5f6aeb7b3ebb2cae5d9721a7be356fbe96
 size 449471589