Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc449c3c9aa977e62e8a253fc1964181c661fbd908462f8287ca14c67fa221d5
+oid sha256:eddb74787696dede4919ec271555a6350a568c321174a7c15dc3e1d67bee90d9
 size 751197645

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c647d2e5ab98d23af56502a4839e2d950f16e5f58d356abdc346b70f550298af
+oid sha256:ab9255443ab93767d06e31e700d16c826a1b9c4bd217525b669b2851a871e8fd
 size 376008389

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392a70bbd171fc077436dd500b1dfc29564709bf147ae66f4482dfc8047b6daf
-size 14503
+oid sha256:955f2254b1e2583a0c202f4167da7de0b528b48ae4ee34006c7519a67f4f2166
+size 14567

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5afed70c6b44287fbb97642baae95caed1fca70c0d2879628f6644dcd1c87ebf
+oid sha256:35de3af080a175fc9162ccb44a37ba550925fde9c9502c74bafce2c813e66388
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ac74872413f57561e77e286f80f4be64cce2d235c693168b3f7d99462940fd
+oid sha256:265e019a5d08011062ca46680adb46fea92faeb6e1ff9bcaf722eb0c685c75c6
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7863522686673812,
-  "global_step": 10000,
+  "epoch": 3.5727045373347623,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -136,11 +136,141 @@
       "eval_samples_per_second": 6.25,
       "eval_steps_per_second": 0.196,
       "step": 10000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.251965689778412e-05,
+      "loss": 0.9,
+      "step": 10500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.073266619013581e-05,
+      "loss": 0.8792,
+      "step": 11000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 5.894924946390279e-05,
+      "loss": 0.8345,
+      "step": 11500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.716583273766977e-05,
+      "loss": 0.8162,
+      "step": 12000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 5.537884203002145e-05,
+      "loss": 0.8095,
+      "step": 12500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 5.359185132237312e-05,
+      "loss": 0.7957,
+      "step": 13000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 5.18048606147248e-05,
+      "loss": 0.7941,
+      "step": 13500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.0017869907076487e-05,
+      "loss": 0.7864,
+      "step": 14000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.823087919942816e-05,
+      "loss": 0.7805,
+      "step": 14500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.6443888491779846e-05,
+      "loss": 0.7744,
+      "step": 15000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.465689778413152e-05,
+      "loss": 0.7757,
+      "step": 15500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.2869907076483206e-05,
+      "loss": 0.7671,
+      "step": 16000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 4.108291636883488e-05,
+      "loss": 0.7618,
+      "step": 16500
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.929592566118656e-05,
+      "loss": 0.7375,
+      "step": 17000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 3.750893495353824e-05,
+      "loss": 0.6979,
+      "step": 17500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.5729092208720514e-05,
+      "loss": 0.7052,
+      "step": 18000
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.39421015010722e-05,
+      "loss": 0.6974,
+      "step": 18500
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.2155110793423873e-05,
+      "loss": 0.6921,
+      "step": 19000
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 3.0368120085775553e-05,
+      "loss": 0.696,
+      "step": 19500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 2.8581129378127237e-05,
+      "loss": 0.6971,
+      "step": 20000
+    },
+    {
+      "epoch": 3.57,
+      "eval_bleu": 5.3321,
+      "eval_gen_len": 44.1972,
+      "eval_loss": 0.8275578618049622,
+      "eval_runtime": 1432.7377,
+      "eval_samples_per_second": 6.233,
+      "eval_steps_per_second": 0.195,
+      "step": 20000
     }
   ],
   "max_steps": 27990,
   "num_train_epochs": 5,
-  "total_flos": 2.16932586356736e+16,
+  "total_flos": 4.33848223531008e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c647d2e5ab98d23af56502a4839e2d950f16e5f58d356abdc346b70f550298af
+oid sha256:ab9255443ab93767d06e31e700d16c826a1b9c4bd217525b669b2851a871e8fd
 size 376008389

runs/Feb08_19-24-11_fadcca9c27d0/events.out.tfevents.1644348258.fadcca9c27d0.35.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb419f0fea41195134665abb1056ce1fcc92f38e8ba7eff4ff72a2e64885d36
-size 7218
+oid sha256:a6d8d0dbfec2c2425f8dbde5ffbd5b91ba063ed34d1bef26590e5f7a9537720b
+size 10759