Training in progress, step 3000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706f00eb19f820fe319f7fafa5e70c41f6a9e1a7d166f8307a88018472cc1657
+oid sha256:5db93d5bbd8ee27e2c605f26462c67689729477710806611d40989d1ddbb37ce
 size 1987250795

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf1f2b9424af846730ab18d00f63657ae804747565792e465df7cbcce97ff99
+oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
 size 996026489

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60916cb59c8af4c3fd3f107d03f442d74a5f179944593d033585e1acab19ee4
+oid sha256:b5af12890d72958474f59e2a6e38aefa8b12d58cc605376a65f0760cdf419671
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b101589015f43511eb0eb50cc023fb256454216407517c39629d0bc69dd1c56c
+oid sha256:0b7708e7360ae5d9dfbc21f14bae0f24f4e0ee89da5d58b4c05796253aac585a
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc9f4c211b246066019b67bda62d8798fabc65b9d4d90687512ceea2d93be15
+oid sha256:025d4a6a1771d5d78df663db14260a7e4dac96d458cc7cf3490ace1f7cc857e7
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 51.282051282051285,
-  "global_step": 2000,
+  "epoch": 76.92307692307692,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,11 +78,47 @@
       "eval_samples_per_second": 2.491,
       "eval_steps_per_second": 0.317,
       "step": 2000
+    },
+    {
+      "epoch": 64.1,
+      "learning_rate": 4.7448453608247423e-05,
+      "loss": 0.0266,
+      "step": 2500
+    },
+    {
+      "epoch": 64.1,
+      "eval_bleu": 96.1601,
+      "eval_em": 0.5516,
+      "eval_gen_len": 80.3981,
+      "eval_loss": 0.21729224920272827,
+      "eval_rm": 0.6211,
+      "eval_runtime": 165.3475,
+      "eval_samples_per_second": 2.522,
+      "eval_steps_per_second": 0.321,
+      "step": 2500
+    },
+    {
+      "epoch": 76.92,
+      "learning_rate": 4.487113402061856e-05,
+      "loss": 0.0191,
+      "step": 3000
+    },
+    {
+      "epoch": 76.92,
+      "eval_bleu": 96.1309,
+      "eval_em": 0.5444,
+      "eval_gen_len": 81.693,
+      "eval_loss": 0.22468438744544983,
+      "eval_rm": 0.6427,
+      "eval_runtime": 164.8881,
+      "eval_samples_per_second": 2.529,
+      "eval_steps_per_second": 0.321,
+      "step": 3000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 2482891695940608.0,
+  "total_flos": 3282494931353088.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf1f2b9424af846730ab18d00f63657ae804747565792e465df7cbcce97ff99
+oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
 size 996026489

runs/May24_14-02-57_8e3a7392af54/events.out.tfevents.1684937027.8e3a7392af54.8284.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3507793a2cbaef8e2d6f31609252db3b06a0dc159c914011f230c63ca7eed9
-size 9833
+oid sha256:9973c2a1b2f99e71423aa797e1b9e0975af9a4af0dcd05a62246b097704d3983
+size 11071