Training in progress, step 9000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc98c7c2bc0c4206028dfacf943fe417a45fd1a4921f341f0b750bb0a800eb46
+oid sha256:2c02848fe198317b9df9c7b015be7a5a8d106b3d8c95581e94d368f12e3bd2aa
 size 1987250795

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
+oid sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
 size 996026489

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda6569db1bc2d3d0435133aaa63d6f8465fafb2497de735ccd7d68f26426942
+oid sha256:989bf089e99481fed8a0ca8c42df0ebf959c5055d0443690a60cd2739bd951a3
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daae6f8fb25a77228382add9166586e74f66ba572bb14f90a533805d7d13d5a9
+oid sha256:5ca42b4728e4a3dd46497569040a4bcb0499b808d030d537723afa704d3d5cea
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1a99d87e2c39ac247735b2acf3b937a77d263374455fdfc4d46375e8f8af01
+oid sha256:42803a5c9416fe30408add7b6997c032033033ede5cc3b581b72368a5f47393e
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 205.12820512820514,
-  "global_step": 8000,
+  "epoch": 230.76923076923077,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -294,11 +294,47 @@
       "eval_samples_per_second": 2.448,
       "eval_steps_per_second": 0.311,
       "step": 8000
+    },
+    {
+      "epoch": 217.95,
+      "learning_rate": 1.6520618556701032e-05,
+      "loss": 0.0023,
+      "step": 8500
+    },
+    {
+      "epoch": 217.95,
+      "eval_bleu": 96.4892,
+      "eval_em": 0.6379,
+      "eval_gen_len": 81.9424,
+      "eval_loss": 0.25497403740882874,
+      "eval_rm": 0.7482,
+      "eval_runtime": 168.8592,
+      "eval_samples_per_second": 2.47,
+      "eval_steps_per_second": 0.314,
+      "step": 8500
+    },
+    {
+      "epoch": 230.77,
+      "learning_rate": 1.3943298969072165e-05,
+      "loss": 0.0022,
+      "step": 9000
+    },
+    {
+      "epoch": 230.77,
+      "eval_bleu": 96.8559,
+      "eval_em": 0.6475,
+      "eval_gen_len": 81.5635,
+      "eval_loss": 0.2539912760257721,
+      "eval_rm": 0.7506,
+      "eval_runtime": 158.2741,
+      "eval_samples_per_second": 2.635,
+      "eval_steps_per_second": 0.335,
+      "step": 9000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 6373629529551360.0,
+  "total_flos": 7171986679845120.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
+oid sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
 size 996026489

runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a0c0976b343685aea77955cc06b9e04bc75d95b3dd3fab3c2ac650bd511676
-size 18465
+oid sha256:58cc137eff897db8b4f86e972869b1df7c24ded97a37d5527235e0aba68862a4
+size 19703