Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9765b22595c184e33de1c8a5fe85591b6189f5f3e2f13a9bbc93863babd47770
+oid sha256:572325b4c805d9958ac8a2859546f38cf4503fbcb46227c17544a87d3142f956
 size 2000137067

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9578fbf5f8f7cdcc90e7f8891555c7950c7e59c54944b6deee667788fdd22f15
+oid sha256:c6fceec78f7ad0d96d996af6c8eb7a438b8ac36ed3291ce49b6d753be4d4f25f
 size 1002469625

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c25b23c6556dd8f7cd651c05eca0d3d18d9c898e1a7a7c551f095fd033b8bd
+oid sha256:bcdf246df0ea414c8accbbd62c3b0dd42ab4fb76c26b865cadbcefaf0274c0f7
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42803a5c9416fe30408add7b6997c032033033ede5cc3b581b72368a5f47393e
+oid sha256:8a900010c1e924e2c38c55144f994fa0e56d928758b4bb433bfccfc95563b3cc
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 230.76923076923077,
-  "global_step": 9000,
+  "epoch": 256.4102564102564,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -330,11 +330,47 @@
       "eval_samples_per_second": 2.635,
       "eval_steps_per_second": 0.335,
       "step": 9000
+    },
+    {
+      "epoch": 243.59,
+      "learning_rate": 1.1365979381443299e-05,
+      "loss": 0.0093,
+      "step": 9500
+    },
+    {
+      "epoch": 243.59,
+      "eval_bleu": 96.8984,
+      "eval_em": 0.6331,
+      "eval_gen_len": 75.7242,
+      "eval_loss": 0.16627563536167145,
+      "eval_rm": 0.7482,
+      "eval_runtime": 159.472,
+      "eval_samples_per_second": 2.615,
+      "eval_steps_per_second": 0.332,
+      "step": 9500
+    },
+    {
+      "epoch": 256.41,
+      "learning_rate": 8.788659793814432e-06,
+      "loss": 0.0084,
+      "step": 10000
+    },
+    {
+      "epoch": 256.41,
+      "eval_bleu": 96.6199,
+      "eval_em": 0.6331,
+      "eval_gen_len": 75.3885,
+      "eval_loss": 0.1675705760717392,
+      "eval_rm": 0.7482,
+      "eval_runtime": 157.5771,
+      "eval_samples_per_second": 2.646,
+      "eval_steps_per_second": 0.336,
+      "step": 10000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 7274529735677952.0,
+  "total_flos": 8083511610848256.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9578fbf5f8f7cdcc90e7f8891555c7950c7e59c54944b6deee667788fdd22f15
+oid sha256:c6fceec78f7ad0d96d996af6c8eb7a438b8ac36ed3291ce49b6d753be4d4f25f
 size 1002469625

runs/Jun06_07-27-34_610b9cc4e650/events.out.tfevents.1686036725.610b9cc4e650.2348.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44558105d5a21d556299f2bb968b1231913d481070fbcf157e2519b701809bf8
-size 19699
+oid sha256:a41a1700de88f32e62a8408f38e7a470be21e3303c0ee187807ba1f8c80363f3
+size 20937