Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7e8f5369bfc2a29f36f7b10957832c0e20a5a70d77b74647f2ca26ac882624
+oid sha256:14c9a2e55c4c50b24b29ffda31bbbf8b2ce79105a3817c65ef74a18d2c29ccd0
 size 2023671531

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563b0a357a2dc71eec9a097e4c7356b071b95a6f14bf272d39a798ac00c8b93f
+oid sha256:1985db2a12fd26ee3312f17e5b5c9269d139ea9375f805eaa6bedfdbc502aed3
 size 1014236857

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb75bd8c52e3fd47730e38465db8261e233f22f3a237ac4bbce2f0d46dafd10
+oid sha256:223d17683d85a6b838bf63109231365183224af0ce92c28b1ea819c53db67266
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbe52cd022df1b5a43d833c96a319fe1d93b440f729ffdf50bc9798e6a7f019
+oid sha256:180a76762e48468dc084ebe39054009bb6587d7f0fcb0961ce0eec20c5af2575
 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": 3.559,
       "eval_steps_per_second": 0.452,
       "step": 9000
+    },
+    {
+      "epoch": 243.59,
+      "learning_rate": 1.1360824742268042e-05,
+      "loss": 0.0502,
+      "step": 9500
+    },
+    {
+      "epoch": 243.59,
+      "eval_bleu": 95.1882,
+      "eval_em": 0.1319,
+      "eval_gen_len": 58.5228,
+      "eval_loss": 0.3490062654018402,
+      "eval_rm": 0.3141,
+      "eval_runtime": 118.559,
+      "eval_samples_per_second": 3.517,
+      "eval_steps_per_second": 0.447,
+      "step": 9500
+    },
+    {
+      "epoch": 256.41,
+      "learning_rate": 8.783505154639175e-06,
+      "loss": 0.0473,
+      "step": 10000
+    },
+    {
+      "epoch": 256.41,
+      "eval_bleu": 95.1198,
+      "eval_em": 0.1319,
+      "eval_gen_len": 58.4245,
+      "eval_loss": 0.3504057824611664,
+      "eval_rm": 0.307,
+      "eval_runtime": 118.462,
+      "eval_samples_per_second": 3.52,
+      "eval_steps_per_second": 0.447,
+      "step": 10000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 7274599459543680.0,
+  "total_flos": 8083589088527040.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563b0a357a2dc71eec9a097e4c7356b071b95a6f14bf272d39a798ac00c8b93f
+oid sha256:1985db2a12fd26ee3312f17e5b5c9269d139ea9375f805eaa6bedfdbc502aed3
 size 1014236857

runs/Jun01_11-16-06_2f3322bc44db/events.out.tfevents.1685618949.2f3322bc44db.4217.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d04c0c561bed68c646c44b3398c50c017920833a05db2429bb948013b4a847c
-size 19699
+oid sha256:21397dc7fa148fe1a54e9c47d988caf74cf88c782cf80ab207dabd14c450b5a5
+size 20937