Training in progress, step 5000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfb9350d92f9461684fc4c4fc33ceedbd71375876a5c1b0a2bbe2bf27badaee
+oid sha256:c7442f9b1b8eaedb28a307ad821bc17333be1ec1db40df16dcb29c589292dd9a
 size 2023671531

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39ee6c6957fc3385d65c47639ebba2ec8fef9b1bc284507592d67724bdd24b2
+oid sha256:6c0dd95c892f20845c651adeb1edb1313f086fd7c6433880a52de996981d6d12
 size 1014236857

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034e8c53fddc29e321c99d796375073622a64b607cfe3d06dfbd060f2c64d672
+oid sha256:fc379462a95446b799f519a1789df0c033332e48886b605cc7e0e41e902ed5eb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48889af94e26503dbf915c66d0aa163f80b49963596e932947df95732f608bcd
+oid sha256:4ea22e1e3d580a233174f36b8254237ec9b07496557b5d4d59b4b19497a3dbac
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 102.56410256410257,
-  "global_step": 4000,
+  "epoch": 128.2051282051282,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -150,11 +150,47 @@
       "eval_samples_per_second": 3.061,
       "eval_steps_per_second": 0.389,
       "step": 4000
+    },
+    {
+      "epoch": 115.38,
+      "learning_rate": 3.71340206185567e-05,
+      "loss": 0.0999,
+      "step": 4500
+    },
+    {
+      "epoch": 115.38,
+      "eval_bleu": 94.6291,
+      "eval_em": 0.0336,
+      "eval_gen_len": 58.6283,
+      "eval_loss": 0.3437003791332245,
+      "eval_rm": 0.0624,
+      "eval_runtime": 139.8829,
+      "eval_samples_per_second": 2.981,
+      "eval_steps_per_second": 0.379,
+      "step": 4500
+    },
+    {
+      "epoch": 128.21,
+      "learning_rate": 3.455670103092783e-05,
+      "loss": 0.0941,
+      "step": 5000
+    },
+    {
+      "epoch": 128.21,
+      "eval_bleu": 94.7896,
+      "eval_em": 0.0695,
+      "eval_gen_len": 58.4149,
+      "eval_loss": 0.351246178150177,
+      "eval_rm": 0.1271,
+      "eval_runtime": 142.599,
+      "eval_samples_per_second": 2.924,
+      "eval_steps_per_second": 0.372,
+      "step": 5000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 3218781457056000.0,
+  "total_flos": 4028902164693120.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39ee6c6957fc3385d65c47639ebba2ec8fef9b1bc284507592d67724bdd24b2
+oid sha256:6c0dd95c892f20845c651adeb1edb1313f086fd7c6433880a52de996981d6d12
 size 1014236857

runs/Jun01_08-15-55_7b8f3300e052/events.out.tfevents.1685608114.7b8f3300e052.20157.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a140a0d02e382e8a241ee92fa569b79e547b2d481c0a1ae6197aaf09cf27c65
-size 13509
+oid sha256:396b3690fc05dd7fbcefb662e6a7101d7c99cf81c6f3ec3bf6980791cb736b80
+size 14747