Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7442f9b1b8eaedb28a307ad821bc17333be1ec1db40df16dcb29c589292dd9a
+oid sha256:fbba5bbb1b84435fdf4b936453e1a9a1c7392c1a15c1565a0f55dad61b600519
 size 2023671531

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0dd95c892f20845c651adeb1edb1313f086fd7c6433880a52de996981d6d12
+oid sha256:a0cca5310b3c6412f68c93da53730bce4f0499a92d2e73c914d211907ca203c6
 size 1014236857

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc379462a95446b799f519a1789df0c033332e48886b605cc7e0e41e902ed5eb
+oid sha256:66d523033a195fd4e9b50639cc4c9fbcdcc6bcaffcba88c0b16f9c68a632d384
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea22e1e3d580a233174f36b8254237ec9b07496557b5d4d59b4b19497a3dbac
+oid sha256:a7b1d42097f30e62e33d325ebb7425a02f7706c3c1da9e8f212c30114570be17
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 128.2051282051282,
-  "global_step": 5000,
+  "epoch": 153.84615384615384,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -186,11 +186,47 @@
       "eval_samples_per_second": 2.924,
       "eval_steps_per_second": 0.372,
       "step": 5000
+    },
+    {
+      "epoch": 141.03,
+      "learning_rate": 3.197938144329897e-05,
+      "loss": 0.0904,
+      "step": 5500
+    },
+    {
+      "epoch": 141.03,
+      "eval_bleu": 94.4101,
+      "eval_em": 0.0719,
+      "eval_gen_len": 58.2518,
+      "eval_loss": 0.34235823154449463,
+      "eval_rm": 0.1439,
+      "eval_runtime": 139.5842,
+      "eval_samples_per_second": 2.987,
+      "eval_steps_per_second": 0.38,
+      "step": 5500
+    },
+    {
+      "epoch": 153.85,
+      "learning_rate": 2.9402061855670106e-05,
+      "loss": 0.0833,
+      "step": 6000
+    },
+    {
+      "epoch": 153.85,
+      "eval_bleu": 94.7141,
+      "eval_em": 0.0887,
+      "eval_gen_len": 59.0312,
+      "eval_loss": 0.3461511433124542,
+      "eval_rm": 0.1775,
+      "eval_runtime": 137.4141,
+      "eval_samples_per_second": 3.035,
+      "eval_steps_per_second": 0.386,
+      "step": 6000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 4028902164693120.0,
+  "total_flos": 4840863271495680.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0dd95c892f20845c651adeb1edb1313f086fd7c6433880a52de996981d6d12
+oid sha256:a0cca5310b3c6412f68c93da53730bce4f0499a92d2e73c914d211907ca203c6
 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 sha256:396b3690fc05dd7fbcefb662e6a7101d7c99cf81c6f3ec3bf6980791cb736b80
-size 14747
+oid sha256:d8e380f641e60e47416c9ef8be040e10b17e40ec679df6b8213d182a3e4238dc
+size 15985