Training in progress, step 7000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbba5bbb1b84435fdf4b936453e1a9a1c7392c1a15c1565a0f55dad61b600519
+oid sha256:e3f274f22aecae3d4151f2b34c0da1c4d45ffec0f7494c90fbd78f6da7fc8713
 size 2023671531

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cca5310b3c6412f68c93da53730bce4f0499a92d2e73c914d211907ca203c6
+oid sha256:433d0236080f4d7c42ae2c7482a9fb685e96819abdd3b3732b25de4f2487e90a
 size 1014236857

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d523033a195fd4e9b50639cc4c9fbcdcc6bcaffcba88c0b16f9c68a632d384
+oid sha256:c58fc81ffea486603cd4bad6370555b29f1fc41e80ff22e3d23b7f0db2e9aaee
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b1d42097f30e62e33d325ebb7425a02f7706c3c1da9e8f212c30114570be17
+oid sha256:e56d3fcdc6be04d2a3d6a16fff77acb30faf8a3306453f8bd6e6ef5435d67471
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 153.84615384615384,
-  "global_step": 6000,
+  "epoch": 179.48717948717947,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -222,11 +222,47 @@
       "eval_samples_per_second": 3.035,
       "eval_steps_per_second": 0.386,
       "step": 6000
+    },
+    {
+      "epoch": 166.67,
+      "learning_rate": 2.6824742268041237e-05,
+      "loss": 0.0772,
+      "step": 6500
+    },
+    {
+      "epoch": 166.67,
+      "eval_bleu": 94.6758,
+      "eval_em": 0.0911,
+      "eval_gen_len": 59.0767,
+      "eval_loss": 0.34671926498413086,
+      "eval_rm": 0.2062,
+      "eval_runtime": 136.1965,
+      "eval_samples_per_second": 3.062,
+      "eval_steps_per_second": 0.389,
+      "step": 6500
+    },
+    {
+      "epoch": 179.49,
+      "learning_rate": 2.4247422680412372e-05,
+      "loss": 0.0722,
+      "step": 7000
+    },
+    {
+      "epoch": 179.49,
+      "eval_bleu": 94.5698,
+      "eval_em": 0.1055,
+      "eval_gen_len": 58.1415,
+      "eval_loss": 0.3461613953113556,
+      "eval_rm": 0.2398,
+      "eval_runtime": 131.5014,
+      "eval_samples_per_second": 3.171,
+      "eval_steps_per_second": 0.403,
+      "step": 7000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 4840863271495680.0,
+  "total_flos": 5649680363057280.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cca5310b3c6412f68c93da53730bce4f0499a92d2e73c914d211907ca203c6
+oid sha256:433d0236080f4d7c42ae2c7482a9fb685e96819abdd3b3732b25de4f2487e90a
 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:d8e380f641e60e47416c9ef8be040e10b17e40ec679df6b8213d182a3e4238dc
-size 15985
+oid sha256:a4c7b52816916a7b544395e3613da58f7a4ebee27e925ee5667013f08e44b3cf
+size 17223