Training in progress, epoch 1, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9257626d935eea005747b6117f38e8db18007dbd38f54949943c9dcf0ab36545
+oid sha256:e75e2c23c99eadad00497a3969a361337133cb50eb29550bcfd57d3c4416b3bf
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a27874f7dc93ced479b2661f0507a486022fb461d136d2fd60f69bdbbfaa50
+oid sha256:a3206cfea353705871f16d46e55ccf93893b489d46b83fd7ba2c4d45d71b93a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f882d1e558074512a0f5a92bb9dda78e5353ba094d4875de647eb3d96a8f6114
+oid sha256:4b9bfd309a58bb117e3966aecfcd713fe78e781c92b596afe99f2ae8dde39b29
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 984,
+  "global_step": 328,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,49 +16,17 @@
       "eval_rouge2": 25.6511,
       "eval_rougeL": 30.5481,
       "eval_rougeLsum": 30.8868,
-      "eval_runtime": 148.51,
-      "eval_samples_per_second": 1.959,
-      "eval_steps_per_second": 0.249,
+      "eval_runtime": 145.9508,
+      "eval_samples_per_second": 1.994,
+      "eval_steps_per_second": 0.254,
       "step": 328
-    },
-    {
-      "epoch": 1.52,
-      "learning_rate": 3.125e-05,
-      "loss": 0.7084,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_gen_len": 10.608247422680412,
-      "eval_loss": 0.6409556865692139,
-      "eval_rouge1": 34.106,
-      "eval_rouge2": 25.6511,
-      "eval_rougeL": 30.5481,
-      "eval_rougeLsum": 30.8868,
-      "eval_runtime": 148.1245,
-      "eval_samples_per_second": 1.965,
-      "eval_steps_per_second": 0.25,
-      "step": 656
-    },
-    {
-      "epoch": 3.0,
-      "eval_gen_len": 10.608247422680412,
-      "eval_loss": 0.6409556865692139,
-      "eval_rouge1": 34.106,
-      "eval_rouge2": 25.6511,
-      "eval_rougeL": 30.5481,
-      "eval_rougeLsum": 30.8868,
-      "eval_runtime": 142.7393,
-      "eval_samples_per_second": 2.039,
-      "eval_steps_per_second": 0.259,
-      "step": 984
     }
   ],
   "logging_steps": 500,
   "max_steps": 2624,
   "num_train_epochs": 8,
   "save_steps": 500,
-  "total_flos": 7374426541719552.0,
+  "total_flos": 2458142180573184.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9162668598cf13fecc16e9e9d7efcfa7ee698b28ece9be6da0a39db65802afa5
-size 4728
+oid sha256:57fefa357a66f843a7892370f3ccf4b6c54dcf7fc01e2cacb473bbb4d60ec07a
+size 4792