Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eded264ca955685abe2238b9d2e7b2ed8ac1dc9f219ce420fba696849aaf5a7
+oid sha256:e769a8adc6851c571d318f9f8d597aa021ab357ebcd61e613e6346460833779a
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfe7706d49fc6bf48bb44f76d1d67aafea9c3cccf0b2ed3fb26572d5cef4ea0
+oid sha256:e81abb427d2bb19813d0e17c56caed64154b36100906c45a8547cd38afbae3d5
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e8af3fcba0c22d51a0c29d95f84426eb1608f280deece66d2d0151b331a6b1
+oid sha256:404667d89973760348cc653c442f08c243df998777422cd0dd9b4e5b7b18505d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36bf8253be861dd64787ad45841b3c195627cbf2433aba9e7bc9f35e6ed232d
+oid sha256:466256ee71b0a044b429768d7371618a1dc77becfc275f201cdc2e4d1e676296
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 1312,
+  "global_step": 1640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,13 +71,32 @@
       "eval_samples_per_second": 1.872,
       "eval_steps_per_second": 0.238,
       "step": 1312
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 2.456140350877193e-06,
+      "loss": 0.8715,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 13.051546391752577,
+      "eval_loss": 0.766891360282898,
+      "eval_rouge1": 24.6538,
+      "eval_rouge2": 17.821,
+      "eval_rougeL": 21.5884,
+      "eval_rougeLsum": 21.9045,
+      "eval_runtime": 157.0206,
+      "eval_samples_per_second": 1.853,
+      "eval_steps_per_second": 0.236,
+      "step": 1640
     }
   ],
   "logging_steps": 500,
   "max_steps": 1640,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 9832568722292736.0,
+  "total_flos": 1.229071090286592e+16,
   "trial_name": null,
   "trial_params": null
 }