Training in progress, epoch 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d482ec5962e01f41fd0f7eb041ec47d4a31fe0e9a51e800094a9edfb3559322d
+oid sha256:b00ed8a1b6f81a55e285aca487e4e861e7edee97528733f115536b4968121224
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3442334df8c4b6987b4d2bcaf446e341a93a9b1a4031dfebe745c7f6a5c4f2b7
+oid sha256:2021f406052a5c04fb7995cadbf904e0eaefc1f075857ce8d82f537285437672
 size 75739130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75d88d701e30f9131432935310d9f24a95661f78d2d791ef1a565095fb6687d
+oid sha256:e0d5b30acb6099f84ca5645a159a8896115070f3d515a6a74b5d3e1471b03c74
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b6ff4bb636f40d19c2dd94537dbb726496273a2193f13306e1cfd18bd4e8fd
+oid sha256:2df8519cbca65bfc58e542f45b37dfdc6badbae94fca6b3d0fe17127c1cbeb47
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2296,
+  "global_step": 2624,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -122,13 +122,32 @@
       "eval_samples_per_second": 1.908,
       "eval_steps_per_second": 0.243,
       "step": 2296
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 5.680048251060194e-06,
+      "loss": 0.4551,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 12.738831615120274,
+      "eval_loss": 0.497775673866272,
+      "eval_rouge1": 29.5362,
+      "eval_rouge2": 20.6621,
+      "eval_rougeL": 25.7689,
+      "eval_rougeLsum": 26.2351,
+      "eval_runtime": 159.8028,
+      "eval_samples_per_second": 1.821,
+      "eval_steps_per_second": 0.232,
+      "step": 2624
     }
   ],
   "logging_steps": 500,
   "max_steps": 2624,
   "num_train_epochs": 8,
   "save_steps": 500,
-  "total_flos": 1.7206995264012288e+16,
+  "total_flos": 1.966513744458547e+16,
   "trial_name": null,
   "trial_params": null
 }