Training in progress, epoch 7, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce587149180939263fb62318aaca469cef4f21dbd7d6813ab2ff9c70370bdde
+oid sha256:35f1322db5e4b60630fee99f016a47aa61c26f28d567b86bd9c1f9b3560c5a4d
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d05a36297913ef7ca3df0f3800fbbf7de67201801356e5dc49b2f13c4b512f
+oid sha256:6cef2c569e1f2247b5b91c1e6f5333ed358528cc3851294ce08cb15162ad66d1
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207bc56c64bb61994761225ef76709b0ff5a216b91ae2af26277273474ff194b
+oid sha256:c75d88d701e30f9131432935310d9f24a95661f78d2d791ef1a565095fb6687d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2cca733337753377d37248c395a53f2d519707d2254c94d9250865c0f419c2
+oid sha256:76f4e9c00ff093d4836b89fbe34d048c10d6d8579a93728043e4d87912cb51bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 1968,
+  "global_step": 2296,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,13 +103,32 @@
       "eval_samples_per_second": 2.062,
       "eval_steps_per_second": 0.262,
       "step": 1968
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 1.036402569593148e-05,
+      "loss": 0.7597,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 10.31958762886598,
+      "eval_loss": 0.6812536716461182,
+      "eval_rouge1": 34.3854,
+      "eval_rouge2": 26.0495,
+      "eval_rougeL": 30.8335,
+      "eval_rougeLsum": 31.1696,
+      "eval_runtime": 143.6068,
+      "eval_samples_per_second": 2.026,
+      "eval_steps_per_second": 0.258,
+      "step": 2296
     }
   ],
   "logging_steps": 500,
   "max_steps": 3936,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 1.4748853083439104e+16,
+  "total_flos": 1.7206995264012288e+16,
   "trial_name": null,
   "trial_params": null
 }