Training in progress, epoch 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a309abc99ba4706546de383556bc050874d59ea05cd3444f8c24c96ccf4384c
+oid sha256:fddc668a24e1c2b491ee51946679ba4f0644e5290a1468ae3444290dd1070c71
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152b3805d4b436f517a65ff6341eaebbca24f23b829d75ab8e3d0bdd2a721990
+oid sha256:d0daacaf0bfad11733ecd7ef1c636b0874d0d9956b0e684e771a94ae4f4f7449
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebf71d3202a9a106afdc002a15f09163d70b25083881b5a4ae30fce925b3dc2
+oid sha256:609dc43f7bad0601f2d47ee5f02a7841f83660e084612271582ed44bc7004499
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8f680af722126f4814f7db0f2f5ca2531bc678b7958042248d2393d138dd8b
+oid sha256:74eaf87d52d5653cb0d365a112bead472c5249b483626675b2c2c01c02be4a77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 3258,
+  "global_step": 3620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,25 @@
       "eval_samples_per_second": 2.058,
       "eval_steps_per_second": 0.262,
       "step": 3258
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.7282,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 10.860248447204969,
+      "eval_loss": 0.7133759260177612,
+      "eval_rouge1": 32.8362,
+      "eval_rouge2": 24.6174,
+      "eval_rougeL": 29.4825,
+      "eval_rougeLsum": 29.8057,
+      "eval_runtime": 156.6659,
+      "eval_samples_per_second": 2.055,
+      "eval_steps_per_second": 0.262,
+      "step": 3620
     }
   ],
   "logging_steps": 500,
@@ -167,7 +186,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.7957897908453376e+16,
+  "total_flos": 3.106433100939264e+16,
   "trial_name": null,
   "trial_params": null
 }