Training in progress, epoch 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db81c884c7d3feb24e858c502bb9d98e803ea91d6d069bedbab15afc2721a429
+oid sha256:41a277b47a550da14b370541981a7ce6840530b7d153c4783999693dbbf44a30
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72391c39c5faf845659b6a22442dfaac40f3a75bfb29d41401286ba77ad4a3d
+oid sha256:8f722515db78859d32e19dbe1a158450f033797198ca8b9c14c9e3f4a2b34a08
 size 75667834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e824f516d7a082a3c00e9ed3bc455d338294a347eeda923154d30a60133d10
+oid sha256:e32134cd2633842511ba5b34cff9c069c31016e097e42184eff2a05a356b8026
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d676e87101a49e17d000c0bd020bdc2cea5ce893e0220004cca62306f32aac4
+oid sha256:f33cd452fcd326d16c4c51edba15ab743cd9b65a125f2664356496a4790a1bb7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1810,
+  "global_step": 2172,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,25 @@
       "eval_samples_per_second": 1.988,
       "eval_steps_per_second": 0.253,
       "step": 1810
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 1.557692307692308e-05,
+      "loss": 0.7683,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 11.70807453416149,
+      "eval_loss": 0.7056237459182739,
+      "eval_rouge1": 30.3901,
+      "eval_rouge2": 21.9556,
+      "eval_rougeL": 26.8053,
+      "eval_rougeLsum": 27.0162,
+      "eval_runtime": 161.96,
+      "eval_samples_per_second": 1.988,
+      "eval_steps_per_second": 0.253,
+      "step": 2172
     }
   ],
   "logging_steps": 500,
@@ -97,7 +116,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 9707603440435200.0,
+  "total_flos": 1.164912412852224e+16,
   "trial_name": null,
   "trial_params": null
 }