Training in progress, epoch 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2ccd4879854685b9c738ebfdee20cceff49eae3355fec81ce10d6cb12e3ab4
+oid sha256:3ea7a1337d72b6f1349cb5df7f79a7b07f01a5386baa9e12d50265c736a181fd
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645fb6e2f9499bb3cd88d5759ea69b7c234c59bcb11246c79da4d414776580de
+oid sha256:fe6e6c7d4af8151365a64245f96a20909c0de649db7e606c3b2a5bde919df669
 size 75667834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e7458c842af9de0ee19f3260ecb652d7e799591013eb3501a8f1bfaa9077c0
+oid sha256:e3928f3acc26ede362c62a0c650a96e511651a2357d653ae6bae0fb694ceee75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae75ec2fcbec4d6a112bf10dea10b38c62ed5914942230f40bd30d52bfdc127c
+oid sha256:af8f680af722126f4814f7db0f2f5ca2531bc678b7958042248d2393d138dd8b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 2896,
+  "global_step": 3258,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,6 +141,25 @@
       "eval_samples_per_second": 1.923,
       "eval_steps_per_second": 0.245,
       "step": 2896
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 5.9615384615384615e-06,
+      "loss": 0.729,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 11.003105590062113,
+      "eval_loss": 0.6830553412437439,
+      "eval_rouge1": 32.7058,
+      "eval_rouge2": 24.4816,
+      "eval_rougeL": 29.4377,
+      "eval_rougeLsum": 29.6886,
+      "eval_runtime": 167.3316,
+      "eval_samples_per_second": 1.924,
+      "eval_steps_per_second": 0.245,
+      "step": 3258
     }
   ],
   "logging_steps": 500,
@@ -148,7 +167,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4.038363031221043e+16,
+  "total_flos": 4.543158410123674e+16,
   "trial_name": null,
   "trial_params": null
 }