Training in progress, epoch 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451eb6d8466c1e9a0f2e0d8ffed0631f25e2bc7383a45e90e6f04380aeb49b31
+oid sha256:7a309abc99ba4706546de383556bc050874d59ea05cd3444f8c24c96ccf4384c
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988b52e988b931a4fc464e3b692e59a58e120f21384612addbabe7d719ac7fd9
+oid sha256:152b3805d4b436f517a65ff6341eaebbca24f23b829d75ab8e3d0bdd2a721990
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd4b56e79788588601c3128dda5a051838c57d8358a86bca0138141a850263e
+oid sha256:0ebf71d3202a9a106afdc002a15f09163d70b25083881b5a4ae30fce925b3dc2
 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": 1.99,
       "eval_steps_per_second": 0.253,
       "step": 2896
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 5.9615384615384615e-06,
+      "loss": 0.7247,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 10.807453416149068,
+      "eval_loss": 0.7143327593803406,
+      "eval_rouge1": 32.9304,
+      "eval_rouge2": 24.7808,
+      "eval_rougeL": 29.6111,
+      "eval_rougeLsum": 29.9039,
+      "eval_runtime": 156.4641,
+      "eval_samples_per_second": 2.058,
+      "eval_steps_per_second": 0.262,
+      "step": 3258
     }
   ],
   "logging_steps": 500,
@@ -148,7 +167,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.485146480751411e+16,
+  "total_flos": 2.7957897908453376e+16,
   "trial_name": null,
   "trial_params": null
 }