Training in progress, epoch 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62aacc804fe0feaac7c4ed8234dffe91091d341716875182fdef7523f840804e
+oid sha256:39175635a5b25e7b27b99521c9d172f131f109f6a4cd7b6fa699891813ae7b86
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5e1d33740b42a64fe152518cc96380472dd314ca83ecb2e8d64b796ef0c06b
+oid sha256:eb4894cfbeb1fa185484f5787d473ce6b86956a18dd144dbc2f1a46d0b36ee8a
 size 75667834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3928f3acc26ede362c62a0c650a96e511651a2357d653ae6bae0fb694ceee75
+oid sha256:1f9b92a51f5d093abd814c49bc9636e3b8dcc3bd0bbe78d17738dd46ead7cbf1
 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": 1.883,
       "eval_steps_per_second": 0.24,
       "step": 3258
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.7215,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 10.959627329192546,
+      "eval_loss": 0.6815938353538513,
+      "eval_rouge1": 32.8295,
+      "eval_rouge2": 24.633,
+      "eval_rougeL": 29.5824,
+      "eval_rougeLsum": 29.842,
+      "eval_runtime": 171.5537,
+      "eval_samples_per_second": 1.877,
+      "eval_steps_per_second": 0.239,
+      "step": 3620
     }
   ],
   "logging_steps": 500,
@@ -167,7 +186,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4.543158410123674e+16,
+  "total_flos": 5.047953789026304e+16,
   "trial_name": null,
   "trial_params": null
 }