Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f444cdb66ea4842d2ffe0e2a9e2e651bc9faaab111ce083eadfedccdcd9b37
+oid sha256:b513f65f071693a24c26f6acfe08868c10cef392b47b5791724718504c59b11c
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6195721bb1eaffad813d47060edaf5b008f841b67118b6704011e6de9e0ab1b
+oid sha256:76f7e75f38e31f3caf6295d2c7a27b005bc90135c402a683980ad863b9088acd
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b6289f04d8e738d0f6d339f3f40afb49e49d9ff6f957798e92c5b34d22baad
+oid sha256:61452000e70e2b50dbac9e487e1828eeb816725960673eeb14278e12e0cf6cb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956f4d9fff765ab8d3a69c2ffeb2c226be5aa26081b4c7d2419d640ea4e52671
+oid sha256:67e029cb676b84aed4d4462a36ff279a302dfdcc098c603c675801d47eb56104
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 26.0341,
-  "best_model_checkpoint": "my-model/checkpoint-4584",
-  "epoch": 3.0,
+  "best_metric": 26.4112,
+  "best_model_checkpoint": "my-model/checkpoint-6112",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 4584,
+  "global_step": 6112,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,38 @@
       "eval_samples_per_second": 5.251,
       "eval_steps_per_second": 0.526,
       "step": 4584
+    },
+    {
+      "epoch": 3.2722513089005236,
+      "grad_norm": 5.353453159332275,
+      "learning_rate": 9.096858638743457e-06,
+      "loss": 0.9969,
+      "step": 5000
+    },
+    {
+      "epoch": 3.599476439790576,
+      "grad_norm": 5.323329925537109,
+      "learning_rate": 5.006544502617801e-06,
+      "loss": 1.0924,
+      "step": 5500
+    },
+    {
+      "epoch": 3.9267015706806285,
+      "grad_norm": 6.1474175453186035,
+      "learning_rate": 9.162303664921465e-07,
+      "loss": 1.2208,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.21282958984375,
+      "eval_rouge1": 26.4112,
+      "eval_rouge2": 10.9605,
+      "eval_rougeL": 23.0258,
+      "eval_runtime": 417.2936,
+      "eval_samples_per_second": 5.26,
+      "eval_steps_per_second": 0.527,
+      "step": 6112
     }
   ],
   "logging_steps": 500,
@@ -117,12 +149,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.198245027118285e+16,
+  "total_flos": 2.930549272296653e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null