Training in progress, epoch 2, checkpoint

checkpoint-3056/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad463059a49b613eb03df4c048d797ae396203ad55df2966259cf6d0832bf908
+oid sha256:b68e41325dbdb1437b0cba550afc81b90e36838c1043f61962d5eded12bdaac6
 size 557116312

checkpoint-3056/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c5b5a9472f5b369c41cc0223a54d821c73eef9313bfc84104b0a8c08145c9f
+oid sha256:35a3bac36de4f7daf69d45a6a1559474ca3a6d2bbf09bff99f6344ec5339c5cc
 size 1113991930

checkpoint-3056/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a10d959c75e03b0f3e40ddccae75cc1c3bb4a7dda726c8500cf7cde82fc0151
+oid sha256:fa9d1335bcf626664b9856d1d0008b505cd442c2fc0ed9f9e4da5747018686cf
 size 1064

checkpoint-3056/trainer_state.json

@@ -42,41 +42,41 @@
     },
     {
       "epoch": 1.3089005235602094,
-      "grad_norm": 3.447214365005493,
-      "learning_rate": 3.691099476439791e-05,
-      "loss": 0.0416,
+      "grad_norm": 3.4732136726379395,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.0456,
       "step": 2000
     },
     {
       "epoch": 1.6361256544502618,
-      "grad_norm": 1.726170301437378,
-      "learning_rate": 3.3638743455497386e-05,
-      "loss": 0.0536,
+      "grad_norm": 2.2575156688690186,
+      "learning_rate": 4.181937172774869e-05,
+      "loss": 0.0619,
       "step": 2500
     },
     {
       "epoch": 1.9633507853403143,
-      "grad_norm": 5.475728511810303,
-      "learning_rate": 3.036649214659686e-05,
-      "loss": 0.0841,
+      "grad_norm": 6.030032157897949,
+      "learning_rate": 4.018324607329843e-05,
+      "loss": 0.0993,
       "step": 3000
     },
     {
       "epoch": 2.0,
-      "eval_loss": 5.553058624267578,
-      "eval_rouge1": 25.1196,
-      "eval_rouge2": 9.8402,
-      "eval_rougeL": 21.832,
-      "eval_runtime": 384.1983,
-      "eval_samples_per_second": 5.713,
-      "eval_steps_per_second": 0.573,
+      "eval_loss": 5.542174339294434,
+      "eval_rouge1": 25.0744,
+      "eval_rouge2": 9.8534,
+      "eval_rougeL": 21.6992,
+      "eval_runtime": 411.9676,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.534,
       "step": 3056
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7640,
+  "max_steps": 15280,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-3056/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0db0c5c28c9a1e67e13675dc0782cb65baca4516e1c39cf487f5c45dc85be680
+oid sha256:a35dd57590090f24ebba9a087e2c3d94297cd357e1c5960144536e9514488b6a
 size 6904