Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988267fa91dde76c97d5f9f4bdc827ce21f64d3d8210cfb9e0a95599c6b2e344
+oid sha256:8fafd8e550218ad55d6b4de7c3dbd8a1efe4b0e19b969ce34f145c07824c7ed1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6186822b08fc70083736d46e84b3aec159961ab50fedc26342e3b2afb0c7d175
+oid sha256:5f67328c52a7cbb0a89ce87cde409a9e3c10b50836dcd93e7c3f18389000eb84
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005f9e7198481e74b4ed4ba5af793791c506ea467a1d762ec7bb45828f94cc44
+oid sha256:6042436c7222de6be2d8a66b6e88538f61781ad871525fe286690e3a8ff7b591
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4bbd98ecf2ab541efa2298ba67df8340fabd983f46354f188b96f0ce56b64f
+oid sha256:75142654ed12b44fcc86b31ea86067aeff7ddefb45caee69287e41b1c7572cbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 4812,
+  "global_step": 6015,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 13.995,
       "eval_steps_per_second": 1.756,
       "step": 4812
+    },
+    {
+      "epoch": 4.156275976724855,
+      "grad_norm": 46259.7421875,
+      "learning_rate": 3.374896093100582e-06,
+      "loss": 0.3315,
+      "step": 5000
+    },
+    {
+      "epoch": 4.57190357439734,
+      "grad_norm": 53976.30859375,
+      "learning_rate": 1.7123857024106402e-06,
+      "loss": 0.3383,
+      "step": 5500
+    },
+    {
+      "epoch": 4.987531172069826,
+      "grad_norm": 48498.83203125,
+      "learning_rate": 4.987531172069826e-08,
+      "loss": 0.3333,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.2967619299888611,
+      "eval_runtime": 35.6175,
+      "eval_samples_per_second": 13.87,
+      "eval_steps_per_second": 1.741,
+      "step": 6015
     }
   ],
   "logging_steps": 500,
@@ -116,12 +145,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.344000712343552e+16,
+  "total_flos": 2.93000089042944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null