Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762566100d643c393dc9765c901427a1a7e585f80720544f1d9732e8c2f1a638
+oid sha256:6c6efbf6915c0d7fd8fc40574e3c70bbbeed5caba0f2eb7d8bed57661bd17296
 size 57029756

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73eb6618c19390aa57b57efc6e80aa55d60ef89276374392558a5141f6563c2a
+oid sha256:58dc8495027d948ee4d9ac9cdbf9285489f20ab3b7c701c7afd65e841482e4da
 size 114100410

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d172399ef3366064f2426bb341e0c2875d4dcfd2615777d3613f0258a4aaa64
+oid sha256:5202dcf80c7b0f10dc986464ca4f6b0ef0ad4a74acba3af2d863fb43e4dbdcfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db35652316cd18818079609bdbd22b09de59e7ca3cd85099fc0bf1dbb6d1001
+oid sha256:0992f3eb6a6e87d7c905716ad6cb10cdc7e7e02476fe12e47e23d9729391391c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,116 +1,19 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 0.5694760820045558,
   "eval_steps": 500,
-  "global_step": 4390,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.5694760820045558,
-      "grad_norm": 1.5356756448745728,
+      "grad_norm": 1.5650427341461182,
       "learning_rate": 1.7722095671981778e-05,
-      "loss": 0.1506,
+      "loss": 0.5173,
       "step": 500
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.9634930973676268,
-      "eval_f1": 0.8442987330517893,
-      "eval_loss": 0.13140565156936646,
-      "eval_precision": 0.8387987192227007,
-      "eval_recall": 0.849871350262893,
-      "eval_runtime": 3.0691,
-      "eval_samples_per_second": 1058.938,
-      "eval_steps_per_second": 66.469,
-      "step": 878
-    },
-    {
-      "epoch": 1.1389521640091116,
-      "grad_norm": 3.3906660079956055,
-      "learning_rate": 1.5444191343963555e-05,
-      "loss": 0.12,
-      "step": 1000
-    },
-    {
-      "epoch": 1.7084282460136673,
-      "grad_norm": 6.772578239440918,
-      "learning_rate": 1.3166287015945332e-05,
-      "loss": 0.1046,
-      "step": 1500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.9679412839372805,
-      "eval_f1": 0.866677846721449,
-      "eval_loss": 0.12156210839748383,
-      "eval_precision": 0.866145251396648,
-      "eval_recall": 0.8672110974381922,
-      "eval_runtime": 3.0579,
-      "eval_samples_per_second": 1062.822,
-      "eval_steps_per_second": 66.712,
-      "step": 1756
-    },
-    {
-      "epoch": 2.277904328018223,
-      "grad_norm": 8.046541213989258,
-      "learning_rate": 1.0888382687927108e-05,
-      "loss": 0.098,
-      "step": 2000
-    },
-    {
-      "epoch": 2.847380410022779,
-      "grad_norm": 3.613861322402954,
-      "learning_rate": 8.610478359908885e-06,
-      "loss": 0.0905,
-      "step": 2500
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9694981492366594,
-      "eval_f1": 0.8722589241103648,
-      "eval_loss": 0.11584340035915375,
-      "eval_precision": 0.8657703328190435,
-      "eval_recall": 0.878845508446135,
-      "eval_runtime": 3.8011,
-      "eval_samples_per_second": 855.007,
-      "eval_steps_per_second": 53.668,
-      "step": 2634
-    },
-    {
-      "epoch": 3.416856492027335,
-      "grad_norm": 3.454561471939087,
-      "learning_rate": 6.3325740318906616e-06,
-      "loss": 0.0841,
-      "step": 3000
-    },
-    {
-      "epoch": 3.9863325740318905,
-      "grad_norm": 7.105097770690918,
-      "learning_rate": 4.054669703872437e-06,
-      "loss": 0.076,
-      "step": 3500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9696570130427185,
-      "eval_f1": 0.8694353812973511,
-      "eval_loss": 0.11094123870134354,
-      "eval_precision": 0.8596894138232721,
-      "eval_recall": 0.8794048551292091,
-      "eval_runtime": 4.8501,
-      "eval_samples_per_second": 670.083,
-      "eval_steps_per_second": 42.061,
-      "step": 3512
-    },
-    {
-      "epoch": 4.555808656036446,
-      "grad_norm": 4.661518096923828,
-      "learning_rate": 1.7767653758542143e-06,
-      "loss": 0.0741,
-      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -125,12 +28,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 91500454459296.0,
+  "total_flos": 10392521743584.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6179295ed33670bef4e6ae443db6c86535ebdf6636bdd940a34e8a5e5cd430e0
+oid sha256:fdba20217acc5727d371bb2b4ee86307f247f3c56144c2ceaef9f29f3d06f144
 size 5304