Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db702d2e68876cab46976c836710ff38917f1da1c2ec63db4b90aea0f31bfad
+oid sha256:474b993621dcf0bddfe1abd8c429bde1a78e3cd28d23183ebdc1cfb5f798f9fb
 size 430935892

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c1c9ff4bb5264948e1e60bae8d14def3974dd4e7f386d9137099068800cfbc8
+oid sha256:7f3373cbddd58f49d7ee1bee615e1e87f0d764904fd125e2f94c5c1ca6b82737
 size 861991482

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2bc70652e6ef170320bcca82afe9a9f4bdf2996075a63ec8a251ac321429afb
+oid sha256:df8904498d0ea4278d68a668aa846964ce80df1ff9136c37871ee274669dc57f
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7c30b78cec564dd03bf88837e697ae6ef4fcc7a8780b9e87c556a24173894f
+oid sha256:4e9de563a795946068ee2943aa801ab2757eb65d8f36f8743830ce3a1cd4b5ce
 size 1064

trainer_state.json

@@ -1,93 +1,100 @@
 {
-  "best_global_step": 476,
-  "best_metric": 0.010661174543201923,
-  "best_model_checkpoint": "projects/PetBERT_annonymisation/data/augment/checkpoint-476",
+  "best_global_step": 609,
+  "best_metric": 0.010163484141230583,
+  "best_model_checkpoint": "projects/PetBERT_annonymisation/data/augment/arrow_4/checkpoint-609",
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 1904,
+  "global_step": 2436,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0,
-      "eval_f1": 0.035302169832600705,
-      "eval_loss": 2.312753200531006,
-      "eval_precision": 0.09090508818188361,
-      "eval_recall": 0.06752732472754598,
-      "eval_runtime": 12.3558,
-      "eval_samples_per_second": 134.107,
-      "eval_steps_per_second": 4.209,
+      "eval_f1": 0.0125291815966952,
+      "eval_loss": 2.3777594566345215,
+      "eval_precision": 0.09023052095482559,
+      "eval_recall": 0.0881670915774344,
+      "eval_runtime": 12.1157,
+      "eval_samples_per_second": 136.764,
+      "eval_steps_per_second": 4.292,
       "step": 0
     },
+    {
+      "epoch": 0.8210180623973727,
+      "grad_norm": 0.28877386450767517,
+      "learning_rate": 4.9959031198686376e-05,
+      "loss": 0.0484,
+      "step": 500
+    },
     {
       "epoch": 1.0,
-      "eval_f1": 0.8995538111348774,
-      "eval_loss": 0.010661174543201923,
-      "eval_precision": 0.8815916042183172,
-      "eval_recall": 0.9190286419243201,
-      "eval_runtime": 12.59,
-      "eval_samples_per_second": 131.612,
-      "eval_steps_per_second": 4.13,
-      "step": 476
+      "eval_f1": 0.9208551148897809,
+      "eval_loss": 0.010163484141230583,
+      "eval_precision": 0.9173087088894764,
+      "eval_recall": 0.9271621325936177,
+      "eval_runtime": 12.5384,
+      "eval_samples_per_second": 132.154,
+      "eval_steps_per_second": 4.147,
+      "step": 609
     },
     {
-      "epoch": 1.050420168067227,
-      "grad_norm": 0.16209110617637634,
-      "learning_rate": 4.994758403361345e-05,
-      "loss": 0.0477,
-      "step": 500
+      "epoch": 1.6420361247947455,
+      "grad_norm": 0.3570762574672699,
+      "learning_rate": 4.99179802955665e-05,
+      "loss": 0.0065,
+      "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.9230744441736807,
-      "eval_loss": 0.010812721215188503,
-      "eval_precision": 0.8937084772102274,
-      "eval_recall": 0.9571896846985819,
-      "eval_runtime": 12.587,
-      "eval_samples_per_second": 131.644,
-      "eval_steps_per_second": 4.131,
-      "step": 952
+      "eval_f1": 0.9295632654722351,
+      "eval_loss": 0.010717815719544888,
+      "eval_precision": 0.9179765798631134,
+      "eval_recall": 0.9419352898275708,
+      "eval_runtime": 12.5527,
+      "eval_samples_per_second": 132.004,
+      "eval_steps_per_second": 4.143,
+      "step": 1218
     },
     {
-      "epoch": 2.100840336134454,
-      "grad_norm": 0.012455416843295097,
-      "learning_rate": 4.989506302521009e-05,
-      "loss": 0.0056,
-      "step": 1000
+      "epoch": 2.4630541871921183,
+      "grad_norm": 0.006953490898013115,
+      "learning_rate": 4.987692939244664e-05,
+      "loss": 0.0033,
+      "step": 1500
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.9348757835672437,
-      "eval_loss": 0.01099320687353611,
-      "eval_precision": 0.9214871357949422,
-      "eval_recall": 0.9494909444630193,
-      "eval_runtime": 12.579,
-      "eval_samples_per_second": 131.728,
-      "eval_steps_per_second": 4.134,
-      "step": 1428
+      "eval_f1": 0.9048958394614014,
+      "eval_loss": 0.013671835884451866,
+      "eval_precision": 0.8760752650167597,
+      "eval_recall": 0.9419362439194514,
+      "eval_runtime": 12.5648,
+      "eval_samples_per_second": 131.877,
+      "eval_steps_per_second": 4.139,
+      "step": 1827
     },
     {
-      "epoch": 3.1512605042016806,
-      "grad_norm": 0.015093757770955563,
-      "learning_rate": 4.9842542016806724e-05,
-      "loss": 0.0029,
-      "step": 1500
+      "epoch": 3.284072249589491,
+      "grad_norm": 0.03194739297032356,
+      "learning_rate": 4.983587848932677e-05,
+      "loss": 0.0024,
+      "step": 2000
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.9105180723758415,
-      "eval_loss": 0.012333991006016731,
-      "eval_precision": 0.8738638072175106,
-      "eval_recall": 0.9524189376430204,
-      "eval_runtime": 12.6079,
-      "eval_samples_per_second": 131.426,
-      "eval_steps_per_second": 4.124,
-      "step": 1904
+      "eval_f1": 0.926800098647886,
+      "eval_loss": 0.013943095691502094,
+      "eval_precision": 0.9002957711004475,
+      "eval_recall": 0.9554729790053276,
+      "eval_runtime": 12.6182,
+      "eval_samples_per_second": 131.319,
+      "eval_steps_per_second": 4.121,
+      "step": 2436
     }
   ],
   "logging_steps": 500,
-  "max_steps": 476000,
+  "max_steps": 609000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1000,
   "save_steps": 500,
@@ -112,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5921584203628544e+16,
+  "total_flos": 2.035249251765043e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b027a28b72c517e30a4a077c26526840f9f8e189cb0dc1de6469ad0645aeeb7
+oid sha256:10d352a09e2aecd9422bdcc1bf58522262d82cd9de793273e937f615b15344c1
 size 5304